STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, int flags, void *args) { int ret; struct xfs_eofblocks *eofb = args; bool need_iolock = true; int match; ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0)); if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); xfs_inode_clear_eofblocks_tag(ip); return 0; } /* * If the mapping is dirty the operation can block and wait for some * time. Unless we are waiting, skip it. */ if (!(flags & SYNC_WAIT) && mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY)) return 0; if (eofb) { if (eofb->eof_flags & XFS_EOF_FLAGS_UNION) match = xfs_inode_match_id_union(ip, eofb); else match = xfs_inode_match_id(ip, eofb); if (!match) return 0; /* skip the inode if the file size is too small */ if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; /* * A scan owner implies we already hold the iolock. Skip it in * xfs_free_eofblocks() to avoid deadlock. This also eliminates * the possibility of EAGAIN being returned. */ if (eofb->eof_scan_owner == ip->i_ino) need_iolock = false; } ret = xfs_free_eofblocks(ip->i_mount, ip, need_iolock); /* don't revisit the inode if we're not waiting */ if (ret == -EAGAIN && !(flags & SYNC_WAIT)) ret = 0; return ret; }
STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, int flags, void *args) { int ret = 0; struct xfs_eofblocks *eofb = args; int match; if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); xfs_inode_clear_eofblocks_tag(ip); return 0; } /* * If the mapping is dirty the operation can block and wait for some * time. Unless we are waiting, skip it. */ if (!(flags & SYNC_WAIT) && mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY)) return 0; if (eofb) { if (eofb->eof_flags & XFS_EOF_FLAGS_UNION) match = xfs_inode_match_id_union(ip, eofb); else match = xfs_inode_match_id(ip, eofb); if (!match) return 0; /* skip the inode if the file size is too small */ if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; } /* * If the caller is waiting, return -EAGAIN to keep the background * scanner moving and revisit the inode in a subsequent pass. */ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { if (flags & SYNC_WAIT) ret = -EAGAIN; return ret; } ret = xfs_free_eofblocks(ip); xfs_iunlock(ip, XFS_IOLOCK_EXCL); return ret; }
STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, struct xfs_perag *pag, int flags, void *args) { int ret; struct xfs_eofblocks *eofb = args; if (!xfs_can_free_eofblocks(ip, false)) { /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); xfs_inode_clear_eofblocks_tag(ip); return 0; } /* * If the mapping is dirty the operation can block and wait for some * time. Unless we are waiting, skip it. */ if (!(flags & SYNC_WAIT) && mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY)) return 0; if (eofb) { if (!xfs_inode_match_id(ip, eofb)) return 0; /* skip the inode if the file size is too small */ if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE && XFS_ISIZE(ip) < eofb->eof_min_file_size) return 0; } ret = xfs_free_eofblocks(ip->i_mount, ip, true); /* don't revisit the inode if we're not waiting */ if (ret == EAGAIN && !(flags & SYNC_WAIT)) ret = 0; return ret; }
/* * Truncate file. Must have write permission and not be a directory. */ int xfs_setattr_size( struct xfs_inode *ip, struct iattr *iattr) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; uint lock_flags = 0; uint commit_flags = 0; trace_xfs_setattr(ip); if (mp->m_flags & XFS_MOUNT_RDONLY) return XFS_ERROR(EROFS); if (XFS_FORCED_SHUTDOWN(mp)) return XFS_ERROR(EIO); error = -inode_change_ok(inode, iattr); if (error) return XFS_ERROR(error); ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; /* * Short circuit the truncate case for zero length files. */ if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) { if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME))) return 0; /* * Use the regular setattr path to update the timestamps. */ iattr->ia_valid &= ~ATTR_SIZE; return xfs_setattr_nonsize(ip, iattr, 0); } /* * Make sure that the dquots are attached to the inode. */ error = xfs_qm_dqattach(ip, 0); if (error) return error; /* * Now we can make the changes. Before we join the inode to the * transaction, take care of the part of the truncation that must be * done without the inode lock. This needs to be done before joining * the inode to the transaction, because the inode cannot be unlocked * once it is a part of the transaction. */ if (newsize > oldsize) { /* * Do the first part of growing a file: zero any data in the * last block that is beyond the old EOF. We need to do this * before the inode is joined to the transaction to modify * i_size. */ error = xfs_zero_eof(ip, newsize, oldsize); if (error) return error; } /* * We are going to log the inode size change in this transaction so * any previous writes that are beyond the on disk EOF and the new * EOF that have not been written out need to be written here. If we * do not write the data out, we expose ourselves to the null files * problem. * * Only flush from the on disk size to the smaller of the in memory * file size or the new size as that's the range we