diff options
Diffstat (limited to 'fs/xfs/xfs_inode_item.c')
| -rw-r--r-- | fs/xfs/xfs_inode_item.c | 1416 |
1 files changed, 888 insertions, 528 deletions
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index f76ff52e43c0..2eb0c6011a2e 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -1,435 +1,688 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_types.h" -#include "xfs_log.h" -#include "xfs_trans.h" -#include "xfs_sb.h" -#include "xfs_ag.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_trans_priv.h" -#include "xfs_bmap_btree.h" -#include "xfs_dinode.h" #include "xfs_inode.h" +#include "xfs_trans.h" #include "xfs_inode_item.h" -#include "xfs_error.h" #include "xfs_trace.h" +#include "xfs_trans_priv.h" +#include "xfs_buf_item.h" +#include "xfs_log.h" +#include "xfs_log_priv.h" +#include "xfs_error.h" +#include "xfs_rtbitmap.h" +#include <linux/iversion.h> -kmem_zone_t *xfs_ili_zone; /* inode log item zone */ +struct kmem_cache *xfs_ili_cache; /* inode log item */ static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_inode_log_item, ili_item); } +static uint64_t +xfs_inode_item_sort( + struct xfs_log_item *lip) +{ + return INODE_ITEM(lip)->ili_inode->i_ino; +} + +#ifdef DEBUG_EXPENSIVE +static void +xfs_inode_item_precommit_check( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_dinode *dip; + xfs_failaddr_t fa; + + dip = kzalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | GFP_NOFS); + if (!dip) { + ASSERT(dip != NULL); + return; + } + + xfs_inode_to_disk(ip, dip, 0); + xfs_dinode_calc_crc(mp, dip); + fa = xfs_dinode_verify(mp, ip->i_ino, dip); + if (fa) { + xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip, + sizeof(*dip), fa); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + ASSERT(fa == NULL); + } + kfree(dip); +} +#else +# define xfs_inode_item_precommit_check(ip) ((void)0) +#endif /* - * This returns the number of iovecs needed to log the given inode item. + * Prior to finally logging the inode, we have to ensure that all the + * per-modification inode state changes are applied. This includes VFS inode + * state updates, format conversions, verifier state synchronisation and + * ensuring the inode buffer remains in memory whilst the inode is dirty. * - * We need one iovec for the inode log format structure, one for the - * inode core, and possibly one for the inode data/extents/b-tree root - * and one for the inode attribute data/extents/b-tree root. + * We have to be careful when we grab the inode cluster buffer due to lock + * ordering constraints. The unlinked inode modifications (xfs_iunlink_item) + * require AGI -> inode cluster buffer lock order. The inode cluster buffer is + * not locked until ->precommit, so it happens after everything else has been + * modified. + * + * Further, we have AGI -> AGF lock ordering, and with O_TMPFILE handling we + * have AGI -> AGF -> iunlink item -> inode cluster buffer lock order. Hence we + * cannot safely lock the inode cluster buffer in xfs_trans_log_inode() because + * it can be called on a inode (e.g. via bumplink/droplink) before we take the + * AGF lock modifying directory blocks. + * + * Rather than force a complete rework of all the transactions to call + * xfs_trans_log_inode() once and once only at the end of every transaction, we + * move the pinning of the inode cluster buffer to a ->precommit operation. This + * matches how the xfs_iunlink_item locks the inode cluster buffer, and it + * ensures that the inode cluster buffer locking is always done last in a + * transaction. i.e. we ensure the lock order is always AGI -> AGF -> inode + * cluster buffer. + * + * If we return the inode number as the precommit sort key then we'll also + * guarantee that the order all inode cluster buffer locking is the same all the + * inodes and unlink items in the transaction. */ -STATIC uint -xfs_inode_item_size( +static int +xfs_inode_item_precommit( + struct xfs_trans *tp, struct xfs_log_item *lip) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - uint nvecs = 2; + struct inode *inode = VFS_I(ip); + unsigned int flags = iip->ili_dirty_flags; - switch (ip->i_d.di_format) { + /* + * Don't bother with i_lock for the I_DIRTY_TIME check here, as races + * don't matter - we either will need an extra transaction in 24 hours + * to log the timestamps, or will clear already cleared fields in the + * worst case. + */ + if (inode_state_read_once(inode) & I_DIRTY_TIME) { + spin_lock(&inode->i_lock); + inode_state_clear(inode, I_DIRTY_TIME); + spin_unlock(&inode->i_lock); + } + + /* + * If we're updating the inode core or the timestamps and it's possible + * to upgrade this inode to bigtime format, do so now. + */ + if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) && + xfs_has_bigtime(ip->i_mount) && + !xfs_inode_has_bigtime(ip)) { + ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME; + flags |= XFS_ILOG_CORE; + } + + /* + * Inode verifiers do not check that the extent size hints are an + * integer multiple of the rt extent size on a directory with + * rtinherit flags set. If we're logging a directory that is + * misconfigured in this way, clear the bad hints. + */ + if (ip->i_diflags & XFS_DIFLAG_RTINHERIT) { + if ((ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && + xfs_extlen_to_rtxmod(ip->i_mount, ip->i_extsize) > 0) { + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + flags |= XFS_ILOG_CORE; + } + if ((ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) && + xfs_extlen_to_rtxmod(ip->i_mount, ip->i_cowextsize) > 0) { + ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE; + ip->i_cowextsize = 0; + flags |= XFS_ILOG_CORE; + } + } + + spin_lock(&iip->ili_lock); + if (!iip->ili_item.li_buf) { + struct xfs_buf *bp; + int error; + + /* + * We hold the ILOCK here, so this inode is not going to be + * flushed while we are here. Further, because there is no + * buffer attached to the item, we know that there is no IO in + * progress, so nothing will clear the ili_fields while we read + * in the buffer. Hence we