/* * linux/fs/ext4/inode.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * 64-bit file support on 64-bit platforms by Jakub Jelinek * (jj@sunsite.ms.mff.cuni.cz) * * Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000 */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "truncate.h" #include #define MPAGE_DA_EXTENT_TAIL 0x01 static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u16 csum_lo; __u16 csum_hi = 0; __u32 csum; csum_lo = le16_to_cpu(raw->i_checksum_lo); raw->i_checksum_lo = 0; if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { csum_hi = le16_to_cpu(raw->i_checksum_hi); raw->i_checksum_hi = 0; } csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, EXT4_INODE_SIZE(inode->i_sb)); raw->i_checksum_lo = cpu_to_le16(csum_lo); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) raw->i_checksum_hi = cpu_to_le16(csum_hi); return csum; } static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 provided, calculated; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); calculated = ext4_inode_csum(inode, raw, ei); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16; else calculated &= 0xFFFF; return provided == calculated; } static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 csum; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) return; csum = ext4_inode_csum(inode, raw, ei); raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) raw->i_checksum_hi = cpu_to_le16(csum >> 16); } static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { trace_ext4_begin_ordered_truncate(inode, new_size); /* * If jinode is zero, then we never opened the file for * writing, so there's no need to call * jbd2_journal_begin_ordered_truncate() since there's no * outstanding writes we need to flush. */ if (!EXT4_I(inode)->jinode) return 0; return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode, new_size); } static void ext4_invalidatepage(struct page *page, unsigned long offset); static int __ext4_journalled_writepage(struct page *page, unsigned int len); static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh); static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, struct inode *inode, struct page *page, loff_t from, loff_t length, int flags); /* * Test whether an inode is a fast symlink. */ static int ext4_inode_is_fast_symlink(struct inode *inode) { int ea_blocks = EXT4_I(inode)->i_file_acl ? (inode->i_sb->s_blocksize >> 9) : 0; return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); } /* * Restart the transaction associated with *handle. This does a commit, * so before we call here everything must be consistently dirtied against * this transaction. */ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, int nblocks) { int ret; /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); jbd_debug(2, "restarting handle %p\n", handle); up_write(&EXT4_I(inode)->i_data_sem); ret = ext4_journal_restart(handle, nblocks); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); return ret; } /* * Called at the last iput() if i_nlink is zero. */ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; trace_ext4_evict_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the * journal. So although mm thinks everything is clean and * ready for reaping the inode might still have some pages to * write in the running transaction or waiting to be * checkpointed. Thus calling jbd2_journal_invalidatepage() * (via truncate_inode_pages()) to discard these buffers can * cause data loss. Also even if we did not discard these * buffers, we would have no way to find them after the inode * is reaped and thus user could see stale data if he tries to * read them before the transaction is checkpointed. So be * careful and force everything to disk here... We use * ei->i_datasync_tid to store the newest transaction * containing inode's data. * * Note that directories do not have this problem because they * don't use page cache. */ if (ext4_should_journal_data(inode) && (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && inode->i_ino != EXT4_JOURNAL_INO) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; jbd2_complete_transaction(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } truncate_inode_pages(&inode->i_data, 0); ext4_ioend_shutdown(inode); goto no_delete; } if (!is_bad_inode(inode)) dquot_initialize(inode); if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); truncate_inode_pages(&inode->i_data, 0); ext4_ioend_shutdown(inode); if (is_bad_inode(inode)) goto no_delete; /* * Protect us against freezing - iput() caller didn't have to have any * protection against it */ sb_start_intwrite(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, ext4_blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* * If we're going to skip the normal cleanup, we still need to * make sure that the in-core orphan linked list is properly * cleaned up. */ ext4_orphan_del(NULL, inode); sb_end_intwrite(inode->i_sb); goto no_delete; } if (IS_SYNC(inode)) ext4_handle_sync(handle); inode->i_size = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_warning(inode->i_sb, "couldn't mark inode dirty (err %d)", err); goto stop_handle; } if (inode->i_blocks) ext4_truncate(inode); /* * ext4_ext_truncate() doesn't reserve any slop when it * restarts journal transactions; therefore there may not be * enough credits left in the handle to remove the inode from * the orphan list and set the dtime field. */ if (!ext4_handle_has_enough_credits(handle, 3)) { err = ext4_journal_extend(handle, 3); if (err > 0) err = ext4_journal_restart(handle, 3); if (err != 0) { ext4_warning(inode->i_sb, "couldn't extend journal (err %d)", err); stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); sb_end_intwrite(inode->i_sb); goto no_delete; } } /* * Kill off the orphan record which ext4_truncate created. * AKPM: I think this can be inside the above `if'. * Note that ext4_orphan_del() has to be able to cope with the * deletion of a non-existent orphan - this is because we don't * know if ext4_truncate() actually created an orphan record. * (Well, we could do this if we need to, but heck - it works) */ ext4_orphan_del(handle, inode); EXT4_I(inode)->i_dtime = get_seconds(); /* * One subtle ordering requirement: if anything has gone wrong * (transaction abort, IO errors, whatever), then we can still * do these next steps (the fs will already have been marked as * having errors), but