really care about * here and prevents waiting for other data not within the range we * care about here. */ if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) { error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ip->i_d.di_size, newsize); if (error) return error; } /* * Wait for all direct I/O to complete. */ inode_dio_wait(inode); error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks); if (error) return error; tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE); error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0); if (error) goto out_trans_cancel; truncate_setsize(inode, newsize); commit_flags = XFS_TRANS_RELEASE_LOG_RES; lock_flags |= XFS_ILOCK_EXCL; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); /* * Only change the c/mtime if we are changing the size 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 (newsize != oldsize && !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) { iattr->ia_ctime = iattr->ia_mtime = current_fs_time(inode->i_sb); iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME; } /* * The first thing we do is set the size to new_size permanently on * disk. This way we don't have to worry about anyone ever being able * to look at the data being freed even in the face of a crash. * What we're getting around here is the case where we free a block, it * is allocated to another file, it is written to, and then we crash. * If the new data gets written to the file but the log buffers * containing the free and reallocation don't, then we'd end up with * garbage in the blocks being freed. As long as we make the new size * permanent before actually freeing any blocks it doesn't matter if * they get written to. */ ip->i_d.di_size = newsize; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); if (newsize <= oldsize) { error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize); if (error) goto out_trans_abort; /* * Truncated "down", so we're removing references to old data * here - if we delay flushing for a long time, we expose * ourselves unduly to the notorious NULL files problem. So, * we mark this inode and flush it when the file is closed, * and do not wait the usual (long) time for writeout. */ xfs_iflags_set(ip, XFS_ITRUNCATED); /* A truncate down always removes post-EOF blocks. */ xfs_inode_clear_eofblocks_tag(ip); } if (iattr->ia_valid & ATTR_MODE) xfs_setattr_mode(ip, iattr); if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) xfs_setattr_time(ip, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(xs_ig_attrchg); if (mp->m_flags & XFS_MOUNT_WSYNC) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); out_unlock: if (lock_flags) xfs_iunlock(ip, lock_flags); return error; out_trans_abort: commit_flags |= XFS_TRANS_ABORT; out_trans_cancel: xfs_trans_cancel(tp, commit_flags); goto out_unlock; }
/* * 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. */ int xfs_free_eofblocks( xfs_mount_t *mp, xfs_inode_t *ip, bool need_iolock) { xfs_trans_t *tp; int error; xfs_fileoff_t end_fsb; xfs_fileoff_t last_fsb; xfs_filblks_t map_len; int nimaps; xfs_bmbt_irec_t imap; /* * Figure out if there are any blocks beyond the end * of the file. If not, then there is nothing to do. */ end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip)); last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes); if (last_fsb <= end_fsb) return 0; map_len = last_fsb - end_fsb; nimaps = 1; xfs_ilock(ip, XFS_ILOCK_SHARED); error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0); xfs_iunlock(ip, XFS_ILOCK_SHARED); if (!error && (nimaps != 0) && (imap.br_startblock != HOLESTARTBLOCK || ip->i_delayed_blks)) { /* * Attach the dquots to the inode up front. */ error = xfs_qm_dqattach(ip, 0); if (error) return error; /* * There are blocks after the end of file. * Free them up now by truncating the file to * its current size. */ tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE); if (need_iolock) { if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { xfs_trans_cancel(tp, 0); return EAGAIN; } } error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0); if (error) { ASSERT(XFS_FORCED_SHUTDOWN(mp)); xfs_trans_cancel(tp, 0); if (need_iolock) xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); /* * Do not update the on-disk file size. If we update the * on-disk file size and then the system crashes before the * contents of the file are flushed to disk then the files * may be full of holes (ie NULL files bug). */ error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, XFS_ISIZE(ip)); if (error) { /* * If we get an error at this point we simply don't * bother truncating the file. */ xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT)); } else { error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); if (!error) xfs_inode_clear_eofblocks_tag(ip); } xfs_iunlock(ip, XFS_ILOCK_EXCL); if (need_iolock) xfs_iunlock(ip, XFS_IOLOCK_EXCL); } return error; }
