diff options
Diffstat (limited to 'fs/xfs/xfs_inode_item.c')
| -rw-r--r-- | fs/xfs/xfs_inode_item.c | 690 |
1 files changed, 427 insertions, 263 deletions
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 8bd5d0de6321..ca2941ab6cbc 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -17,17 +17,32 @@ #include "xfs_trans_priv.h" #include "xfs_buf_item.h" #include "xfs_log.h" +#include "xfs_log_priv.h" #include "xfs_error.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); } +/* + * 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, @@ -36,13 +51,13 @@ xfs_inode_item_data_fork_size( { struct xfs_inode *ip = iip->ili_inode; - switch (ip->i_d.di_format) { + 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_nextents > 0 && ip->i_df.if_bytes > 0) { /* worst case, doesn't subtract delalloc extents */ - *nbytes += XFS_IFORK_DSIZE(ip); + *nbytes += xfs_inode_data_fork_size(ip); *nvecs += 1; } break; @@ -56,7 +71,7 @@ xfs_inode_item_data_fork_size( case XFS_DINODE_FMT_LOCAL: if ((iip->ili_fields & XFS_ILOG_DDATA) && ip->i_df.if_bytes > 0) { - *nbytes += roundup(ip->i_df.if_bytes, 4); + *nbytes += xlog_calc_iovec_len(ip->i_df.if_bytes); *nvecs += 1; } break; @@ -77,27 +92,27 @@ xfs_inode_item_attr_fork_size( { struct xfs_inode *ip = iip->ili_inode; - 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) { + ip->i_af.if_nextents > 0 && + ip->i_af.if_bytes > 0) { /* worst case, doesn't subtract unused space */ - *nbytes += XFS_IFORK_ASIZE(ip); + *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) { - *nbytes += ip->i_afp->if_broot_bytes; + 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) { - *nbytes += roundup(ip->i_afp->if_bytes, 4); + ip->i_af.if_bytes > 0) { + *nbytes += xlog_calc_iovec_len(ip->i_af.if_bytes); *nvecs += 1; } break; @@ -125,10 +140,10 @@ xfs_inode_item_size( *nvecs += 2; *nbytes += sizeof(struct xfs_inode_log_format) + - xfs_log_dinode_size(ip->i_d.di_version); + xfs_log_dinode_size(ip->i_mount); xfs_inode_item_data_fork_size(iip, nvecs, nbytes); - if (XFS_IFORK_Q(ip)) + if (xfs_inode_has_attr_fork(ip)) xfs_inode_item_attr_fork_size(iip, nvecs, nbytes); } @@ -142,13 +157,13 @@ xfs_inode_item_format_data_fork( struct xfs_inode *ip = iip->ili_inode; size_t data_bytes; - 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); 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) { struct xfs_bmbt_rec *p; @@ -189,17 +204,12 @@ xfs_inode_item_format_data_fork( ~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | XFS_ILOG_DEV); if ((iip->ili_fields & XFS_ILOG_DDATA) && ip->i_df.if_bytes > 0) { - /* - * 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_u1.if_data != NULL); - ASSERT(ip->i_d.di_size > 0); + ASSERT(ip->i_disk_size > 0); xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL, - ip->i_df.if_u1.if_data, data_bytes); - ilf->ilf_dsize = (unsigned)data_bytes; + ip->i_df.if_u1.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; @@ -227,18 +237,18 @@ xfs_inode_item_format_attr_fork( 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) { + ip->i_af.if_nextents > 0 && + ip->i_af.if_bytes > 0) { struct xfs_bmbt_rec *p; - ASSERT(xfs_iext_count(ip->i_afp) == - ip->i_d.di_anextents); + 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); @@ -255,13 +265,13 @@ xfs_inode_item_format_attr_fork( ~(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); + 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_afp->if_broot, - ip->i_afp->if_broot_bytes); - ilf->ilf_asize = ip->i_afp->if_broot_bytes; + 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; @@ -272,18 +282,12 @@ xfs_inode_item_format_attr_fork( ~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT); if ((iip->ili_fields & XFS_ILOG_ADATA) && - ip->i_afp->if_bytes > 0) { - /* - * 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_u1.if_data != NULL); + ip->i_af.if_bytes > 0) { + ASSERT(ip->i_af.if_u1.if_data != NULL); xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL, - ip->i_afp->if_u1.if_data, - data_bytes); - ilf->ilf_asize = (unsigned)data_bytes; + ip->i_af.if_u1.