diff options
Diffstat (limited to 'fs/xfs/libxfs')
| -rw-r--r-- | fs/xfs/libxfs/xfs_alloc_btree.c | 2 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_attr_sf.h | 16 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_bmap.c | 176 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_bmap_btree.c | 5 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_btree.c | 32 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_da_format.h | 16 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_dir2.c | 12 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_dir2_node.c | 4 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_ialloc.c | 4 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_ialloc_btree.c | 12 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_inode_buf.c | 170 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_inode_buf.h | 38 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_inode_fork.c | 3 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_log_format.h | 19 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_quota_defs.h | 3 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_rtbitmap.c | 32 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_sb.h | 1 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_shared.h | 1 |
18 files changed, 368 insertions, 178 deletions
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 444626ddb..d9b424252 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -118,8 +118,6 @@ xfs_allocbt_free_block( xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_trans_agbtree_delta(cur->bc_tp, -1); - - xfs_trans_binval(cur->bc_tp, bp); return 0; } diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h index 919756e3b..90928bbe6 100644 --- a/fs/xfs/libxfs/xfs_attr_sf.h +++ b/fs/xfs/libxfs/xfs_attr_sf.h @@ -24,22 +24,6 @@ * Small attribute lists are packed as tightly as possible so as * to fit into the literal area of the inode. */ - -/* - * Entries are packed toward the top as tight as possible. - */ -typedef 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 */ - } 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[1]; /* name & value bytes concatenated */ - } list[1]; /* variable sized array */ -} xfs_attr_shortform_t; typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t; typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index ef00156f4..ce41d7fe7 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -477,10 +477,7 @@ xfs_bmap_check_leaf_extents( } block = XFS_BUF_TO_BLOCK(bp); } - if (bp_release) { - bp_release = 0; - xfs_trans_brelse(NULL, bp); - } + return; error0: @@ -912,7 +909,7 @@ xfs_bmap_local_to_extents( * We don't want to deal with the case of keeping inode data inline yet. * So sending the data fork of a regular inode is invalid. */ - ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK)); + ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK)); ifp = XFS_IFORK_PTR(ip, whichfork); ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL); @@ -1079,7 +1076,7 @@ xfs_bmap_add_attrfork_local( if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip)) return 0; - if (S_ISDIR(ip->i_d.di_mode)) { + if (S_ISDIR(VFS_I(ip)->i_mode)) { memset(&dargs, 0, sizeof(dargs)); dargs.geo = ip->i_mount->m_dir_geo; dargs.dp = ip; @@ -1091,7 +1088,7 @@ xfs_bmap_add_attrfork_local( return xfs_dir2_sf_to_block(&dargs); } - if (S_ISLNK(ip->i_d.di_mode)) + if (S_ISLNK(VFS_I(ip)->i_mode)) return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags, XFS_DATA_FORK, xfs_symlink_local_to_remote); @@ -3745,11 +3742,11 @@ xfs_bmap_btalloc( args.prod = align; if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod))) args.mod = (xfs_extlen_t)(args.prod - args.mod); - } else if (mp->m_sb.sb_blocksize >= PAGE_CACHE_SIZE) { + } else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) { args.prod = 1; args.mod = 0; } else { - args.prod = PAGE_CACHE_SIZE >> mp->m_sb.sb_blocklog; + args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog; if ((args.mod = (xfs_extlen_t)(do_mod(ap->offset, args.prod)))) args.mod = (xfs_extlen_t)(args.prod - args.mod); } @@ -4721,6 +4718,66 @@ error0: } /* + * When a delalloc extent is split (e.g., due to a hole punch), the original + * indlen reservation must be shared across the two new extents that are left + * behind. + * + * Given the original reservation and the worst case indlen for the two new + * extents (as calculated by xfs_bmap_worst_indlen()), split the original + * reservation fairly across the two new extents. If necessary, steal available + * blocks from a deleted extent to make up a reservation deficiency (e.g., if + * 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 +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 len1 = *indlen1; + xfs_filblks_t len2 = *indlen2; + xfs_filblks_t nres = len1 + len2; /* new total res. */ + xfs_filblks_t stolen = 0; + + /* + * Steal as many blocks as we can to try and satisfy the worst case + * indlen for both new extents. + */ + while (nres > ores && avail) { + nres--; + avail--; + stolen++; + } + + /* + * The only blocks available are those reserved for the original + * extent and what we can steal from the extent being removed. + * If this still isn't enough to satisfy the combined + * requirements for the two new extents, skim blocks off of each + * of the new reservations until they match what is available. + */ + while (nres > ores) { + if (len1) { + len1--; + nres--; + } + if (nres == ores) + break; + if (len2) { + len2--; + nres--; + } + } + + *indlen1 = len1; + *indlen2 = len2; + + return stolen; +} + +/* * Called by xfs_bmapi to update file extent records and the btree * after removing space (or undoing a delayed allocation). */ @@ -4984,28 +5041,29 @@ xfs_bmap_del_extent( XFS_IFORK_NEXT_SET(ip, whichfork, XFS_IFORK_NEXTENTS(ip, whichfork) + 1); } else { + xfs_filblks_t stolen; ASSERT(whichfork == XFS_DATA_FORK); - temp = xfs_bmap_worst_indlen(ip, temp); + + /* + * Distribute the original indlen reservation across the + * two new extents. Steal blocks from the deleted extent + * if necessary. Stealing blocks simply fudges the + * fdblocks accounting in xfs_bunmapi(). + */ + temp = xfs_bmap_worst_indlen(ip, got.br_blockcount); + temp2 = xfs_bmap_worst_indlen(ip, new.br_blockcount); + stolen = xfs_bmap_split_indlen(da_old, &temp, &temp2, + del->br_blockcount); + da_new = temp + temp2 - stolen; + del->br_blockcount -= stolen; + + /* + * Set the reservation for each extent. Warn if either + * is zero as this can lead to delalloc problems. + */ + WARN_ON_ONCE(!temp || !temp2); xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - temp2 = xfs_bmap_worst_indlen(ip, temp2); new.br_startblock = nullstartblock((int)temp2); - da_new = temp + temp2; - while (da_new > da_old) { - if (temp) { - temp--; - da_new--; - xfs_bmbt_set_startblock(ep, - nullstartblock((int)temp)); - } - if (da_new == da_old) - break; - if (temp2) { - temp2--; - da_new--; - new.br_startblock = - nullstartblock((int)temp2); - } - } } trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); xfs_iext_insert(ip, *idx + 1, 1, &new, state); @@ -5210,7 +5268,7 @@ xfs_bunmapi( * This is better than zeroing it. */ ASSERT(del.br_state == XFS_EXT_NORM); - ASSERT(xfs_trans_get_block_res(tp) > 0); + ASSERT(tp->t_blk_res > 0); /* * If this spans a realtime extent boundary, * chop it back to the start of the one we end at. @@ -5241,7 +5299,7 @@ xfs_bunmapi( del.br_startblock += mod; } else if ((del.br_startoff == start && (del.br_state == XFS_EXT_UNWRITTEN || - xfs_trans_get_block_res(tp) == 0)) || + tp->t_blk_res == 0)) || !xfs_sb_version_hasextflgbit(&mp->m_sb)) { /* * Can't make it unwritten. There isn't @@ -5296,9 +5354,37 @@ xfs_bunmapi( goto nodelete; } } + + /* + * If it's the case where the directory code is running + * with no block reservation, and the deleted block is in + * the middle of its extent, and the resulting insert + * of an extent would cause transformation to btree format, + * then reject it. The calling code will then swap + * blocks around instead. + * We have to do this now, rather than waiting for the + * conversion to btree format, since the transaction + * will be dirty. + */ + if (!wasdel && tp->t_blk_res == 0 && + XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */ + XFS_IFORK_MAXEXT(ip, whichfork) && + del.br_startoff > got.br_startoff && + del.br_startoff + del.br_blockcount < + got.br_startoff + got.br_blockcount) { + error = -ENOSPC; + goto error0; + } + + /* + * Unreserve quota and update realtime free space, if + * appropriate. If delayed allocation, update the inode delalloc + * counter now and wait to update the sb counters as + * xfs_bmap_del_extent() might need to borrow some blocks. + */ if (wasdel) { ASSERT(startblockval(del.br_startblock) > 0); - /* Update realtime/data freespace, unreserve quota */ if (isrt) { xfs_filblks_t rtexts; @@ -5309,8 +5395,6 @@ xfs_bunmapi( ip, -((long)del.br_blockcount), 0, XFS_QMOPT_RES_RTBLKS); } else { - xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, - false); (void)xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del.br_blockcount), 0, XFS_QMOPT_RES_REGBLKS); @@ -5321,32 +5405,16 @@ xfs_bunmapi( XFS_BTCUR_BPRV_WASDEL; } else if (cur) cur->bc_private.b.flags &= ~XFS_BTCUR_BPRV_WASDEL; - /* - * If it's the case where the directory code is running - * with no block reservation, and the deleted block is in - * the middle of its extent, and the resulting insert - * of an extent would cause transformation to btree format, - * then reject it. The calling code will then swap - * blocks around instead. - * We have to do this now, rather than waiting for the - * conversion to btree format, since the transaction - * will be dirty. - */ - if (!wasdel && xfs_trans_get_block_res(tp) == 0 && - XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS && - XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */ - XFS_IFORK_MAXEXT(ip, whichfork) && - del.br_startoff > got.br_startoff && - del.br_startoff + del.br_blockcount < - got.br_startoff + got.br_blockcount) { - error = -ENOSPC; - goto error0; - } + error = xfs_bmap_del_extent(ip, tp, &lastx, flist, cur, &del, &tmp_logflags, whichfork); logflags |= tmp_logflags; if (error) goto error0; + + if (!isrt && wasdel) + xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false); + bno = del.br_startoff - 1; nodelete: /* diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 1637c37bf..6282f6e70 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -461,7 +461,7 @@ xfs_bmbt_alloc_block( * reservation amount is insufficient then we may fail a * block allocation here and corrupt the filesystem. */ - args.minleft = xfs_trans_get_block_res(args.tp); + args.minleft = args.tp->t_blk_res; } else if (cur->bc_private.b.flist->xbf_low) { args.type = XFS_ALLOCTYPE_START_BNO; } else { @@ -470,7 +470,7 @@ xfs_bmbt_alloc_block( args.minlen = args.maxlen = args.prod = 1; args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL; - if (!args.wasdel && xfs_trans_get_block_res(args.tp) == 0) { + if (!args.wasdel && args.tp->t_blk_res == 0) { error = -ENOSPC; goto error0; } @@ -531,7 +531,6 @@ xfs_bmbt_free_block( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); - xfs_trans_binval(tp, bp); return 0; } diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index a0eb18ce3..1f88e1ce7 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -294,6 +294,21 @@ xfs_btree_sblock_verify_crc( return true; } +static int +xfs_btree_free_block( + struct xfs_btree_cur *cur, + struct xfs_buf *bp) +{ + int error; + + error = cur->bc_ops->free_block(cur, bp); + if (!error) { + xfs_trans_binval(cur->bc_tp, bp); + XFS_BTREE_STATS_INC(cur, free); + } + return error; +} + /* * Delete the btree cursor. */ @@ -3209,6 +3224,7 @@ xfs_btree_kill_iroot( int level; int index; int numrecs; + int error; #ifdef DEBUG union xfs_btree_ptr ptr; int i; @@ -3272,8 +3288,6 @@ xfs_btree_kill_iroot( cpp = xfs_btree_ptr_addr(cur, 1, cblock); #ifdef DEBUG for (i = 0; i < numrecs; i++) { - int error; - error = xfs_btree_check_ptr(cur, cpp, i, level - 1); if (error) { XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); @@ -3283,8 +3297,11 @@ xfs_btree_kill_iroot( #endif xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); - cur->bc_ops->free_block(cur, cbp); - XFS_BTREE_STATS_INC(cur, free); + error = xfs_btree_free_block(cur, cbp); + if (error) { + XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); + return error; + } cur->bc_bufs[level - 1] = NULL; be16_add_cpu(&block->bb_level, -1); @@ -3317,14 +3334,12 @@ xfs_btree_kill_root( */ cur->bc_ops->set_root(cur, newroot, -1); - error = cur->bc_ops->free_block(cur, bp); + error = xfs_btree_free_block(cur, bp); if (error) { XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR); return error; } - XFS_BTREE_STATS_INC(cur, free); - cur->bc_bufs[level] = NULL; cur->bc_ra[level] = 0; cur->bc_nlevels--; @@ -3830,10 +3845,9 @@ xfs_btree_delrec( } /* Free the deleted block. */ - error = cur->bc_ops->free_block(cur, rbp); + error = xfs_btree_free_block(cur, rbp); if (error) goto error0; - XFS_BTREE_STATS_INC(cur, free); /* * If we joined with the left neighbor, set the buffer in the diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h index b14bbd6bb..8d4d8bce4 100644 --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -641,6 +641,22 @@ 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. + */ +typedef 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 */ + } 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[1]; /* name & value bytes concatenated */ + } list[1]; /* variable sized array */ +} xfs_attr_shortform_t; + typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */ __be16 base; /* base of free region */ __be16 size; /* length of free region */ diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 2fb53a5c0..af0f9d171 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -176,7 +176,7 @@ xfs_dir_isempty( { xfs_dir2_sf_hdr_t *sfp; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (dp->i_d.di_size == 0) /* might happen during shutdown. */ return 1; if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp)) @@ -231,7 +231,7 @@ xfs_dir_init( struct xfs_da_args *args; int error; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); error = xfs_dir_ino_validate(tp->t_mountp, pdp->i_ino); if (error) return error; @@ -266,7 +266,7 @@ xfs_dir_createname( int rval; int v; /* type-checking value */ - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); if (inum) { rval = xfs_dir_ino_validate(tp->t_mountp, inum); if (rval) @@ -364,7 +364,7 @@ xfs_dir_lookup( int v; /* type-checking value */ int lock_mode; - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_lookup); /* @@ -443,7 +443,7 @@ xfs_dir_removename( int rval; int v; /* type-checking value */ - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); XFS_STATS_INC(dp->i_mount, xs_dir_remove); args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS); @@ -505,7 +505,7 @@ xfs_dir_replace( int rval; int v; /* type-checking value */ - ASSERT(S_ISDIR(dp->i_d.di_mode)); + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); rval = xfs_dir_ino_validate(tp->t_mountp, inum); if (rval) diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 63ee03db7..75a557432 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -2235,6 +2235,9 @@ xfs_dir2_node_trim_free( dp = args->dp; tp = args->trans; + + *rvalp = 0; + /* * Read the freespace block. */ @@ -2255,7 +2258,6 @@ xfs_dir2_node_trim_free( */ if (freehdr.nused > 0) { xfs_trans_brelse(tp, bp); - *rvalp = 0; return 0; } /* diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 66d702e6b..22297f9b0 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2403,8 +2403,8 @@ xfs_ialloc_compute_maxlevels( maxleafents = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG; - minleafrecs = mp->m_alloc_mnr[0]; - minnoderecs = mp->m_alloc_mnr[1]; + minleafrecs = mp->m_inobt_mnr[0]; + minnoderecs = mp->m_inobt_mnr[1]; maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs; for (level = 1; maxblocks > 1; level++) maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index c679f3c05..89c21d771 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -125,16 +125,8 @@ xfs_inobt_free_block( struct xfs_btree_cur *cur, struct xfs_buf *bp) { - xfs_fsblock_t fsbno; - int error; - - fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)); - error = xfs_free_extent(cur->bc_tp, fsbno, 1); - if (error) - return error; - - xfs_trans_binval(cur->bc_tp, bp); - return