diff options
Diffstat (limited to 'fs/xfs')
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_acl.c | 3 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_aops.c | 118 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_ioctl.c | 2 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_iops.c | 6 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_super.c | 65 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_sync.c | 285 | ||||
| -rw-r--r-- | fs/xfs/linux-2.6/xfs_sync.h | 8 | ||||
| -rw-r--r-- | fs/xfs/quota/xfs_qm_bhv.c | 2 | ||||
| -rw-r--r-- | fs/xfs/quota/xfs_qm_syscalls.c | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_ag.h | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_alloc.c | 52 | ||||
| -rw-r--r-- | fs/xfs/xfs_dfrag.c | 111 | ||||
| -rw-r--r-- | fs/xfs/xfs_fsops.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_iget.c | 31 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode.c | 17 | ||||
| -rw-r--r-- | fs/xfs/xfs_iomap.c | 9 | ||||
| -rw-r--r-- | fs/xfs/xfs_log_recover.c | 24 | ||||
| -rw-r--r-- | fs/xfs/xfs_mount.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_mount.h | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_rw.h | 7 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.c | 7 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.h | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_vnodeops.c | 179 | ||||
| -rw-r--r-- | fs/xfs/xfs_vnodeops.h | 1 |
24 files changed, 582 insertions, 357 deletions
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index b23a54506446..4c7b14503716 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -250,8 +250,9 @@ xfs_set_mode(struct inode *inode, mode_t mode) if (mode != inode->i_mode) { struct iattr iattr; - iattr.ia_valid = ATTR_MODE; + iattr.ia_valid = ATTR_MODE | ATTR_CTIME; iattr.ia_mode = mode; + iattr.ia_ctime = current_fs_time(inode->i_sb); error = -xfs_setattr(XFS_I(inode), &iattr, XFS_ATTR_NOACL); } diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index c2e30eea74dc..7263002fac64 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -204,14 +204,17 @@ xfs_ioend_new_eof( } /* - * Update on-disk file size now that data has been written to disk. - * The current in-memory file size is i_size. If a write is beyond - * eof i_new_size will be the intended file size until i_size is - * updated. If this write does not extend all the way to the valid - * file size then restrict this update to the end of the write. + * Update on-disk file size now that data has been written to disk. The + * current in-memory file size is i_size. If a write is beyond eof i_new_size + * will be the intended file size until i_size is updated. If this write does + * not extend all the way to the valid file size then restrict this update to + * the end of the write. + * + * This function does not block as blocking on the inode lock in IO completion + * can lead to IO completion order dependency deadlocks.. If it can't get the + * inode ilock it will return EAGAIN. Callers must handle this. */ - -STATIC void +STATIC int xfs_setfilesize( xfs_ioend_t *ioend) { @@ -222,9 +225,11 @@ xfs_setfilesize( ASSERT(ioend->io_type != IOMAP_READ); if (unlikely(ioend->io_error)) - return; + return 0; + + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) + return EAGAIN; - xfs_ilock(ip, XFS_ILOCK_EXCL); isize = xfs_ioend_new_eof(ioend); if (isize) { ip->i_d.di_size = isize; @@ -232,6 +237,28 @@ xfs_setfilesize( } xfs_iunlock(ip, XFS_ILOCK_EXCL); + return 0; +} + +/* + * Schedule IO completion handling on a xfsdatad if this was + * the final hold on this ioend. If we are asked to wait, + * flush the workqueue. + */ +STATIC void +xfs_finish_ioend( + xfs_ioend_t *ioend, + int wait) +{ + if (atomic_dec_and_test(&ioend->io_remaining)) { + struct workqueue_struct *wq; + + wq = (ioend->io_type == IOMAP_UNWRITTEN) ? + xfsconvertd_workqueue : xfsdatad_workqueue; + queue_work(wq, &ioend->io_work); + if (wait) + flush_workqueue(wq); + } } /* @@ -243,9 +270,23 @@ xfs_end_bio_delalloc( { xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work); + int error; - xfs_setfilesize(ioend); - xfs_destroy_ioend(ioend); + /* + * If we didn't complete processing of the ioend, requeue it to the + * tail of the workqueue for another attempt later. Otherwise destroy + * it. + */ + error = xfs_setfilesize(ioend); + if (error == EAGAIN) { + atomic_inc(&ioend->io_remaining); + xfs_finish_ioend(ioend, 0); + /* ensure we don't spin on blocked ioends */ + delay(1); + } else { + ASSERT(!error); + xfs_destroy_ioend(ioend); + } } /* @@ -257,9 +298,23 @@ xfs_end_bio_written( { xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work); + int error; - xfs_setfilesize(ioend); - xfs_destroy_ioend(ioend); + /* + * If we didn't complete processing of the ioend, requeue it to the + * tail of the workqueue for another attempt later. Otherwise destroy + * it. + */ + error = xfs_setfilesize(ioend); + if (error == EAGAIN) { + atomic_inc(&ioend->io_remaining); + xfs_finish_ioend(ioend, 0); + /* ensure we don't spin on blocked ioends */ + delay(1); + } else { + ASSERT(!error); + xfs_destroy_ioend(ioend); + } } /* @@ -279,13 +334,25 @@ xfs_end_bio_unwritten( size_t size = ioend->io_size; if (likely(!ioend->io_error)) { + int error; if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { - int error; error = xfs_iomap_write_unwritten(ip, offset, size); if (error) ioend->io_error = error; } - xfs_setfilesize(ioend); + /* + * If we didn't complete processing of the ioend, requeue it to the + * tail of the workqueue for another attempt later. Otherwise destroy + * it. + */ + error = xfs_setfilesize(ioend); + if (error == EAGAIN) { + atomic_inc(&ioend->io_remaining); + xfs_finish_ioend(ioend, 0); + /* ensure we don't spin on blocked ioends */ + delay(1); + return; + } } xfs_destroy_ioend(ioend); } @@ -304,27 +371,6 @@ xfs_end_bio_read( } /* - * Schedule IO completion handling on a xfsdatad if this was - * the final hold on this ioend. If we are asked to wait, - * flush the workqueue. - */ -STATIC void -xfs_finish_ioend( - xfs_ioend_t *ioend, - int wait) -{ - if (atomic_dec_and_test(&ioend->io_remaining)) { - struct workqueue_struct *wq = xfsdatad_workqueue; - if (ioend->io_work.func == xfs_end_bio_unwritten) - wq = xfsconvertd_workqueue; - - queue_work(wq, &ioend->io_work); - if (wait) - flush_workqueue(wq); - } -} - -/* * Allocate and initialise an IO completion structure. * We need to track unwritten extent write completion here initially. * We'll need to extend this for updating the ondisk inode size later diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index 5bb523d7f37e..98fe0db674bc 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -789,6 +789,8 @@ xfs_ioc_fsgetxattr( { struct fsxattr fa; + memset(&fa, 0, sizeof(struct fsxattr)); + xfs_ilock(ip, XFS_ILOCK_SHARED); fa.fsx_xflags = xfs_ip2xflags(ip); fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index cd42ef78f6b5..1f3b4b8f7dd4 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -573,8 +573,8 @@ xfs_vn_fallocate( bf.l_len = len; xfs_ilock(ip, XFS_IOLOCK_EXCL); - error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf, - 0, XFS_ATTR_NOLOCK); + error = -xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf, + 0, XFS_ATTR_NOLOCK); if (!error && !(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) new_size = offset + len; @@ -585,7 +585,7 @@ xfs_vn_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK); + error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK); } xfs_iunlock(ip, XFS_IOLOCK_EXCL); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 18a4b8e11df2..d95bfa27c62a 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -930,13 +930,37 @@ xfs_fs_alloc_inode( */ STATIC void xfs_fs_destroy_inode( - struct inode *inode) + struct inode *inode) { - xfs_inode_t *ip = XFS_I(inode); + struct xfs_inode *ip = XFS_I(inode); + + xfs_itrace_entry(ip); XFS_STATS_INC(vn_reclaim); - if (xfs_reclaim(ip)) - panic("%s: cannot reclaim 0x%p\n", __func__, inode); + + /* bad inode, get out here ASAP */ + if (is_bad_inode(inode)) + goto out_reclaim; + + xfs_ioend_wait(ip); + + ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0); + + /* + * We should never get here with one of the reclaim flags already set. + */ + ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE)); + ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM)); + + /* + * We always use background reclaim here because even if the + * inode is clean, it still may be under IO and hence we have + * to take the flush lock. The background reclaim path handles + * this more efficiently than we can here, so simply let background + * reclaim tear down all inodes. + */ +out_reclaim: + xfs_inode_set_reclaim_tag(ip); } /* @@ -1140,6 +1164,7 @@ xfs_fs_put_super( xfs_unmountfs(mp); xfs_freesb(mp); + xfs_inode_shrinker_unregister(mp); xfs_icsb_destroy_counters(mp); xfs_close_devices(mp); xfs_dmops_put(mp); @@ -1299,6 +1324,8 @@ xfs_fs_remount( /* ro -> rw */ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { + __uint64_t resblks; + mp->m_flags &= ~XFS_MOUNT_RDONLY; if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_mountfs_check_barriers(mp); @@ -1316,11 +1343,37 @@ xfs_fs_remount( } mp->m_update_flags = 0; } + + /* + * Fill out the reserve pool if it is empty. Use the stashed + * value if it is non-zero, otherwise go with the default. + */ + if (mp->m_resblks_save) { + resblks = mp->m_resblks_save; + mp->m_resblks_save = 0; + } else { + resblks = mp->m_sb.sb_dblocks; + do_div(resblks, 20); + resblks = min_t(__uint64_t, resblks, 1024); + } + xfs_reserve_blocks(mp, &resblks, NULL); } /* rw -> ro */ if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) { + /* + * After we have synced the data but before we sync the + * metadata, we need to free up the reserve block pool so that + * the used block count in the superblock on disk is correct at + * the end of the remount. Stash the current reserve pool size + * so that if we get remounted rw, we can return it to the same + * size. + */ + __uint64_t resblks = 0; + xfs_quiesce_data(mp); + mp->m_resblks_save = mp->m_resblks; + xfs_reserve_blocks(mp, &resblks, NULL); xfs_quiesce_attr(mp); mp->m_flags |= XFS_MOUNT_RDONLY; } @@ -1503,6 +1556,8 @@ xfs_fs_fill_super( if (error) goto fail_vnrele; + xfs_inode_shrinker_register(mp); + kfree(mtpt); xfs_itrace_exit(XFS_I(sb->s_root->d_inode)); @@ -1842,6 +1897,7 @@ init_xfs_fs(void) goto out_cleanup_procfs; vfs_initquota(); + xfs_inode_shrinker_init(); error = register_filesystem(&xfs_fs_type); if (error) @@ -1871,6 +1927,7 @@ exit_xfs_fs(void) { vfs_exitquota(); unregister_filesystem(&xfs_fs_type); + xfs_inode_shrinker_destroy(); xfs_sysctl_unregister(); xfs_cleanup_procfs(); xfs_buf_terminate(); diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 961df0a22c78..c82683ad1484 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -64,7 +64,6 @@ xfs_inode_ag_lookup( * as the tree is sparse and a gang lookup walks to find * the number of objects requested. */ - read_lock(&pag->pag_ici_lock); if (tag == XFS_ICI_NO_TAG) { nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void **)&ip, *first_index, 1); @@ -73,7 +72,7 @@ xfs_inode_ag_lookup( (void **)&ip, *first_index, 1, tag); } if (!nr_found) - goto unlock; + return NULL; /* * Update the index for the next lookup. Catch overflows @@ -83,13 +82,8 @@ xfs_inode_ag_lookup( */ *first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1); if (*first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) - goto unlock; - + return NULL; return ip; - -unlock: - read_unlock(&pag->pag_ici_lock); - return NULL; } STATIC int @@ -99,7 +93,9 @@ xfs_inode_ag_walk( int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), int flags, - int tag) + int tag, + int exclusive, + int *nr_to_scan) { struct xfs_perag *pag = &mp->m_perag[ag]; uint32_t first_index; @@ -113,10 +109,20 @@ restart: int error = 0; xfs_inode_t *ip; + if (exclusive) + write_lock(&pag->pag_ici_lock); + else + read_lock(&pag->pag_ici_lock); ip = xfs_inode_ag_lookup(mp, pag, &first_index, tag); - if (!ip) + if (!ip) { + if (exclusive) + write_unlock(&pag->pag_ici_lock); + else + read_unlock(&pag->pag_ici_lock); break; + } + /* execute releases pag->pag_ici_lock */ error = execute(ip, pag, flags); if (error == EAGAIN) { skipped++; @@ -124,13 +130,12 @@ restart: } if (error) last_error = error; - /* - * bail out if the filesystem is corrupted. - */ + + /* bail out if the filesystem is corrupted. */ if (error == EFSCORRUPTED) break; - } while (1); + } while ((*nr_to_scan)--); if (skipped) { delay(1); @@ -147,22 +152,31 @@ xfs_inode_ag_iterator( int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), int flags, - int tag) + int tag, + int exclusive, + int *nr_to_scan) { int error = 0; int last_error = 0; xfs_agnumber_t ag; + int nr; + nr = nr_to_scan ? *nr_to_scan : INT_MAX; for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) { if (!mp->m_perag[ag].pag_ici_init) continue; - error = xfs_inode_ag_walk(mp, ag, execute, flags, tag); + error = xfs_inode_ag_walk(mp, ag, execute, flags, tag, + exclusive, &nr); if (error) { last_error = error; if (error == EFSCORRUPTED) break; } + if (nr <= 0) + break; } + if (nr_to_scan) + *nr_to_scan = nr; return XFS_ERROR(last_error); } @@ -173,30 +187,31 @@ xfs_sync_inode_valid( struct xfs_perag *pag) { struct inode *inode = VFS_I(ip); + int error = EFSCORRUPTED; /* nothing to sync during shutdown */ - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { - read_unlock(&pag->pag_ici_lock); - return EFSCORRUPTED; - } + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + goto out_unlock; - /* - * If we can't get a reference on the inode, it must be in reclaim. - * Leave it for the reclaim code to flush. Also avoid inodes that - * haven't been fully initialised. - */ - if (!igrab(inode)) { - read_unlock(&pag->pag_ici_lock); - return ENOENT; - } - read_unlock(&pag->pag_ici_lock); + /* avoid new or reclaimable inodes. Leave for reclaim code to flush */ + error = ENOENT; + if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM)) + goto out_unlock; - if (is_bad_inode(inode) || xfs_iflags_test(ip, XFS_INEW)) { + /* If we can't grab the inode, it must on it's way to reclaim. */ + if (!igrab(inode)) + goto out_unlock; + + if (is_bad_inode(inode)) { IRELE(ip); - return ENOENT; + goto out_unlock; } - return 0; + /* inode is valid */ + error = 0; +out_unlock: + read_unlock(&pag->pag_ici_lock); + return error; } STATIC int @@ -281,7 +296,7 @@ xfs_sync_data( ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0); error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags, - XFS_ICI_NO_TAG); + XFS_ICI_NO_TAG, 0, NULL); if (error) return XFS_ERROR(error); @@ -303,7 +318,7 @@ xfs_sync_attr( ASSERT((flags & ~SYNC_WAIT) == 0); return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags, - XFS_ICI_NO_TAG); + XFS_ICI_NO_TAG, 0, NULL); } STATIC int @@ -663,35 +678,71 @@ xfs_syncd_stop( kthread_stop(mp->m_sync_task); } -int -xfs_reclaim_inode( - xfs_inode_t *ip, - int locked, - int sync_mode) +void +__xfs_inode_set_reclaim_tag( + struct xfs_perag *pag, + struct xfs_inode *ip) { - xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino); + radix_tree_tag_set(&pag->pag_ici_root, + XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), + XFS_ICI_RECLAIM_TAG); + pag->pag_ici_reclaimable++; +} + +/* + * We set the inode flag atomically with the radix tree tag. + * Once we get tag lookups on the radix tree, this inode flag + * can go away. + */ +void +xfs_inode_set_reclaim_tag( + xfs_inode_t *ip) +{ + xfs_mount_t *mp = ip->i_mount; + xfs_perag_t *pag = xfs_get_perag(mp, ip->i_ino); - /* The hash lock here protects a thread in xfs_iget_core from - * racing with us on linking the inode back with a vnode. - * Once we have the XFS_IRECLAIM flag set it will not touch - * us. - */ write_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); - if (__xfs_iflags_test(ip, XFS_IRECLAIM) || - !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) { + __xfs_inode_set_reclaim_tag(pag, ip); + __xfs_iflags_set(ip, XFS_IRECLAIMABLE); + spin_unlock(&ip->i_flags_lock); + write_unlock(&pag->pag_ici_lock); + xfs_put_perag(mp, pag); +} + +void +__xfs_inode_clear_reclaim_tag( + xfs_mount_t *mp, + xfs_perag_t *pag, + xfs_inode_t *ip) +{ + radix_tree_tag_clear(&pag->pag_ici_root, + XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); + pag->pag_ici_reclaimable--; +} + +STATIC int +xfs_reclaim_inode( + struct xfs_inode *ip, + struct xfs_perag *pag, + int sync_mode) +{ + /* + * The radix tree lock here protects a thread in xfs_iget from racing + * with us starting reclaim on the inode. Once we have the + * XFS_IRECLAIM flag set it will not touch us. + */ + spin_lock(&ip->i_flags_lock); + ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE)); + if (__xfs_iflags_test(ip, XFS_IRECLAIM)) { + /* ignore as it is already under reclaim */ spin_unlock(&ip->i_flags_lock); write_unlock(&pag->pag_ici_lock); - if (locked) { - xfs_ifunlock(ip); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - } - return -EAGAIN; + return 0; } __xfs_iflags_set(ip, XFS_IRECLAIM); spin_unlock(&ip->i_flags_lock); write_unlock(&pag->pag_ici_lock); - xfs_put_perag(ip->i_mount, pag); /* * If the inode is still dirty, then flush it out. If the inode @@ -704,10 +755,8 @@ xfs_reclaim_inode( * We get the flush lock regardless, though, just to make sure * we don't free it while it is being flushed. */ - if (!locked) { - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_iflock(ip); - } + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_iflock(ip); /* * In the case of a forced shutdown we rely on xfs_iflush() to @@ -724,68 +773,94 @@ xfs_reclaim_inode( return 0; } -void -__xfs_inode_set_reclaim_tag( - struct xfs_perag *pag, - struct xfs_inode *ip) +int +xfs_reclaim_inodes( + xfs_mount_t *mp, + int mode) { - radix_tree_tag_set(&pag->pag_ici_root, - XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), - XFS_ICI_RECLAIM_TAG); + return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode, + XFS_ICI_RECLAIM_TAG, 1, NULL); } /* - * We set the inode flag atomically with the radix tree tag. - * Once we get tag lookups on the radix tree, this inode flag - * can go away. + * Shrinker infrastructure. + * + * This is all far more complex than it needs to be. It adds a global list of + * mounts because the shrinkers can only call a global context. We need to make + * the shrinkers pass a context to avoid the need for global state. */ -void -xfs_inode_set_reclaim_tag( - xfs_inode_t *ip) +static LIST_HEAD(xfs_mount_list); +static struct rw_semaphore xfs_mount_list_lock; + +static int +xfs_reclaim_inode_shrink( + int nr_to_scan, + gfp_t gfp_mask) { - xfs_mount_t *mp = ip->i_mount; - xfs_perag_t *pag = xfs_get_perag(mp, ip->i_ino); + struct xfs_mount *mp; + xfs_agnumber_t ag; + int reclaimable = 0; + + if (nr_to_scan) { + if (!