diff options
Diffstat (limited to 'fs/xfs')
54 files changed, 1169 insertions, 570 deletions
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 339c696..bb2beae 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -24,24 +24,6 @@ #include "kmem.h" #include "xfs_message.h" -/* - * Greedy allocation. May fail and may return vmalloced memory. - */ -void * -kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize) -{ - void *ptr; - size_t kmsize = maxsize; - - while (!(ptr = vzalloc(kmsize))) { - if ((kmsize >>= 1) <= minsize) - kmsize = minsize; - } - if (ptr) - *size = kmsize; - return ptr; -} - void * kmem_alloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 689f746..f0fc84f 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -69,8 +69,6 @@ static inline void kmem_free(const void *ptr) } -extern void *kmem_zalloc_greedy(size_t *, size_t, size_t); - static inline void * kmem_zalloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index 33db69b..eed8f58 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -157,7 +157,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -217,7 +218,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * 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) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 9f06a21..c3702cd 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1579,6 +1579,10 @@ xfs_alloc_ag_vextent_small( bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto error0; + } xfs_trans_binval(args->tp, bp); } args->len = 1; @@ -2136,6 +2140,10 @@ xfs_alloc_fix_freelist( if (error) goto out_agbp_relse; bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto out_agbp_relse; + } xfs_trans_binval(tp, bp); } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 2852521..c6c15e5 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -351,7 +351,7 @@ xfs_attr3_leaf_read( err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp, XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 2a8cbd1..7eb9970 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -579,7 +579,7 @@ xfs_bmap_validate_ret( #else #define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0) -#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) +#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) do { } while (0) #endif /* DEBUG */ /* @@ -4057,6 +4057,17 @@ xfs_trim_extent( } } +/* trim extent to within eof */ +void +xfs_trim_extent_eof( + struct xfs_bmbt_irec *irec, + struct xfs_inode *ip) + +{ + xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount, + i_size_read(VFS_I(ip)))); +} + /* * Trim the returned map to the required bounds */ @@ -5555,6 +5566,8 @@ __xfs_bunmapi( int whichfork; /* data or attribute fork */ xfs_fsblock_t sum; xfs_filblks_t len = *rlen; /* length to unmap in file */ + xfs_fileoff_t max_len; + xfs_agnumber_t prev_agno = NULLAGNUMBER, agno; trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_); @@ -5576,6 +5589,16 @@ __xfs_bunmapi( ASSERT(len > 0); ASSERT(nexts >= 0); + /* + * Guesstimate how many blocks we can unmap without running the risk of + * blowing out the transaction with a mix of EFIs and reflink + * adjustments. + */ + if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) + max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); + else + max_len = len; + if (!(ifp->if_flags & XFS_IFEXTENTS) && (error = xfs_iread_extents(tp, ip, whichfork))) return error; @@ -5621,7 +5644,7 @@ __xfs_bunmapi( extno = 0; while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 && - (nexts == 0 || extno < nexts)) { + (nexts == 0 || extno < nexts) && max_len > 0) { /* * Is the found extent after a hole in which bno lives? * Just back up to the previous extent, if so. @@ -5647,6 +5670,17 @@ __xfs_bunmapi( ASSERT(ep != NULL); del = got; wasdel = isnullstartblock(del.br_startblock); + + /* + * Make sure we don't touch multiple AGF headers out of order + * in a single transaction, as that could cause AB-BA deadlocks. + */ + if (!wasdel) { + agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); + if (prev_agno != NULLAGNUMBER && prev_agno > agno) + break; + prev_agno = agno; + } if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; @@ -5655,6 +5689,15 @@ __xfs_bunmapi( } if (del.br_startoff + del.br_blockcount > bno + 1) del.br_blockcount = bno + 1 - del.br_startoff; + + /* How much can we safely unmap? */ + if (max_len < del.br_blockcount) { + del.br_startoff += del.br_blockcount - max_len; + if (!wasdel) + del.br_startblock += del.br_blockcount - max_len; + del.br_blockcount = max_len; + } + sum = del.br_startblock + del.br_blockcount; if (isrt && (mod = do_mod(sum, mp->m_sb.sb_rextsize))) { @@ -5835,6 +5878,7 @@ __xfs_bunmapi( if (!isrt && wasdel) xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false); + max_len -= del.br_blockcount; bno = del.br_startoff - 1; nodelete: /* @@ -6604,25 +6648,33 @@ xfs_bmap_finish_one( int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, + xfs_filblks_t *blockcount, xfs_exntst_t state) { struct xfs_bmbt_irec bmap; int nimaps = 1; xfs_fsblock_t firstfsb; int flags = XFS_BMAPI_REMAP; - int done; int error = 0; bmap.br_startblock = startblock; bmap.br_startoff = startoff; - bmap.br_blockcount = blockcount; + bmap.br_blockcount = *blockcount; bmap.br_state = state; + /* + * firstfsb is tied to the transaction lifetime and is used to + * ensure correct AG locking order and schedule work item + * continuations. XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us + * to only making one bmap call per transaction, so it should + * be safe to have it as a local variable here. + */ + firstfsb = NULLFSBLOCK; + 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); + ip->i_ino, whichfork, startoff, *blockcount, state); if (whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK) return -EFSCORRUPTED; @@ -6641,12 +6693,11 @@ xfs_bmap_finish_one( bmap.br_blockcount, flags, &firstfsb, bmap.br_blockcount, &bmap, &nimaps, dfops); + *blockcount = 0; break; case XFS_BMAP_UNMAP: - error = xfs_bunmapi(tp, ip, bmap.br_startoff, - bmap.br_blockcount, flags, 1, &firstfsb, - dfops, &done); - ASSERT(done); + error = __xfs_bunmapi(tp, ip, startoff, blockcount, + XFS_BMAPI_REMAP, 1, &firstfsb, dfops); break; default: ASSERT(0); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index e7d40b3..f1446d1 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -196,6 +196,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); +void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, @@ -265,7 +266,7 @@ struct xfs_bmap_intent { int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops, struct xfs_inode *ip, enum xfs_bmap_intent_type type, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, xfs_exntst_t state); + xfs_filblks_t *blockcount, xfs_exntst_t state); int xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, struct xfs_inode *ip, struct xfs_bmbt_irec *imap); int xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 5c39186..9968a74 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -888,6 +888,7 @@ xfs_bmbt_change_owner( cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork); if (!cur) return -ENOMEM; + cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER; error = xfs_btree_change_owner(cur, new_owner, buffer_list); xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 91c6891..4ad1e21 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -714,7 +714,8 @@ xfs_btree_firstrec( * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); - xfs_btree_check_block(cur, block, level, bp); + if (xfs_btree_check_block(cur, block, level, bp)) + return 0; /* * It's empty, there is no such record. */ @@ -743,7 +744,8 @@ xfs_btree_lastrec( * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); - xfs_btree_check_block(cur, block, level, bp); + if (xfs_btree_check_block(cur, block, level, bp)) + return 0; /* * It's empty, there is no such record. */ @@ -1772,6 +1774,7 @@ xfs_btree_lookup_get_block( /* Check the inode owner since the verifiers don't. */ if (xfs_sb_version_hascrc(&cur->bc_mp->m_sb) && + !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_INVALID_OWNER) && (cur->bc_flags & XFS_BTREE_LONG_PTRS) && be64_to_cpu((*blkp)->bb_u.l.bb_owner) != cur->bc_private.b.ip->i_ino) @@ -4432,10 +4435,15 @@ 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_flags & XFS_BTREE_LONG_PTRS) { + 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); - else + } else { + if (block->bb_u.s.bb_owner == cpu_to_be32(bbcoi->new_owner)) + return 0; block->bb_u.s.bb_owner = cpu_to_be32(bbcoi->new_owner); + } /* * If the block is a root block hosted in an inode, we might not have a @@ -4444,16 +4452,19 @@ xfs_btree_block_change_owner( * block is formatted into the on-disk inode fork. We still change it, * though, so everything is consistent in memory. */ - if (bp) { - if (cur->bc_tp) { - xfs_trans_ordered_buf(cur->bc_tp, bp); + if (!bp) { + ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(level == cur->bc_nlevels - 1); + return 0; + } + + if (cur->bc_tp) { + if (!xfs_trans_ordered_buf(cur->bc_tp, bp)) { xfs_btree_log_block(cur, bp, XFS_BB_OWNER); - } else { - xfs_buf_delwri_queue(bp, bbcoi->buffer_list); + return -EAGAIN; } } else { - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); - ASSERT(level == cur->bc_nlevels - 1); + xfs_buf_delwri_queue(bp, bbcoi->buffer_list); } return 0; diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 3b0fc1a..33c7be2 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -268,7 +268,8 @@ typedef struct xfs_btree_cur short forksize; /* fork's inode space */ char whichfork; /* data or attr fork */ char flags; /* flags */ -#define XFS_BTCUR_BPRV_WASDEL 1 /* was delayed */ +#define XFS_BTCUR_BPRV_WASDEL (1<<0) /* was delayed */ +#define XFS_BTCUR_BPRV_INVALID_OWNER (1<<1) /* for ext swap */ } b; } bc_private; /* per-btree type data */ } xfs_btree_cur_t; diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 1bdf288..b305dbf 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -263,7 +263,7 @@ xfs_da3_node_read( err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp, which_fork, &xfs_da3_node_buf_ops); - if (!err && tp) { + if (!err && tp && *bpp) { struct xfs_da_blkinfo *info = (*bpp)->b_addr; int type; diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index aa17cb7..43c902f 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -139,7 +139,7 @@ xfs_dir3_block_read( err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp, XFS_DATA_FORK, &xfs_dir3_block_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index b887fb2..f2e342e 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -268,7 +268,7 @@ xfs_dir3_leaf_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF); return err; } @@ -285,7 +285,7 @@ xfs_dir3_leafn_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index a2818f6..42fef07 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -368,8 +368,6 @@ xfs_ialloc_inode_init( * transaction and pin the log appropriately. */ xfs_trans_ordered_buf(tp, fbuf); - xfs_trans_log_buf(tp, fbuf, 0, - BBTOB(fbuf->b_length) - 1); } } else { fbuf->b_flags |= XBF_DONE; @@ -1123,6 +1121,7 @@ xfs_dialloc_ag_inobt( int error; int offset; int i, j; + int searchdistance = 10; pag = xfs_perag_get(mp, agno); @@ -1149,7 +1148,6 @@ xfs_dialloc_ag_inobt( if (pagno == agno) { int doneleft; /* done, to the left */ int doneright; /* done, to the right */ - int searchdistance = 10; error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i); if (error) @@ -1210,21 +1208,9 @@ xfs_dialloc_ag_inobt( /* * Loop until we find an inode chunk with a free inode. */ - while (!doneleft || !doneright) { + while (--searchdistance > 0 && (!doneleft || !doneright)) { int useleft; /* using left inode chunk this time */ - if (!