From bdb2ed2dbdc227a97e8f37ecf0effc3537bcf789 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Oct 2019 10:07:21 -0700 Subject: xfs: ignore extent size hints for always COW inodes There is no point in applying extent size hints for always COW inodes, as we would just have to COW any extra allocation beyond the data actually written. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_inode.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/xfs/xfs_inode.c') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 18f4b262e61c..2e94deb4610a 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -55,6 +55,12 @@ xfs_extlen_t xfs_get_extsz_hint( struct xfs_inode *ip) { + /* + * No point in aligning allocations if we need to COW to actually + * write to them. + */ + if (xfs_is_always_cow_inode(ip)) + return 0; if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize) return ip->i_d.di_extsize; if (XFS_IS_REALTIME_INODE(ip)) -- cgit v1.2.3 From 3fb21fc8cc04e9a75a426510dfe597f0d0b19134 Mon Sep 17 00:00:00 2001 From: kaixuxia Date: Mon, 21 Oct 2019 08:55:33 -0700 Subject: xfs: remove the duplicated inode log fieldmask set The xfs_bumplink() call has set the inode log fieldmask XFS_ILOG_CORE, so the next xfs_trans_log_inode() call is not necessary. Signed-off-by: kaixuxia Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_inode.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/xfs/xfs_inode.c') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 2e94deb4610a..e9e4f444f8ce 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3333,7 +3333,6 @@ xfs_rename( goto out_trans_cancel; xfs_bumplink(tp, wip); - xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE); VFS_I(wip)->i_state &= ~I_LINKABLE; } -- cgit v1.2.3 From a5155b870d687de1a5f07e774b49b1e8ef0f6f50 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 2 Nov 2019 09:40:53 -0700 Subject: xfs: always log corruption errors Make sure we log something to dmesg whenever we return -EFSCORRUPTED up the call stack. Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_alloc.c | 9 +++++++-- fs/xfs/libxfs/xfs_attr_leaf.c | 12 +++++++++--- fs/xfs/libxfs/xfs_bmap.c | 8 +++++++- fs/xfs/libxfs/xfs_btree.c | 5 ++++- fs/xfs/libxfs/xfs_da_btree.c | 24 ++++++++++++++++++------ fs/xfs/libxfs/xfs_dir2.c | 4 +++- fs/xfs/libxfs/xfs_dir2_leaf.c | 4 +++- fs/xfs/libxfs/xfs_dir2_node.c | 12 +++++++++--- fs/xfs/libxfs/xfs_inode_fork.c | 6 ++++++ fs/xfs/libxfs/xfs_refcount.c | 4 +++- fs/xfs/libxfs/xfs_rtbitmap.c | 6 ++++-- fs/xfs/xfs_acl.c | 15 ++++++++++++--- fs/xfs/xfs_attr_inactive.c | 6 +++++- fs/xfs/xfs_attr_list.c | 5 ++++- fs/xfs/xfs_bmap_item.c | 3 ++- fs/xfs/xfs_error.c | 21 +++++++++++++++++++++ fs/xfs/xfs_error.h | 1 + fs/xfs/xfs_extfree_item.c | 3 ++- fs/xfs/xfs_inode.c | 15 ++++++++++++--- fs/xfs/xfs_inode_item.c | 5 ++++- fs/xfs/xfs_iops.c | 10 +++++++--- fs/xfs/xfs_log_recover.c | 23 ++++++++++++++++++----- fs/xfs/xfs_qm.c | 13 +++++++++++-- fs/xfs/xfs_refcount_item.c | 3 ++- fs/xfs/xfs_rmap_item.c | 7 +++++-- 25 files changed, 179 insertions(+), 45 deletions(-) (limited to 'fs/xfs/xfs_inode.c') diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index b8d48d5fa6a5..f7a4b54c5bc2 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -702,8 +702,10 @@ xfs_alloc_update_counters( xfs_trans_agblocks_delta(tp, len); if (unlikely(be32_to_cpu(agf->agf_freeblks) > - be32_to_cpu(agf->agf_length))) + be32_to_cpu(agf->agf_length))) { + xfs_buf_corruption_error(agbp); return -EFSCORRUPTED; + } xfs_alloc_log_agf(tp, agbp, XFS_AGF_FREEBLKS); return 0; @@ -1048,6 +1050,7 @@ xfs_alloc_ag_vextent_small( bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno); if (!bp) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, args->mp); error = -EFSCORRUPTED; goto error; } @@ -2215,8 +2218,10 @@ xfs_free_agfl_block( return error; bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno); - if (!bp) + if (!bp) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, tp->t_mountp); return -EFSCORRUPTED; + } xfs_trans_binval(tp, bp); return 0; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 56e62b3d9bb7..dca8840496ea 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -2346,8 +2346,10 @@ xfs_attr3_leaf_lookup_int( leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(args->geo, &ichdr, leaf); entries = xfs_attr3_leaf_entryp(leaf); - if (ichdr.count >= args->geo->blksize / 8) + if (ichdr.count >= args->geo->blksize / 8) { + xfs_buf_corruption_error(bp); return -EFSCORRUPTED; + } /* * Binary search. (note: small blocks will skip this loop) @@ -2363,10 +2365,14 @@ xfs_attr3_leaf_lookup_int( else break; } - if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) + if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) { + xfs_buf_corruption_error(bp); return -EFSCORRUPTED; - if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) + } + if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) { + xfs_buf_corruption_error(bp); return -EFSCORRUPTED; + } /* * Since we may have duplicate hashval's, find the first matching diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index bbabbb41e9d8..64f623d07f82 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -730,6 +730,7 @@ xfs_bmap_extents_to_btree( xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); abp = xfs_btree_get_bufl(mp, tp, args.fsbno); if (!abp) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto out_unreserve_dquot; } @@ -1085,6 +1086,7 @@ xfs_bmap_add_attrfork( if (XFS_IFORK_Q(ip)) goto trans_cancel; if (ip->i_d.di_anextents != 0) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto trans_cancel; } @@ -1338,6 +1340,7 @@ xfs_bmap_last_before( case XFS_DINODE_FMT_EXTENTS: break; default: + ASSERT(0); return -EFSCORRUPTED; } @@ -1438,8 +1441,10 @@ xfs_bmap_last_offset( return 0; if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE && - XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) + XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) { + ASSERT(0); return -EFSCORRUPTED; + } error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty); if (error || is_empty) @@ -5830,6 +5835,7 @@ xfs_bmap_insert_extents( del_cursor); if (stop_fsb >= got.br_startoff + got.br_blockcount) { + ASSERT(0); error = -EFSCORRUPTED; goto del_cursor; } diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 4fd89c80c821..98843f1258b8 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -1820,6 +1820,7 @@ xfs_btree_lookup_get_block( out_bad: *blkp = NULL; + xfs_buf_corruption_error(bp); xfs_trans_brelse(cur->bc_tp, bp); return -EFSCORRUPTED; } @@ -1867,8 +1868,10 @@ xfs_btree_lookup( XFS_BTREE_STATS_INC(cur, lookup); /* No such thing as a zero-level tree. */ - if (cur->bc_nlevels == 0) + if (cur->bc_nlevels == 0) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, cur->bc_mp); return -EFSCORRUPTED; + } block = NULL; keyno = 0; diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 4fd1223c1bd5..1e2dc65adeb8 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -504,6 +504,7 @@ xfs_da3_split( node = oldblk->bp->b_addr; if (node->hdr.info.forw) { if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) { + xfs_buf_corruption_error(oldblk->bp); error = -EFSCORRUPTED; goto out; } @@ -516,6 +517,7 @@ xfs_da3_split( node = oldblk->bp->b_addr; if (node->hdr.info.back) { if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) { + xfs_buf_corruption_error(oldblk->bp); error = -EFSCORRUPTED; goto out; } @@ -1541,8 +1543,10 @@ xfs_da3_node_lookup_int( break; } - if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) + if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) { + xfs_buf_corruption_error(blk->bp); return -EFSCORRUPTED; + } blk->magic = XFS_DA_NODE_MAGIC; @@ -1554,15 +1558,18 @@ xfs_da3_node_lookup_int( btree = dp->d_ops->node_tree_p(node); /* Tree taller than we can handle; bail out! */ - if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) + if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) { + xfs_buf_corruption_error(blk->bp); return -EFSCORRUPTED; + } /* Check the level from the root. */ if (blkno == args->geo->leafblk) expected_level = nodehdr.level - 1; - else if (expected_level != nodehdr.level) + else if (expected_level != nodehdr.level) { + xfs_buf_corruption_error(blk->bp); return -EFSCORRUPTED; - else + } else expected_level--; max = nodehdr.count; @@ -1612,12 +1619,17 @@ xfs_da3_node_lookup_int( } /* We can't point back to the root. */ - if (blkno == args->geo->leafblk) + if (blkno == args->geo->leafblk) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, + dp->i_mount); return -EFSCORRUPTED; + } } - if (expected_level != 0) + if (expected_level != 0) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, dp->i_mount); return -EFSCORRUPTED; + } /* * A leaf block that ends in the hashval that we are interested in diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 867c5dee0751..452d04ae10ce 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -600,8 +600,10 @@ xfs_dir2_isblock( if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK))) return rval; rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize; - if (rval != 0 && args->dp->i_d.di_size != args->geo->blksize) + if (rval != 0 && args->dp->i_d.di_size != args->geo->blksize) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, args->dp->i_mount); return -EFSCORRUPTED; + } *vp = rval; return 0; } diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index a53e4585a2f3..388b5da12228 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -1343,8 +1343,10 @@ xfs_dir2_leaf_removename( oldbest = be16_to_cpu(bf[0].length); ltp = xfs_dir2_leaf_tail_p(args->geo, leaf); bestsp = xfs_dir2_leaf_bests_p(ltp); - if (be16_to_cpu(bestsp[db]) != oldbest) + if (be16_to_cpu(bestsp[db]) != oldbest) { + xfs_buf_corruption_error(lbp); return -EFSCORRUPTED; + } /* * Mark the former data entry unused. */ diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 705c4f562758..72d7ed17eef5 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -373,8 +373,10 @@ xfs_dir2_leaf_to_node( leaf = lbp->b_addr; ltp = xfs_dir2_leaf_tail_p(args->geo, leaf); if (be32_to_cpu(ltp->bestcount) > - (uint)dp->i_d.di_size / args->geo->blksize) + (uint)dp->i_d.di_size / args->geo->blksize) { + xfs_buf_corruption_error(lbp); return -EFSCORRUPTED; + } /* * Copy freespace entries from the leaf block to the new block. @@ -445,8 +447,10 @@ xfs_dir2_leafn_add( * Quick check just to make sure we are not going to index * into other peoples memory */ - if (index < 0) + if (index < 0) { + xfs_buf_corruption_error(bp); return -EFSCORRUPTED; + } /* * If there are already the maximum number of leaf entries in @@ -739,8 +743,10 @@ xfs_dir2_leafn_lookup_for_entry( ents = dp->d_ops->leaf_ents_p(leaf); xfs_dir3_leaf_check(dp, bp); - if (leafhdr.count <= 0) + if (leafhdr.count <= 0) { + xfs_buf_corruption_error(bp); return -EFSCORRUPTED; + } /* * Look up the hash