error; + return xfs_free_extent(cur->bc_tp, + XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1); } STATIC int diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 1aabfda66..9d9559eb2 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -195,28 +195,50 @@ xfs_imap_to_bp( } void -xfs_dinode_from_disk( - xfs_icdinode_t *to, - xfs_dinode_t *from) +xfs_inode_from_disk( + struct xfs_inode *ip, + struct xfs_dinode *from) { - to->di_magic = be16_to_cpu(from->di_magic); - to->di_mode = be16_to_cpu(from->di_mode); - to->di_version = from ->di_version; + struct xfs_icdinode *to = &ip->i_d; + struct inode *inode = VFS_I(ip); + + + /* + * Convert v1 inodes immediately to v2 inode format as this is the + * minimum inode version format we support in the rest of the code. + */ + to->di_version = from->di_version; + if (to->di_version == 1) { + set_nlink(inode, be16_to_cpu(from->di_onlink)); + to->di_projid_lo = 0; + to->di_projid_hi = 0; + to->di_version = 2; + } else { + set_nlink(inode, be32_to_cpu(from->di_nlink)); + to->di_projid_lo = be16_to_cpu(from->di_projid_lo); + to->di_projid_hi = be16_to_cpu(from->di_projid_hi); + } + to->di_format = from->di_format; - to->di_onlink = be16_to_cpu(from->di_onlink); to->di_uid = be32_to_cpu(from->di_uid); to->di_gid = be32_to_cpu(from->di_gid); - to->di_nlink = be32_to_cpu(from->di_nlink); - to->di_projid_lo = be16_to_cpu(from->di_projid_lo); - to->di_projid_hi = be16_to_cpu(from->di_projid_hi); - memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad)); to->di_flushiter = be16_to_cpu(from->di_flushiter); - to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec); - to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec); - to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec); - to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec); - to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec); - to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec); + + /* + * Time is signed, so need to convert to signed 32 bit before + * storing in inode timestamp which may be 64 bit. Otherwise + * a time before epoch is converted to a time long after epoch + * on 64 bit systems. + */ + inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec); + inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec); + inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec); + inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec); + inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec); + inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec); + inode->i_generation = be32_to_cpu(from->di_gen); + inode->i_mode = be16_to_cpu(from->di_mode); + to->di_size = be64_to_cpu(from->di_size); to->di_nblocks = be64_to_cpu(from->di_nblocks); to->di_extsize = be32_to_cpu(from->di_extsize); @@ -227,42 +249,96 @@ xfs_dinode_from_disk( to->di_dmevmask = be32_to_cpu(from->di_dmevmask); to->di_dmstate = be16_to_cpu(from->di_dmstate); to->di_flags = be16_to_cpu(from->di_flags); - to->di_gen = be32_to_cpu(from->di_gen); if (to->di_version == 3) { - to->di_changecount = be64_to_cpu(from->di_changecount); + inode->i_version = be64_to_cpu(from->di_changecount); to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec); to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec); to->di_flags2 = be64_to_cpu(from->di_flags2); - to->di_ino = be64_to_cpu(from->di_ino); - to->di_lsn = be64_to_cpu(from->di_lsn); - memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2)); - uuid_copy(&to->di_uuid, &from->di_uuid); } } void -xfs_dinode_to_disk( - xfs_dinode_t *to, - xfs_icdinode_t *from) +xfs_inode_to_disk( + struct xfs_inode *ip, + struct xfs_dinode *to, + xfs_lsn_t lsn) +{ + struct xfs_icdinode *from = &ip->i_d; + struct inode *inode = VFS_I(ip); + + to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC); + to->di_onlink = 0; + + to->di_version = from->di_version; + to->di_format = from->di_format; + to->di_uid = cpu_to_be32(from->di_uid); + to->di_gid = cpu_to_be32(from->di_gid); + to->di_projid_lo = cpu_to_be16(from->di_projid_lo); + to->di_projid_hi = cpu_to_be16(from->di_projid_hi); + + memset(to->di_pad, 