--searchdistance) { - /* - * Not in range - save last search - * location and allocate a new inode - */ - xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); - pag->pagl_leftrec = trec.ir_startino; - pag->pagl_rightrec = rec.ir_startino; - pag->pagl_pagino = pagino; - goto newino; - } - /* figure out the closer block if both are valid. */ if (!doneleft && !doneright) { useleft = pagino - @@ -1236,13 +1222,13 @@ xfs_dialloc_ag_inobt( /* free inodes to the left? */ if (useleft && trec.ir_freecount) { - rec = trec; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); cur = tcur; pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; + rec = trec; goto alloc_inode; } @@ -1268,26 +1254,37 @@ xfs_dialloc_ag_inobt( goto error1; } - /* - * We've reached the end of the btree. because - * we are only searching a small chunk of the - * btree each search, there is obviously free - * inodes closer to the parent inode than we - * are now. restart the search again. - */ - pag->pagl_pagino = NULLAGINO; - pag->pagl_leftrec = NULLAGINO; - pag->pagl_rightrec = NULLAGINO; - xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); - xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); - goto restart_pagno; + if (searchdistance <= 0) { + /* + * Not in range - save last search + * location and allocate a new inode + */ + xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); + pag->pagl_leftrec = trec.ir_startino; + pag->pagl_rightrec = rec.ir_startino; + pag->pagl_pagino = pagino; + + } else { + /* + * We've reached the end of the btree. because + * we are only searching a small chunk of the + * btree each search, there is obviously free + * inodes closer to the parent inode than we + * are now. restart the search again. + */ + pag->pagl_pagino = NULLAGINO; + pag->pagl_leftrec = NULLAGINO; + pag->pagl_rightrec = NULLAGINO; + xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + goto restart_pagno; + } } /* * In a different AG from the parent. * See if the most recently allocated block has any free. */ -newino: if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), XFS_LOOKUP_EQ, &i); diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 8a37efe..4e30448 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -1539,14 +1539,11 @@ xfs_iext_realloc_indirect( xfs_ifork_t *ifp, /* inode fork pointer */ int new_size) /* new indirection array size */ { - int nlists; /* number of irec's (ex lists) */ - int size; /* current indirection array size */ - ASSERT(ifp->if_flags & XFS_IFEXTIREC); - nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; - size = nlists * sizeof(xfs_ext_irec_t); ASSERT(ifp->if_real_bytes); - ASSERT((new_size >= 0) && (new_size != size)); + ASSERT((new_size >= 0) && + (new_size != ((ifp->if_real_bytes / XFS_IEXT_BUFSZ) * + sizeof(xfs_ext_irec_t)))); if (new_size == 0) { xfs_iext_destroy(ifp); } else { diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 083cdd6..ce6958b 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -270,6 +270,7 @@ typedef struct xfs_inode_log_format { __uint32_t ilf_fields; /* flags for fields logged */ __uint16_t ilf_asize; /* size of attr d/ext/root */ __uint16_t ilf_dsize; /* size of data/ext/root */ + __uint32_t ilf_pad; /* pad for 64 bit boundary */ __uint64_t ilf_ino; /* inode number */ union { __uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -280,29 +281,17 @@ typedef struct xfs_inode_log_format { __int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_t; -typedef struct xfs_inode_log_format_32 { - __uint16_t ilf_type; /* inode log item type */ - __uint16_t ilf_size; /* size of this item */ - __uint32_t ilf_fields; /* flags for fields logged */ - __uint16_t ilf_asize; /* size of attr d/ext/root */ - __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint64_t ilf_ino; /* inode number */ - union { - __uint32_t ilfu_rdev; /* rdev value for dev inode*/ - uuid_t ilfu_uuid; /* mount point value */ - } ilf_u; - __int64_t ilf_blkno; /* blkno of inode buffer */ - __int32_t ilf_len; /* len of inode buffer */ - __int32_t ilf_boffset; /* off of inode in buffer */ -} __attribute__((packed)) xfs_inode_log_format_32_t; - -typedef struct xfs_inode_log_format_64 { +/* + * Old 32 bit systems will log in this format without the 64 bit + * alignment padding. Recovery will detect this and convert it to the + * correct format. + */ +struct xfs_inode_log_format_32 { __uint16_t ilf_type; /* inode log item type */ __uint16_t ilf_size; /* size of this item */ __uint32_t ilf_fields; /* flags for fields logged */ __uint16_t ilf_asize; /* size of attr d/ext/root */ __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint32_t ilf_pad; /* pad for 64 bit boundary */ __uint64_t ilf_ino; /* inode number */ union { __uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -311,7 +300,7 @@ typedef struct xfs_inode_log_format_64 { __int64_t ilf_blkno; /* blkno of inode buffer */ __int32_t ilf_len; /* len of inode buffer */ __int32_t ilf_boffset; /* off of inode in buffer */ -} xfs_inode_log_format_64_t; +} __attribute__((packed)); /* diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 82a38d8..d71cb63 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -784,14 +784,6 @@ xfs_refcount_merge_extents( } /* - * While we're adjusting the refcounts records of an extent, we have - * to keep an eye on the number of extents we're dirtying -- run too - * many in a single transaction and we'll exceed the transaction's - * reservation and crash the fs. Each record adds 12 bytes to the - * log (plus any key updates) so we'll conservatively assume 24 bytes - * per record. We must also leave space for btree splits on both ends - * of the range and space for the CUD and a new CUI. - * * XXX: This is a pretty hand-wavy estimate. The penalty for guessing * true incorrectly is a shutdown FS; the penalty for guessing false * incorrectly is more transaction rolls than might be necessary. @@ -822,7 +814,7 @@ xfs_refcount_still_have_space( else if (overhead > cur->bc_tp->t_log_res) return false; return cur->bc_tp->t_log_res - overhead > - cur->bc_private.a.priv.refc.nr_ops * 32; + cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } /* @@ -1648,6 +1640,10 @@ xfs_refcount_recover_cow_leftovers( error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (error) goto out_trans; + if (!agbp) { + error = -ENOMEM; + goto out_trans; + } cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL); /* Find all the leftover CoW staging extents. */ diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 098dc66..eafb9d1 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp, extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, xfs_agnumber_t agno); +/* + * While we're adjusting the refcounts records of an extent, we have + * to keep an eye on the number of extents we're dirtying -- run too + * many in a single transaction and we'll exceed the transaction's + * reservation and crash the fs. Each record adds 12 bytes to the + * log (plus any key updates) so we'll conservatively assume 32 bytes + * per record. We must also leave space for btree splits on both ends + * of the range and space for the CUD and a new CUI. + */ +#define XFS_REFCOUNT_ITEM_OVERHEAD 32 + +static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res) +{ + return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD; +} + #endif /* __XFS_REFCOUNT_H__ */ diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index b468e04..3354140 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -170,8 +170,8 @@ xfs_get_acl(struct inode *inode, int type) return acl; } -STATIC int -__xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) +int +__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct xfs_inode *ip = XFS_I(inode); unsigned char *ea_name; @@ -247,6 +247,8 @@ xfs_set_mode(struct inode *inode, umode_t mode) int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + umode_t mode; + bool set_mode = false; int error = 0; if (!acl) @@ -257,16 +259,24 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode; - error = posix_acl_update_mode(inode, &mode, &acl); if (error) return error; - error = xfs_set_mode(inode, mode); - if (error) - return error; + set_mode = true; } set_acl: - return __xfs_set_acl(inode, type, acl); + error = __xfs_set_acl(inode, acl, type); + if (error) + return error; + + /* + * We set the mode after successfully updating the ACL xattr because the + * xattr update can fail at ENOSPC and we don't want to change the mode + * if the ACL update hasn't been applied. + */ + if (set_mode) + error = xfs_set_mode(inode, mode); + + return error; } diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 286fa89..0432731 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -24,6 +24,7 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); #else static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) { diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5789814..d31cd1e 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -90,11 +90,11 @@ xfs_find_bdev_for_inode( * associated buffer_heads, paying attention to the start and end offsets that * we need to process on the page. * - * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last - * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or - * the page at all, as we may be racing with memory reclaim and it can free both - * the bufferhead chain and the page as it will see the page as clean and - * unused. + * Note that we open code the action in end_buffer_async_write here so that we + * only have to iterate over the buffers attached to the page once. This is not + * only more efficient, but also ensures that we only calls end_page_writeback + * at the end of the iteration, and thus avoids the pitfall of having the page + * and buffers potentially freed after every call to end_buffer_async_write. */ static void xfs_finish_page_writeback( @@ -102,29 +102,45 @@ xfs_finish_page_writeback( struct bio_vec *bvec, int error) { - unsigned int end = bvec->bv_offset + bvec->bv_len - 1; - struct buffer_head *head, *bh, *next; + struct buffer_head *head = page_buffers(bvec->bv_page), *bh = head; + bool busy = false; unsigned int off = 0; - unsigned int bsize; + unsigned long flags; ASSERT(bvec->bv_offset < PAGE_SIZE); ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0); - ASSERT(end < PAGE_SIZE); + ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE); ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); - bh = head = page_buffers(bvec->bv_page); - - bsize = bh->b_size; + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &head->b_state); do { - if (off > end) - break; - next = bh->b_this_page; - if (off < bvec->bv_offset) - goto next_bh; - bh->b_end_io(bh, !error); -next_bh: - off += bsize; - } while ((bh = next) != head); + if (off >= bvec->bv_offset && + off < bvec->bv_offset + bvec->bv_len) { + ASSERT(buffer_async_write(bh)); + ASSERT(bh->b_end_io == NULL); + + if (error) { + mapping_set_error(bvec->bv_page->mapping, -EIO); + set_buffer_write_io_error(bh); + clear_buffer_uptodate(bh); + SetPageError(bvec->bv_page); + } else { + set_buffer_uptodate(bh); + } + clear_buffer_async_write(bh); + unlock_buffer(bh); + } else if (buffer_async_write(bh)) { + ASSERT(buffer_locked(bh)); + busy = true; + } + off += bh->b_size; + } while ((bh = bh->b_this_page) != head); + bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); + local_irq_restore(flags); + + if (!busy) + end_page_writeback(bvec->bv_page); } /* @@ -138,8 +154,10 @@ xfs_destroy_ioend( int error) { struct inode *inode = ioend->io_inode; - struct bio *last = ioend->io_bio; - struct bio *bio, *next; + struct bio *bio = &ioend->io_inline_bio; + struct bio *last = ioend->io_bio, *next; + u64 start = bio->bi_iter.bi_sector; + bool quiet = bio_flagged(bio, BIO_QUIET); for (bio = &ioend->io_inline_bio; bio; bio = next) { struct