value in the leaf entries. diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 8fdd0424070e..15d6f947620f 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -75,11 +75,15 @@ xfs_iformat_fork( error = xfs_iformat_btree(ip, dip, XFS_DATA_FORK); break; default: + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, + dip, sizeof(*dip), __this_address); return -EFSCORRUPTED; } break; default: + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), __this_address); return -EFSCORRUPTED; } if (error) @@ -110,6 +114,8 @@ xfs_iformat_fork( error = xfs_iformat_btree(ip, dip, XFS_ATTR_FORK); break; default: + xfs_inode_verifier_error(ip, error, __func__, dip, + sizeof(*dip), __this_address); error = -EFSCORRUPTED; break; } diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 9a7fadb1361c..78236bd6c64f 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1591,8 +1591,10 @@ xfs_refcount_recover_extent( struct list_head *debris = priv; struct xfs_refcount_recovery *rr; - if (be32_to_cpu(rec->refc.rc_refcount) != 1) + if (be32_to_cpu(rec->refc.rc_refcount) != 1) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, cur->bc_mp); return -EFSCORRUPTED; + } rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 8ea1efc97b41..d8aaa1de921c 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -15,7 +15,7 @@ #include "xfs_bmap.h" #include "xfs_trans.h" #include "xfs_rtalloc.h" - +#include "xfs_error.h" /* * Realtime allocator bitmap functions shared with userspace. @@ -70,8 +70,10 @@ xfs_rtbuf_get( if (error) return error; - if (nmap == 0 || !xfs_bmap_is_real_extent(&map)) + if (nmap == 0 || !xfs_bmap_is_real_extent(&map)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; + } ASSERT(map.br_startblock != NULLFSBLOCK); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 96d7071cfa46..3f2292c7835c 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -12,6 +12,7 @@ #include "xfs_inode.h" #include "xfs_attr.h" #include "xfs_trace.h" +#include "xfs_error.h" #include @@ -23,6 +24,7 @@ STATIC struct posix_acl * xfs_acl_from_disk( + struct xfs_mount *mp, const struct xfs_acl *aclp, int len, int max_entries) @@ -32,11 +34,18 @@ xfs_acl_from_disk( const struct xfs_acl_entry *ace; unsigned int count, i; - if (len < sizeof(*aclp)) + if (len < sizeof(*aclp)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, aclp, + len); return ERR_PTR(-EFSCORRUPTED); + } + count = be32_to_cpu(aclp->acl_cnt); - if (count > max_entries || XFS_ACL_SIZE(count) != len) + if (count > max_entries || XFS_ACL_SIZE(count) != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, aclp, + len); return ERR_PTR(-EFSCORRUPTED); + } acl = posix_acl_alloc(count, GFP_KERNEL); if (!acl) @@ -145,7 +154,7 @@ xfs_get_acl(struct inode *inode, int type) if (error != -ENOATTR) acl = ERR_PTR(error); } else { - acl = xfs_acl_from_disk(xfs_acl, len, + acl = xfs_acl_from_disk(ip->i_mount, xfs_acl, len, XFS_ACL_MAX_ENTRIES(ip->i_mount)); kmem_free(xfs_acl); } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index f83f11d929e4..43ae392992e7 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -22,6 +22,7 @@ #include "xfs_attr_leaf.h" #include "xfs_quota.h" #include "xfs_dir2.h" +#include "xfs_error.h" /* * Look at all the extents for this logical region, @@ -209,6 +210,7 @@ xfs_attr3_node_inactive( */ if (level > XFS_DA_NODE_MAXDEPTH) { xfs_trans_brelse(*trans, bp); /* no locks for later trans */ + xfs_buf_corruption_error(bp); return -EFSCORRUPTED; } @@ -258,8 +260,9 @@ xfs_attr3_node_inactive( error = xfs_attr3_leaf_inactive(trans, dp, child_bp); break; default: - error = -EFSCORRUPTED; + xfs_buf_corruption_error(child_bp); xfs_trans_brelse(*trans, child_bp); + error = -EFSCORRUPTED; break; } if (error) @@ -342,6 +345,7 @@ xfs_attr3_root_inactive( break; default: error = -EFSCORRUPTED; + xfs_buf_corruption_error(bp); xfs_trans_brelse(*trans, bp); break; } diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index c02f22d50e45..64f6ceba9254 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -269,8 +269,10 @@ xfs_attr_node_list_lookup( return 0; /* We can't point back to the root. */ - if (cursor->blkno == 0) + if (cursor->blkno == 0) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; + } } if (expected_level != 0) @@ -280,6 +282,7 @@ xfs_attr_node_list_lookup( return 0; out_corruptbuf: + xfs_buf_corruption_error(bp); xfs_trans_brelse(tp, bp); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 83d24e983d4c..26c87fd9ac9f 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -21,7 +21,7 @@ #include "xfs_icache.h" #include "xfs_bmap_btree.h" #include "xfs_trans_space.h" - +#include "xfs_error.h" kmem_zone_t *xfs_bui_zone; kmem_zone_t *xfs_bud_zone; @@ -525,6 +525,7 @@ xfs_bui_recover( type = bui_type; break; default: + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto err_inode; } diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 0b156cc88108..d8cdb27fe6ed 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -341,6 +341,27 @@ xfs_corruption_error( xfs_alert(mp, "Corruption detected. Unmount and run xfs_repair"); } +/* + * Complain about the kinds of metadata corruption that we can't detect from a + * verifier, such as incorrect inter-block relationship data. Does not set + * bp->b_error. + */ +void +xfs_buf_corruption_error( + struct xfs_buf *bp) +{ + struct xfs_mount *mp = bp->b_mount; + + xfs_alert_tag(mp, XFS_PTAG_VERIFIER_ERROR, + "Metadata corruption detected at %pS, %s block 