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; @@ -295,64 +299,123 @@ xfs_inode_item_format_attr_fork( } } +/* + * 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 xfs_icdinode *from = &ip->i_d; 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_version = from->di_version; - 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 & 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)); - to->di_atime.t_sec = inode->i_atime.tv_sec; - to->di_atime.t_nsec = inode->i_atime.tv_nsec; - to->di_mtime.t_sec = inode->i_mtime.tv_sec; - to->di_mtime.t_nsec = inode->i_mtime.tv_nsec; - to->di_ctime.t_sec = inode->i_ctime.tv_sec; - to->di_ctime.t_nsec = inode->i_ctime.tv_nsec; + to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode->i_atime); + to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode->i_mtime); + to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode->i_ctime); to->di_nlink = inode->i_nlink; to->di_gen = inode->i_generation; to->di_mode = inode->i_mode; - to->di_size = from->di_size; - to->di_nblocks = from->di_nblocks; - to->di_extsize = from->di_extsize; - to->di_nextents = from->di_nextents; - to->di_anextents = from->di_anextents; - to->di_forkoff = from->di_forkoff; - to->di_aformat = from->di_aformat; - to->di_dmevmask = from->di_dmevmask; - to->di_dmstate = from->di_dmstate; - to->di_flags = from->di_flags; + 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 (from->di_version == 3) { + if (xfs_has_v3inodes(ip->i_mount)) { + to->di_version = 3; to->di_changecount = inode_peek_iversion(inode); - 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_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime); + to->di_flags2 = ip->i_diflags2; + 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_flushiter = 0; + to->di_v3_pad = 0; } else { - to->di_flushiter = from->di_flushiter; + to->di_version = 2; + to->di_flushiter = ip->i_flushiter; + memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad)); } + + xfs_inode_to_log_dinode_iext_counters(ip, to); } /* @@ -370,7 +433,7 @@ xfs_inode_item_format_core( 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_d.di_version)); + xlog_finish_iovec(lv, *vecp, xfs_log_dinode_size(ip->i_mount)); } /* @@ -395,8 +458,6 @@ xfs_inode_item_format( struct xfs_log_iovec *vecp = NULL; struct xfs_inode_log_format *ilf; - ASSERT(ip->i_d.di_version > 1); - ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT); ilf->ilf_type = XFS_LI_INODE; ilf->ilf_ino = ip->i_ino; @@ -419,7 +480,7 @@ xfs_inode_item_format( xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); - if (XFS_IFORK_Q(ip)) { + if (xfs_inode_has_attr_fork(ip)) { xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp); } else { iip->ili_fields &= @@ -441,6 +502,7 @@ xfs_inode_item_pin( struct xfs_inode *ip = INODE_ITEM(lip)->ili_inode; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(lip->li_buf); trace_xfs_inode_pin(ip, _RET_IP_); atomic_inc(&ip->i_pincount); @@ -452,6 +514,12 @@ 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( @@ -461,28 +529,12 @@ xfs_inode_item_unpin( struct xfs_inode *ip = INODE_ITEM(lip)->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)) wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } -/* - * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer - * have been failed during writeback - * - * This informs the AIL that the inode is already flush locked on the next push, - * and acquires a hold on the buffer to ensure that it isn't reclaimed before - * dirty data makes it to disk. - */ -STATIC void -xfs_inode_item_error( - struct xfs_log_item *lip, - struct xfs_buf *bp) -{ - ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode)); - xfs_set_li_failed(lip, bp); -} - STATIC uint xfs_inode_item_push( struct xfs_log_item *lip, @@ -496,69 +548,50 @@ xfs_inode_item_push( 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. + */ return XFS_ITEM_PINNED; + } - /* - * The buffer containing this item failed to be written back - * previously. Resubmit the buffer for IO. - */ - if (test_bit(XFS_LI_FAILED, &lip->li_flags)) { - if (!xfs_buf_trylock(bp)) - return XFS_ITEM_LOCKED; - - if (!xfs_buf_resubmit_failed_buffers(bp, buffer_list)) - rval = XFS_ITEM_FLUSHING; + if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) + return XFS_ITEM_PINNED; - xfs_buf_unlock(bp); - return rval; - } + if (xfs_iflags_test(ip, XFS_IFLUSHING)) + return XFS_ITEM_FLUSHING; - if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) + if (!xfs_buf_trylock(bp)) 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; - } + spin_unlock(&lip->li_ailp->ail_lock); /* - * 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. + * 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. */ - if (!xfs_iflock_nowait(ip)) { - rval = XFS_ITEM_FLUSHING; - goto out_unlock; - } - - ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); - ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); - - spin_unlock(&lip->li_ailp->ail_lock); - - error = xfs_iflush(ip, &bp); + 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->ail_lock); -out_unlock: - xfs_iunlock(ip, XFS_ILOCK_SHARED); return rval; } @@ -622,9 +655,9 @@ xfs_inode_item_committed( STATIC void xfs_inode_item_committing( struct xfs_log_item *lip, - xfs_lsn_t commit_lsn) + xfs_csn_t seq) { - INODE_ITEM(lip)->ili_last_lsn = commit_lsn; + INODE_ITEM(lip)->ili_commit_seq = seq; return xfs_inode_item_release(lip); } @@ -637,7 +670,6 @@ static const struct xfs_item_ops xfs_inode_item_ops = { .