can safely drop the spin lock and + * read the buffer knowing that the state will not change from + * here. + */ + spin_unlock(&iip->ili_lock); + error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp); + if (error) + return error; + + /* + * We need an explicit buffer reference for the log item but + * don't want the buffer to remain attached to the transaction. + * Hold the buffer but release the transaction reference once + * we've attached the inode log item to the buffer log item + * list. + */ + xfs_buf_hold(bp); + spin_lock(&iip->ili_lock); + iip->ili_item.li_buf = bp; + bp->b_iodone = xfs_buf_inode_iodone; + list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); + xfs_trans_brelse(tp, bp); + } + + /* + * Store the dirty flags back into the inode item as this state is used + * later on in xfs_inode_item_committing() to determine whether the + * transaction is relevant to fsync state or not. + */ + iip->ili_dirty_flags = flags; + + /* + * Convert the flags on-disk fields that have been modified in the + * transaction so that ili_fields tracks the changes correctly. + */ + if (flags & XFS_ILOG_IVERSION) + flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE); + + /* + * Always OR in the bits from the ili_last_fields field. This is to + * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines + * in the eventual clearing of the ili_fields bits. See the big comment + * in xfs_iflush() for an explanation of this coordination mechanism. + */ + iip->ili_fields |= (flags | iip->ili_last_fields); + spin_unlock(&iip->ili_lock); + + xfs_inode_item_precommit_check(ip); + return 0; +} + +/* + * The logged size of an inode fork is always the current size of the inode + * fork. This means that when an inode fork is relogged, the size of the logged + * region is determined by the current state, not the combination of the + * previously logged state + the current state. This is different relogging + * behaviour to most other log items which will retain the size of the + * previously logged changes when smaller regions are relogged. + * + * Hence operations that remove data from the inode fork (e.g. shortform + * dir/attr remove, extent form extent removal, etc), the size of the relogged + * inode gets -smaller- rather than stays the same size as the previously logged + * size and this can result in the committing transaction reducing the amount of + * space being consumed by the CIL. + */ +STATIC void +xfs_inode_item_data_fork_size( + struct xfs_inode_log_item *iip, + int *nvecs, + int *nbytes) +{ + struct xfs_inode *ip = iip->ili_inode; + + switch (ip->i_df.if_format) { case XFS_DINODE_FMT_EXTENTS: if ((iip->ili_fields & XFS_ILOG_DEXT) && - ip->i_d.di_nextents > 0 && - ip->i_df.if_bytes > 0) - nvecs++; + ip->i_df.if_nextents > 0 && + ip->i_df.if_bytes > 0) { + /* worst case, doesn't subtract delalloc extents */ + *nbytes += xfs_inode_data_fork_size(ip); + *nvecs += 1; + } break; - case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: if ((iip->ili_fields & XFS_ILOG_DBROOT) && - ip->i_df.if_broot_bytes > 0) - nvecs++; + ip->i_df.if_broot_bytes > 0) { + *nbytes += ip->i_df.if_broot_bytes; + *nvecs += 1; + } break; - case XFS_DINODE_FMT_LOCAL: if ((iip->ili_fields & XFS_ILOG_DDATA) && - ip->i_df.if_bytes > 0) - nvecs++; + ip->i_df.if_bytes > 0) { + *nbytes += xlog_calc_iovec_len(ip->i_df.if_bytes); + *nvecs += 1; + } break; case XFS_DINODE_FMT_DEV: - case XFS_DINODE_FMT_UUID: break; - default: ASSERT(0); break; } +} - if (!XFS_IFORK_Q(ip)) - return nvecs; - +STATIC void +xfs_inode_item_attr_fork_size( + struct xfs_inode_log_item *iip, + int *nvecs, + int *nbytes) +{ + struct xfs_inode *ip = iip->ili_inode; - /* - * Log any necessary attribute data. - */ - switch (ip->i_d.di_aformat) { + switch (ip->i_af.if_format) { case XFS_DINODE_FMT_EXTENTS: if ((iip->ili_fields & XFS_ILOG_AEXT) && - ip->i_d.di_anextents > 0 && - ip->i_afp->if_bytes > 0) - nvecs++; + ip->i_af.if_nextents > 0 && + ip->i_af.if_bytes > 0) { + /* worst case, doesn't subtract unused space */ + *nbytes += xfs_inode_attr_fork_size(ip); + *nvecs += 1; + } break; - case XFS_DINODE_FMT_BTREE: if ((iip->ili_fields & XFS_ILOG_ABROOT) && - ip->i_afp->if_broot_bytes > 0) - nvecs++; + ip->i_af.if_broot_bytes > 0) { + *nbytes += ip->i_af.if_broot_bytes; + *nvecs += 1; + } break; - case XFS_DINODE_FMT_LOCAL: if ((iip->ili_fields & XFS_ILOG_ADATA) && - ip->i_afp->if_bytes > 0) - nvecs++; + ip->i_af.if_bytes > 0) { + *nbytes += xlog_calc_iovec_len(ip->i_af.if_bytes); + *nvecs += 1; + } break; - default: ASSERT(0); break; } - - return nvecs; } /* - * xfs_inode_item_format_extents - convert in-core extents to on-disk form - * - * For either the data or attr fork in extent format, we need to endian convert - * the in-core extent as we place them into the on-disk inode. In this case, we - * need to do this conversion before we write the extents into the log. Because - * we don't have the disk inode to write into here, we allocate a buffer and - * format the extents into it via xfs_iextents_copy(). We free the buffer in - * the unlock routine after the copy for the log has been made. + * This returns the number of iovecs needed to log the given inode item. * - * In the case of the data fork, the in-core and on-disk fork sizes can be - * different due to delayed allocation extents. We only log on-disk extents - * here, so always use the physical fork size to determine the size of the - * buffer we need to allocate. + * We need one iovec for the inode log format structure, one for the + * inode core, and possibly one for the inode data/extents/b-tree root + * and one for the inode attribute data/extents/b-tree root. */ STATIC void -xfs_inode_item_format_extents( - struct xfs_inode *ip, - struct xfs_log_iovec *vecp, - int whichfork, - int type) +xfs_inode_item_size( + struct xfs_log_item *lip, + int *nvecs, + int *nbytes) { - xfs_bmbt_rec_t *ext_buffer; + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; - ext_buffer = kmem_alloc(XFS_IFORK_SIZE(ip, whichfork), KM_SLEEP); - if (whichfork == XFS_DATA_FORK) - ip->i_itemp->ili_extents_buf = ext_buffer; - else - ip->i_itemp->ili_aextents_buf = ext_buffer; + *nvecs += 2; + *nbytes += sizeof(struct xfs_inode_log_format) + + xfs_log_dinode_size(ip->i_mount); - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, whichfork); - vecp->i_type = type; + xfs_inode_item_data_fork_size(iip, nvecs, nbytes); + if (xfs_inode_has_attr_fork(ip)) + xfs_inode_item_attr_fork_size(iip, nvecs, nbytes); } -/* - * This is called to fill in the vector of log iovecs for the - * given inode log item. It fills the first item with an inode - * log format structure, 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. - */ STATIC void -xfs_inode_item_format( - struct xfs_log_item *lip, - struct xfs_log_iovec *vecp) +xfs_inode_item_format_data_fork( + struct xfs_inode_log_item *iip, + struct xfs_inode_log_format *ilf, + struct xfs_log_vec *lv, + struct xfs_log_iovec **vecp) { - struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - uint nvecs; size_t data_bytes; - xfs_mount_t *mp; - - vecp->i_addr = &iip->ili_format; - vecp->i_len = sizeof(xfs_inode_log_format_t); - vecp->i_type = XLOG_REG_TYPE_IFORMAT; - vecp++; - nvecs = 1; - - vecp->i_addr = &ip->i_d; - vecp->i_len = xfs_icdinode_size(ip->i_d.di_version); - vecp->i_type = XLOG_REG_TYPE_ICORE; - vecp++; - nvecs++; - - /* - * If this is really an old format inode, then we need to - * log it as such. This means that we have to copy the link - * count from the new field to the old. We don't have to worry - * about the new fields, because nothing trusts them as long as - * the old inode version number is there. If the superblock already - * has a new version number, then we don't bother converting back. - */ - mp = ip->i_mount; - ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb)); - if (ip->i_d.di_version == 1) { - if (!xfs_sb_version_hasnlink(&mp->m_sb)) { - /* - * Convert it back. - */ - ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1); - ip->i_d.di_onlink = ip->i_d.di_nlink; - } else { - /* - * The superblock version has already been bumped, - * so just make the conversion to the new inode - * format permanent. - */ - ip->i_d.di_version = 2; - ip->i_d.di_onlink = 0; - memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); - } - } - switch (ip->i_d.di_format) { + switch (ip->i_df.if_format) { case XFS_DINODE_FMT_EXTENTS: iip->ili_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEV | XFS_ILOG_UUID); + ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | XFS_ILOG_DEV); if ((iip->ili_fields & XFS_ILOG_DEXT) && - ip->i_d.di_nextents > 0 && + ip->i_df.if_nextents > 0 && ip->i_df.if_bytes > 0) { - ASSERT(ip->i_df.if_u1.if_extents != NULL); - ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0); - ASSERT(iip->ili_extents_buf == NULL); - -#ifdef XFS_NATIVE_HOST - if (ip->i_d.di_nextents == ip->i_df.if_bytes / - (uint)sizeof(xfs_bmbt_rec_t)) { - /* - * There are no delayed allocation - * extents, so just point to the - * real extents array. - */ - vecp->i_addr = ip->i_df.if_u1.if_extents; - vecp->i_len = ip->i_df.if_bytes; - vecp->i_type = XLOG_REG_TYPE_IEXT; - } else -#endif - { - xfs_inode_item_format_extents(ip, vecp, - XFS_DATA_FORK, XLOG_REG_TYPE_IEXT); - } - ASSERT(vecp->i_len <= ip->i_df.if_bytes); - iip->ili_format.ilf_dsize = vecp->i_len; - vecp++; - nvecs++; + struct xfs_bmbt_rec *p; + + ASSERT(xfs_iext_count(&ip->i_df) > 0); + + p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT); + data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK); + xlog_finish_iovec(lv, *vecp, data_bytes); + + ASSERT(data_bytes <= ip->i_df.if_bytes); + + ilf->ilf_dsize = data_bytes; + ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_DEXT; } break; - case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: iip->ili_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | - XFS_ILOG_DEV | XFS_ILOG_UUID); + ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV); if ((iip->ili_fields & XFS_ILOG_DBROOT) && ip->i_df.if_broot_bytes > 0) { ASSERT(ip->i_df.if_broot != NULL); - vecp->i_addr = ip->i_df.if_broot; - vecp->i_len = ip->i_df.if_broot_bytes; - vecp->i_type = XLOG_REG_TYPE_IBROOT; - vecp++; - nvecs++; - iip->ili_format.ilf_dsize = ip->i_df.if_broot_bytes; + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IBROOT, + ip->i_df.if_broot, + ip->i_df.if_broot_bytes); + ilf->ilf_dsize = ip->i_df.if_broot_bytes; + ilf->ilf_size++; } else { ASSERT(!(iip->ili_fields & XFS_ILOG_DBROOT)); iip->ili_fields &= ~XFS_ILOG_DBROOT; } break; - case XFS_DINODE_FMT_LOCAL: iip->ili_fields &= - ~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | - XFS_ILOG_DEV | XFS_ILOG_UUID); + ~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | XFS_ILOG_DEV); if ((iip->ili_fields & XFS_ILOG_DDATA) && ip->i_df.if_bytes > 0) { - ASSERT(ip->i_df.if_u1.if_data != NULL); - ASSERT(ip->i_d.di_size > 0); - - vecp->i_addr = ip->i_df.if_u1.if_data; - /* - * Round i_bytes up to a word boundary. - * The underlying memory is guaranteed to - * to be there by xfs_idata_realloc(). - */ - data_bytes = roundup(ip->i_df.if_bytes, 4); - ASSERT((ip->i_df.if_real_bytes == 0) || - (ip->i_df.if_real_bytes == data_bytes)); - vecp->i_len = (int)data_bytes; - vecp->i_type = XLOG_REG_TYPE_ILOCAL; - vecp++; - nvecs++; - iip->ili_format.ilf_dsize = (unsigned)data_bytes; + ASSERT(ip->i_df.if_data != NULL); + ASSERT(ip->i_disk_size > 0); + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL, + ip->i_df.if_data, ip->i_df.if_bytes); + ilf->ilf_dsize = (unsigned)ip->i_df.if_bytes; + ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_DDATA; } break; - case XFS_DINODE_FMT_DEV: iip->ili_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEXT | XFS_ILOG_UUID); - if (iip->ili_fields & XFS_ILOG_DEV) { - iip->ili_format.ilf_u.ilfu_rdev = - ip->i_df.if_u2.if_rdev; - } - break; - - case XFS_DINODE_FMT_UUID: - iip->ili_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEXT | XFS_ILOG_DEV); - if (iip->ili_fields & XFS_ILOG_UUID) { - iip->ili_format.ilf_u.ilfu_uuid = - ip->i_df.if_u2.if_uuid; - } + ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | XFS_ILOG_DEXT); + if (iip->ili_fields & XFS_ILOG_DEV) + ilf->ilf_u.ilfu_rdev = sysv_encode_dev(VFS_I(ip)->i_rdev); break; - default: ASSERT(0); break; } +} - /* - * If there are no attributes associated with the file, then we're done. - */ - if (!XFS_IFORK_Q(ip)) { - iip->ili_fields &= - ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT); - goto out; - } +STATIC void +xfs_inode_item_format_attr_fork( + struct xfs_inode_log_item *iip, + struct xfs_inode_log_format *ilf, + struct xfs_log_vec *lv, + struct xfs_log_iovec **vecp) +{ + struct xfs_inode *ip = iip->ili_inode; + size_t data_bytes; - switch (ip->i_d.di_aformat) { + switch (ip->i_af.if_format) { case XFS_DINODE_FMT_EXTENTS: iip->ili_fields &= ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT); if ((iip->ili_fields & XFS_ILOG_AEXT) && - ip->i_d.di_anextents > 0 && - ip->i_afp->if_bytes > 0) { - ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) == - ip->i_d.di_anextents); - ASSERT(ip->i_afp->if_u1.if_extents != NULL); -#ifdef XFS_NATIVE_HOST - /* - * There are not delayed allocation extents - * for attributes, so just point at the array. - */ - vecp->i_addr = ip->i_afp->if_u1.if_extents; - vecp->i_len = ip->i_afp->if_bytes; - vecp->i_type = XLOG_REG_TYPE_IATTR_EXT; -#else - ASSERT(iip->ili_aextents_buf == NULL); - xfs_inode_item_format_extents(ip, vecp, - XFS_ATTR_FORK, XLOG_REG_TYPE_IATTR_EXT); -#endif - iip->ili_format.ilf_asize = vecp->i_len; - vecp++; - nvecs++; + ip->i_af.if_nextents > 0 && + ip->i_af.if_bytes > 0) { + struct xfs_bmbt_rec *p; + + ASSERT(xfs_iext_count(&ip->i_af) == + ip->i_af.if_nextents); + + p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_EXT); + data_bytes = xfs_iextents_copy(ip, p, XFS_ATTR_FORK); + xlog_finish_iovec(lv, *vecp, data_bytes); + + ilf->ilf_asize = data_bytes; + ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_AEXT; } break; - case XFS_DINODE_FMT_BTREE: iip->ili_fields &= ~(XFS_ILOG_ADATA | XFS_ILOG_AEXT); if ((iip->ili_fields & XFS_ILOG_ABROOT) && - ip->i_afp->if_broot_bytes > 0) { - ASSERT(ip->i_afp->if_broot != NULL); - - vecp->i_addr = ip->i_afp->if_broot; - vecp->i_len = ip->i_afp->if_broot_bytes; - vecp->i_type = XLOG_REG_TYPE_IATTR_BROOT; - vecp++; - nvecs++; - iip->ili_format.ilf_asize = ip->i_afp->if_broot_bytes; + ip->i_af.if_broot_bytes > 0) { + ASSERT(ip->i_af.if_broot != NULL); + + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_BROOT, + ip->i_af.if_broot, + ip->i_af.if_broot_bytes); + ilf->ilf_asize = ip->i_af.if_broot_bytes; + ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_ABROOT; } break; - case XFS_DINODE_FMT_LOCAL: iip->ili_fields &= ~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT); if ((iip->ili_fields & XFS_ILOG_ADATA) && - ip->i_afp->if_bytes > 0) { - ASSERT(ip->i_afp->if_u1.if_data != NULL); - - vecp->i_addr = ip->i_afp->if_u1.if_data; - /* - * Round i_bytes up to a word boundary. - * The underlying memory is guaranteed to - * to be there by xfs_idata_realloc(). - */ - data_bytes = roundup(ip->i_afp->if_bytes, 4); - ASSERT((ip->i_afp->if_real_bytes == 0) || - (ip->i_afp->if_real_bytes == data_bytes)); - vecp->i_len = (int)data_bytes; - vecp->i_type = XLOG_REG_TYPE_IATTR_LOCAL; - vecp++; - nvecs++; - iip->ili_format.ilf_asize = (unsigned)data_bytes; + ip->i_af.if_bytes > 0) { + ASSERT(ip->i_af.if_data != NULL); + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL, + ip->i_af.if_data, ip->i_af.if_bytes); + ilf->ilf_asize = (unsigned)ip->i_af.if_bytes; + ilf->ilf_size++; } else { iip->ili_fields &= ~XFS_ILOG_ADATA; } break; - default: ASSERT(0); break; } +} + +/* + * Convert an incore timestamp to a log timestamp. Note that the log format + * specifies host endian format! + */ +static inline xfs_log_timestamp_t +xfs_inode_to_log_dinode_ts( + struct xfs_inode *ip, + const struct timespec64 tv) +{ + struct xfs_log_legacy_timestamp *lits; + xfs_log_timestamp_t its; + + if (xfs_inode_has_bigtime(ip)) + return xfs_inode_encode_bigtime(tv); + + lits = (struct xfs_log_legacy_timestamp *)&its; + lits->t_sec = tv.tv_sec; + lits->t_nsec = tv.tv_nsec; + + return its; +} + +/* + * The legacy DMAPI fields are only present in the on-disk and in-log inodes, + * but not in the in-memory one. But we are guaranteed to have an inode buffer + * in memory when logging an inode, so we can just copy it from the on-disk + * inode to the in-log inode here so that recovery of file system with these + * fields set to non-zero values doesn't lose them. For all other cases we zero + * the fields. + */ +static void +xfs_copy_dm_fields_to_log_dinode( + struct xfs_inode *ip, + struct xfs_log_dinode *to) +{ + struct xfs_dinode *dip; + + dip = xfs_buf_offset(ip->i_itemp->ili_item.li_buf, + ip->i_imap.im_boffset); + + if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) { + to->di_dmevmask = be32_to_cpu(dip->di_dmevmask); + to->di_dmstate = be16_to_cpu(dip->di_dmstate); + } else { + to->di_dmevmask = 0; + to->di_dmstate = 0; + } +} + +static inline void +xfs_inode_to_log_dinode_iext_counters( + struct xfs_inode *ip, + struct xfs_log_dinode *to) +{ + if (xfs_inode_has_large_extent_counts(ip)) { + to->di_big_nextents = xfs_ifork_nextents(&ip->i_df); + to->di_big_anextents = xfs_ifork_nextents(&ip->i_af); + to->di_nrext64_pad = 0; + } else { + to->di_nextents = xfs_ifork_nextents(&ip->i_df); + to->di_anextents = xfs_ifork_nextents(&ip->i_af); + } +} + +static void +xfs_inode_to_log_dinode( + struct xfs_inode *ip, + struct xfs_log_dinode *to, + xfs_lsn_t lsn) +{ + struct inode *inode = VFS_I(ip); + + to->di_magic = XFS_DINODE_MAGIC; + to->di_format = xfs_ifork_format(&ip->i_df); + to->di_uid = i_uid_read(inode); + to->di_gid = i_gid_read(inode); + to->di_projid_lo = ip->i_projid & 0xffff; + to->di_projid_hi = ip->i_projid >> 16; + + to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode_get_atime(inode)); + to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode_get_mtime(inode)); + to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode_get_ctime(inode)); + to->di_nlink = inode->i_nlink; + to->di_gen = inode->i_generation; + to->di_mode = inode->i_mode; + + to->di_size = ip->i_disk_size; + to->di_nblocks = ip->i_nblocks; + to->di_extsize = ip->i_extsize; + to->di_forkoff = ip->i_forkoff; + to->di_aformat = xfs_ifork_format(&ip->i_af); + to->di_flags = ip->i_diflags; + + xfs_copy_dm_fields_to_log_dinode(ip, to); + + /* log a dummy value to ensure log structure is fully initialised */ + to->di_next_unlinked = NULLAGINO; + + if (xfs_has_v3inodes(ip->i_mount)) { + to->di_version = 3; + to->di_changecount = inode_peek_iversion(inode); + to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime); + to->di_flags2 = ip->i_diflags2; + /* also covers the di_used_blocks union arm: */ + to->di_cowextsize = ip->i_cowextsize; + to->di_ino = ip->i_ino; + to->di_lsn = lsn; + memset(to->di_pad2, 0, sizeof(to->di_pad2)); + uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid); + to->di_v3_pad = 0; + + /* dummy value for initialisation */ + to->di_crc = 0; + + if (xfs_is_metadir_inode(ip)) + to->di_metatype = ip->i_metatype; + else + to->di_metatype = 0; + } else { + to->di_version = 2; + to->di_flushiter = ip->i_flushiter; + memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad)); + to->di_metatype = 0; + } + + xfs_inode_to_log_dinode_iext_counters(ip, to); +} + +/* + * Format the inode core. Current timestamp data is only in the VFS inode + * fields, so we need to grab them from there. Hence rather than just copying + * the XFS inode core structure, format the fields directly into the iovec. + */ +static void +xfs_inode_item_format_core( + struct xfs_inode *ip, + struct xfs_log_vec *lv, + struct xfs_log_iovec **vecp) +{ + struct xfs_log_dinode *dic; + + dic = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_ICORE); + xfs_inode_to_log_dinode(ip, dic, ip->i_itemp->ili_item.li_lsn); + xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_mount)); +} + +/* + * This is called to fill in the vector of log iovecs for the given inode + * log item. It fills the first item with an inode log format structure, + * 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( + struct xfs_log_item *lip, + struct xfs_log_vec *lv) +{ + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; + struct xfs_log_iovec *vecp = NULL; + struct xfs_inode_log_format *ilf; + + ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT); + ilf->ilf_type = XFS_LI_INODE; + ilf->ilf_ino = ip->i_ino; + ilf->ilf_blkno = ip->i_imap.im_blkno; + ilf->ilf_len = ip->i_imap.im_len; + ilf->ilf_boffset = ip->i_imap.im_boffset; + ilf->ilf_fields = XFS_ILOG_CORE; + ilf->ilf_size = 2; /* format + core */ -out: /* - * Now update the log format that goes out to disk from the in-core - * values. We always write the inode core to make the arithmetic - * games in recovery easier, which isn't a big deal as just about any - * transaction would dirty it anyway. + * make sure we don't leak uninitialised data into the log in the case + * when we don't log every field in the inode. */ - iip->ili_format.ilf_fields = XFS_ILOG_CORE | - (iip->ili_fields & ~XFS_ILOG_TIMESTAMP); - iip->ili_format.ilf_size = nvecs; -} + ilf->ilf_dsize = 0; + ilf->ilf_asize = 0; + ilf->ilf_pad = 0; + memset(&ilf->ilf_u, 0, sizeof(ilf->ilf_u)); + + 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); + if (xfs_inode_has_attr_fork(ip)) { + xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp); + } else { + iip->ili_fields &= + ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT); + } + /* update the format with the exact fields we actually logged */ + ilf->ilf_fields |= (iip->ili_fields & ~XFS_ILOG_TIMESTAMP); +} /* * This is called to pin the inode associated with the inode log @@ -441,7 +694,8 @@ xfs_inode_item_pin( { struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + ASSERT(lip->li_buf); trace_xfs_inode_pin(ip, _RET_IP_); atomic_inc(&ip->i_pincount); @@ -453,90 +707,106 @@ xfs_inode_item_pin( * item which was previously pinned with a call to xfs_inode_item_pin(). * * Also wake up anyone in xfs_iunpin_wait() if the count goes to 0. + * + * Note that unpin can race with inode cluster buffer freeing marking the buffer + * stale. In that case, flush completions are run from the buffer unpin call, + * which may happen before the inode is unpinned. If we lose the race, there + * will be no buffer attached to the log item, but the inode will be marked + * XFS_ISTALE. */ STATIC void xfs_inode_item_unpin( struct xfs_log_item *lip, int remove) { - struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode; + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; trace_xfs_inode_unpin(ip, _RET_IP_); + ASSERT(lip->li_buf || xfs_iflags_test(ip, XFS_ISTALE)); ASSERT(atomic_read(&ip->i_pincount) > 0); - if (atomic_dec_and_test(&ip->i_pincount)) + + /* + * If this is the last unpin, then the inode no longer needs a journal + * flush to persist it. Hence we can clear the commit sequence numbers + * as a fsync/fdatasync operation on the inode at this point is a no-op. + */ + if (atomic_dec_and_lock(&ip->i_pincount, &iip->ili_lock)) { + iip->ili_commit_seq = 0; + iip->ili_datasync_seq = 0; + spin_unlock(&iip->ili_lock); wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); + } } STATIC uint xfs_inode_item_push( struct xfs_log_item *lip, struct list_head *buffer_list) + __releases(&lip->li_ailp->ail_lock) + __acquires(&lip->li_ailp->ail_lock) { 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) + if (!bp || (ip->i_flags & XFS_ISTALE)) { + /* + * Inode item/buffer is being aborted due to cluster + * buffer deletion. Trigger a log force to have that operation + * completed and items removed from the AIL before the next push + * attempt. + */ + trace_xfs_inode_push_stale(ip, _RET_IP_); return XFS_ITEM_PINNED; - - if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) - return XFS_ITEM_LOCKED; - - /* - * Re-check the pincount now that we stabilized the value by - * taking