bio_vec *bvec; @@ -160,6 +178,11 @@ xfs_destroy_ioend( bio_put(bio); } + + if (unlikely(error && !quiet)) { + xfs_err_ratelimited(XFS_I(inode)->i_mount, + "writeback error on sector %llu", start); + } } /* @@ -312,7 +335,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); @@ -414,6 +438,19 @@ xfs_imap_valid( { offset >>= inode->i_blkbits; + /* + * We have to make sure the cached mapping is within EOF to protect + * against eofblocks trimming on file release leaving us with a stale + * mapping. Otherwise, a page for a subsequent file extending buffered + * write could get picked up by this writeback cycle and written to the + * wrong blocks. + * + * Note that what we really want here is a generic mapping invalidation + * mechanism to protect us from arbitrary extent modifying contexts, not + * just eofblocks. + */ + xfs_trim_extent_eof(imap, XFS_I(inode)); + return offset >= imap->br_startoff && offset < imap->br_startoff + imap->br_blockcount; } @@ -427,7 +464,8 @@ xfs_start_buffer_writeback( ASSERT(!buffer_delay(bh)); ASSERT(!buffer_unwritten(bh)); - mark_buffer_async_write(bh); + bh->b_end_io = NULL; + set_buffer_async_write(bh); set_buffer_uptodate(bh); clear_buffer_dirty(bh); } @@ -701,6 +739,14 @@ xfs_vm_invalidatepage( { trace_xfs_invalidatepage(page->mapping->host, page, offset, length); + + /* + * If we are invalidating the entire page, clear the dirty state from it + * so that we can check for attempts to release dirty cached pages in + * xfs_vm_releasepage(). + */ + if (offset == 0 && length >= PAGE_SIZE) + cancel_dirty_page(page); block_invalidatepage(page, offset, length); } @@ -1156,25 +1202,27 @@ xfs_vm_releasepage( * mm accommodates an old ext3 case where clean pages might not have had * the dirty bit cleared. Thus, it can send actual dirty pages to * ->releasepage() via shrink_active_list(). Conversely, - * block_invalidatepage() can send pages that are still marked dirty - * but otherwise have invalidated buffers. + * block_invalidatepage() can send pages that are still marked dirty but + * otherwise have invalidated buffers. * * We want to release the latter to avoid unnecessary buildup of the - * LRU, skip the former and warn if we've left any lingering - * delalloc/unwritten buffers on clean pages. Skip pages with delalloc - * or unwritten buffers and warn if the page is not dirty. Otherwise - * try to release the buffers. + * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages + * that are entirely invalidated and need to be released. Hence the + * only time we should get dirty pages here is through + * shrink_active_list() and so we can simply skip those now. + * + * warn if we've left any lingering delalloc/unwritten buffers on clean + * or invalidated pages we are about to release. */ + if (PageDirty(page)) + return 0; + xfs_count_page_state(page, &delalloc, &unwritten); - if (delalloc) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(delalloc)) return 0; - } - if (unwritten) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(unwritten)) return 0; - } return try_to_free_buffers(page); } @@ -1508,6 +1556,21 @@ xfs_end_io_direct_write( return 0; } + if (flags & XFS_DIO_FLAG_COW) + error = xfs_reflink_end_cow(ip, offset, size); + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & XFS_DIO_FLAG_UNWRITTEN) { + trace_xfs_end_io_direct_write_unwritten(ip, offset, size); + + return xfs_iomap_write_unwritten(ip, offset, size, true); + } + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -1524,13 +1587,6 @@ xfs_end_io_direct_write( i_size_write(inode, offset + size); spin_unlock(&ip->i_flags_lock); - if (flags & XFS_DIO_FLAG_COW) - error = xfs_reflink_end_cow(ip, offset, size); - if (flags & XFS_DIO_FLAG_UNWRITTEN) { - trace_xfs_end_io_direct_write_unwritten(ip, offset, size); - - error = xfs_iomap_write_unwritten(ip, offset, size); - } if (flags & XFS_DIO_FLAG_APPEND) { trace_xfs_end_io_direct_write_append(ip, offset, size); @@ -1566,9 +1622,12 @@ xfs_vm_bmap( * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasseѕ the file system for actual I/O. We really can't allow * that on reflinks inodes, so we have to skip out here. And yes, - * 0 is the magic code for a bmap error.. + * 0 is the magic code for a bmap error. + * + * Since we don't pass back blockdev info, we can't return bmap + * information for rt files either. */ - if (xfs_is_reflink_inode(ip)) { + if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip)) { xfs_iunlock(ip, XFS_IOLOCK_SHARED); return 0; } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index be0b79d..c664300 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -302,6 +302,8 @@ xfs_attr3_node_inactive( &bp, XFS_ATTR_FORK); if (error) return error; + node = bp->b_addr; + btree = dp->d_ops->node_tree_p(node); child_fsb = be32_to_cpu(btree[i + 1].before); xfs_trans_brelse(*trans, bp); } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index c4b90e7..5a54dcd 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -395,6 +395,7 @@ xfs_bui_recover( struct xfs_map_extent *bmap; xfs_fsblock_t startblock_fsb; xfs_fsblock_t inode_fsb; + xfs_filblks_t count; bool op_ok; struct xfs_bud_log_item *budp; enum xfs_bmap_intent_type type; @@ -403,6 +404,7 @@ xfs_bui_recover( struct xfs_trans *tp; struct xfs_inode *ip = NULL; struct xfs_defer_ops dfops; + struct xfs_bmbt_irec irec; xfs_fsblock_t firstfsb; ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags)); @@ -480,13 +482,24 @@ xfs_bui_recover( } xfs_trans_ijoin(tp, ip, 0); + count = bmap->me_len; error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type, ip, whichfork, bmap->me_startoff, - bmap->me_startblock, bmap->me_len, - state); + bmap->me_startblock, &count, state); if (error) goto err_dfops; + if (count > 0) { + ASSERT(type == XFS_BMAP_UNMAP); + irec.br_startblock = bmap->me_startblock; + irec.br_blockcount = count; + irec.br_startoff = bmap->me_startoff; + irec.br_state = state; + error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec); + if (error) + goto err_dfops; + } + /* Finish transaction, free inodes. */ error = xfs_defer_finish(&tp, &dfops, NULL); if (error) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 87b495e..cb62871 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -84,6 +84,7 @@ xfs_zero_extent( GFP_NOFS, true); } +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ @@ -195,6 +196,7 @@ xfs_bmap_rtalloc( } return 0; } +#endif /* CONFIG_XFS_RT */ /* * Check if the endoff is outside the last extent. If so the caller will grow @@ -1445,7 +1447,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ @@ -1825,29 +1839,18 @@ xfs_swap_extent_forks( } /* - * Before we've swapped the forks, lets set the owners of the forks - * appropriately. We have to do this as we are demand paging the btree - * buffers, and so the validation done on read will expect the owner - * field to be correctly set. Once we change the owners, we can swap the - * inode forks. + * Btree format (v3) inodes have the inode number stamped in the bmbt + * block headers. We can't start changing the bmbt blocks until the + * inode owner change is logged so recovery does the right thing in the + * event of a crash. Set the owner change log flags now and leave the + * bmbt scan as the last step. */ if (ip->i_d.di_version == 3 && - ip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + ip->i_d.di_format == XFS_DINODE_FMT_BTREE) (*target_log_flags) |= XFS_ILOG_DOWNER; - error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, - tip->i_ino, NULL); - if (error) - return error; - } - if (tip->i_d.di_version == 3 && - tip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + tip->i_d.di_format == XFS_DINODE_FMT_BTREE) (*src_log_flags) |= XFS_ILOG_DOWNER; - error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK, - ip->i_ino, NULL); - if (error) - return error; - } /* * Swap the data forks of the inodes @@ -1925,6 +1928,48 @@ xfs_swap_extent_forks( return 0; } +/* + * Fix up the owners of the bmbt blocks to refer to the current inode. The + * change owner scan attempts to order all modified buffers in the current + * transaction. In the event of ordered buffer failure, the offending buffer is + * physically logged as a fallback and the scan returns -EAGAIN. We must roll + * the transaction in this case to replenish the fallback log reservation and + * restart the scan. This process repeats until the scan completes. + */ +static int +xfs_swap_change_owner( + struct xfs_trans **tpp, + struct xfs_inode *ip, + struct xfs_inode *tmpip) +{ + int error; + struct xfs_trans *tp = *tpp; + + do { + error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino, + NULL); + /* success or fatal error */ + if (error != -EAGAIN) + break; + + error = xfs_trans_roll(tpp, NULL); + if (error) + break; + tp = *tpp; + + /* + * Redirty both inodes so they can relog and keep the log tail + * moving forward. + */ + xfs_trans_ijoin(tp, ip, 0); + xfs_trans_ijoin(tp, tmpip, 0); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE); + } while (true); + + return error; +} + int xfs_swap_extents( struct xfs_inode *ip, /* target inode */ @@ -1938,8 +1983,8 @@ xfs_swap_extents( int error = 0; int lock_flags; struct xfs_ifork *cowfp; - __uint64_t f; - int resblks; + uint64_t f; + int resblks = 0; /* * Lock the inodes against other IO, page faults and truncate to @@ -1987,11 +2032,8 @@ xfs_swap_extents( XFS_SWAP_RMAP_SPACE_RES(mp, XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK), XFS_DATA_FORK); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, - 0, 0, &tp); - } else - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, - 0, 0, &tp); + } + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); if (error) goto out_unlock; @@ -2066,17 +2108,54 @@ xfs_swap_extents( ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK; + } + + /* Swap the cow forks. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + xfs_extnum_t extnum; + + ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS); + ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS); + + extnum = ip->i_cnextents; + ip->i_cnextents = tip->i_cnextents; + tip->i_cnextents = extnum; + cowfp = ip->i_cowfp; ip->i_cowfp = tip->i_cowfp; tip->i_cowfp = cowfp; - xfs_inode_set_cowblocks_tag(ip); - xfs_inode_set_cowblocks_tag(tip); + + if (ip->i_cowfp && ip->i_cnextents) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); + if (tip->i_cowfp && tip->i_cnextents) + xfs_inode_set_cowblocks_tag(tip); + else + xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); xfs_trans_log_inode(tp, tip, target_log_flags); /* + * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems + * have inode number owner values in the bmbt blocks that still refer to + * the old inode. Scan each bmbt to fix up the owner values with the + * inode number of the current inode. + */ + if (src_log_flags & XFS_ILOG_DOWNER) { + error = xfs_swap_change_owner(&tp, ip, tip); + if (error) + goto out_trans_cancel; + } + if (target_log_flags & XFS_ILOG_DOWNER) { + error = xfs_swap_change_owner(&tp, tip, ip); + if (error) + goto out_trans_cancel; + } + + /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. */ diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index f100539..ce330f0 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -28,7 +28,20 @@ struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); +#else /* !CONFIG_XFS_RT */ +/* + * Attempts to allocate RT extents when RT is disable indicates corruption and + * should trigger a shutdown. + */ +static inline int +xfs_bmap_rtalloc(struct xfs_bmalloca *ap) +{ + return -EFSCORRUPTED; +} +#endif /* CONFIG_XFS_RT */ + int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 1626927..eca7bae 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -116,7 +116,7 @@ static inline void __xfs_buf_ioacct_dec( struct