0x%llx", + __return_address, bp->b_ops->name, bp->b_bn); + + xfs_alert(mp, "Unmount and run xfs_repair"); + + if (xfs_error_level >= XFS_ERRLEVEL_HIGH) + xfs_stack_trace(); +} + /* * Warnings specifically for verifier errors. Differentiate CRC vs. invalid * values, and omit the stack trace unless the error level is tuned high. diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h index e6a22cfb542f..c319379f7d1a 100644 --- a/fs/xfs/xfs_error.h +++ b/fs/xfs/xfs_error.h @@ -15,6 +15,7 @@ extern void xfs_corruption_error(const char *tag, int level, struct xfs_mount *mp, const void *buf, size_t bufsize, const char *filename, int linenum, xfs_failaddr_t failaddr); +void xfs_buf_corruption_error(struct xfs_buf *bp); extern void xfs_buf_verifier_error(struct xfs_buf *bp, int error, const char *name, const void *buf, size_t bufsz, xfs_failaddr_t failaddr); diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index e44efc41a041..a6f6acc8fbb7 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -21,7 +21,7 @@ #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_trace.h" - +#include "xfs_error.h" kmem_zone_t *xfs_efi_zone; kmem_zone_t *xfs_efd_zone; @@ -228,6 +228,7 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) } return 0; } + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index e9e4f444f8ce..a92d4521748d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2136,8 +2136,10 @@ xfs_iunlink_update_bucket( * passed in because either we're adding or removing ourselves from the * head of the list. */ - if (old_value == new_agino) + if (old_value == new_agino) { + xfs_buf_corruption_error(agibp); return -EFSCORRUPTED; + } agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino); offset = offsetof(struct xfs_agi, agi_unlinked) + @@ -2200,6 +2202,8 @@ xfs_iunlink_update_inode( /* Make sure the old pointer isn't garbage. */ old_value = be32_to_cpu(dip->di_next_unlinked); if (!xfs_verify_agino_or_null(mp, agno, old_value)) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), __this_address); error = -EFSCORRUPTED; goto out; } @@ -2211,8 +2215,11 @@ xfs_iunlink_update_inode( */ *old_next_agino = old_value; if (old_value == next_agino) { - if (next_agino != NULLAGINO) + if (next_agino != NULLAGINO) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, + dip, sizeof(*dip), __this_address); error = -EFSCORRUPTED; + } goto out; } @@ -2263,8 +2270,10 @@ xfs_iunlink( */ next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); if (next_agino == agino || - !xfs_verify_agino_or_null(mp, agno, next_agino)) + !xfs_verify_agino_or_null(mp, agno, next_agino)) { + xfs_buf_corruption_error(agibp); return -EFSCORRUPTED; + } if (next_agino != NULLAGINO) { struct xfs_perag *pag; diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index bb8f076805b9..726aa3bfd6e8 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -17,6 +17,7 @@ #include "xfs_trans_priv.h" #include "xfs_buf_item.h" #include "xfs_log.h" +#include "xfs_error.h" #include @@ -828,8 +829,10 @@ xfs_inode_item_format_convert( { struct xfs_inode_log_format_32 *in_f32 = buf->i_addr; - if (buf->i_len != sizeof(*in_f32)) + if (buf->i_len != sizeof(*in_f32)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); return -EFSCORRUPTED; + } in_f->ilf_type = in_f32->ilf_type; in_f->ilf_size = in_f32->ilf_size; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 18e45e3a3f9f..4c7962ccb0c4 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -20,6 +20,7 @@ #include "xfs_symlink.h" #include "xfs_dir2.h" #include "xfs_iomap.h" +#include "xfs_error.h" #include #include @@ -470,17 +471,20 @@ xfs_vn_get_link_inline( struct inode *inode, struct delayed_call *done) { + struct xfs_inode *ip = XFS_I(inode); char *link; - ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE); + ASSERT(ip->i_df.if_flags & XFS_IFINLINE); /* * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if * if_data is junk. */ - link = XFS_I(inode)->i_df.if_u1.if_data; - if (!link) + link = ip->i_df.if_u1.if_data; + if (!link) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, ip->i_mount); return ERR_PTR(-EFSCORRUPTED); + } return link; } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index c1a514ffff55..648d5ecafd91 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3537,6 +3537,7 @@ xfs_cui_copy_format( memcpy(dst_cui_fmt, src_cui_fmt, len); return 0; } + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); return -EFSCORRUPTED; } @@ -3601,8 +3602,10 @@ xlog_recover_cud_pass2( struct xfs_ail *ailp = log->l_ailp; cud_formatp = item->ri_buf[0].i_addr; - if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) + if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); return -EFSCORRUPTED; + } cui_id = cud_formatp->cud_cui_id; /* @@ -3654,6 +3657,7 @@ xfs_bui_copy_format( memcpy(dst_bui_fmt, src_bui_fmt, len); return 0; } + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); return -EFSCORRUPTED; } @@ -3677,8 +3681,10 @@ xlog_recover_bui_pass2( bui_formatp = item->ri_buf[0].i_addr; - if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) + if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); return -EFSCORRUPTED; + } buip = xfs_bui_init(mp); error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format); if (error) { @@ -3720,8 +3726,10 @@ xlog_recover_bud_pass2( struct xfs_ail *ailp = log->l_ailp; bud_formatp = item->ri_buf[0].i_addr; - if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) + if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); return -EFSCORRUPTED; + } bui_id = bud_formatp->bud_bui_id; /* @@ -5172,8 +5180,10 @@ xlog_recover_process( * If the filesystem is CRC enabled, this mismatch becomes a * fatal log corruption failure. */ - if (xfs_sb_version_hascrc(&log->l_mp->m_sb)) + if (xfs_sb_version_hascrc(&log->l_mp->m_sb)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); return -EFSCORRUPTED; + } } xlog_unpack_data(rhead, dp, log); @@ -5296,8 +5306,11 @@ xlog_do_recovery_pass( "invalid iclog size (%d bytes), using lsunit (%d bytes)", h_size, log->l_mp->m_logbsize); h_size = log->l_mp->m_logbsize; - } else + } else { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, + log->l_mp); return -EFSCORRUPTED; + } } if ((be32_to_cpu(rhead->h_version) & XLOG_VERSION_2) && diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index ecd8ce152ab1..66ea8e4fca86 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -22,6 +22,7 @@ #include "xfs_qm.h" #include "xfs_trace.h" #include "xfs_icache.h" +#include "xfs_error.h" /* * The global quota manager. There is only one of these for the entire @@ -754,11 +755,19 @@ xfs_qm_qino_alloc( if ((flags & XFS_QMOPT_PQUOTA) && (mp->m_sb.sb_gquotino != NULLFSINO)) { ino = mp->m_sb.sb_gquotino; - ASSERT(mp->m_sb.sb_pquotino == NULLFSINO); + if (mp->m_sb.sb_pquotino != NULLFSINO) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, + mp); + return -EFSCORRUPTED; + } } else if ((flags & XFS_QMOPT_GQUOTA) && (mp->m_sb.sb_pquotino != NULLFSINO)) { ino = mp->m_sb.sb_pquotino; - ASSERT(mp->m_sb.sb_gquotino == NULLFSINO); + if (mp->m_sb.sb_gquotino != NULLFSINO) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, + mp); + return -EFSCORRUPTED; + } } if (ino != NULLFSINO) { error = xfs_iget(mp, NULL, ino, 0, 0, ip); diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 2328268e6245..576f59fe370e 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -17,7 +17,7 @@ #include "xfs_refcount_item.h" #include "xfs_log.h" #include "xfs_refcount.h" - +#include "xfs_error.h" kmem_zone_t *xfs_cui_zone; kmem_zone_t *xfs_cud_zone; @@ -536,6 +536,7 @@ xfs_cui_recover( type = refc_type; break; default: + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto abort_error; } diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 8939e0ea09cd..1d72e4b3ebf1 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -17,7 +17,7 @@ #include "xfs_rmap_item.h" #include "xfs_log.h" #include "xfs_rmap.h" - +#include "xfs_error.h" kmem_zone_t *xfs_rui_zone; kmem_zone_t *xfs_rud_zone; @@ -171,8 +171,10 @@ xfs_rui_copy_format( src_rui_fmt = buf->i_addr; len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents); - if (buf->i_len != len) + if (buf->i_len != len) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); return -EFSCORRUPTED; + } memcpy(dst_rui_fmt, src_rui_fmt, len); return 0; @@ -581,6 +583,7 @@ xfs_rui_recover( type = XFS_RMAP_FREE; break; default: + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); error = -EFSCORRUPTED; goto abort_error; } -- cgit v1.2.3 From 8d2d878db897d7501aaa2f72e10bb28295bb5498 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 08:20:42 -0800 Subject: xfs: use a struct timespec64 for the in-core crtime struct xfs_icdinode is purely an in-memory data structure, so don't use a log on-disk structure for it. This simplifies the code a bit, and also reduces our include hell slightly. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong [darrick: fix a minor indenting problem in xfs_trans_ichgtime] Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_inode_buf.c | 8 ++++---- fs/xfs/libxfs/xfs_inode_buf.h | 2 +- fs/xfs/libxfs/xfs_trans_inode.c | 8 +++----- fs/xfs/xfs_inode.c | 3 +-- fs/xfs/xfs_inode_item.c | 4 ++-- fs/xfs/xfs_iops.c | 3 +-- fs/xfs/xfs_itable.c | 4 ++-- 7 files changed, 14 insertions(+), 18 deletions(-) (limited to 'fs/xfs/xfs_inode.c') diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 28ab3c5255e1..d31156718b20 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -256,8 +256,8 @@ xfs_inode_from_disk( if (to->di_version == 3) { inode_set_iversion_queried(inode, be64_to_cpu(from->di_changecount)); - to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec); - to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec); + to->di_crtime.tv_sec = be32_to_cpu(from->di_crtime.t_sec); + to->di_crtime.tv_nsec = be32_to_cpu(from->di_crtime.t_nsec); to->di_flags2 = be64_to_cpu(from->di_flags2); to->di_cowextsize = be32_to_cpu(from->di_cowextsize); } @@ -306,8 +306,8 @@ xfs_inode_to_disk( if (from->di_version == 3) { to->di_changecount = cpu_to_be64(inode_peek_iversion(inode)); - to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec); - to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec); + to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.tv_sec); + to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.tv_nsec); to->di_flags2 = cpu_to_be64(from->di_flags2); to->di_cowextsize = cpu_to_be32(from->di_cowextsize); to->di_ino = cpu_to_be64(ip->i_ino); diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index ab0f84165317..c9ac69c82d21 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -37,7 +37,7 @@ struct xfs_icdinode { uint64_t di_flags2; /* more random flags */ uint32_t di_cowextsize; /* basic cow extent size for file */ - xfs_ictimestamp_t di_crtime; /* time created */ + struct timespec64 di_crtime; /* time created */ }; /* diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index