the ilock. - */ - if (xfs_ipincount(ip) > 0) { - rval = XFS_ITEM_PINNED; - goto out_unlock; } - /* - * Stale inode items should force out the iclog. - */ - if (ip->i_flags & XFS_ISTALE) { - rval = XFS_ITEM_PINNED; - goto out_unlock; + if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) { + trace_xfs_inode_push_pinned(ip, _RET_IP_); + return XFS_ITEM_PINNED; } - /* - * Someone else is already flushing the inode. Nothing we can do - * here but wait for the flush to finish and remove the item from - * the AIL. - */ - if (!xfs_iflock_nowait(ip)) { - rval = XFS_ITEM_FLUSHING; - goto out_unlock; - } + if (xfs_iflags_test(ip, XFS_IFLUSHING)) + return XFS_ITEM_FLUSHING; - ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); - ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); + if (!xfs_buf_trylock(bp)) + return XFS_ITEM_LOCKED; - spin_unlock(&lip->li_ailp->xa_lock); + spin_unlock(&lip->li_ailp->ail_lock); - error = xfs_iflush(ip, &bp); + /* + * We need to hold a reference for flushing the cluster buffer as it may + * fail the buffer without IO submission. In which case, we better get a + * reference for that completion because otherwise we don't get a + * reference for IO until we queue the buffer for delwri submission. + */ + xfs_buf_hold(bp); + error = xfs_iflush_cluster(bp); if (!error) { if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; xfs_buf_relse(bp); + } else { + /* + * Release the buffer if we were unable to flush anything. On + * any other error, the buffer has already been released. + */ + if (error == -EAGAIN) + xfs_buf_relse(bp); + rval = XFS_ITEM_LOCKED; } - spin_lock(&lip->li_ailp->xa_lock); -out_unlock: - xfs_iunlock(ip, XFS_ILOCK_SHARED); + spin_lock(&lip->li_ailp->ail_lock); return rval; } /* * Unlock the inode associated with the inode log item. - * Clear the fields of the inode and inode log item that - * are specific to the current transaction. If the - * hold flags is set, do not unlock the inode. */ STATIC void -xfs_inode_item_unlock( +xfs_inode_item_release( struct xfs_log_item *lip) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); @@ -544,28 +814,7 @@ xfs_inode_item_unlock( unsigned short lock_flags; ASSERT(ip->i_itemp != NULL); - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - /* - * If the inode needed a separate buffer with which to log - * its extents, then free it now. - */ - if (iip->ili_extents_buf != NULL) { - ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS); - ASSERT(ip->i_d.di_nextents > 0); - ASSERT(iip->ili_fields & XFS_ILOG_DEXT); - ASSERT(ip->i_df.if_bytes > 0); - kmem_free(iip->ili_extents_buf); - iip->ili_extents_buf = NULL; - } - if (iip->ili_aextents_buf != NULL) { - ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS); - ASSERT(ip->i_d.di_anextents > 0); - ASSERT(iip->ili_fields & XFS_ILOG_AEXT); - ASSERT(ip->i_afp->if_bytes > 0); - kmem_free(iip->ili_aextents_buf); - iip->ili_aextents_buf = NULL; - } + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); lock_flags = iip->ili_lock_flags; iip->ili_lock_flags = 0; @@ -611,29 +860,58 @@ xfs_inode_item_committed( } /* - * XXX rcc - this one really has to do something. Probably needs - * to stamp in a new field in the incore inode. + * The modification is now complete, so before we unlock the inode we need to + * update the commit sequence numbers for data integrity journal flushes. We + * always record the commit sequence number (ili_commit_seq) so that anything + * that needs a full journal sync will capture all of this modification. + * + * We then + * check if the changes will impact a datasync (O_DSYNC) journal flush. If the + * changes will require a datasync flush, then we also record the sequence in + * ili_datasync_seq. + * + * These commit sequence numbers will get cleared atomically with the inode being + * unpinned (i.e. pin count goes to zero), and so it will only be set when the + * inode is dirty in the journal. This removes the need for checking if the + * inode is pinned to determine if a journal flush is necessary, and hence + * removes the need for holding the ILOCK_SHARED in xfs_file_fsync() to + * serialise pin counts against commit sequence number updates. + * */ STATIC void xfs_inode_item_committing( struct xfs_log_item *lip, - xfs_lsn_t lsn) + xfs_csn_t seq) { - INODE_ITEM(lip)->ili_last_lsn = lsn; + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + + spin_lock(&iip->ili_lock); + iip->ili_commit_seq = seq; + if (iip->ili_dirty_flags & ~(XFS_ILOG_IVERSION | XFS_ILOG_TIMESTAMP)) + iip->ili_datasync_seq = seq; + spin_unlock(&iip->ili_lock); + + /* + * Clear the per-transaction dirty flags now that we have finished + * recording the transaction's inode modifications in the CIL and are + * about to release and (maybe) unlock the inode. + */ + iip->ili_dirty_flags = 0; + + return xfs_inode_item_release(lip); } -/* - * This is the ops vector shared by all buf log items. - */ static const struct xfs_item_ops xfs_inode_item_ops = { + .iop_sort = xfs_inode_item_sort, + .iop_precommit = xfs_inode_item_precommit, .iop_size = xfs_inode_item_size, .iop_format = xfs_inode_item_format, .iop_pin = xfs_inode_item_pin, .iop_unpin = xfs_inode_item_unpin, - .iop_unlock = xfs_inode_item_unlock, + .iop_release = xfs_inode_item_release, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_committing = xfs_inode_item_committing + .iop_committing = xfs_inode_item_committing, }; @@ -648,16 +926,13 @@ xfs_inode_item_init( struct xfs_inode_log_item *iip; ASSERT(ip->i_itemp == NULL); - iip = ip->i_itemp = kmem_zone_zalloc(xfs_ili_zone, KM_SLEEP); + iip = ip->i_itemp = kmem_cache_zalloc(xfs_ili_cache, + GFP_KERNEL | __GFP_NOFAIL); iip->ili_inode = ip; + spin_lock_init(&iip->ili_lock); xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE, &xfs_inode_item_ops); - iip->ili_format.ilf_type = XFS_LI_INODE; - iip->ili_format.ilf_ino = ip->i_ino; - iip->ili_format.ilf_blkno = ip->i_imap.im_blkno; - iip->ili_format.ilf_len = ip->i_imap.im_len; - iip->ili_format.ilf_boffset = ip->i_imap.im_boffset; } /* @@ -665,215 +940,300 @@ xfs_inode_item_init( */ void xfs_inode_item_destroy( - xfs_inode_t *ip) + struct xfs_inode *ip) { - kmem_zone_free(xfs_ili_zone, ip->i_itemp); + struct xfs_inode_log_item *iip = ip->i_itemp; + + ASSERT(iip->ili_item.li_buf == NULL); + + ip->i_itemp = NULL; + kvfree(iip->ili_item.li_lv_shadow); + kmem_cache_free(xfs_ili_cache, iip); } /* - * This is the inode flushing I/O completion routine. It is called - * from interrupt level when the buffer containing the inode is - * flushed to disk. It is responsible for removing the inode item - * from the AIL if it has not been re-logged, and unlocking the inode's - * flush lock. - * - * To reduce AIL lock traffic as much as possible, we scan the buffer log item - * list for other inodes that will run this function. We remove them from the - * buffer list so we can process all the inode IO completions in one AIL lock - * traversal. + * We only want to pull the item from the AIL if it is actually there + * and its location in the log has not changed since we started the + * flush. Thus, we only bother if the inode's lsn has not changed. */ -void -xfs_iflush_done( - struct xfs_buf *bp, - struct xfs_log_item *lip) +static void +xfs_iflush_ail_updates( + struct xfs_ail *ailp, + struct list_head *list) { - struct xfs_inode_log_item *iip; - struct xfs_log_item *blip; - struct xfs_log_item *next; - struct xfs_log_item *prev; - struct xfs_ail *ailp = lip->li_ailp; - int need_ail = 0; + struct xfs_log_item *lip; + xfs_lsn_t tail_lsn = 0; - /* - * Scan the buffer IO completions for other inodes being completed and - * attach them to the current inode log item. - */ - blip = bp->b_fspriv; - prev = NULL; - while (blip != NULL) { - if (lip->li_cb != xfs_iflush_done) { - prev = blip; - blip = blip->li_bio_list; + /* this is an opencoded batch version of xfs_trans_ail_delete */ + spin_lock(&ailp->ail_lock); + list_for_each_entry(lip, list, li_bio_list) { + xfs_lsn_t lsn; + + clear_bit(XFS_LI_FAILED, &lip->li_flags); + if (INODE_ITEM(lip)->ili_flush_lsn != lip->li_lsn) continue; - } - /* remove from list */ - next = blip->li_bio_list; - if (!prev) { - bp->b_fspriv = next; - } else { - prev->li_bio_list = next; + /* + * dgc: Not sure how this happens, but it happens very + * occassionaly via generic/388. xfs_iflush_abort() also + * silently handles this same "under writeback but not in AIL at + * shutdown" condition via xfs_trans_ail_delete(). + */ + if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) { + ASSERT(xlog_is_shutdown(lip->li_log)); + continue; } - /* add to current list */ - blip->li_bio_list = lip->li_bio_list; - lip->li_bio_list = blip; + lsn = xfs_ail_delete_one(ailp, lip); + if (!tail_lsn && lsn) + tail_lsn = lsn; + } + xfs_ail_update_finish(ailp, tail_lsn); +} + +/* + * Walk the list of inodes that have completed their IOs. If they are clean + * remove them from the list and dissociate them from the buffer. Buffers that + * are still dirty remain linked to the buffer and on the list. Caller must + * handle them appropriately. + */ +static void +xfs_iflush_finish( + struct xfs_buf *bp, + struct list_head *list) +{ + struct xfs_log_item *lip, *n; + + list_for_each_entry_safe(lip, n, list, li_bio_list) { + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + bool drop_buffer = false; + + spin_lock(&iip->ili_lock); /* - * while we have the item, do the unlocked check for needing - * the AIL lock. + * Remove the reference to the cluster buffer if the inode is + * clean in memory and drop the buffer reference once we've + * dropped the locks we hold. */ - iip = INODE_ITEM(blip); - if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) - need_ail++; - - blip = next; + ASSERT(iip->ili_item.li_buf == bp); + if (!iip->ili_fields) { + iip->ili_item.li_buf = NULL; + list_del_init(&lip->li_bio_list); + drop_buffer = true; + } + iip->ili_last_fields = 0; + iip->ili_flush_lsn = 0; + clear_bit(XFS_LI_FLUSHING, &lip->li_flags); + spin_unlock(&iip->ili_lock); + xfs_iflags_clear(iip->ili_inode, XFS_IFLUSHING); + if (drop_buffer) + xfs_buf_rele(bp); } +} - /* 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) - need_ail++; +/* + * Inode buffer IO completion routine. It is responsible for removing inodes + * attached to the buffer from the AIL if they have not been re-logged and + * completing the inode flush. + */ +void +xfs_buf_inode_iodone( + struct xfs_buf *bp) +{ + struct xfs_log_item *lip, *n; + LIST_HEAD(flushed_inodes); + LIST_HEAD(ail_updates); /* - * We only want to pull the item from the AIL if it is - * actually there and its location in the log has not - * changed since we started the flush. Thus, we only bother - * if the ili_logged flag is set and the inode's lsn has not - * changed. First we check the lsn outside - * the lock since it's cheaper, and then we recheck while - * holding the lock before removing the inode from the AIL. + * Pull the attached inodes from the buffer one at a time and take the + * appropriate action on them. */ - if (need_ail) { - struct xfs_log_item *log_items[need_ail]; - int i = 0; - 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; - } - ASSERT(i <= need_ail); + list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + + if (xfs_iflags_test(iip->ili_inode, XFS_ISTALE)) { + xfs_iflush_abort(iip->ili_inode); + continue; } - /* xfs_trans_ail_delete_bulk() drops the AIL lock. */ - xfs_trans_ail_delete_bulk(ailp, log_items, i, - SHUTDOWN_CORRUPT_INCORE); + if (!iip->ili_last_fields) + continue; + + /* Do an unlocked check for needing the AIL lock. */ + if (iip->ili_flush_lsn == lip->li_lsn || + test_bit(XFS_LI_FAILED, &lip->li_flags)) + list_move_tail(&lip->li_bio_list, &ail_updates); + else + list_move_tail(&lip->li_bio_list, &flushed_inodes); } + if (!list_empty(&ail_updates)) { + xfs_iflush_ail_updates(bp->b_mount->m_ail, &ail_updates); + list_splice_tail(&ail_updates, &flushed_inodes); + } - /* - * clean up and unlock the flush lock now we are done. We can clear the - * ili_last_fields bits now that we