From bb9b8e86ad083ecb2567ae909c1d6cb0bbaa60fe Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 3 Jun 2013 15:28:46 +1000 Subject: xfs: rework dquot CRCs Calculating dquot CRCs when the backing buffer is written back just doesn't work reliably. There are several places which manipulate dquots directly in the buffers, and they don't calculate CRCs appropriately, nor do they always set the buffer up to calculate CRCs appropriately. Firstly, if we log a dquot buffer (e.g. during allocation) it gets logged without valid CRC, and so on recovery we end up with a dquot that is not valid. Secondly, if we recover/repair a dquot, we don't have a verifier attached to the buffer and hence CRCs are not calculated on the way down to disk. Thirdly, calculating the CRC after we've changed the contents means that if we re-read the dquot from the buffer, we cannot verify the contents of the dquot are valid, as the CRC is invalid. So, to avoid all the dquot CRC errors that are being detected by the read verifier, change to using the same model as for inodes. That is, dquot CRCs are calculated and written to the backing buffer at the time the dquot is flushed to the backing buffer. If we modify the dquot directly in the backing buffer, calculate the CRC immediately after the modification is complete. Hence the dquot in the on-disk buffer should always have a valid CRC. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Ben Myers Signed-off-by: Ben Myers (cherry picked from commit 6fcdc59de28817d1fbf1bd58cc01f4f3fac858fb) --- fs/xfs/xfs_log_recover.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs/xfs/xfs_log_recover.c') diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index d9e4d3c3991a..d6204d1ac47f 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2266,6 +2266,12 @@ xfs_qm_dqcheck( d->dd_diskdq.d_flags = type; d->dd_diskdq.d_id = cpu_to_be32(id); + if (xfs_sb_version_hascrc(&mp->m_sb)) { + uuid_copy(&d->dd_uuid, &mp->m_sb.sb_uuid); + xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); + } + return errs; } @@ -2793,6 +2799,10 @@ xlog_recover_dquot_pass2( } memcpy(ddq, recddq, item->ri_buf[1].i_len); + if (xfs_sb_version_hascrc(&mp->m_sb)) { + xfs_update_cksum((char *)ddq, sizeof(struct xfs_dqblk), + XFS_DQUOT_CRC_OFF); + } ASSERT(dq_f->qlf_size == 2); ASSERT(bp->b_target->bt_mount == mp); -- cgit v1.2.3 From 75406170751b4de88a01f73dda56efa617ddd5d7 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 5 Jun 2013 12:09:07 +1000 Subject: xfs: fix log recovery transaction item reordering There are several constraints that inode allocation and unlink logging impose on log recovery. These all stem from the fact that inode alloc/unlink are logged in buffers, but all other inode changes are logged in inode items. Hence there are ordering constraints that recovery must follow to ensure the correct result occurs. As it turns out, this ordering has been working mostly by chance than good management. The existing code moves all buffers except cancelled buffers to the head of the list, and everything else to the tail of the list. The problem with this is that is interleaves inode items with the buffer cancellation items, and hence whether the inode item in an cancelled buffer gets replayed is essentially left to chance. Further, this ordering causes problems for log recovery when inode CRCs are enabled. It typically replays the inode unlink buffer long before it replays the inode core changes, and so the CRC recorded in an unlink buffer is going to be invalid and hence any attempt to validate the inode in the buffer is going to fail. Hence we really need to enforce the ordering that the inode alloc/unlink code has expected log recovery to have since inode chunk de-allocation was introduced back in 2003... Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers (cherry picked from commit a775ad778073d55744ed6709ccede36310638911) --- fs/xfs/xfs_log_recover.c | 65 ++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 58 insertions(+), 7 deletions(-) (limited to 'fs/xfs/xfs_log_recover.c') diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index d6204d1ac47f..83088d96e6c4 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1599,10 +1599,43 @@ xlog_recover_add_to_trans( } /* - * Sort the log items in the transaction. Cancelled buffers need - * to be put first so they are processed before any items that might - * modify the buffers. If they are cancelled, then the modifications - * don't need to be replayed. + * Sort the log items in the transaction. + * + * The ordering constraints are defined by the inode allocation and unlink + * behaviour. The rules are: + * + * 1. Every item is only logged once in a given transaction. Hence it + * represents