a9ad90926b87..2b8ccb5b975d 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -55,7 +55,7 @@ xfs_trans_ichgtime( int flags) { struct inode *inode = VFS_I(ip); - struct timespec64 tv; + struct timespec64 tv; ASSERT(tp); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); @@ -66,10 +66,8 @@ xfs_trans_ichgtime( inode->i_mtime = tv; if (flags & XFS_ICHGTIME_CHG) inode->i_ctime = tv; - if (flags & XFS_ICHGTIME_CREATE) { - ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec; - ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec; - } + if (flags & XFS_ICHGTIME_CREATE) + ip->i_d.di_crtime = tv; } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index a92d4521748d..caf4f830936e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -851,8 +851,7 @@ xfs_ialloc( inode_set_iversion(inode, 1); ip->i_d.di_flags2 = 0; ip->i_d.di_cowextsize = 0; - ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec; - ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec; + ip->i_d.di_crtime = tv; } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 726aa3bfd6e8..a3a75db4d158 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -341,8 +341,8 @@ xfs_inode_to_log_dinode( if (from->di_version == 3) { to->di_changecount = inode_peek_iversion(inode); - to->di_crtime.t_sec = from->di_crtime.t_sec; - to->di_crtime.t_nsec = from->di_crtime.t_nsec; + to->di_crtime.t_sec = from->di_crtime.tv_sec; + to->di_crtime.t_nsec = from->di_crtime.tv_nsec; to->di_flags2 = from->di_flags2; to->di_cowextsize = from->di_cowextsize; to->di_ino = ip->i_ino; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index b129e077a5fa..fc766b3f6119 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -554,8 +554,7 @@ xfs_vn_getattr( if (ip->i_d.di_version == 3) { if (request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; - stat->btime.tv_sec = ip->i_d.di_crtime.t_sec; - stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec; + stat->btime = ip->i_d.di_crtime; } } diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 884950adbd16..11771112a634 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -97,8 +97,8 @@ xfs_bulkstat_one_int( buf->bs_mtime_nsec = inode->i_mtime.tv_nsec; buf->bs_ctime = inode->i_ctime.tv_sec; buf->bs_ctime_nsec = inode->i_ctime.tv_nsec; - buf->bs_btime = dic->di_crtime.t_sec; - buf->bs_btime_nsec = dic->di_crtime.t_nsec; + buf->bs_btime = dic->di_crtime.tv_sec; + buf->bs_btime_nsec = dic->di_crtime.tv_nsec; buf->bs_gen = inode->i_generation; buf->bs_mode = inode->i_mode; -- cgit v1.2.3 From de7a866fd41b227b0aa6e9cbeb0dae221c12f542 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 08:22:54 -0800 Subject: xfs: merge the projid fields in struct xfs_icdinode There is no point in splitting the fields like this in an purely in-memory structure. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_inode_buf.c | 11 +++++------ fs/xfs/libxfs/xfs_inode_buf.h | 3 +-- fs/xfs/xfs_dquot.c | 2 +- fs/xfs/xfs_icache.c | 4 ++-- fs/xfs/xfs_inode.c | 6 +++--- fs/xfs/xfs_inode.h | 21 +-------------------- fs/xfs/xfs_inode_item.c | 4 ++-- fs/xfs/xfs_ioctl.c | 8 ++++---- fs/xfs/xfs_iops.c | 2 +- fs/xfs/xfs_itable.c | 2 +- fs/xfs/xfs_qm.c | 8 ++++---- fs/xfs/xfs_qm_bhv.c | 2 +- 12 files changed, 26 insertions(+), 47 deletions(-) (limited to 'fs/xfs/xfs_inode.c') diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index d31156718b20..019c9be677cc 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -213,13 +213,12 @@ xfs_inode_from_disk( to->di_version = from->di_version; if (to->di_version == 1) { set_nlink(inode, be16_to_cpu(from->di_onlink)); - to->di_projid_lo = 0; - to->di_projid_hi = 0; + to->di_projid = 0; to->di_version = 2; } else { set_nlink(inode, be32_to_cpu(from->di_nlink)); - to->di_projid_lo = be16_to_cpu(from->di_projid_lo); - to->di_projid_hi = be16_to_cpu(from->di_projid_hi); + to->di_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 | + be16_to_cpu(from->di_projid_lo); } to->di_format = from->di_format; @@ -279,8 +278,8 @@ xfs_inode_to_disk( to->di_format = from->di_format; to->di_uid = cpu_to_be32(from->di_uid); to->di_gid = cpu_to_be32(from->di_gid); - to->di_projid_lo = cpu_to_be16(from->di_projid_lo); - to->di_projid_hi = cpu_to_be16(from->di_projid_hi); + to->di_projid_lo = cpu_to_be16(from->di_projid & 0xffff); + to->di_projid_hi = cpu_to_be16(from->di_projid >> 16); memset(to->di_pad, 0, sizeof(to->di_pad)); to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec); diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index c9ac69c82d21..fd94b1078722 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -21,8 +21,7 @@ struct xfs_icdinode { uint16_t di_flushiter; /* incremented on flush */ uint32_t di_uid; /* owner's user id */ uint32_t di_gid; /* owner's group id */ - uint16_t di_projid_lo; /* lower part of owner's project id */ - uint16_t di_projid_hi; /* higher part of owner's project id */ + uint32_t di_projid; /* owner's project id */ xfs_fsize_t di_size; /* number of bytes in file */ xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */ xfs_extlen_t di_extsize; /* basic/minimum extent size for file */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index bcd4247b5014..091faaa5f8ba 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -833,7 +833,7 @@ xfs_qm_id_for_quotatype( case XFS_DQ_GROUP: return ip->i_d.di_gid; case XFS_DQ_PROJ: - return xfs_get_projid(ip); + return ip->i_d.di_projid; } ASSERT(0); return 0; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 944add5ff8e0..ec302b7e48f3 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1419,7 +1419,7 @@ xfs_inode_match_id( return 0; if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) && - xfs_get_projid(ip) != eofb->eof_prid) + ip->i_d.di_projid != eofb->eof_prid) return 0; return 1; @@ -1443,7 +1443,7 @@ xfs_inode_match_id_union( return 1; if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) && - xfs_get_projid(ip) == eofb->eof_prid) + ip->i_d.di_projid == eofb->eof_prid) return 1; return 0; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index caf4f830936e..76424fcc189d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -815,7 +815,7 @@ xfs_ialloc( ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid()); ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid()); inode->i_rdev = rdev; - xfs_set_projid(ip, prid); + ip->i_d.di_projid = prid; if (pip && XFS_INHERIT_GID(pip)) { ip->i_d.di_gid = pip->i_d.di_gid; @@ -1423,7 +1423,7 @@ xfs_link( * the tree quota mechanism could be circumvented. */ if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (xfs_get_projid(tdp) != xfs_get_projid(sip)))) { + tdp->i_d.di_projid != sip->i_d.di_projid)) { error = -EXDEV; goto error_return; } @@ -3284,7 +3284,7 @@ xfs_rename( * tree quota mechanism would be circumvented. */ if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) { + target_dp->i_d.di_projid != src_ip->i_d.di_projid)) { error = -EXDEV; goto out_trans_cancel; } diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 6516dd1fc86a..492e53992fa9 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -174,30 +174,11 @@ xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags) return ret; } -/* - * Project quota id helpers (previously projid was 16bit only - * and using two 16bit values to hold new 32bit projid was chosen - * to retain compatibility with "old" filesystems). - */ -static inline prid_t -xfs_get_projid(struct xfs_inode *ip) -{ - return (prid_t)ip->i_d.di_projid_hi << 16 | ip->i_d.di_projid_lo; -} - -static inline void -xfs_set_projid(struct xfs_inode *ip, - prid_t projid) -{ - ip->i_d.di_projid_hi = (uint16_t) (projid >> 16); - ip->i_d.di_projid_lo = (uint16_t) (projid & 0xffff); -} - static inline prid_t xfs_get_initial_prid(struct xfs_inode *dp) { if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) - return xfs_get_projid(dp); + return dp->i_d.di_projid; return XFS_PROJID_DEFAULT; } diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index a3a75db4d158..07f2b57feecb 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -310,8 +310,8 @@ xfs_inode_to_log_dinode( to->di_format = from->di_format; to->di_uid = from->di_uid; to->di_gid = from->di_gid; - to->di_projid_lo = from->di_projid_lo; - to->di_projid_hi = from->di_projid_hi; + to->di_projid_lo = from->di_projid & 0xffff; + to->di_projid_hi = from->di_projid >> 16; memset(to->di_pad, 0, sizeof(to->di_pad)); memset(to->di_pad3, 0, sizeof(to->di_pad3)); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 364961c23cd0..bf1f3fceb7f1 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1069,7 +1069,7 @@ xfs_fill_fsxattr( fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; fa->fsx_cowextsize = ip->i_d.di_cowextsize << ip->i_mount->m_sb.sb_blocklog; - fa->fsx_projid = xfs_get_projid(ip); + fa->fsx_projid = ip->i_d.di_projid; if (attr) { if (ip->i_afp) { @@ -1521,7 +1521,7 @@ xfs_ioctl_setattr( } if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && - xfs_get_projid(ip) != fa->fsx_projid) { + ip->i_d.di_projid != fa->fsx_projid) { code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp, capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); if (code) /* out of quota */ @@ -1558,13 +1558,13 @@ xfs_ioctl_setattr( VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID); /* Change the ownerships and register project quota modifications */ - if (xfs_get_projid(ip) != fa->fsx_projid) { + if (ip->i_d.di_projid != fa->fsx_projid) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { olddquot = xfs_qm_vop_chown(tp, ip, &ip->i_pdquot, pdqp); } ASSERT(ip->i_d.di_version > 1); - xfs_set_projid(ip, fa->fsx_projid); + ip->i_d.di_projid = fa->fsx_projid; } /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index fc766b3f6119..8afe69ca188b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -692,7 +692,7 @@ xfs_setattr_nonsize( ASSERT(gdqp == NULL); error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid), xfs_kgid_to_gid(gid), - xfs_get_projid(ip), + ip->i_d.di_projid, qflags, &udqp, &gdqp, NULL); if (error) return error; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 11771112a634..4b31c29b7e6b 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -84,7 +84,7 @@ xfs_bulkstat_one_int( /* xfs_iget returns the following without needing * further change. */ - buf->bs_projectid = xfs_get_projid(ip); + buf->bs_projectid = ip->i_d.di_projid; buf->bs_ino = ino; buf->bs_uid = dic->di_uid; buf->bs_gid = dic->di_gid; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 7e264cbd15b9..de346d560bbf 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -342,7 +342,7 @@ xfs_qm_dqattach_locked( } if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) { - error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ, + error = xfs_qm_dqattach_one(ip, ip->i_d.di_projid, XFS_DQ_PROJ, doalloc, &ip->i_pdquot); if (error) goto done; @@ -1698,7 +1698,7 @@ xfs_qm_vop_dqalloc( } } if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) { - if (xfs_get_projid(ip) != prid) { + if (ip->i_d.di_projid != prid) { xfs_iunlock(ip, lockflags); error = xfs_qm_dqget(mp, (xfs_dqid_t)prid, XFS_DQ_PROJ, true, &pq); @@ -1832,7 +1832,7 @@ xfs_qm_vop_chown_reserve( } if (XFS_IS_PQUOTA_ON(ip->i_mount) && pdqp && - xfs_get_projid(ip) != be32_to_cpu(pdqp->q_core.d_id)) { + ip->i_d.di_projid != be32_to_cpu(pdqp->q_core.d_id)) { prjflags = XFS_QMOPT_ENOSPC; pdq_delblks = pdqp; if (delblks) { @@ -1933,7 +1933,7 @@ xfs_qm_vop_create_dqattach( } if (pdqp && XFS_IS_PQUOTA_ON(mp)) { ASSERT(ip->i_pdquot == NULL); - ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id)); + ASSERT(ip->i_d.di_projid == be32_to_cpu(pdqp->q_core.d_id)); ip->i_pdquot = xfs_qm_dqhold(pdqp); xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1); diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 5d72e88598b4..ac8885d0f752 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -60,7 +60,7 @@ xfs_qm_statvfs( xfs_mount_t *mp = ip->i_mount; xfs_dquot_t *dqp; - if (!xfs_qm_dqget(mp, xfs_get_projid(ip), XFS_DQ_PROJ, false, &dqp)) { + if (!xfs_qm_dqget(mp, ip->i_d.di_projid, XFS_DQ_PROJ, false, &dqp)) { xfs_fill_statvfs_from_dquot(statp, dqp); xfs_qm_dqput(dqp); } -- cgit v1.2.3 From 93597ae8dac0149b5c00b787cba6bf7ba213e666 Mon Sep 17 00:00:00 2001 From: kaixuxia Date: Tue, 12 Nov 2019 08:34:23 -0800 Subject: xfs: Fix deadlock between AGI and AGF when target_ip exists in xfs_rename() When target_ip exists in xfs_rename(), the xfs_dir_replace() call may need to hold the AGF lock to allocate more blocks, and then invoking the xfs_droplink() call to hold AGI lock to drop target_ip onto the unlinked list, so we get the lock order AGF->AGI. This would break the ordering constraint on AGI and AGF locking - inode allocation locks the AGI, then can allocate a new extent for new inodes, locking the AGF after the AGI. In this patch we check whether the replace operation need more blocks firstly. If so, acquire the agi lock firstly to preserve locking order(AGI/AGF). Actually, the locking order problem only occurs when we are locking the AGI/AGF of the same AG. For multiple AGs the AGI lock will be released after the transaction committed. Signed-off-by: kaixuxia Reviewed-by: Darrick J. Wong [darrick: reword the comment] Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_dir2.h | 2 ++ fs/xfs/libxfs/xfs_dir2_sf.c | 28 +++++++++++++++++++++++----- fs/xfs/xfs_inode.c | 17 +++++++++++++++++ 3 files changed, 42 insertions(+), 5 deletions(-) (limited to 'fs/xfs/xfs_inode.c') diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index 34e7a0b64205..033777e282f2 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -47,6 +47,8 @@ extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp, extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t ino, xfs_extlen_t tot); +extern bool xfs_dir2_sf_replace_needblock(struct xfs_inode *dp, + xfs_ino_t inum); extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t inum, xfs_extlen_t tot); diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 41eb8a676bf3..8b94d33d232f 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -1016,6 +1016,27 @@ xfs_dir2_sf_removename( return 0; } +/* + * Check whether the sf dir replace operation need more blocks. + */ +bool +xfs_dir2_sf_replace_needblock( + struct xfs_inode *dp, + xfs_ino_t inum) +{ + int newsize; + struct xfs_dir2_sf_hdr *sfp; + + if (dp->i_d.di_format != XFS_DINODE_FMT_LOCAL) + return false; + + sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data; + newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF; + + return inum > XFS_DIR2_MAX_SHORT_INUM && + sfp->i8count == 0 && newsize > XFS_IFORK_DSIZE(dp); +} + /* * Replace the inode number of an entry in a shortform directory. */ @@ -1045,17 +1066,14 @@ xfs_dir2_sf_replace( */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { int error; /* error return value */ - int newsize; /* new inode size */ - newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF; /* * Won't fit as shortform, convert to block then do replace. */ - if (newsize > XFS_IFORK_DSIZE(dp)) { + if (xfs_dir2_sf_replace_needblock(dp, args->inumber)) { error = xfs_dir2_sf_to_block(args); - if (error) { + if (error) return error; - } return xfs_dir2_block_replace(args); } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 76424fcc189d..401da197f012 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3210,6 +3210,7 @@ xfs_rename( struct xfs_trans *tp; struct xfs_inode *wip = NULL; /* whiteout inode */ struct xfs_inode *inodes[__XFS_SORT_INODES]; + struct xfs_buf *agibp; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); @@ -3374,6 +3375,22 @@ xfs_rename( * In case there is already an entry with the same * name at the destination directory, remove it first. */ + + /* + * Check whether the replace operation will need to allocate + * blocks. This happens when the shortform directory lacks + * space and we have to convert it to a block format directory. + * When more blocks are necessary, we must lock the AGI first + * to preserve locking order (AGI -> AGF). + */ + if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) { + error = xfs_read_agi(mp, tp, + XFS_INO_TO_AGNO(mp, target_ip->i_ino), + &agibp); + if (error) + goto out_trans_cancel; + } + error = xfs_dir_replace(tp, target_dp, target_name, src_ip->i_ino, spaceres); if (error) -- cgit v1.2.3