0, sizeof(to->di_pad)); + to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec); + to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec); + to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec); + to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec); + to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec); + to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec); + 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); + + to->di_size = cpu_to_be64(from->di_size); + to->di_nblocks = cpu_to_be64(from->di_nblocks); + to->di_extsize = cpu_to_be32(from->di_extsize); + to->di_nextents = cpu_to_be32(from->di_nextents); + to->di_anextents = cpu_to_be16(from->di_anextents); + to->di_forkoff = from->di_forkoff; + to->di_aformat = from->di_aformat; + to->di_dmevmask = cpu_to_be32(from->di_dmevmask); + to->di_dmstate = cpu_to_be16(from->di_dmstate); + to->di_flags = cpu_to_be16(from->di_flags); + + if (from->di_version == 3) { + to->di_changecount = cpu_to_be64(inode->i_version); + to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec); + to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec); + to->di_flags2 = cpu_to_be64(from->di_flags2); + + to->di_ino = cpu_to_be64(ip->i_ino); + to->di_lsn = cpu_to_be64(lsn); + memset(to->di_pad2, 0, sizeof(to->di_pad2)); + uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid); + to->di_flushiter = 0; + } else { + to->di_flushiter = cpu_to_be16(from->di_flushiter); + } +} + +void +xfs_log_dinode_to_disk( + struct xfs_log_dinode *from, + struct xfs_dinode *to) { to->di_magic = cpu_to_be16(from->di_magic); to->di_mode = cpu_to_be16(from->di_mode); - to->di_version = from ->di_version; + to->di_version = from->di_version; to->di_format = from->di_format; - to->di_onlink = cpu_to_be16(from->di_onlink); + to->di_onlink = 0; to->di_uid = cpu_to_be32(from->di_uid); to->di_gid = cpu_to_be32(from->di_gid); to->di_nlink = cpu_to_be32(from->di_nlink); to->di_projid_lo = cpu_to_be16(from->di_projid_lo); to->di_projid_hi = cpu_to_be16(from->di_projid_hi); memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad)); + to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec); to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec); to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec); to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec); to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec); to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec); + to->di_size = cpu_to_be64(from->di_size); to->di_nblocks = cpu_to_be64(from->di_nblocks); to->di_extsize = cpu_to_be32(from->di_extsize); @@ -367,13 +443,10 @@ xfs_iread( !(mp->m_flags & XFS_MOUNT_IKEEP)) { /* initialise the on-disk inode core */ memset(&ip->i_d, 0, sizeof(ip->i_d)); - ip->i_d.di_magic = XFS_DINODE_MAGIC; - ip->i_d.di_gen = prandom_u32(); - if (xfs_sb_version_hascrc(&mp->m_sb)) { + VFS_I(ip)->i_generation = prandom_u32(); + if (xfs_sb_version_hascrc(&mp->m_sb)) ip->i_d.di_version = 3; - ip->i_d.di_ino = ip->i_ino; - uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_meta_uuid); - } else + else ip->i_d.di_version = 2; return 0; } @@ -403,7 +476,7 @@ xfs_iread( * Otherwise, just get the truly permanent information. */ if (dip->di_mode) { - xfs_dinode_from_disk(&ip->i_d, dip); + xfs_inode_from_disk(ip, dip); error = xfs_iformat_fork(ip, dip); if (error) { #ifdef DEBUG @@ -417,16 +490,10 @@ xfs_iread( * Partial initialisation of the in-core inode. Just the bits * that xfs_ialloc won't overwrite or relies on being correct. */ - ip->i_d.di_magic = be16_to_cpu(dip->di_magic); ip->i_d.di_version = dip->di_version; - ip->i_d.di_gen = be32_to_cpu(dip->di_gen); + VFS_I(ip)->i_generation = be32_to_cpu(dip->di_gen); ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter); - if (dip->di_version == 3) { - ip->i_d.di_ino = be64_to_cpu(dip->di_ino); - uuid_copy(&ip->i_d.di_uuid, &dip->di_uuid); - } - /* * Make sure to pull in the mode here as well in * case the inode is released without being used. @@ -434,25 +501,10 @@ xfs_iread( * the inode is already free and not try to mess * with the uninitialized part of it. */ - ip->i_d.di_mode = 