the last logged state of the item. Hence ordering is + * dependent on the order in which operations need to be performed so + * required initial conditions are always met. + * + * 2. Cancelled buffers are recorded in pass 1 in a separate table and + * there's nothing to replay from them so we can simply cull them + * from the transaction. However, we can't do that until after we've + * replayed all the other items because they may be dependent on the + * cancelled buffer and replaying the cancelled buffer can remove it + * form the cancelled buffer table. Hence they have tobe done last. + * + * 3. Inode allocation buffers must be replayed before inode items that + * read the buffer and replay changes into it. + * + * 4. Inode unlink buffers must be replayed after inode items are replayed. + * This ensures that inodes are completely flushed to the inode buffer + * in a "free" state before we remove the unlinked inode list pointer. + * + * Hence the ordering needs to be inode allocation buffers first, inode items + * second, inode unlink buffers third and cancelled buffers last. + * + * But there's a problem with that - we can't tell an inode allocation buffer + * apart from a regular buffer, so we can't separate them. We can, however, + * tell an inode unlink buffer from the others, and so we can separate them out + * from all the other buffers and move them to last. + * + * Hence, 4 lists, in order from head to tail: + * - buffer_list for all buffers except cancelled/inode unlink buffers + * - item_list for all non-buffer items + * - inode_buffer_list for inode unlink buffers + * - cancel_list for the cancelled buffers */ STATIC int xlog_recover_reorder_trans( @@ -1612,6 +1645,10 @@ xlog_recover_reorder_trans( { xlog_recover_item_t *item, *n; LIST_HEAD(sort_list); + LIST_HEAD(cancel_list); + LIST_HEAD(buffer_list); + LIST_HEAD(inode_buffer_list); + LIST_HEAD(inode_list); list_splice_init(&trans->r_itemq, &sort_list); list_for_each_entry_safe(item, n, &sort_list, ri_list) { @@ -1619,12 +1656,18 @@ xlog_recover_reorder_trans( switch (ITEM_TYPE(item)) { case XFS_LI_BUF: - if (!(buf_f->blf_flags & XFS_BLF_CANCEL)) { + if (buf_f->blf_flags & XFS_BLF_CANCEL) { trace_xfs_log_recover_item_reorder_head(log, trans, item, pass); - list_move(&item->ri_list, &trans->r_itemq); + list_move(&item->ri_list, &cancel_list); break; } + if (buf_f->blf_flags & XFS_BLF_INODE_BUF) { + list_move(&item->ri_list, &inode_buffer_list); + break; + } + list_move_tail(&item->ri_list, &buffer_list); + break; case XFS_LI_INODE: case XFS_LI_DQUOT: case XFS_LI_QUOTAOFF: @@ -1632,7 +1675,7 @@ xlog_recover_reorder_trans( case XFS_LI_EFI: trace_xfs_log_recover_item_reorder_tail(log, trans, item, pass); - list_move_tail(&item->ri_list, &trans->r_itemq); + list_move_tail(&item->ri_list, &inode_list); break; default: xfs_warn(log->l_mp, @@ -1643,6 +1686,14 @@ xlog_recover_reorder_trans( } } ASSERT(list_empty(&sort_list)); + if (!list_empty(&buffer_list)) + list_splice(&buffer_list, &trans->r_itemq); + if (!list_empty(&inode_list)) + list_splice_tail(&inode_list, &trans->r_itemq); + if (!list_empty(&inode_buffer_list)) + list_splice_tail(&inode_buffer_list, &trans->r_itemq); + if (!list_empty(&cancel_list)) + list_splice_tail(&cancel_list, &trans->r_itemq); return 0; } -- cgit v1.2.3 From ad868afddb908a5d4015c6b7637721b48fb9c8f9 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 5 Jun 2013 12:09:08 +1000 Subject: xfs: inode unlinked list needs to recalculate the inode CRC The inode unlinked list manipulations operate directly on the inode buffer, and so bypass the inode CRC calculation mechanisms. Hence an inode on the unlinked list has an invalid CRC. Fix this by recalculating the CRC whenever we modify an unlinked list pointer in an inode, ncluding during log recovery. This is trivial to do and results in unlinked list operations always leaving a consistent inode in the buffer. Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers (cherry picked from commit 0a32c26e720a8b38971d0685976f4a7d63f9e2ef) --- fs/xfs/xfs_log_recover.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs/xfs/xfs_log_recover.c') diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 83088d96e6c4..45a85ff84da1 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1912,6 +1912,15 @@ xlog_recover_do_inode_buffer( buffer_nextp = (xfs_agino_t *)xfs_buf_offset(bp, next_unlinked_offset); *buffer_nextp = *logged_nextp; + + /* + * If necessary, recalculate the CRC in the on-disk inode. We + * have to leave the inode in a consistent state for whoever + * reads it next.... + */ + xfs_dinode_calc_crc(mp, (struct xfs_dinode *) + xfs_buf_offset(bp, i * mp->m_sb.sb_inodesize)); + } return 0; -- cgit v1.2.3