(gfp_mask & __GFP_FS)) + return -1; + + down_read(&xfs_mount_list_lock); + list_for_each_entry(mp, &xfs_mount_list, m_mplist) { + xfs_inode_ag_iterator(mp, xfs_reclaim_inode, 0, + XFS_ICI_RECLAIM_TAG, 1, &nr_to_scan); + if (nr_to_scan <= 0) + break; + } + up_read(&xfs_mount_list_lock); + } - read_lock(&pag->pag_ici_lock); - spin_lock(&ip->i_flags_lock); - __xfs_inode_set_reclaim_tag(pag, ip); - __xfs_iflags_set(ip, XFS_IRECLAIMABLE); - spin_unlock(&ip->i_flags_lock); - read_unlock(&pag->pag_ici_lock); - xfs_put_perag(mp, pag); + down_read(&xfs_mount_list_lock); + list_for_each_entry(mp, &xfs_mount_list, m_mplist) { + for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) { + + if (!mp->m_perag[ag].pag_ici_init) + continue; + reclaimable += mp->m_perag[ag].pag_ici_reclaimable; + } + } + up_read(&xfs_mount_list_lock); + return reclaimable; } -void -__xfs_inode_clear_reclaim_tag( - xfs_mount_t *mp, - xfs_perag_t *pag, - xfs_inode_t *ip) +static struct shrinker xfs_inode_shrinker = { + .shrink = xfs_reclaim_inode_shrink, + .seeks = DEFAULT_SEEKS, +}; + +void __init +xfs_inode_shrinker_init(void) { - radix_tree_tag_clear(&pag->pag_ici_root, - XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); + init_rwsem(&xfs_mount_list_lock); + register_shrinker(&xfs_inode_shrinker); } -STATIC int -xfs_reclaim_inode_now( - struct xfs_inode *ip, - struct xfs_perag *pag, - int flags) +void +xfs_inode_shrinker_destroy(void) { - /* ignore if already under reclaim */ - if (xfs_iflags_test(ip, XFS_IRECLAIM)) { - read_unlock(&pag->pag_ici_lock); - return 0; - } - read_unlock(&pag->pag_ici_lock); + ASSERT(list_empty(&xfs_mount_list)); + unregister_shrinker(&xfs_inode_shrinker); +} - return xfs_reclaim_inode(ip, 0, flags); +void +xfs_inode_shrinker_register( + struct xfs_mount *mp) +{ + down_write(&xfs_mount_list_lock); + list_add_tail(&mp->m_mplist, &xfs_mount_list); + up_write(&xfs_mount_list_lock); } -int -xfs_reclaim_inodes( - xfs_mount_t *mp, - int mode) +void +xfs_inode_shrinker_unregister( + struct xfs_mount *mp) { - return xfs_inode_ag_iterator(mp, xfs_reclaim_inode_now, mode, - XFS_ICI_RECLAIM_TAG); + down_write(&xfs_mount_list_lock); + list_del(&mp->m_mplist); + up_write(&xfs_mount_list_lock); } diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index 27920eb7a820..0b28c13bdf94 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -44,7 +44,6 @@ void xfs_quiesce_attr(struct xfs_mount *mp); void xfs_flush_inodes(struct xfs_inode *ip); -int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode); int xfs_reclaim_inodes(struct xfs_mount *mp, int mode); void xfs_inode_set_reclaim_tag(struct xfs_inode *ip); @@ -55,6 +54,11 @@ void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag, int xfs_sync_inode_valid(struct xfs_inode *ip, struct xfs_perag *pag); int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags), - int flags, int tag); + int flags, int tag, int write_lock, int *nr_to_scan); + +void xfs_inode_shrinker_init(void); +void xfs_inode_shrinker_destroy(void); +void xfs_inode_shrinker_register(struct xfs_mount *mp); +void xfs_inode_shrinker_unregister(struct xfs_mount *mp); #endif diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c index a5346630dfae..97b410c12794 100644 --- a/fs/xfs/quota/xfs_qm_bhv.c +++ b/fs/xfs/quota/xfs_qm_bhv.c @@ -59,7 +59,7 @@ xfs_fill_statvfs_from_dquot( be64_to_cpu(dp->d_blk_hardlimit); if (limit && statp->f_blocks > limit) { statp->f_blocks = limit; - statp->f_bfree = + statp->f_bfree = statp->f_bavail = (statp->f_blocks > be64_to_cpu(dp->d_bcount)) ? (statp->f_blocks - be64_to_cpu(dp->d_bcount)) : 0; } diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c index 5d1a3b98a6e6..60fe35821cff 100644 --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -893,7 +893,8 @@ xfs_qm_dqrele_all_inodes( uint flags) { ASSERT(mp->m_quotainfo); - xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, XFS_ICI_NO_TAG); + xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, + XFS_ICI_NO_TAG, 0, NULL); } /*------------------------------------------------------------------------*/ diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h index a5d54bf4931b..381fba77b28d 100644 --- a/fs/xfs/xfs_ag.h +++ b/fs/xfs/xfs_ag.h @@ -215,6 +215,7 @@ typedef struct xfs_perag int pag_ici_init; /* incore inode cache initialised */ rwlock_t pag_ici_lock; /* incore inode lock */ struct radix_tree_root pag_ici_root; /* incore inode cache root */ + int pag_ici_reclaimable; /* reclaimable inodes */ #endif } xfs_perag_t; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 2cf944eb796d..4cd1c23b77f0 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -2703,45 +2703,35 @@ xfs_alloc_search_busy(xfs_trans_t *tp, xfs_mount_t *mp; xfs_perag_busy_t *bsy; xfs_agblock_t uend, bend; - xfs_lsn_t lsn; + xfs_lsn_t lsn = 0; int cnt; mp = tp->t_mountp; spin_lock(&mp->m_perag[agno].pagb_lock); - cnt = mp->m_perag[agno].pagb_count; - uend = bno + len - 1; - /* search pagb_list for this slot, skipping open slots */ - for (bsy = mp->m_perag[agno].pagb_list; cnt; bsy++) { - - /* - * (start1,length1) within (start2, length2) - */ - if (bsy->busy_tp != NULL) { - bend = bsy->busy_start + bsy->busy_length - 1; - if ((bno > bend) || (uend < bsy->busy_start)) { - cnt--; - } else { - TRACE_BUSYSEARCH("xfs_alloc_search_busy", - "found1", agno, bno, len, tp); - break; - } - } - } - /* - * If a block was found, force the log through the LSN of the - * transaction that freed the block + * search pagb_list for this slot, skipping open slots. We have to + * search the entire array as there may be multiple overlaps and + * we have to get the most recent LSN for the log force to push out + * all the transactions that span the range. */ - if (cnt) { - TRACE_BUSYSEARCH("xfs_alloc_search_busy", "found", agno, bno, len, tp); - lsn = bsy->busy_tp->t_commit_lsn; - spin_unlock(&mp->m_perag[agno].pagb_lock); - xfs_log_force(mp, lsn, XFS_LOG_FORCE|XFS_LOG_SYNC); - } else { - TRACE_BUSYSEARCH("xfs_alloc_search_busy", "not-found", agno, bno, len, tp); - spin_unlock(&mp->m_perag[agno].pagb_lock); + for (cnt = 0; cnt < mp->m_perag[agno].pagb_count; cnt++) { + bsy = &mp->m_perag[agno].pagb_list[cnt]; + if (!bsy->busy_tp) + continue; + bend = bsy->busy_start + bsy->busy_length - 1; + if (bno > bend || uend < bsy->busy_start) + continue; + + /* (start1,length1) within (start2, length2) */ + if (XFS_LSN_CMP(bsy->busy_tp->t_commit_lsn, lsn) > 0) + lsn = bsy->busy_tp->t_commit_lsn; } + spin_unlock(&mp->m_perag[agno].pagb_lock); + TRACE_BUSYSEARCH("xfs_alloc_search_busy", lsn ? "found" : "not-found", + agno, bno, len, tp); + if (lsn) + xfs_log_force(mp, lsn, XFS_LOG_FORCE|XFS_LOG_SYNC); } diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index ab89a7e94a0f..e4ccd9f24829 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -62,7 +62,9 @@ xfs_swapext( goto out; } - if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) { + if (!(file->f_mode & FMODE_WRITE) || + !(file->f_mode & FMODE_READ) || + (file->f_flags & O_APPEND)) { error = XFS_ERROR(EBADF); goto out_put_file; } @@ -74,6 +76,7 @@ xfs_swapext( } if (!(target_file->f_mode & FMODE_WRITE) || + !(target_file->f_mode & FMODE_READ) || (target_file->f_flags & O_APPEND)) { error = XFS_ERROR(EBADF); goto out_put_target_file; @@ -113,10 +116,82 @@ xfs_swapext( return error; } +/* + * We need to check that the format of the data fork in the temporary inode is + * valid for the target inode before doing the swap. This is not a problem with + * attr1 because of the fixed fork offset, but attr2 has a dynamically sized + * data fork depending on the space the attribute fork is taking so we can get + * invalid formats on the target inode. + * + * E.g. target has space for 7 extents in extent format, temp inode only has + * space for 6. If we defragment down to 7 extents, then the tmp format is a + * btree, but when swapped it needs to be in extent format. Hence we can't just + * blindly swap data forks on attr2 filesystems. + * + * Note that we check the swap in both directions so that we don't end up with + * a corrupt temporary inode, either. + * + * Note that fixing the way xfs_fsr sets up the attribute fork in the source + * inode will prevent this situation from occurring, so all we do here is + * reject and log the attempt. basically we are putting the responsibility on + * userspace to get this right. + */ +static int +xfs_swap_extents_check_format( + xfs_inode_t *ip, /* target inode */ + xfs_inode_t *tip) /* tmp inode */ +{ + + /* Should never get a local format */ + if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL || + tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) + return EINVAL; + + /* + * if the target inode has less extents that then temporary inode then + * why did userspace call us? + */ + if (ip->i_d.di_nextents < tip->i_d.di_nextents) + return EINVAL; + + /* + * if the target inode is in extent form and the temp inode is in btree + * form then we will end up with the target inode in the wrong format + * as we already know there are less extents in the temp inode. + */ + if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && + tip->i_d.di_format == XFS_DINODE_FMT_BTREE) + return EINVAL; + + /* Check temp in extent form to max in target */ + if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > ip->i_df.if_ext_max) + return EINVAL; + + /* Check target in extent form to max in temp */ + if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && + XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > tip->i_df.if_ext_max) + return EINVAL; + + /* Check root block of temp in btree form to max in target */ + if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE && + XFS_IFORK_BOFF(ip) && + tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip)) + return EINVAL; + + /* Check root block of target in btree form to max in temp */ + if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE && + XFS_IFORK_BOFF(tip) && + ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip)) + return EINVAL; + + return 0; +} + int xfs_swap_extents( - xfs_inode_t *ip, - xfs_inode_t *tip, + xfs_inode_t *ip, /* target inode */ + xfs_inode_t *tip, /* tmp inode */ xfs_swapext_t *sxp) { xfs_mount_t *mp; @@ -160,13 +235,6 @@ xfs_swap_extents( goto out_unlock; } - /* Should never get a local format */ - if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL || - tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) { - error = XFS_ERROR(EINVAL); - goto out_unlock; - } - if (VN_CACHED(VFS_I(tip)) != 0) { xfs_inval_cached_trace(tip, 0, -1, 0, -1); error = xfs_flushinval_pages(tip, 0, -1, @@ -189,13 +257,12 @@ xfs_swap_extents( goto out_unlock; } - /* - * If the target has extended attributes, the tmp file - * must also in order to ensure the correct data fork - * format. - */ - if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) { - error = XFS_ERROR(EINVAL); + /* check inode formats now that data is flushed */ + error = xfs_swap_extents_check_format(ip, tip); + if (error) { + xfs_fs_cmn_err(CE_NOTE, mp, + "%s: inode 0x%llx format is incompatible for exchanging.", + __FILE__, ip->i_ino); goto out_unlock; } @@ -276,6 +343,16 @@ xfs_swap_extents( *tifp = *tempifp; /* struct copy */ /* + * Fix the in-memory data fork values that are dependent on the fork + * offset in the inode. We can't assume they remain the same as attr2 + * has dynamic fork offsets. + */ + ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) / + (uint)sizeof(xfs_bmbt_rec_t); + tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) / + (uint)sizeof(xfs_bmbt_rec_t); + + /* * Fix the on-disk inode values */ tmp = (__uint64_t)ip->i_d.di_nblocks; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 2d0b3e1da9e6..6f83f58c099f 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -611,7 +611,7 @@ xfs_fs_log_dummy( xfs_inode_t *ip; int error; - tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1); + tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP); error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0); if (error) { xfs_trans_cancel(tp, 0); diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 80e526489be5..a04a72fbbb65 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -228,13 +228,12 @@ xfs_iget_cache_hit( xfs_itrace_exit_tag(ip, "xfs_iget.alloc"); /* - * We need to set XFS_INEW atomically with clearing the - * reclaimable tag so that we do have an indicator of the - * inode still being initialized. + * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode + * from stomping over us while we recycle the inode. We can't + * clear the radix tree reclaimable tag yet as it requires + * pag_ici_lock to be held exclusive. */ - ip->i_flags |= XFS_INEW; - ip->i_flags &= ~XFS_IRECLAIMABLE; - __xfs_inode_clear_reclaim_tag(mp, pag, ip); + ip->i_flags |= XFS_IRECLAIM; spin_unlock(&ip->i_flags_lock); read_unlock(&pag->pag_ici_lock); @@ -253,7 +252,15 @@ xfs_iget_cache_hit( __xfs_inode_set_reclaim_tag(pag, ip); goto out_error; } + + write_lock(&pag->pag_ici_lock); + spin_lock(&ip->i_flags_lock); + ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM); + ip->i_flags |= XFS_INEW; + __xfs_inode_clear_reclaim_tag(mp, pag, ip); inode->i_state = I_LOCK|I_NEW; + spin_unlock(&ip->i_flags_lock); + write_unlock(&pag->pag_ici_lock); } else { /* If the VFS inode is being torn down, pause and try again. */ if (!igrab(inode)) { @@ -511,17 +518,21 @@ xfs_ireclaim( { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); XFS_STATS_INC(xs_ig_reclaims); /* - * Remove the inode from the per-AG radix tree. It doesn't matter - * if it was never added to it because radix_tree_delete can deal - * with that case just fine. + * Remove the inode from the per-AG radix tree. + * + * Because radix_tree_delete won't complain even if the item was never + * added to the tree assert that it's been there before to catch + * problems with the inode life time early on. */ pag = xfs_get_perag(mp, ip->i_ino); write_lock(&pag->pag_ici_lock); - radix_tree_delete(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino)); + if (!radix_tree_delete(&pag->pag_ici_root, agino)) + ASSERT(0); write_unlock(&pag->pag_ici_lock); xfs_put_perag(mp, pag); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index b92a4fa2a0a1..523a1ae4964d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2877,8 +2877,8 @@ xfs_iflush( mp = ip->i_mount; /* - * If the inode isn't dirty, then just release the inode - * flush lock and do nothing. + * If the inode isn't dirty, then just release the inode flush lock and + * do nothing. */ if (xfs_inode_clean(ip)) { xfs_ifunlock(ip); @@ -2904,6 +2904,19 @@ xfs_iflush( xfs_iunpin_wait(ip); /* + * For stale inodes we cannot rely on the backing buffer remaining + * stale in cache for the remaining life of the stale inode and so + * xfs_itobp() below may give us a buffer that no longer contains + * inodes below. We have to check this after ensuring the inode is + * unpinned so that it is safe to reclaim the stale inode after the + * flush call. + */ + if (xfs_iflags_test(ip, XFS_ISTALE)) { + xfs_ifunlock(ip); + return 0; + } + + /* * This may have been unpinned because the filesystem is shutting * down forcibly. If that's the case we must not write this inode * to disk, because the log record didn't make it to disk! diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 67ae5555a30a..7294abce6ef2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -860,8 +860,15 @@ xfs_iomap_write_unwritten( * set up a transaction to convert the range of extents * from unwritten to real. Do allocations in a loop until * we have covered the range passed in. + * + * Note that we open code the transaction allocation here + * to pass KM_NOFS--we can't risk to recursing back into + * the filesystem here as we might be asked to write out + * the same inode that we complete here and might deadlock + * on the iolock. */ - tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE); + xfs_wait_for_freeze(mp, SB_FREEZE_TRANS); + tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS); tp->t_flags |= XFS_TRANS_RESERVE; error = xfs_trans_reserve(tp, resblks, XFS_WRITE_LOG_RES(mp), 0, diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index fb17f8226b09..b5b0d8055910 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3517,7 +3517,7 @@ xlog_do_recovery_pass( { xlog_rec_header_t *rhead; xfs_daddr_t blk_no; - xfs_caddr_t bufaddr, offset; + xfs_caddr_t offset; xfs_buf_t *hbp, *dbp; int error = 0, h_size; int bblks, split_bblks; @@ -3610,7 +3610,7 @@ xlog_do_recovery_pass( /* * Check for header wrapping around physical end-of-log */ - offset = NULL; + offset = XFS_BUF_PTR(hbp); split_hblks = 0; wrapped_hblks = 0; if (blk_no + hblks <= log->l_logBBsize) { @@ -3646,9 +3646,8 @@ xlog_do_recovery_pass( * - order is important. */ wrapped_hblks = hblks - split_hblks; - bufaddr = XFS_BUF_PTR(hbp); error = XFS_BUF_SET_PTR(hbp, - bufaddr + BBTOB(split_hblks), + offset + BBTOB(split_hblks), BBTOB(hblks - split_hblks)); if (error) goto bread_err2; @@ -3658,14 +3657,10 @@ xlog_do_recovery_pass( if (error) goto bread_err2; - error = XFS_BUF_SET_PTR(hbp, bufaddr, + error = XFS_BUF_SET_PTR(hbp, offset, BBTOB(hblks)); if (error) goto bread_err2; - - if (!offset) - offset = xlog_align(log, 0, - wrapped_hblks, hbp); } rhead = (xlog_rec_header_t *)offset; error = xlog_valid_rec_header(log, rhead, @@ -3685,7 +3680,7 @@ xlog_do_recovery_pass( } else { /* This log record is split across the * physical end of log */ - offset = NULL; + offset = XFS_BUF_PTR(dbp); split_bblks = 0; if (blk_no != log->l_logBBsize) { /* some data is before the physical @@ -3714,9 +3709,8 @@ xlog_do_recovery_pass( * _first_, then the log start (LR header end) * - order is important. */ - bufaddr = XFS_BUF_PTR(dbp); error = XFS_BUF_SET_PTR(dbp, - bufaddr + BBTOB(split_bblks), + offset + BBTOB(split_bblks), BBTOB(bblks - split_bblks)); if (error) goto bread_err2; @@ -3727,13 +3721,9 @@ xlog_do_recovery_pass( if (error) goto bread_err2; - error = XFS_BUF_SET_PTR(dbp, bufaddr, h_size); + error = XFS_BUF_SET_PTR(dbp, offset, h_size); if (error) goto bread_err2; - - if (!offset) - offset = xlog_align(log, wrapped_hblks, - bblks - split_bblks, dbp); } xlog_unpack_data(rhead, offset, log); if ((error = xlog_recover_process_data(log, rhash, diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 8b6c9e807efb..4d509f742bd2 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1471,7 +1471,7 @@ xfs_log_sbcount( if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) return 0; - tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT); + tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP); error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0, XFS_DEFAULT_LOG_COUNT); if (error) { diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index a6c023bc0fb2..08fdb6d43efd 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -209,6 +209,7 @@ typedef struct xfs_mount { __uint64_t m_maxioffset; /* maximum inode offset */ __uint64_t m_resblks; /* total reserved blocks */ __uint64_t m_resblks_avail;/* available reserved blocks */ + __uint64_t m_resblks_save; /* reserved blks @ remount,ro */ int m_dalign; /* stripe unit */ int m_swidth; /* stripe width */ int m_sinoalign; /* stripe unit inode alignment */ @@ -242,6 +243,7 @@ typedef struct xfs_mount { wait_queue_head_t m_wait_single_sync_task; __int64_t m_update_flags; /* sb flags we need to update on the next remount,rw */ + struct list_head m_mplist; /* inode shrinker mount list */ } xfs_mount_t; /* diff --git a/fs/xfs/xfs_rw.h b/fs/xfs/xfs_rw.h index f5e4874c37d8..726014d1c925 100644 --- a/fs/xfs/xfs_rw.h +++ b/fs/xfs/xfs_rw.h @@ -37,13 +37,6 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb) } /* - * Flags for xfs_free_eofblocks - */ -#define XFS_FREE_EOF_LOCK (1<<0) -#define XFS_FREE_EOF_NOLOCK (1<<1) - - -/* * helper function to extract extent size hint from inode */ STATIC_INLINE xfs_extlen_t diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 66b849358e62..237badcbac3b 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -236,19 +236,20 @@ xfs_trans_alloc( uint type) { xfs_wait_for_freeze(mp, SB_FREEZE_TRANS); - return _xfs_trans_alloc(mp, type); + return _xfs_trans_alloc(mp, type, KM_SLEEP); } xfs_trans_t * _xfs_trans_alloc( xfs_mount_t *mp, - uint type) + uint type, + uint memflags) { xfs_trans_t *tp; atomic_inc(&mp->m_active_trans); - tp = kmem_zone_zalloc(xfs_trans_zone, KM_SLEEP); + tp = kmem_zone_zalloc(xfs_trans_zone, memflags); tp->t_magic = XFS_TRANS_MAGIC; tp->t_type = type; tp->t_mountp = mp; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index ed47fc77759c..a0574f593f52 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -924,7 +924,7 @@ typedef struct xfs_trans { * XFS transaction mechanism exported interfaces. */ xfs_trans_t *xfs_trans_alloc(struct xfs_mount *, uint); -xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint); +xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint, uint); xfs_trans_t *xfs_trans_dup(xfs_trans_t *); int xfs_trans_reserve(xfs_trans_t *, uint, uint, uint, uint, uint); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index b572f7e840e0..38a63244e75d 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -69,7 +69,6 @@ xfs_setattr( uint commit_flags=0; uid_t uid=0, iuid=0; gid_t gid=0, igid=0; - int timeflags = 0; struct xfs_dquot *udqp, *gdqp, *olddquot1, *olddquot2; int need_iolock = 1; @@ -134,16 +133,13 @@ xfs_setattr( if (flags & XFS_ATTR_NOLOCK) need_iolock = 0; if (!(mask & ATTR_SIZE)) { - if ((mask != (ATTR_CTIME|ATTR_ATIME|ATTR_MTIME)) || - (mp->m_flags & XFS_MOUNT_WSYNC)) { - tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); - commit_flags = 0; - if ((code = xfs_trans_reserve(tp, 0, - XFS_ICHANGE_LOG_RES(mp), 0, - 0, 0))) { - lock_flags = 0; - goto error_return; - } + tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); + commit_flags = 0; + code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), + 0, 0, 0); + if (code) { + lock_flags = 0; + goto error_return; } } else { if (DM_EVENT_ENABLED(ip, DM_EVENT_TRUNCATE) && @@ -294,15 +290,23 @@ xfs_setattr( * or we are explicitly asked to change it. This handles * the semantic difference between truncate() and ftruncate() * as implemented in the VFS. + * + * The regular truncate() case without ATTR_CTIME and ATTR_MTIME + * is a special case where we need to update the times despite + * not having these flags set. For all other operations the + * VFS set these flags explicitly if it wants a timestamp + * update. */ - if (iattr->ia_size != ip->i_size || (mask & ATTR_CTIME)) - timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + if (iattr->ia_size != ip->i_size && + (!(mask & (ATTR_CTIME | ATTR_MTIME)))) { + iattr->ia_ctime = iattr->ia_mtime = + current_fs_time(inode->i_sb); + mask |= ATTR_CTIME | ATTR_MTIME; + } if (iattr->ia_size > ip->i_size) { ip->i_d.di_size = iattr->ia_size; ip->i_size = iattr->ia_size; - if (!(flags & XFS_ATTR_DMI)) - xfs_ichgtime(ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } else if (iattr->ia_size <= ip->i_size || (iattr->ia_size == 0 && ip->i_d.di_nextents)) { @@ -373,9 +377,6 @@ xfs_setattr( ip->i_d.di_gid = gid; inode->i_gid = gid; } - - xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE); - timeflags |= XFS_ICHGTIME_CHG; } /* @@ -392,51 +393,37 @@ xfs_setattr( inode->i_mode &= S_IFMT; inode->i_mode |= mode & ~S_IFMT; - - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - timeflags |= XFS_ICHGTIME_CHG; } /* * Change file access or modified times. */ - if (mask & (ATTR_ATIME|ATTR_MTIME)) { - if (mask & ATTR_ATIME) { - inode->i_atime = iattr->ia_atime; - ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec; - ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec; - ip->i_update_core = 1; - } - if (mask & ATTR_MTIME) { - inode->i_mtime = iattr->ia_mtime; - ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; - ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; - timeflags &= ~XFS_ICHGTIME_MOD; - timeflags |= XFS_ICHGTIME_CHG; - } - if (tp && (mask & (ATTR_MTIME_SET|ATTR_ATIME_SET))) - xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE); + if (mask & ATTR_ATIME) { + inode->i_atime = iattr->ia_atime; + ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec; + ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec; + ip->i_update_core = 1; } - - /* - * Change file inode change time only if ATTR_CTIME set - * AND we have been called by a DMI function. - */ - - if ((flags & XFS_ATTR_DMI) && (mask & ATTR_CTIME)) { + if (mask & ATTR_CTIME) { inode->i_ctime = iattr->ia_ctime; ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec; ip->i_update_core = 1; - timeflags &= ~XFS_ICHGTIME_CHG; + } + if (mask & ATTR_MTIME) { + inode->i_mtime = iattr->ia_mtime; + ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; + ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; + ip->i_update_core = 1; } /* - * Send out timestamp changes that need to be set to the - * current time. Not done when called by a DMI function. + * And finally, log the inode core if any attribute in it + * has been changed. */ - if (timeflags && !