0; - } - - /* - * Automatically convert version 1 inode formats in memory to version 2 - * inode format. If the inode is modified, it will get logged and - * rewritten as a version 2 inode. We can do this because we set the - * superblock feature bit for v2 inodes unconditionally during mount - * and it means the reast of the code can assume the inode version is 2 - * or higher. - */ - if (ip->i_d.di_version == 1) { - ip->i_d.di_version = 2; - memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); - ip->i_d.di_nlink = ip->i_d.di_onlink; - ip->i_d.di_onlink = 0; - xfs_set_projid(ip, 0); + VFS_I(ip)->i_mode = 0; } + ASSERT(ip->i_d.di_version >= 2); ip->i_delayed_blks = 0; /* diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 9308c47f2..7c4dd321b 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -20,7 +20,36 @@ struct xfs_inode; struct xfs_dinode; -struct xfs_icdinode; + +/* + * In memory representation of the XFS inode. This is held in the in-core struct + * xfs_inode and represents the current on disk values but the structure is not + * in on-disk format. That is, this structure is always translated to on-disk + * format specific structures at the appropriate time. + */ +struct xfs_icdinode { + __int8_t di_version; /* inode version */ + __int8_t di_format; /* format of di_c data */ + __uint16_t di_flushiter; /* incremented on flush */ + __uint32_t di_uid; /* owner's user id */ + __uint32_t di_gid; /* owner's group id */ + __uint16_t di_projid_lo; /* lower part of owner's project id */ + __uint16_t di_projid_hi; /* higher part of owner's project id */ + xfs_fsize_t di_size; /* number of bytes in file */ + xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */ + xfs_extlen_t di_extsize; /* basic/minimum extent size for file */ + xfs_extnum_t di_nextents; /* number of extents in data fork */ + xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/ + __uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */ + __int8_t di_aformat; /* format of attr fork's data */ + __uint32_t di_dmevmask; /* DMIG event mask */ + __uint16_t di_dmstate; /* DMIG state info */ + __uint16_t di_flags; /* random flags, XFS_DIFLAG_... */ + + __uint64_t di_flags2; /* more random flags */ + + xfs_ictimestamp_t di_crtime; /* time created */ +}; /* * Inode location information. Stored in the inode and passed to @@ -38,8 +67,11 @@ int xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *, int xfs_iread(struct xfs_mount *, struct xfs_trans *, struct xfs_inode *, uint); void xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *); -void xfs_dinode_to_disk(struct xfs_dinode *to, struct xfs_icdinode *from); -void xfs_dinode_from_disk(struct xfs_icdinode *to, struct xfs_dinode *from); +void xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to, + xfs_lsn_t lsn); +void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); +void xfs_log_dinode_to_disk(struct xfs_log_dinode *from, + struct xfs_dinode *to); #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 0defbd02f..11faf7df1 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -31,6 +31,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_attr_sf.h" +#include "xfs_da_format.h" kmem_zone_t *xfs_ifork_zone; @@ -120,7 +121,7 @@ xfs_iformat_fork( return -EFSCORRUPTED; } - switch (ip->i_d.di_mode & S_IFMT) { + switch (VFS_I(ip)->i_mode & S_IFMT) { case S_IFIFO: case S_IFCHR: case S_IFBLK: diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 265314690..d54a8018b 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -290,6 +290,7 @@ typedef struct xfs_inode_log_format_64 { __int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_64_t; + /* * Flags for xfs_trans_log_inode flags field. */ @@ -360,15 +361,15 @@ typedef struct xfs_ictimestamp { } xfs_ictimestamp_t; /* - * NOTE: This structure must be kept identical to struct xfs_dinode - * except for the endianness annotations. + * Define the format of the inode core that is logged. This structure must be + * kept identical to struct xfs_dinode except for the endianness annotations. */ -typedef struct xfs_icdinode { +struct xfs_log_dinode { __uint16_t di_magic; /* inode magic # = XFS_DINODE_MAGIC */ __uint16_t di_mode; /* mode and type of file */ __int8_t di_version; /* inode version */ __int8_t di_format; /* format of di_c data */ - __uint16_t di_onlink; /* old number of links to file */ + __uint8_t di_pad3[2]; /* unused in v2/3 inodes */ __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 */ @@ -407,13 +408,13 @@ typedef struct xfs_icdinode { uuid_t di_uuid; /* UUID of the filesystem */ /* structure must be padded to 64 bit alignment */ -} xfs_icdinode_t; +}; -static inline uint xfs_icdinode_size(int version) +static inline uint xfs_log_dinode_size(int version) { if (version == 3) - return sizeof(struct xfs_icdinode); - return offsetof(struct xfs_icdinode, di_next_unlinked); + return sizeof(struct xfs_log_dinode); + return offsetof(struct xfs_log_dinode, di_next_unlinked); } /* @@ -495,6 +496,8 @@ enum xfs_blft { XFS_BLFT_ATTR_LEAF_BUF, XFS_BLFT_ATTR_RMT_BUF, XFS_BLFT_SB_BUF, + XFS_BLFT_RTBITMAP_BUF, + XFS_BLFT_RTSUMMARY_BUF, XFS_BLFT_MAX_BUF = (1 << XFS_BLFT_BITS), }; diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index f51078f1e..8eed51275 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -37,7 +37,7 @@ typedef __uint16_t xfs_qwarncnt_t; #define XFS_DQ_PROJ 0x0002 /* project quota */ #define XFS_DQ_GROUP 0x0004 /* a group quota */ #define XFS_DQ_DIRTY 0x0008 /* dquot is dirty */ -#define XFS_DQ_FREEING 0x0010 /* dquot is beeing torn down */ +#define XFS_DQ_FREEING 0x0010 /* dquot is being torn down */ #define XFS_DQ_ALLTYPES (XFS_DQ_USER|XFS_DQ_PROJ|XFS_DQ_GROUP) @@ -116,6 +116,7 @@ typedef __uint16_t xfs_qwarncnt_t; #define XFS_QMOPT_DQREPAIR 0x0001000 /* repair dquot if damaged */ #define XFS_QMOPT_GQUOTA 0x0002000 /* group dquot requested */ #define XFS_QMOPT_ENOSPC 0x0004000 /* enospc instead of edquot (prj) */ +#define XFS_QMOPT_DQNEXT 0x0008000 /* return next dquot >= this ID */ /* * flags to xfs_trans_mod_dquot to indicate which field needs to be diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 9b59ffa1f..951c044e2 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -42,6 +42,31 @@ */ /* + * 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 void +xfs_rtbuf_verify_read( + struct xfs_buf *bp) +{ + return; +} + +static void +xfs_rtbuf_verify_write( + struct xfs_buf *bp) +{ + return; +} + +const struct xfs_buf_ops xfs_rtbuf_ops = { + .name = "rtbuf", + .verify_read = xfs_rtbuf_verify_read, + .verify_write = xfs_rtbuf_verify_write, +}; + +/* * Get a buffer for the bitmap or summary file block specified. * The buffer is returned read and locked. */ @@ -68,9 +93,12 @@ xfs_rtbuf_get( ASSERT(map.br_startblock != NULLFSBLOCK); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, map.br_startblock), - mp->m_bsize, 0, &bp, NULL); + mp->m_bsize, 0, &bp, &xfs_rtbuf_ops); if (error) return error; + + xfs_trans_buf_set_type(tp, bp, issum ? XFS_BLFT_RTSUMMARY_BUF + : XFS_BLFT_RTBITMAP_BUF); *bpp = bp; return 0; } @@ -983,7 +1011,7 @@ xfs_rtfree_extent( mp->m_sb.sb_rextents) { if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM; - *(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0; + *(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0; xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); } return 0; diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index b25bb9a34..961e6475a 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -27,7 +27,6 @@ extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t, extern void xfs_perag_put(struct xfs_perag *pag); extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t); -extern void xfs_sb_calc_crc(struct xfs_buf *bp); extern void xfs_log_sb(struct xfs_trans *tp); extern int xfs_sync_sb(struct xfs_mount *mp, bool wait); extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp); diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 15c3ceb84..81ac87083 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -53,6 +53,7 @@ extern const struct xfs_buf_ops xfs_dquot_buf_ra_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; +extern const struct xfs_buf_ops xfs_rtbuf_ops; /* * Transaction types. Used to distinguish types of buffers. These never reach |