xfs_buf *bp) { - ASSERT(spin_is_locked(&bp->b_lock)); + lockdep_assert_held(&bp->b_lock); if (bp->b_state & XFS_BSTATE_IN_FLIGHT) { bp->b_state &= ~XFS_BSTATE_IN_FLIGHT; @@ -2022,6 +2022,66 @@ xfs_buf_delwri_submit( return error; } +/* + * Push a single buffer on a delwri queue. + * + * The purpose of this function is to submit a single buffer of a delwri queue + * and return with the buffer still on the original queue. The waiting delwri + * buffer submission infrastructure guarantees transfer of the delwri queue + * buffer reference to a temporary wait list. We reuse this infrastructure to + * transfer the buffer back to the original queue. + * + * Note the buffer transitions from the queued state, to the submitted and wait + * listed state and back to the queued state during this call. The buffer + * locking and queue management logic between _delwri_pushbuf() and + * _delwri_queue() guarantee that the buffer cannot be queued to another list + * before returning. + */ +int +xfs_buf_delwri_pushbuf( + struct xfs_buf *bp, + struct list_head *buffer_list) +{ + LIST_HEAD (submit_list); + int error; + + ASSERT(bp->b_flags & _XBF_DELWRI_Q); + + trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); + + /* + * Isolate the buffer to a new local list so we can submit it for I/O + * independently from the rest of the original list. + */ + xfs_buf_lock(bp); + list_move(&bp->b_list, &submit_list); + xfs_buf_unlock(bp); + + /* + * Delwri submission clears the DELWRI_Q buffer flag and returns with + * the buffer on the wait list with an associated reference. Rather than + * bounce the buffer from a local wait list back to the original list + * after I/O completion, reuse the original list as the wait list. + */ + xfs_buf_delwri_submit_buffers(&submit_list, buffer_list); + + /* + * The buffer is now under I/O and wait listed as during typical delwri + * submission. Lock the buffer to wait for I/O completion. Rather than + * remove the buffer from the wait list and release the reference, we + * want to return with the buffer queued to the original list. The + * buffer already sits on the original list with a wait list reference, + * however. If we let the queue inherit that wait list reference, all we + * need to do is reset the DELWRI_Q flag. + */ + xfs_buf_lock(bp); + error = bp->b_error; + bp->b_flags |= _XBF_DELWRI_Q; + xfs_buf_unlock(bp); + + return error; +} + int __init xfs_buf_init(void) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index ad514a8..f961b19 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -333,6 +333,7 @@ extern void xfs_buf_delwri_cancel(struct list_head *); extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); +extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); /* Buffer Daemon Setup Routines */ extern int xfs_buf_init(void); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 0306168..e0a0af0 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -29,6 +29,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_log.h" +#include "xfs_inode.h" kmem_zone_t *xfs_buf_item_zone; @@ -322,6 +323,8 @@ xfs_buf_item_format( ASSERT((bip->bli_flags & XFS_BLI_STALE) || (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED) || + (bip->bli_flags & XFS_BLI_STALE)); /* @@ -346,16 +349,6 @@ xfs_buf_item_format( bip->bli_flags &= ~XFS_BLI_INODE_BUF; } - if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) == - XFS_BLI_ORDERED) { - /* - * The buffer has been logged just to order it. It is not being - * included in the transaction commit, so don't format it. - */ - trace_xfs_buf_item_format_ordered(bip); - return; - } - for (i = 0; i < bip->bli_format_count; i++) { xfs_buf_item_format_segment(bip, lv, &vecp, offset, &bip->bli_formats[i]); @@ -574,26 +567,20 @@ xfs_buf_item_unlock( { struct xfs_buf_log_item *bip = BUF_ITEM(lip); struct xfs_buf *bp = bip->bli_buf; - bool clean; - bool aborted; - int flags; + bool aborted = !!(lip->li_flags & XFS_LI_ABORTED); + bool hold = !!(bip->bli_flags & XFS_BLI_HOLD); + bool dirty = !!(bip->bli_flags & XFS_BLI_DIRTY); +#if defined(DEBUG) || defined(XFS_WARN) + bool ordered = !!(bip->bli_flags & XFS_BLI_ORDERED); +#endif /* Clear the buffer's association with this transaction. */ bp->b_transp = NULL; /* - * If this is a transaction abort, don't return early. Instead, allow - * the brelse to happen. Normally it would be done for stale - * (cancelled) buffers at unpin time, but we'll never go through the - * pin/unpin cycle if we abort inside commit. - */ - aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false; - /* - * Before possibly freeing the buf item, copy the per-transaction state - * so we can reference it safely later after clearing it from the - * buffer log item. + * The per-transaction state has been copied above so clear it from the + * bli. */ - flags = bip->bli_flags; bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED); /* @@ -601,7 +588,7 @@ xfs_buf_item_unlock( * unlock the buffer and free the buf item when the buffer is unpinned * for the last time. */ - if (flags & XFS_BLI_STALE) { + if (bip->bli_flags & XFS_BLI_STALE) { trace_xfs_buf_item_unlock_stale(bip); ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); if (!aborted) { @@ -619,40 +606,34 @@ xfs_buf_item_unlock( * regardless of whether it is dirty or not. A dirty abort implies a * shutdown, anyway. * - * Ordered buffers are dirty but may have no recorded changes, so ensure - * we only release clean items here. + * The bli dirty state should match whether the blf has logged segments + * except for ordered buffers, where only the bli should be dirty. */ - clean = (flags & XFS_BLI_DIRTY) ? false : true; - if (clean) { - int i; - for (i = 0; i < bip->bli_format_count; i++) { - if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map, - bip->bli_formats[i].blf_map_size)) { - clean = false; - break; - } - } - } + ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) || + (ordered && dirty && !xfs_buf_item_dirty_format(bip))); /* * Clean buffers, by definition, cannot be in the AIL. However, aborted - * buffers may be dirty and hence in the AIL. Therefore if we are - * aborting a buffer and we've just taken the last refernce away, we - * have to check if it is in the AIL before freeing it. We need to free - * it in this case, because an aborted transaction has already shut the - * filesystem down and this is the last chance we will have to do so. + * buffers may be in the AIL regardless of dirty state. An aborted + * transaction that invalidates a buffer already in the AIL may have + * marked it stale and cleared the dirty state, for example. + * + * Therefore if we are aborting a buffer and we've just taken the last + * reference away, we have to check if it is in the AIL before freeing + * it. We need to free it in this case, because an aborted transaction + * has already shut the filesystem down and this is the last chance we + * will have to do so. */ if (atomic_dec_and_test(&bip->bli_refcount)) { - if (clean) - xfs_buf_item_relse(bp); - else if (aborted) { + if (aborted) { ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR); xfs_buf_item_relse(bp); - } + } else if (!dirty) + xfs_buf_item_relse(bp); } - if (!(flags & XFS_BLI_HOLD)) + if (!hold) xfs_buf_relse(bp); } @@ -942,14 +923,22 @@ xfs_buf_item_log( /* - * Return 1 if the buffer has been logged or ordered in a transaction (at any - * point, not just the current transaction) and 0 if not. + * Return true if the buffer has any ranges logged/dirtied by a transaction, + * false otherwise. */ -uint -xfs_buf_item_dirty( - xfs_buf_log_item_t *bip) +bool +xfs_buf_item_dirty_format( + struct xfs_buf_log_item *bip) { - return (bip->bli_flags & XFS_BLI_DIRTY); + int i; + + for (i = 0; i < bip->bli_format_count; i++) { + if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map, + bip->bli_formats[i].blf_map_size)) + return true; + } + + return false; } STATIC void @@ -1051,6 +1040,31 @@ xfs_buf_do_callbacks( } } +/* + * Invoke the error state callback for each log item affected by the failed I/O. + * + * If a metadata buffer write fails with a non-permanent error, the buffer is + * eventually resubmitted and so the completion callbacks are not run. The error + * state may need to be propagated to the log items attached to the buffer, + * however, so the next AIL push of the item knows hot to handle it correctly. + */ +STATIC void +xfs_buf_do_callbacks_fail( + struct xfs_buf *bp) +{ + struct xfs_log_item *next; + struct xfs_log_item *lip = bp->b_fspriv; + struct xfs_ail *ailp = lip->li_ailp; + + spin_lock(&ailp->xa_lock); + for (; lip; lip = next) { + next = lip->li_bio_list; + if (lip->li_ops->iop_error) + lip->li_ops->iop_error(lip, bp); + } + spin_unlock(&ailp->xa_lock); +} + static bool xfs_buf_iodone_callback_error( struct xfs_buf *bp) @@ -1120,7 +1134,11 @@ xfs_buf_iodone_callback_error( if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount) goto permanent_error; - /* still a transient error, higher layers will retry */ + /* + * Still a transient error, run IO completion failure callbacks and let + * the higher layers retry the buffer. + */ + xfs_buf_do_callbacks_fail(bp); xfs_buf_ioerror(bp, 0); xfs_buf_relse(bp); return true; @@ -1201,3 +1219,31 @@ xfs_buf_iodone( xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE); xfs_buf_item_free(BUF_ITEM(lip)); } + +/* + * Requeue a failed buffer for writeback + * + * Return true if the buffer has been re-queued properly, false otherwise + */ +bool +xfs_buf_resubmit_failed_buffers( + struct xfs_buf *bp, + struct xfs_log_item *lip, + struct list_head *buffer_list) +{ + struct xfs_log_item *next; + + /* + * Clear XFS_LI_FAILED flag from all items before resubmit + * + * XFS_LI_FAILED set/clear is protected by xa_lock, caller this + * function already have it acquired + */ + for (; lip; lip = next) { + next = lip->li_bio_list; + xfs_clear_li_failed(lip); + } + + /* Add this buffer back to the delayed write list */ + return xfs_buf_delwri_queue(bp, buffer_list); +} diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index f7eba99..9690ce6 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -64,12 +64,15 @@ typedef struct xfs_buf_log_item { int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *); void xfs_buf_item_relse(struct xfs_buf *); void xfs_buf_item_log(xfs_buf_log_item_t *, uint, uint); -uint xfs_buf_item_dirty(xfs_buf_log_item_t *); +bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_attach_iodone(struct xfs_buf *, void(*)(struct xfs_buf *, xfs_log_item_t *), xfs_log_item_t *); void xfs_buf_iodone_callbacks(struct xfs_buf *); void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *); +bool xfs_buf_resubmit_failed_buffers(struct xfs_buf *, + struct xfs_log_item *, + struct list_head *); extern kmem_zone_t *xfs_buf_item_zone; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index ed7ee4e..bcf7297 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -167,7 +167,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index df206cf..362c6b4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -92,7 +92,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int @@ -729,6 +729,7 @@ write_retry: xfs_rw_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; xfs_icache_free_eofblocks(ip->i_mount, &eofb); + xfs_icache_free_cowblocks(ip->i_mount, &eofb); goto write_retry; } @@ -1139,29 +1140,8 @@ xfs_find_get_desired_pgoff( want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); - /* - * No page mapped into given range. If we are searching holes - * and if this is the first time we got into the loop, it means - * that the given offset is landed in a hole, return it. - * - * If we have already stepped through some block buffers to find - * holes but they all contains data. In this case, the