know that the data corresponding to - * them is safely on disk. - */ - for (blip = lip; blip; blip = next) { - next = blip->li_bio_list; - blip->li_bio_list = NULL; + xfs_iflush_finish(bp, &flushed_inodes); + if (!list_empty(&flushed_inodes)) + list_splice_tail(&flushed_inodes, &bp->b_li_list); +} - iip = INODE_ITEM(blip); - iip->ili_logged = 0; - iip->ili_last_fields = 0; - xfs_ifunlock(iip->ili_inode); - } +/* + * Clear the inode logging fields so no more flushes are attempted. If we are + * on a buffer list, it is now safe to remove it because the buffer is + * guaranteed to be locked. The caller will drop the reference to the buffer + * the log item held. + */ +static void +xfs_iflush_abort_clean( + struct xfs_inode_log_item *iip) +{ + iip->ili_last_fields = 0; + iip->ili_fields = 0; + iip->ili_flush_lsn = 0; + iip->ili_item.li_buf = NULL; + list_del_init(&iip->ili_item.li_bio_list); + clear_bit(XFS_LI_FLUSHING, &iip->ili_item.li_flags); } /* - * This is the inode flushing abort routine. It is called from xfs_iflush when - * the filesystem is shutting down to clean up the inode state. It is - * responsible for removing the inode item from the AIL if it has not been - * re-logged, and unlocking the inode's flush lock. + * Abort flushing the inode from a context holding the cluster buffer locked. + * + * This is the normal runtime method of aborting writeback of an inode that is + * attached to a cluster buffer. It occurs when the inode and the backing + * cluster buffer have been freed (i.e. inode is XFS_ISTALE), or when cluster + * flushing or buffer IO completion encounters a log shutdown situation. + * + * If we need to abort inode writeback and we don't already hold the buffer + * locked, call xfs_iflush_shutdown_abort() instead as this should only ever be + * necessary in a shutdown situation. */ void xfs_iflush_abort( - xfs_inode_t *ip, - bool stale) + struct xfs_inode *ip) { - xfs_inode_log_item_t *iip = ip->i_itemp; - - if (iip) { - struct xfs_ail *ailp = iip->ili_item.li_ailp; - if (iip->ili_item.li_flags & XFS_LI_IN_AIL) { - spin_lock(&ailp->xa_lock); - if (iip->ili_item.li_flags & XFS_LI_IN_AIL) { - /* xfs_trans_ail_delete() drops the AIL lock. */ - xfs_trans_ail_delete(ailp, &iip->ili_item, - stale ? - SHUTDOWN_LOG_IO_ERROR : - SHUTDOWN_CORRUPT_INCORE); - } else - spin_unlock(&ailp->xa_lock); - } - iip->ili_logged = 0; - /* - * Clear the ili_last_fields bits now that we know that the - * data corresponding to them is safely on disk. - */ - iip->ili_last_fields = 0; - /* - * Clear the inode logging fields so no more flushes are - * attempted. - */ - iip->ili_fields = 0; + struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_buf *bp; + + if (!iip) { + /* clean inode, nothing to do */ + xfs_iflags_clear(ip, XFS_IFLUSHING); + return; } + /* - * Release the inode's flush lock since we're done with it. + * Remove the inode item from the AIL before we clear its internal + * state. Whilst the inode is in the AIL, it should have a valid buffer + * pointer for push operations to access - it is only safe to remove the + * inode from the buffer once it has been removed from the AIL. */ - xfs_ifunlock(ip); + xfs_trans_ail_delete(&iip->ili_item, 0); + + /* + * Grab the inode buffer so can we release the reference the inode log + * item holds on it. + */ + spin_lock(&iip->ili_lock); + bp = iip->ili_item.li_buf; + xfs_iflush_abort_clean(iip); + spin_unlock(&iip->ili_lock); + + xfs_iflags_clear(ip, XFS_IFLUSHING); + if (bp) + xfs_buf_rele(bp); } +/* + * Abort an inode flush in the case of a shutdown filesystem. This can be called + * from anywhere with just an inode reference and does not require holding the + * inode cluster buffer locked. If the inode is attached to a cluster buffer, + * it will grab and lock it safely, then abort the inode flush. + */ void -xfs_istale_done( - struct xfs_buf *bp, - struct xfs_log_item *lip) +xfs_iflush_shutdown_abort( + struct xfs_inode *ip) { - xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true); + struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_buf *bp; + + if (!iip) { + /* clean inode, nothing to do */ + xfs_iflags_clear(ip, XFS_IFLUSHING); + return; + } + + spin_lock(&iip->ili_lock); + bp = iip->ili_item.li_buf; + if (!bp) { + spin_unlock(&iip->ili_lock); + xfs_iflush_abort(ip); + return; + } + + /* + * We have to take a reference to the buffer so that it doesn't get + * freed when we drop the ili_lock and then wait to lock the buffer. + * We'll clean up the extra reference after we pick up the ili_lock + * again. + */ + xfs_buf_hold(bp); + spin_unlock(&iip->ili_lock); + xfs_buf_lock(bp); + + spin_lock(&iip->ili_lock); + if (!iip->ili_item.li_buf) { + /* + * Raced with another removal, hold the only reference + * to bp now. Inode should not be in the AIL now, so just clean + * up and return; + */ + ASSERT(list_empty(&iip->ili_item.li_bio_list)); + ASSERT(!test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags)); + xfs_iflush_abort_clean(iip); + spin_unlock(&iip->ili_lock); + xfs_iflags_clear(ip, XFS_IFLUSHING); + xfs_buf_relse(bp); + return; + } + + /* + * Got two references to bp. The first will get dropped by + * xfs_iflush_abort() when the item is removed from the buffer list, but + * we can't drop our reference until _abort() returns because we have to + * unlock the buffer as well. Hence we abort and then unlock and release + * our reference to the buffer. + */ + ASSERT(iip->ili_item.li_buf == bp); + spin_unlock(&iip->ili_lock); + xfs_iflush_abort(ip); + xfs_buf_relse(bp); } + /* - * 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 kvec *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; + struct xfs_inode_log_format_32 *in_f32 = buf->iov_base; + + if (buf->iov_len != sizeof(*in_f32)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + return -EFSCORRUPTED; } - 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; + memcpy(&in_f->ilf_u, &in_f32->ilf_u, sizeof(in_f->ilf_u)); + 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; } |