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, .iop_committing = xfs_inode_item_committing, - .iop_error = xfs_inode_item_error }; @@ -652,9 +684,11 @@ 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, 0); + 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); } @@ -664,160 +698,290 @@ xfs_inode_item_init( */ void xfs_inode_item_destroy( - xfs_inode_t *ip) + struct xfs_inode *ip) { - kmem_free(ip->i_itemp->ili_item.li_lv_shadow); - kmem_cache_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; + kmem_free(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, *n; - struct xfs_ail *ailp = lip->li_ailp; - int need_ail = 0; - LIST_HEAD(tmp); + 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. - */ + /* 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; - list_add_tail(&lip->li_bio_list, &tmp); + clear_bit(XFS_LI_FAILED, &lip->li_flags); + if (INODE_ITEM(lip)->ili_flush_lsn != lip->li_lsn) + continue; - list_for_each_entry_safe(blip, n, &bp->b_li_list, li_bio_list) { - if (lip->li_cb != xfs_iflush_done) + /* + * 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; + } + + 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); - list_move_tail(&blip->li_bio_list, &tmp); /* - * 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) || - test_bit(XFS_LI_FAILED, &blip->li_flags)) - need_ail++; + 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; + 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) || - test_bit(XFS_LI_FAILED, &lip->li_flags)) - 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) { - bool mlip_changed = false; - - /* this is an opencoded batch version of xfs_trans_ail_delete */ - spin_lock(&ailp->ail_lock); - list_for_each_entry(blip, &tmp, li_bio_list) { - if (INODE_ITEM(blip)->ili_logged && - blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) - mlip_changed |= xfs_ail_delete_one(ailp, blip); - else { - xfs_clear_li_failed(blip); - } - } + list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { + struct xfs_inode_log_item *iip = INODE_ITEM(lip); - if (mlip_changed) { - if (!XFS_FORCED_SHUTDOWN(ailp->ail_mount)) - xlog_assign_tail_lsn_locked(ailp->ail_mount); - if (list_empty(&ailp->ail_head)) - wake_up_all(&ailp->ail_empty); + if (xfs_iflags_test(iip->ili_inode, XFS_ISTALE)) { + xfs_iflush_abort(iip->ili_inode); + continue; } - spin_unlock(&ailp->ail_lock); + if (!iip->ili_last_fields) + continue; - if (mlip_changed) - xfs_log_space_wake(ailp->ail_mount); + /* 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); } - /* - * 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. - */ - list_for_each_entry_safe(blip, n, &tmp, li_bio_list) { - list_del_init(&blip->li_bio_list); - iip = INODE_ITEM(blip); - iip->ili_logged = 0; - iip->ili_last_fields = 0; - xfs_ifunlock(iip->ili_inode); + if (!list_empty(&ail_updates)) { + xfs_iflush_ail_updates(bp->b_mount->m_ail, &ail_updates); + list_splice_tail(&ail_updates, &flushed_inodes); } - list_del(&tmp); + + xfs_iflush_finish(bp, &flushed_inodes); + if (!list_empty(&flushed_inodes)) + list_splice_tail(&flushed_inodes, &bp->b_li_list); +} + +void +xfs_buf_inode_io_fail( + struct xfs_buf *bp) +{ + struct xfs_log_item *lip; + + list_for_each_entry(lip, &bp->b_li_list, li_bio_list) + set_bit(XFS_LI_FAILED, &lip->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. + * 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_fsync_fields = 0; + iip->ili_flush_lsn = 0; + iip->ili_item.li_buf = NULL; + list_del_init(&iip->ili_item.li_bio_list); +} + +/* + * 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; + struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_buf *bp; - if (iip) { - if (test_bit(XFS_LI_IN_AIL, &iip->ili_item.li_flags)) { - xfs_trans_ail_remove(&iip->ili_item, - stale ? SHUTDOWN_LOG_IO_ERROR : - SHUTDOWN_CORRUPT_INCORE); - } - 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; - iip->ili_fsync_fields = 0; + 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. + * + * We also clear the failed bit before removing the item from the AIL + * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer + * references the inode item owns and needs to hold until we've fully + * aborted the inode log item and detached it from the buffer. */ - xfs_ifunlock(ip); + clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags); + 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 the old 32 bit version * (which can have different field alignments) to the native 64 bit version |