last - * offset is already updated and pointed to the end of the last - * mapped page, if it does not reach the endpoint to search, - * that means there should be a hole between them. - */ - if (nr_pages == 0) { - /* Data search found nothing */ - if (type == DATA_OFF) - break; - - ASSERT(type == HOLE_OFF); - if (lastoff == startoff || lastoff < endoff) { - found = true; - *offset = lastoff; - } + if (nr_pages == 0) break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1227,21 +1207,20 @@ xfs_find_get_desired_pgoff( /* * The number of returned pages less than our desired, search - * done. In this case, nothing was found for searching data, - * but we found a hole behind the last offset. + * done. */ - if (nr_pages < want) { - if (type == HOLE_OFF) { - *offset = lastoff; - found = true; - } + if (nr_pages < want) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + /* No page at lastoff and we are not done - we found a hole. */ + if (type == HOLE_OFF && lastoff < endoff) { + *offset = lastoff; + found = true; + } out: pagevec_release(&pvec); return found; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 74304b6..86a4911 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -66,7 +66,6 @@ xfs_inode_alloc( XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!spin_is_locked(&ip->i_flags_lock)); ASSERT(!xfs_isiflocked(ip)); ASSERT(ip->i_ino == 0); @@ -192,7 +191,7 @@ xfs_perag_set_reclaim_tag( { struct xfs_mount *mp = pag->pag_mount; - ASSERT(spin_is_locked(&pag->pag_ici_lock)); + lockdep_assert_held(&pag->pag_ici_lock); if (pag->pag_ici_reclaimable++) return; @@ -214,7 +213,7 @@ xfs_perag_clear_reclaim_tag( { struct xfs_mount *mp = pag->pag_mount; - ASSERT(spin_is_locked(&pag->pag_ici_lock)); + lockdep_assert_held(&pag->pag_ici_lock); if (--pag->pag_ici_reclaimable) return; @@ -1079,11 +1078,11 @@ reclaim: * Because we use RCU freeing we need to ensure the inode always appears * to be reclaimed with an invalid inode number when in the free state. * We do this as early as possible under the ILOCK so that - * xfs_iflush_cluster() can be guaranteed to detect races with us here. - * By doing this, we guarantee that once xfs_iflush_cluster has locked - * XFS_ILOCK that it will see either a valid, flushable inode that will - * serialise correctly, or it will see a clean (and invalid) inode that - * it can skip. + * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to + * detect races with us here. By doing this, we guarantee that once + * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that + * it will see either a valid inode that will serialise correctly, or it + * will see an invalid inode that it can skip. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 7a0b4ee..fe9a9a1 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -881,7 +881,6 @@ xfs_ialloc( case S_IFREG: case S_IFDIR: if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) { - uint64_t di_flags2 = 0; uint di_flags = 0; if (S_ISDIR(mode)) { @@ -918,20 +917,23 @@ xfs_ialloc( di_flags |= XFS_DIFLAG_NODEFRAG; if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; - if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; ip->i_d.di_flags |= di_flags; - ip->i_d.di_flags2 |= di_flags2; } if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) && pip->i_d.di_version == 3 && ip->i_d.di_version == 3) { + uint64_t di_flags2 = 0; + if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) { - ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_d.di_cowextsize = pip->i_d.di_cowextsize; } + if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + + ip->i_d.di_flags2 |= di_flags2; } /* FALLTHROUGH */ case S_IFLNK: @@ -1630,10 +1632,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } @@ -2366,11 +2370,24 @@ retry: * already marked stale. If we can't lock it, back off * and retry. */ - if (ip != free_ip && - !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { - rcu_read_unlock(); - delay(1); - goto retry; + if (ip != free_ip) { + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { + rcu_read_unlock(); + delay(1); + goto retry; + } + + /* + * Check the inode number again in case we're + * racing with freeing in xfs_reclaim_inode(). + * See the comments in that function for more + * information as to why the initial check is + * not sufficient. + */ + if (ip->i_ino != inum + i) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); + continue; + } } rcu_read_unlock(); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index d90e781..d0a3c4b 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -27,6 +27,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans_priv.h" +#include "xfs_buf_item.h" #include "xfs_log.h" @@ -363,6 +364,9 @@ xfs_inode_to_log_dinode( to->di_dmstate = from->di_dmstate; to->di_flags = from->di_flags; + /* log a dummy value to ensure log structure is fully initialised */ + to->di_next_unlinked = NULLAGINO; + if (from->di_version == 3) { to->di_changecount = inode->i_version; to->di_crtime.t_sec = from->di_crtime.t_sec; @@ -403,6 +407,11 @@ xfs_inode_item_format_core( * the second with the on-disk inode structure, and a possible third and/or * fourth with the inode data/extents/b-tree root and inode attributes * data/extents/b-tree root. + * + * Note: Always use the 64 bit inode log format structure so we don't + * leave an uninitialised hole in the format item on 64 bit systems. Log + * recovery on 32 bit systems handles this just fine, so there's no reason + * for not using an initialising the properly padded structure all the time. */ STATIC void xfs_inode_item_format( @@ -411,8 +420,8 @@ xfs_inode_item_format( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_inode_log_format *ilf; struct xfs_log_iovec *vecp = NULL; + struct xfs_inode_log_format *ilf; ASSERT(ip->i_d.di_version > 1); @@ -424,7 +433,17 @@ xfs_inode_item_format( ilf->ilf_boffset = ip->i_imap.im_boffset; ilf->ilf_fields = XFS_ILOG_CORE; ilf->ilf_size = 2; /* format + core */ - xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); + + /* + * make sure we don't leak uninitialised data into the log in the case + * when we don't log every field in the inode. + */ + ilf->ilf_dsize = 0; + ilf->ilf_asize = 0; + ilf->ilf_pad = 0; + memset(&ilf->ilf_u.ilfu_uuid, 0, sizeof(ilf->ilf_u.ilfu_uuid)); + + xlog_finish_iovec(lv, vecp, sizeof(*ilf)); xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); @@ -475,6 +494,23 @@ xfs_inode_item_unpin( wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } +/* + * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer + * have been failed during writeback + * + * This informs the AIL that the inode is already flush locked on the next push, + * and acquires a hold on the buffer to ensure that it isn't reclaimed before + * dirty data makes it to disk. + */ +STATIC void +xfs_inode_item_error( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode)); + xfs_set_li_failed(lip, bp); +} + STATIC uint xfs_inode_item_push( struct xfs_log_item *lip, @@ -484,13 +520,28 @@ xfs_inode_item_push( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_buf *bp = NULL; + struct xfs_buf *bp = lip->li_buf; uint rval = XFS_ITEM_SUCCESS; int error; if (xfs_ipincount(ip) > 0) return XFS_ITEM_PINNED; + /* + * The buffer containing this item failed to be written back + * previously. Resubmit the buffer for IO. + */ + if (lip->li_flags & XFS_LI_FAILED) { + if (!xfs_buf_trylock(bp)) + return XFS_ITEM_LOCKED; + + if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list)) + rval = XFS_ITEM_FLUSHING; + + xfs_buf_unlock(bp); + return rval; + } + if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) return XFS_ITEM_LOCKED; @@ -622,7 +673,8 @@ static const struct xfs_item_ops xfs_inode_item_ops = { .iop_unlock = xfs_inode_item_unlock, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_committing = xfs_inode_item_committing + .iop_committing = xfs_inode_item_committing, + .iop_error = xfs_inode_item_error }; @@ -710,7 +762,8 @@ xfs_iflush_done( * the AIL lock. */ iip = INODE_ITEM(blip); - if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) + if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; @@ -718,7 +771,8 @@ xfs_iflush_done( /* make sure we capture the state of the initial inode. */ iip = INODE_ITEM(lip); - if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) + if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) || + lip->li_flags & XFS_LI_FAILED) need_ail++; /* @@ -731,22 +785,30 @@ xfs_iflush_done( * holding the lock before removing the inode from the AIL. */ if (need_ail) { - struct xfs_log_item *log_items[need_ail]; - int i = 0; + bool mlip_changed = false; + + /* this is an opencoded batch version of xfs_trans_ail_delete */ spin_lock(&ailp->xa_lock); for (blip = lip; blip; blip = blip->li_bio_list) { - iip = INODE_ITEM(blip); - if (iip->ili_logged && - blip->li_lsn == iip->ili_flush_lsn) { - log_items[i++] = blip; + if (INODE_ITEM(blip)->ili_logged && + blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) + mlip_changed |= xfs_ail_delete_one(ailp, blip); + else { + xfs_clear_li_failed(blip); } - ASSERT(i <= need_ail); } - /* xfs_trans_ail_delete_bulk() drops the AIL lock. */ - xfs_trans_ail_delete_bulk(ailp, log_items, i, - SHUTDOWN_CORRUPT_INCORE); - } + if (mlip_changed) { + if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount)) + xlog_assign_tail_lsn_locked(ailp->xa_mount); + if (list_empty(&ailp->xa_ail)) + wake_up_all(&ailp->xa_empty); + } + spin_unlock(&ailp->xa_lock); + + if (mlip_changed) + xfs_log_space_wake(ailp->xa_mount); + } /* * clean up and unlock the flush lock now we are done. We can clear the @@ -811,48 +873,30 @@ xfs_istale_done( } /* - * convert an xfs_inode_log_format struct from either 32 or 64 bit versions - * (which can have different field alignments) to the native version + * convert an xfs_inode_log_format struct from the old 32 bit version + * (which can have different field alignments) to the native 64 bit version */ int xfs_inode_item_format_convert( - xfs_log_iovec_t *buf, - xfs_inode_log_format_t *in_f) + struct xfs_log_iovec *buf, + struct xfs_inode_log_format *in_f) { - if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) { - xfs_inode_log_format_32_t *in_f32 = buf->i_addr; - - in_f->ilf_type = in_f32->ilf_type; - in_f->ilf_size = in_f32->ilf_size; - in_f->ilf_fields = in_f32->ilf_fields; - in_f->ilf_asize = in_f32->ilf_asize; - in_f->ilf_dsize = in_f32->ilf_dsize; - in_f->ilf_ino = in_f32->ilf_ino; - /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f32->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); - in_f->ilf_blkno = in_f32->ilf_blkno; - in_f->ilf_len = in_f32->ilf_len; - in_f->ilf_boffset = in_f32->ilf_boffset; - return 0; - } else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){ - xfs_inode_log_format_64_t *in_f64 = buf->i_addr; - - in_f->ilf_type = in_f64->ilf_type; - in_f->ilf_size = in_f64->ilf_size; - in_f->ilf_fields = in_f64->ilf_fields; - in_f->ilf_asize = in_f64->ilf_asize; - in_f->ilf_dsize = in_f64->ilf_dsize; - in_f->ilf_ino = in_f64->ilf_ino; - /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f64->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); - in_f->ilf_blkno = in_f64->ilf_blkno; - in_f->ilf_len = in_f64->ilf_len; - in_f->ilf_boffset = in_f64->ilf_boffset; - return 0; - } - return -EFSCORRUPTED; + struct xfs_inode_log_format_32 *in_f32 = buf->i_addr; + + if (buf->i_len != sizeof(*in_f32)) + return -EFSCORRUPTED; + + in_f->ilf_type = in_f32->ilf_type; + in_f->ilf_size = in_f32->ilf_size; + in_f->ilf_fields = in_f32->ilf_fields; + in_f->ilf_asize = in_f32->ilf_asize; + in_f->ilf_dsize = in_f32->ilf_dsize; + in_f->ilf_ino = in_f32->ilf_ino; + /* copy biggest field of ilf_u */ + memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, + in_f32->ilf_u.ilfu_uuid.