/* * Truncate file. Must have write permission and not be a directory. */ int xfs_setattr_size( struct xfs_inode *ip, struct iattr *iattr) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; uint lock_flags = 0; bool did_zeroing = false; trace_xfs_setattr(ip); if (mp->m_flags & XFS_MOUNT_RDONLY) return -EROFS; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; error = inode_change_ok(inode, iattr); if (error) return error; ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(inode->i_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; /* * Short circuit the truncate case for zero length files. */ if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) { if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME))) return 0; /* * Use the regular setattr path to update the timestamps. */ iattr->ia_valid &= ~ATTR_SIZE; return xfs_setattr_nonsize(ip, iattr, 0); } /* * Make sure that the dquots are attached to the inode. */ error = xfs_qm_dqattach(ip, 0); if (error) return error; /* * Wait for all direct I/O to complete. */ inode_dio_wait(inode); /* * File data changes must be complete before we start the transaction to * modify the inode. This needs to be done before joining the inode to * the transaction because the inode cannot be unlocked once it is a * part of the transaction. * * Start with zeroing any data beyond EOF that we may expose on file * extension, or zeroing out the rest of the block on a downward * truncate. */ if (newsize > oldsize) { error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing); } else { error = iomap_truncate_page(inode, newsize, &did_zeroing, &xfs_iomap_ops); } if (error) return error; /* * We are going to log the inode size change in this transaction so * any previous writes that are beyond the on disk EOF and the new * EOF that have not been written out need to be written here. If we * do not write the data out, we expose ourselves to the null files * problem. Note that this includes any block zeroing we did above; * otherwise those blocks may not be zeroed after a crash. */ if (did_zeroing || (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) { error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ip->i_d.di_size, newsize); if (error) return error; } /* * We've already locked out new page faults, so now we can safely remove * pages from the page cache knowing they won't get refaulted until we * drop the XFS_MMAP_EXCL lock after the extent manipulations are * complete. The truncate_setsize() call also cleans partial EOF page * PTEs on extending truncates and hence ensures sub-page block size * filesystems are correctly handled, too. * * We have to do all the page cache truncate work outside the * transaction context as the "lock" order is page lock->log space * reservation as defined by extent allocation in the writeback path. * Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but * having already truncated the in-memory version of the file (i.e. made * user visible changes). There's not much we can do about this, except * to hope that the caller sees ENOMEM and retries the truncate * operation. */ truncate_setsize(inode, newsize); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) return error; lock_flags |= XFS_ILOCK_EXCL; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); /* * Only change the c/mtime if we are changing the size 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 (newsize != oldsize && !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) { iattr->ia_ctime = iattr->ia_mtime = current_fs_time(inode->i_sb); iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME; } /* * The first thing we do is set the size to new_size permanently on * disk. This way we don't have to worry about anyone ever being able * to look at the data being freed even in the face of a crash. * What we're getting around here is the case where we free a block, it * is allocated to another file, it is written to, and then we crash. * If the new data gets written to the file but the log buffers * containing the free and reallocation don't, then we'd end up with * garbage in the blocks being freed. As long as we make the new size * permanent before actually freeing any blocks it doesn't matter if * they get written to. */ ip->i_d.di_size = newsize; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); if (newsize <= oldsize) { error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize); if (error) goto out_trans_cancel; /* * Truncated "down", so we're removing references to old data * here - if we delay flushing for a long time, we expose * ourselves unduly to the notorious NULL files problem. So, * we mark this inode and flush it when the file is closed, * and do not wait the usual (long) time for writeout. */ xfs_iflags_set(ip, XFS_ITRUNCATED); /* A truncate down always removes post-EOF blocks. */ xfs_inode_clear_eofblocks_tag(ip); } if (iattr->ia_valid & ATTR_MODE) xfs_setattr_mode(ip, iattr); if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) xfs_setattr_time(ip, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(mp, xs_ig_attrchg); if (mp->m_flags & XFS_MOUNT_WSYNC) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); out_unlock: if (lock_flags) xfs_iunlock(ip, lock_flags); return error; out_trans_cancel: xfs_trans_cancel(tp); goto out_unlock; }