(flags & XFS_ATTR_DMI)) - xfs_ichgtime(ip, timeflags); + if (mask & (ATTR_UID|ATTR_GID|ATTR_MODE| + ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(xs_ig_attrchg); @@ -451,12 +438,10 @@ xfs_setattr( * mix so this probably isn't worth the trouble to optimize. */ code = 0; - if (tp) { - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(tp); + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(tp); - code = xfs_trans_commit(tp, commit_flags); - } + code = xfs_trans_commit(tp, commit_flags); xfs_iunlock(ip, lock_flags); @@ -612,7 +597,7 @@ xfs_fsync( { xfs_trans_t *tp; int error = 0; - int log_flushed = 0, changed = 1; + int log_flushed = 0; xfs_itrace_entry(ip); @@ -642,19 +627,11 @@ xfs_fsync( * disk yet, the inode will be still be pinned. If it is, * force the log. */ - xfs_iunlock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) { error = _xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC, &log_flushed); - } else { - /* - * If the inode is not pinned and nothing has changed - * we don't need to flush the cache. - */ - changed = 0; } } else { /* @@ -689,7 +666,7 @@ xfs_fsync( xfs_iunlock(ip, XFS_ILOCK_EXCL); } - if ((ip->i_mount->m_flags & XFS_MOUNT_BARRIER) && changed) { + if (ip->i_mount->m_flags & XFS_MOUNT_BARRIER) { /* * If the log write didn't issue an ordered tag we need * to flush the disk cache for the data device now. @@ -709,6 +686,11 @@ xfs_fsync( } /* + * Flags for xfs_free_eofblocks + */ +#define XFS_FREE_EOF_TRYLOCK (1<<0) + +/* * This is called by xfs_inactive to free any blocks beyond eof * when the link count isn't zero and by xfs_dm_punch_hole() when * punching a hole to EOF. @@ -726,7 +708,6 @@ xfs_free_eofblocks( xfs_filblks_t map_len; int nimaps; xfs_bmbt_irec_t imap; - int use_iolock = (flags & XFS_FREE_EOF_LOCK); /* * Figure out if there are any blocks beyond the end @@ -768,14 +749,19 @@ xfs_free_eofblocks( * cache and we can't * do that within a transaction. */ - if (use_iolock) + if (flags & XFS_FREE_EOF_TRYLOCK) { + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { + xfs_trans_cancel(tp, 0); + return 0; + } + } else { xfs_ilock(ip, XFS_IOLOCK_EXCL); + } error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, ip->i_size); if (error) { xfs_trans_cancel(tp, 0); - if (use_iolock) - xfs_iunlock(ip, XFS_IOLOCK_EXCL); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } @@ -812,8 +798,7 @@ xfs_free_eofblocks( error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); } - xfs_iunlock(ip, (use_iolock ? (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL) - : XFS_ILOCK_EXCL)); + xfs_iunlock(ip, XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL); } return error; } @@ -1113,7 +1098,17 @@ xfs_release( (ip->i_df.if_flags & XFS_IFEXTENTS)) && (!(ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))) { - error = xfs_free_eofblocks(mp, ip, XFS_FREE_EOF_LOCK); + + /* + * If we can't get the iolock just skip truncating + * the blocks past EOF because we could deadlock + * with the mmap_sem otherwise. We'll get another + * chance to drop them once the last reference to + * the inode is dropped, so we'll never leak blocks + * permanently. + */ + error = xfs_free_eofblocks(mp, ip, + XFS_FREE_EOF_TRYLOCK); if (error) return error; } @@ -1184,7 +1179,7 @@ xfs_inactive( (!(ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) || (ip->i_delayed_blks != 0)))) { - error = xfs_free_eofblocks(mp, ip, XFS_FREE_EOF_LOCK); + error = xfs_free_eofblocks(mp, ip, 0); if (error) return VN_INACTIVE_CACHE; } @@ -2456,46 +2451,6 @@ xfs_set_dmattrs( return error; } -int -xfs_reclaim( - xfs_inode_t *ip) -{ - - xfs_itrace_entry(ip); - - ASSERT(!VN_MAPPED(VFS_I(ip))); - - /* bad inode, get out here ASAP */ - if (is_bad_inode(VFS_I(ip))) { - xfs_ireclaim(ip); - return 0; - } - - xfs_ioend_wait(ip); - - ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0); - - /* - * If we have nothing to flush with this inode then complete the - * teardown now, otherwise break the link between the xfs inode and the - * linux inode and clean up the xfs inode later. This avoids flushing - * the inode to disk during the delete operation itself. - * - * When breaking the link, we need to set the XFS_IRECLAIMABLE flag - * first to ensure that xfs_iunpin() will never see an xfs inode - * that has a linux inode being reclaimed. Synchronisation is provided - * by the i_flags_lock. - */ - if (!ip->i_update_core && (ip->i_itemp == NULL)) { - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_iflock(ip); - xfs_iflags_set(ip, XFS_IRECLAIMABLE); - return xfs_reclaim_inode(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC); - } - xfs_inode_set_reclaim_tag(ip); - return 0; -} - /* * xfs_alloc_file_space() * This routine allocates disk space for the given file. diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h index a9e102de71a1..167a467403a5 100644 --- a/fs/xfs/xfs_vnodeops.h +++ b/fs/xfs/xfs_vnodeops.h @@ -38,7 +38,6 @@ int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name, const char *target_path, mode_t mode, struct xfs_inode **ipp, cred_t *credp); int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state); -int xfs_reclaim(struct xfs_inode *ip); int xfs_change_file_space(struct xfs_inode *ip, int cmd, xfs_flock64_t *bf, xfs_off_t offset, int attr_flags); int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name, |