__u_bits, sizeof(uuid_t)); + in_f->ilf_blkno = in_f32->ilf_blkno; + in_f->ilf_len = in_f32->ilf_len; + in_f->ilf_boffset = in_f32->ilf_boffset; + return 0; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 73cfc71..6c95812 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -928,16 +928,15 @@ xfs_ioc_fsgetxattr( return 0; } -STATIC void -xfs_set_diflags( +STATIC uint16_t +xfs_flags2diflags( struct xfs_inode *ip, unsigned int xflags) { - unsigned int di_flags; - uint64_t di_flags2; - /* can't set PREALLOC this way, just preserve it */ - di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); + uint16_t di_flags = + (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); + if (xflags & FS_XFLAG_IMMUTABLE) di_flags |= XFS_DIFLAG_IMMUTABLE; if (xflags & FS_XFLAG_APPEND) @@ -967,19 +966,24 @@ xfs_set_diflags( if (xflags & FS_XFLAG_EXTSIZE) di_flags |= XFS_DIFLAG_EXTSIZE; } - ip->i_d.di_flags = di_flags; - /* diflags2 only valid for v3 inodes. */ - if (ip->i_d.di_version < 3) - return; + return di_flags; +} + +STATIC uint64_t +xfs_flags2diflags2( + struct xfs_inode *ip, + unsigned int xflags) +{ + uint64_t di_flags2 = + (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK); - di_flags2 = (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK); if (xflags & FS_XFLAG_DAX) di_flags2 |= XFS_DIFLAG2_DAX; if (xflags & FS_XFLAG_COWEXTSIZE) di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; - ip->i_d.di_flags2 = di_flags2; + return di_flags2; } STATIC void @@ -1005,11 +1009,12 @@ xfs_diflags_to_linux( inode->i_flags |= S_NOATIME; else inode->i_flags &= ~S_NOATIME; +#if 0 /* disabled until the flag switching races are sorted out */ if (xflags & FS_XFLAG_DAX) inode->i_flags |= S_DAX; else inode->i_flags &= ~S_DAX; - +#endif } static int @@ -1019,6 +1024,7 @@ xfs_ioctl_setattr_xflags( struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; + uint64_t di_flags2; /* Can't change realtime flag if any extents are allocated. */ if ((ip->i_d.di_nextents || ip->i_delayed_blks) && @@ -1049,7 +1055,14 @@ xfs_ioctl_setattr_xflags( !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; - xfs_set_diflags(ip, fa->fsx_xflags); + /* diflags2 only valid for v3 inodes. */ + di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); + if (di_flags2 && ip->i_d.di_version < 3) + return -EINVAL; + + ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags); + ip->i_d.di_flags2 = di_flags2; + xfs_diflags_to_linux(ip); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); @@ -1072,6 +1085,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1084,7 +1098,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 65740d1..f286f63 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -836,7 +836,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -847,6 +848,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -906,7 +908,8 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 6d45cf0..d71703a 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f5e0f60..5b81f7f 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -190,12 +190,12 @@ xfs_generic_create( #ifdef CONFIG_XFS_POSIX_ACL if (default_acl) { - error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); if (error) goto out_cleanup_inode; } if (acl) { - error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); if (error) goto out_cleanup_inode; } @@ -802,7 +802,7 @@ xfs_vn_setattr_nonsize( * Caution: The caller of this function is responsible for calling * setattr_prepare() or otherwise verifying the change is fine. */ -int +STATIC int xfs_setattr_size( struct xfs_inode *ip, struct iattr *iattr) diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index d8a77db..26d67ce 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -361,7 +361,6 @@ xfs_bulkstat( xfs_agino_t agino; /* inode # in allocation group */ xfs_agnumber_t agno; /* allocation group number */ xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ - size_t irbsize; /* size of irec buffer in bytes */ xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */ int nirbuf; /* size of irbuf */ int ubcount; /* size of user's buffer */ @@ -388,11 +387,10 @@ xfs_bulkstat( *ubcountp = 0; *done = 0; - irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4); + irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP); if (!irbuf) return -ENOMEM; - - nirbuf = irbsize / sizeof(*irbuf); + nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf); /* * Loop over the allocation groups, starting from the last diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 1455b2520..3ebed16 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -363,7 +363,14 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y) #endif /* DEBUG */ #ifdef CONFIG_XFS_RT -#define XFS_IS_REALTIME_INODE(ip) ((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) + +/* + * make sure we ignore the inode flag if the filesystem doesn't have a + * configured realtime device. + */ +#define XFS_IS_REALTIME_INODE(ip) \ + (((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) && \ + (ip)->i_mount->m_rtdev_targp) #else #define XFS_IS_REALTIME_INODE(ip) (0) #endif diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index b57ab34..33c9a3a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -743,15 +743,45 @@ xfs_log_mount_finish( struct xfs_mount *mp) { int error = 0; + bool readonly = (mp->m_flags & XFS_MOUNT_RDONLY); if (mp->m_flags & XFS_MOUNT_NORECOVERY) { ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; + } else if (readonly) { + /* Allow unlinked processing to proceed */ + mp->m_flags &= ~XFS_MOUNT_RDONLY; } + /* + * During the second phase of log recovery, we need iget and + * iput to behave like they do for an active filesystem. + * xfs_fs_drop_inode needs to be able to prevent the deletion + * of inodes before we're done replaying log items on those + * inodes. Turn it off immediately after recovery finishes + * so that we don't leak the quota inodes if subsequent mount + * activities fail. + * + * We let all inodes involved in redo item processing end up on + * the LRU instead of being evicted immediately so that if we do + * something to an unlinked inode, the irele won't cause + * premature truncation and freeing of the inode, which results + * in log recovery failure. We have to evict the unreferenced + * lru inodes after clearing MS_ACTIVE because we don't + * otherwise clean up the lru if there's a subsequent failure in + * xfs_mountfs, which leads to us leaking the inodes if nothing + * else (e.g. quotacheck) references the inodes before the + * mount failure occurs. + */ + mp->m_super->s_flags |= MS_ACTIVE; error = xlog_recover_finish(mp->m_log); if (!error) xfs_log_work_queue(mp); + mp->m_super->s_flags &= ~MS_ACTIVE; + evict_inodes(mp->m_super); + + if (readonly) + mp->m_flags |= XFS_MOUNT_RDONLY; return error; } @@ -801,11 +831,14 @@ xfs_log_unmount_write(xfs_mount_t *mp) int error; /* - * Don't write out unmount record on read-only mounts. + * Don't write out unmount record on norecovery mounts or ro devices. * Or, if we are doing a forced umount (typically because of IO errors). */ - if (mp->m_flags & XFS_MOUNT_RDONLY) + if (mp->m_flags & XFS_MOUNT_NORECOVERY || + xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) { + ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; + } error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL); ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log))); @@ -3304,8 +3337,6 @@ maybe_sleep: */ if (iclog->ic_state & XLOG_STATE_IOERROR) return -EIO; - if (log_flushed) - *log_flushed = 1; } else { no_sleep: @@ -3409,8 +3440,6 @@ try_again: xlog_wait(&iclog->ic_prev->ic_write_wait, &log->l_icloglock); - if (log_flushed) - *log_flushed = 1; already_slept = 1; goto try_again; } @@ -3444,9 +3473,6 @@ try_again: */ if (iclog->ic_state & XLOG_STATE_IOERROR) return -EIO; - - if (log_flushed) - *log_flushed = 1; } else { /* just return */ spin_unlock(&log->l_icloglock); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 9b3d7c7..0590926 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1029,61 +1029,106 @@ out_error: } /* - * Check the log tail for torn writes. This is required when torn writes are - * detected at the head and the head had to be walked back to a previous record. - * The tail of the previous record must now be verified to ensure the torn - * writes didn't corrupt the previous tail. + * Calculate distance from head to tail (i.e., unused space in the log). + */ +static inline int +xlog_tail_distance( + struct xlog *log, + xfs_daddr_t head_blk, + xfs_daddr_t tail_blk) +{ + if (head_blk < tail_blk) + return tail_blk - head_blk; + + return tail_blk + (log->l_logBBsize - head_blk); +} + +/* + * Verify the log tail. This is particularly important when torn or incomplete + * writes have been detected near the front of the log and the head has been + * walked back accordingly. * - * Return an error if CRC verification fails as recovery cannot proceed. + * We also have to handle the case where the tail was pinned and the head + * blocked behind the tail right before a crash. If the tail had been pushed + * immediately prior to the crash and the subsequent checkpoint was only + * partially written, it's possible it overwrote the last referenced tail in the + * log with garbage. This is not a coherency problem because the tail must have + * been pushed before it can be overwritten, but appears as log corruption to + * recovery because we have no way to know the tail was updated if the + * subsequent checkpoint didn't write successfully. + * + * Therefore, CRC check the log from tail to head. If a failure occurs and the + * offending record is within max iclog bufs from the head, walk the tail + * forward and retry until a valid tail is found or corruption is detected out + * of the range of a possible overwrite. */ STATIC int xlog_verify_tail( struct xlog *log, xfs_daddr_t head_blk, - xfs_daddr_t tail_blk) + xfs_daddr_t *tail_blk, + int hsize) { struct xlog_rec_header *thead; struct xfs_buf *bp; xfs_daddr_t first_bad; - int count; int error = 0; bool wrapped; - xfs_daddr_t tmp_head; + xfs_daddr_t tmp_tail; + xfs_daddr_t orig_tail = *tail_blk; bp = xlog_get_bp(log, 1); if (!bp) return -ENOMEM; /* - * Seek XLOG_MAX_ICLOGS + 1 records past the current tail record to get - * a temporary head block that points after the last possible - * concurrently written record of the tail. + * Make sure the tail points to a record (returns positive count on + * success). */ - count = xlog_seek_logrec_hdr(log, head_blk, tail_blk, - XLOG_MAX_ICLOGS + 1, bp, &tmp_head, &thead, - &wrapped); - if (count < 0) { - error = count; + error = xlog_seek_logrec_hdr(log, head_blk, *tail_blk, 1, bp, + &tmp_tail, &thead, &wrapped); + if (error < 0) goto out; - } - - /* - * If the call above didn't find XLOG_MAX_ICLOGS + 1 records, we ran - * into the actual log head. tmp_head points to the start of the record - * so update it to the actual head block. - */ - if (count < XLOG_MAX_ICLOGS + 1) - tmp_head = head_blk; + if (*tail_blk != tmp_tail) + *tail_blk = tmp_tail; /* - * We now have a tail and temporary head block that covers at least - * XLOG_MAX_ICLOGS records from the tail. We need to verify that these - * records were completely written. Run a CRC verification pass from - * tail to head and return the result. + * Run a CRC check from the tail to the head. We can't just check + * MAX_ICLOGS records past the tail because the tail may point to stale + * blocks cleared during the search for the head/tail. These blocks are + * overwritten with zero-length records and thus record count is not a + * reliable indicator of the iclog state before a crash. */ - error = xlog_do_recovery_pass(log, tmp_head, tail_blk, + first_bad = 0; + error = xlog_do_recovery_pass(log, head_blk, *tail_blk, XLOG_RECOVER_CRCPASS, &first_bad); + while ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) { + int tail_distance; + + /* + * Is corruption within range of the head? If so, retry from + * the next record. Otherwise return an error. + */ + tail_distance = xlog_tail_distance(log, head_blk, first_bad); + if (tail_distance > BTOBB(XLOG_MAX_ICLOGS * hsize)) + break; + + /* skip to the next record; returns positive count on success */ + error = xlog_seek_logrec_hdr(log, head_blk, first_bad, 2, bp, + &tmp_tail, &thead, &wrapped); + if (error < 0) + goto out; + + *tail_blk = tmp_tail; + first_bad = 0; + error = xlog_do_recovery_pass(log, head_blk, *tail_blk, + XLOG_RECOVER_CRCPASS, &first_bad); + } + if (!error && *tail_blk != orig_tail) + xfs_warn(log->l_mp, + "Tail block (0x%llx) overwrite detected. Updated to 0x%llx", + orig_tail, *tail_blk); out: xlog_put_bp(bp); return error; @@ -1143,7 +1188,7 @@ xlog_verify_head( */ error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk, XLOG_RECOVER_CRCPASS, &first_bad); - if (error == -EFSBADCRC) { + if ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) { /* * We've hit a potential torn write. Reset the error and warn * about it. @@ -1183,31 +1228,12 @@ xlog_verify_head( ASSERT(0); return 0; } - - /* - * Now verify the tail based on the updated head. This is - * required because the torn writes trimmed from the head could - * have been written over the tail of a previous record. Return - * any errors since recovery cannot proceed if the tail is - * corrupt. - * - * XXX: This leaves a gap in truly robust protection from torn - * writes in the log. If the head is behind the tail, the tail - * pushes forward to create some space and then a crash occurs - * causing the writes into the previous record's tail region to - * tear, log recovery isn't able to recover. - * - * How likely is this to occur? If possible, can we do something - * more intelligent here? Is it safe to push the tail forward if - * we can determine that the tail is within the range of the - * torn write (e.g., the kernel can only overwrite the tail if - * it has actually been pushed forward)? Alternatively, could we - * somehow prevent this condition at runtime? - */ - error = xlog_verify_tail(log, *head_blk, *tail_blk); } + if (error) + return error; - return error; + return xlog_verify_tail(log, *head_blk, tail_blk, + be32_to_cpu((*rhead)->h_size)); } /* @@ -4152,7 +4178,7 @@ xlog_recover_commit_trans( #define XLOG_RECOVER_COMMIT_QUEUE_MAX 100 - hlist_del(&trans->r_list); + hlist_del_init(&trans->r_list); error = xlog_recover_reorder_trans(log, trans, pass); if (error) @@ -4354,6 +4380,8 @@ xlog_recover_free_trans( xlog_recover_item_t *item, *n; int i; + hlist_del_init(&trans->r_list); + list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) { /* Free the regions in the item. */ list_del(&item->ri_list); @@ -4799,12 +4827,16 @@ xlog_recover_process_intents( int error = 0; struct xfs_ail_cursor cur; struct xfs_ail *ailp; +#if defined(DEBUG) || defined(XFS_WARN) xfs_lsn_t last_lsn; +#endif ailp = log->l_ailp; spin_lock(&ailp->xa_lock); lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); +#if defined(DEBUG) || defined(XFS_WARN) last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block); +#endif while (lip != NULL) { /* * We're done when we see something other than an intent. @@ -5214,7 +5246,7 @@ xlog_do_recovery_pass( xfs_daddr_t *first_bad) /* out: first bad log rec */ { xlog_rec_header_t *rhead; - xfs_daddr_t blk_no; + xfs_daddr_t blk_no, rblk_no; xfs_daddr_t rhead_blk; char *offset; xfs_buf_t *hbp, *dbp; @@ -5222,11 +5254,15 @@ xlog_do_recovery_pass( int error2 = 0; int bblks, split_bblks; int hblks, split_hblks, wrapped_hblks; + int i; struct hlist_head rhash[XLOG_RHASH_SIZE]; LIST_HEAD (buffer_list); ASSERT(head_blk != tail_blk); - rhead_blk = 0; + blk_no = rhead_blk = tail_blk; + + for (i = 0; i < XLOG_RHASH_SIZE; i++) + INIT_HLIST_HEAD(&rhash[i]); /* * Read the header of the tail block and get the iclog buffer size from @@ -5301,7 +5337,6 @@ xlog_do_recovery_pass( } memset(rhash, 0, sizeof(rhash)); - blk_no = rhead_blk = tail_blk; if (tail_blk > head_blk) { /* * Perform recovery around the end of the physical log. @@ -5363,9 +5398,19 @@ xlog_do_recovery_pass( bblks = (int)BTOBB(be32_to_cpu(rhead->h_len)); blk_no += hblks; - /* Read in data for log record */ - if (blk_no + bblks <= log->l_logBBsize) { - error = xlog_bread(log, blk_no, bblks, dbp, + /* + * Read the log record data in multiple reads if it + * wraps around the end of the log. Note that if the + * header already wrapped, blk_no could point past the + * end of the log. The record data is contiguous in + * that case. + */ + if (blk_no + bblks <= log->l_logBBsize || + blk_no >= log->l_logBBsize) { + /* mod blk_no in case the header wrapped and + * pushed it beyond the end of the log */ + rblk_no = do_mod(blk_no, log->l_logBBsize); + error = xlog_bread(log, rblk_no, bblks, dbp, &offset); if (error) goto bread_err2; @@ -5464,6 +5509,19 @@ xlog_do_recovery_pass( if (error && first_bad) *first_bad = rhead_blk; + /* + * Transactions are freed at commit time but transactions without commit + * records on disk are never committed. Free any that may be left in the + * hash table. + */ + for (i = 0; i < XLOG_RHASH_SIZE; i++) { + struct hlist_node *tmp; + struct xlog_recover *trans; + + hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list) + xlog_recover_free_trans(trans); + } + return error ? error : error2; } @@ -5542,6 +5600,8 @@ xlog_do_recover( xfs_buf_t *bp; xfs_sb_t *sbp; + trace_xfs_log_recover(log, head_blk, tail_blk); + /* * First replay the images in the log. */ diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 13796f2..d4ce8d2 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -925,15 +925,6 @@ xfs_mountfs( } /* - * During the second phase of log recovery, we need iget and - * iput to behave like they do for an active filesystem. - * xfs_fs_drop_inode needs to be able to prevent the deletion - * of inodes before we're done replaying log items on those - * inodes. - */ - mp->m_super->s_flags |= MS_ACTIVE; - - /* * Finish recovering the file system. This part needed to be delayed * until after the root and real-time bitmap inodes were consistently * read in. @@ -1008,12 +999,13 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: - mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); + /* Clean out dquots that might be in memory after quotacheck. */ + xfs_qm_unmount(mp); out_log_dealloc: mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 0c381d7..0492436 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -134,7 +134,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28); XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52); - XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64, 56); + 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); } diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 93a7aaf..cecd375 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -279,7 +279,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 8b9a9f1..1fdd3fa 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -111,6 +111,9 @@ restart: skipped = 0; break; } + /* we're done if id overflows back to zero */ + if (!next_index) + break; } if (skipped) { @@ -1247,6 +1250,7 @@ xfs_qm_flush_one( struct xfs_dquot *dqp, void *data) { + struct xfs_mount *mp = dqp->q_mount; struct list_head *buffer_list = data; struct xfs_buf *bp = NULL; int error = 0; @@ -1257,7 +1261,32 @@ xfs_qm_flush_one( if (!XFS_DQ_IS_DIRTY(dqp)) goto out_unlock; - xfs_dqflock(dqp); + /* + * The only way the dquot is already flush locked by the time quotacheck + * gets here is if reclaim flushed it before the dqadjust walk dirtied + * it for the final time. Quotacheck collects all dquot bufs in the + * local delwri queue before dquots are dirtied, so reclaim can't have + * possibly queued it for I/O. The only way out is to push the buffer to + * cycle the flush lock. + */ + if (!xfs_dqflock_nowait(dqp)) { + /* buf is pinned in-core by delwri list */ + DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen); + bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL); + if (!bp) { + error = -EINVAL; + goto out_unlock; + } + xfs_buf_unlock(bp); + + xfs_buf_delwri_pushbuf(bp, buffer_list); + xfs_buf_rele(bp); + + error = -EAGAIN; + goto out_unlock; + } + error = xfs_qm_dqflush(dqp, &bp); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 29a75ec..17d3c96 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -169,6 +169,8 @@ xfs_reflink_find_shared( error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); if (error) return error; + if (!agbp) + return -ENOMEM; cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL); @@ -333,7 +335,7 @@ xfs_reflink_convert_cow_extent( struct xfs_defer_ops *dfops) { struct xfs_bmbt_irec irec = *imap; - xfs_fsblock_t first_block; + xfs_fsblock_t first_block = NULLFSBLOCK; int nimaps = 1; if (imap->br_state == XFS_EXT_NORM) @@ -765,7 +767,13 @@ xfs_reflink_end_cow( /* If there is a hole at end_fsb - 1 go to the previous extent */ if (eof || got.br_startoff > end_fsb) { - ASSERT(idx > 0); + /* + * In case of racing, overlapping AIO writes no COW extents + * might be left by the time I/O completes for the loser of + * the race. In that case we are done. + */ + if (idx <= 0) + goto out_cancel; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got); } @@ -839,6 +847,7 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); +out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 882fb85..67d589e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1214,7 +1214,7 @@ xfs_test_remount_options( tmp_mp->m_super = sb; error = xfs_parseargs(tmp_mp, options); xfs_free_fsname(tmp_mp); - kfree(tmp_mp); + kmem_free(tmp_mp); return error; } diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 828f383..bdf69e1 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -366,6 +366,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); DEFINE_BUF_EVENT(xfs_buf_delwri_queued); DEFINE_BUF_EVENT(xfs_buf_delwri_split); +DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf); DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_bdstrat_shut); DEFINE_BUF_EVENT(xfs_buf_item_relse); @@ -519,7 +520,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); @@ -1990,6 +1990,24 @@ DEFINE_EVENT(xfs_swap_extent_class, name, \ DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); +TRACE_EVENT(xfs_log_recover, + TP_PROTO(struct xlog *log, xfs_daddr_t headblk, xfs_daddr_t tailblk), + TP_ARGS(log, headblk, tailblk), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_daddr_t, headblk) + __field(xfs_daddr_t, tailblk) + ), + TP_fast_assign( + __entry->dev = log->l_mp->m_super->s_dev; + __entry->headblk = headblk; + __entry->tailblk = tailblk; + ), + TP_printk("dev %d:%d headblk 0x%llx tailblk 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->headblk, + __entry->tailblk) +) + TRACE_EVENT(xfs_log_recover_record, TP_PROTO(struct xlog *log, struct xlog_rec_header *rhead, int pass), TP_ARGS(log, rhead, pass), diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 98024cb..5669cf0 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -50,6 +50,7 @@ typedef struct xfs_log_item { struct xfs_ail *li_ailp; /* ptr to AIL */ uint li_type; /* item type */ uint li_flags; /* misc flags */ + struct xfs_buf *li_buf; /* real buffer pointer */ struct xfs_log_item *li_bio_list; /* buffer item list */ void (*li_cb)(struct xfs_buf *, struct xfs_log_item *); @@ -65,11 +66,13 @@ typedef struct xfs_log_item { } xfs_log_item_t; #define XFS_LI_IN_AIL 0x1 -#define XFS_LI_ABORTED 0x2 +#define XFS_LI_ABORTED 0x2 +#define XFS_LI_FAILED 0x4 #define XFS_LI_FLAGS \ { XFS_LI_IN_AIL, "IN_AIL" }, \ - { XFS_LI_ABORTED, "ABORTED" } + { XFS_LI_ABORTED, "ABORTED" }, \ + { XFS_LI_FAILED, "FAILED" } struct xfs_item_ops { void (*iop_size)(xfs_log_item_t *, int *, int *); @@ -80,6 +83,7 @@ struct xfs_item_ops { void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); + void (*iop_error)(xfs_log_item_t *, xfs_buf_t *); }; void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, @@ -213,12 +217,14 @@ void xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *); void xfs_trans_binval(xfs_trans_t *, struct xfs_buf *); void xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *); -void xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); +bool xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint); void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int); void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint); -void xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint); +void xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint, + uint); +void xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *); void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint); void xfs_extent_free_init_defer_op(void); @@ -277,6 +283,6 @@ int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp, struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops, enum xfs_bmap_intent_type type, struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, xfs_exntst_t state); + xfs_filblks_t *blockcount, xfs_exntst_t state); #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index d6c9c3e..70f5ab0 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -684,8 +684,24 @@ xfs_trans_ail_update_bulk( } } -/* - * xfs_trans_ail_delete_bulk - remove multiple log items from the AIL +bool +xfs_ail_delete_one( + struct xfs_ail *ailp, + struct xfs_log_item *lip) +{ + struct xfs_log_item *mlip = xfs_ail_min(ailp); + + trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); + xfs_ail_delete(ailp, lip); + xfs_clear_li_failed(lip); + lip->li_flags &= ~XFS_LI_IN_AIL; + lip->li_lsn = 0; + + return mlip == lip; +} + +/** + * Remove a log items from the AIL * * @xfs_trans_ail_delete_bulk takes an array of log items that all need to * removed from the AIL. The caller is already holding the AIL lock, and done @@ -706,52 +722,36 @@ xfs_trans_ail_update_bulk( * before returning. */ void -xfs_trans_ail_delete_bulk( +xfs_trans_ail_delete( struct xfs_ail *ailp, - struct xfs_log_item **log_items, - int nr_items, + struct xfs_log_item *lip, int shutdown_type) __releases(ailp->xa_lock) { - xfs_log_item_t *mlip; - int mlip_changed = 0; - int i; - - mlip = xfs_ail_min(ailp); + struct xfs_mount *mp = ailp->xa_mount; + bool mlip_changed; - for (i = 0; i < nr_items; i++) { - struct xfs_log_item *lip = log_items[i]; - if (!(lip->li_flags & XFS_LI_IN_AIL)) { - struct xfs_mount *mp = ailp->xa_mount; - - spin_unlock(&ailp->xa_lock); - if (!XFS_FORCED_SHUTDOWN(mp)) { - xfs_alert_tag(mp, XFS_PTAG_AILDELETE, - "%s: attempting to delete a log item that is not in the AIL", - __func__); - xfs_force_shutdown(mp, shutdown_type); - } - return; + if (!(lip->li_flags & XFS_LI_IN_AIL)) { + spin_unlock(&ailp->xa_lock); + if (!XFS_FORCED_SHUTDOWN(mp)) { + xfs_alert_tag(mp, XFS_PTAG_AILDELETE, + "%s: attempting to delete a log item that is not in the AIL", + __func__); + xfs_force_shutdown(mp, shutdown_type); } - - trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); - xfs_ail_delete(ailp, lip); - lip->li_flags &= ~XFS_LI_IN_AIL; - lip->li_lsn = 0; - if (mlip == lip) - mlip_changed = 1; + return; } + mlip_changed = xfs_ail_delete_one(ailp, lip); if (mlip_changed) { - if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount)) - xlog_assign_tail_lsn_locked(ailp->xa_mount); + if (!XFS_FORCED_SHUTDOWN(mp)) + xlog_assign_tail_lsn_locked(mp); if (list_empty(&ailp->xa_ail)) wake_up_all(&ailp->xa_empty); - spin_unlock(&ailp->xa_lock); + } + spin_unlock(&ailp->xa_lock); + if (mlip_changed) xfs_log_space_wake(ailp->xa_mount); - } else { - spin_unlock(&ailp->xa_lock); - } } int diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c index 6408e7d..14543d9 100644 --- a/fs/xfs/xfs_trans_bmap.c +++ b/fs/xfs/xfs_trans_bmap.c @@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update( int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, + xfs_filblks_t *blockcount, xfs_exntst_t state) { int error; @@ -196,16 +196,23 @@ xfs_bmap_update_finish_item( void **state) { struct xfs_bmap_intent *bmap; + xfs_filblks_t count; int error; bmap = container_of(item, struct xfs_bmap_intent, bi_list); + count = bmap->bi_bmap.br_blockcount; error = xfs_trans_log_finish_bmap_update(tp, done_item, dop, bmap->bi_type, bmap->bi_owner, bmap->bi_whichfork, bmap->bi_bmap.br_startoff, bmap->bi_bmap.br_startblock, - bmap->bi_bmap.br_blockcount, + &count, bmap->bi_bmap.br_state); + if (!error && count > 0) { + ASSERT(bmap->bi_type == XFS_BMAP_UNMAP); + bmap->bi_bmap.br_blockcount = count; + return -EAGAIN; + } kmem_free(bmap); return error; } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 8ee29ca..3ba7a96 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t *tp, xfs_buf_t *bp) { xfs_buf_log_item_t *bip; + int freed; /* * Default to a normal brelse() call if the tp is NULL. @@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t *tp, /* * Drop our reference to the buf log item. */ - atomic_dec(&bip->bli_refcount); + freed = atomic_dec_and_test(&bip->bli_refcount); /* - * If the buf item is not tracking data in the log, then - * we must free it before releasing the buffer back to the - * free pool. Before releasing the buffer to the free pool, - * clear the transaction pointer in b_fsprivate2 to dissolve - * its relation to this transaction. + * If the buf item is not tracking data in the log, then we must free it + * before releasing the buffer back to the free pool. + * + * If the fs has shutdown and we dropped the last reference, it may fall + * on us to release a (possibly dirty) bli if it never made it to the + * AIL (e.g., the aborted unpin already happened and didn't release it + * due to our reference). Since we're already shutdown and need xa_lock, + * just force remove from the AIL and release the bli here. */ - if (!xfs_buf_item_dirty(bip)) { + if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) { + xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR); + xfs_buf_item_relse(bp); + } else if (!(bip->bli_flags & XFS_BLI_DIRTY)) { /*** ASSERT(bp->b_pincount == 0); ***/ @@ -486,25 +493,17 @@ xfs_trans_bhold_release(xfs_trans_t *tp, } /* - * This is called to mark bytes first through last inclusive of the given - * buffer as needing to be logged when the transaction is committed. - * The buffer must already be associated with the given transaction. - * - * First and last are numbers relative to the beginning of this buffer, - * so the first byte in the buffer is numbered 0 regardless of the - * value of b_blkno. + * Mark a buffer dirty in the transaction. */ void -xfs_trans_log_buf(xfs_trans_t *tp, - xfs_buf_t *bp, - uint first, - uint last) +xfs_trans_dirty_buf( + struct xfs_trans *tp, + struct xfs_buf *bp) { - xfs_buf_log_item_t *bip = bp->b_fspriv; + struct xfs_buf_log_item *bip = bp->b_fspriv; ASSERT(bp->b_transp == tp); ASSERT(bip != NULL); - ASSERT(first <= last && last < BBTOB(bp->b_length)); ASSERT(bp->b_iodone == NULL || bp->b_iodone == xfs_buf_iodone_callbacks); @@ -524,8 +523,6 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_iodone = xfs_buf_iodone_callbacks; bip->bli_item.li_cb = xfs_buf_iodone; - trace_xfs_trans_log_buf(bip); - /* * If we invalidated the buffer within this transaction, then * cancel the invalidation now that we're dirtying the buffer @@ -538,17 +535,37 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_flags &= ~XBF_STALE; bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL; } + bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED; tp->t_flags |= XFS_TRANS_DIRTY; bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY; +} - /* - * If we have an ordered buffer we are not logging any dirty range but - * it still needs to be marked dirty and that it has been logged. - */ - bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED; - if (!(bip->bli_flags & XFS_BLI_ORDERED)) - xfs_buf_item_log(bip, first, last); +/* + * This is called to mark bytes first through last inclusive of the given + * buffer as needing to be logged when the transaction is committed. + * The buffer must already be associated with the given transaction. + * + * First and last are numbers relative to the beginning of this buffer, + * so the first byte in the buffer is numbered 0 regardless of the + * value of b_blkno. + */ +void +xfs_trans_log_buf( + struct xfs_trans *tp, + struct xfs_buf *bp, + uint first, + uint last) +{ + struct xfs_buf_log_item *bip = bp->b_fspriv; + + ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); + + xfs_trans_dirty_buf(tp, bp); + + trace_xfs_trans_log_buf(bip); + xfs_buf_item_log(bip, first, last); } @@ -701,14 +718,13 @@ xfs_trans_inode_alloc_buf( } /* - * Mark the buffer as ordered for this transaction. This means - * that the contents of the buffer are not recorded in the transaction - * but it is tracked in the AIL as though it was. This allows us - * to record logical changes in transactions rather than the physical - * changes we make to the buffer without changing writeback ordering - * constraints of metadata buffers. + * Mark the buffer as ordered for this transaction. This means that the contents + * of the buffer are not recorded in the transaction but it is tracked in the + * AIL as though it was. This allows us to record logical changes in + * transactions rather than the physical changes we make to the buffer without + * changing writeback ordering constraints of metadata buffers. */ -void +bool xfs_trans_ordered_buf( struct xfs_trans *tp, struct xfs_buf *bp) @@ -719,8 +735,18 @@ xfs_trans_ordered_buf( ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); + if (xfs_buf_item_dirty_format(bip)) + return false; + bip->bli_flags |= XFS_BLI_ORDERED; trace_xfs_buf_item_ordered(bip); + + /* + * We don't log a dirty range of an ordered buffer but it still needs + * to be marked dirty and that it has been logged. + */ + xfs_trans_dirty_buf(tp, bp); + return true; } /* diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 49931b7..b317a36 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -106,18 +106,9 @@ xfs_trans_ail_update( xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn); } -void xfs_trans_ail_delete_bulk(struct xfs_ail *ailp, - struct xfs_log_item **log_items, int nr_items, - int shutdown_type) - __releases(ailp->xa_lock); -static inline void -xfs_trans_ail_delete( - struct xfs_ail *ailp, - xfs_log_item_t *lip, - int shutdown_type) __releases(ailp->xa_lock) -{ - xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type); -} +bool xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip); +void xfs_trans_ail_delete(struct xfs_ail *ailp, struct xfs_log_item *lip, + int shutdown_type) __releases(ailp->xa_lock); static inline void xfs_trans_ail_remove( @@ -173,4 +164,35 @@ xfs_trans_ail_copy_lsn( *dst = *src; } #endif + +static inline void +xfs_clear_li_failed( + struct xfs_log_item *lip) +{ + struct xfs_buf *bp = lip->li_buf; + + ASSERT(lip->li_flags & XFS_LI_IN_AIL); + lockdep_assert_held(&lip->li_ailp->xa_lock); + + if (lip->li_flags & XFS_LI_FAILED) { + lip->li_flags &= ~XFS_LI_FAILED; + lip->li_buf = NULL; + xfs_buf_rele(bp); + } +} + +static inline void +xfs_set_li_failed( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + lockdep_assert_held(&lip->li_ailp->xa_lock); + + if (!(lip->li_flags & XFS_LI_FAILED)) { + xfs_buf_hold(bp); + lip->li_flags |= XFS_LI_FAILED; + lip->li_buf = bp; + } +} + #endif /* __XFS_TRANS_PRIV_H__ */ |