we can't free the inode if the mark_dirty * fails. */ if (ext4_mark_inode_dirty(handle, inode)) /* If that failed, just do the required in-core inode clear. */ ext4_clear_inode(inode); else ext4_free_inode(handle, inode); ext4_journal_stop(handle); sb_end_intwrite(inode->i_sb); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } #ifdef CONFIG_QUOTA qsize_t *ext4_get_reserved_space(struct inode *inode) { return &EXT4_I(inode)->i_reserved_quota; } #endif /* * Calculate the number of metadata blocks need to reserve * to allocate a block located at @lblock */ static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock) { if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return ext4_ext_calc_metadata_amount(inode, lblock); return ext4_ind_calc_metadata_amount(inode, lblock); } /* * Called with i_data_sem down, which is important since we can call * ext4_discard_preallocations() from here. */ void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); spin_lock(&ei->i_block_reservation_lock); trace_ext4_da_update_reserve_space(inode, used, quota_claim); if (unlikely(used > ei->i_reserved_data_blocks)) { ext4_warning(inode->i_sb, "%s: ino %lu, used %d " "with only %d reserved data blocks", __func__, inode->i_ino, used, ei->i_reserved_data_blocks); WARN_ON(1); used = ei->i_reserved_data_blocks; } if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) { ext4_warning(inode->i_sb, "ino %lu, allocated %d " "with only %d reserved metadata blocks " "(releasing %d blocks with reserved %d data blocks)", inode->i_ino, ei->i_allocated_meta_blocks, ei->i_reserved_meta_blocks, used, ei->i_reserved_data_blocks); WARN_ON(1); ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks; } /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; percpu_counter_sub(&sbi->s_dirtyclusters_counter, used + ei->i_allocated_meta_blocks); ei->i_allocated_meta_blocks = 0; if (ei->i_reserved_data_blocks == 0) { /* * We can release all of the reserved metadata blocks * only when we have written all of the delayed * allocation blocks. */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); ei->i_reserved_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; } spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); /* Update quota subsystem for data blocks */ if (quota_claim) dquot_claim_block(inode, EXT4_C2B(sbi, used)); else { /* * We did fallocate with an offset that is already delayed * allocated. So on delayed allocated writeback we should * not re-claim the quota for fallocated blocks. */ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used)); } /* * If we have done all the pending block allocations and if * there aren't any writers on the inode, we can discard the * inode's preallocations. */ if ((ei->i_reserved_data_blocks == 0) && (atomic_read(&inode->i_writecount) == 0)) ext4_discard_preallocations(inode); } static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock " "(length %d)", (unsigned long) map->m_lblk, map->m_len); return -EIO; } return 0; } #define check_block_validity(inode, map) \ __check_block_validity((inode), __func__, __LINE__, (map)) /* * Return the number of contiguous dirty pages in a given inode * starting at page frame idx. */ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, unsigned int max_pages) { struct address_space *mapping = inode->i_mapping; pgoff_t index; struct pagevec pvec; pgoff_t num = 0; int i, nr_pages, done = 0; if (max_pages == 0) return 0; pagevec_init(&pvec, 0); while (!done) { index = idx; nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, (pgoff_t)PAGEVEC_SIZE); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; struct buffer_head *bh, *head; lock_page(page); if (unlikely(page->mapping != mapping) || !PageDirty(page) || PageWriteback(page) || page->index != idx) { done = 1; unlock_page(page); break; } if (page_has_buffers(page)) { bh = head = page_buffers(page); do { if (!buffer_delay(bh) && !buffer_unwritten(bh)) done = 1; bh = bh->b_this_page; } while (!done && (bh != head)); } unlock_page(page); if (done) break; idx++; num++; if (num >= max_pages) { done = 1; break; } } pagevec_release(&pvec); } return num; } #ifdef ES_AGGRESSIVE_TEST static void ext4_map_blocks_es_recheck(handle_t *handle, struct inode *inode, struct ext4_map_blocks *es_map, struct ext4_map_blocks *map, int flags) { int retval; map->m_flags = 0; /* * There is a race window that the result is not the same. * e.g. xfstests #223 when dioread_nolock enables. The reason * is that we lookup a block mapping in extent status tree with * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) up_read((&EXT4_I(inode)->i_data_sem)); /* * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag * because it shouldn't be marked in es_map->m_flags. */ map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY); /* * We don't check m_len because extent will be collpased in status * tree. So the m_len might not equal. */ if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { printk("ES cache assertation failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, es_map->m_pblk, es_map->m_flags, map->m_lblk, map->m_len, map->m_pblk, map->m_flags, retval, flags); } } #endif /* ES_AGGRESSIVE_TEST */ /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks * and store the allocated blocks in the result buffer head and mark it * mapped. * * If file type is extents based, it will call ext4_ext_map_blocks(), * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping * based files * * On success, it returns the number of blocks being mapped or allocate. * if create==0 and the blocks are pre-allocated and uninitialized block, * the result buffer head is unmapped. If the create ==1, it will make sure * the buffer head is mapped. * * It returns 0 if plain look up failed (blocks have not been allocated), in * that case, buffer head is unmapped * * It returns the error in case of allocation failure. */ int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct extent_status es; int retval; #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif map->m_flags = 0; ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u," "logical block %lu\n", inode->i_ino, flags, map->m_len, (unsigned long) map->m_lblk); /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; map->m_flags |= ext4_es_is_written(&es) ? EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN; retval = es.es_len - (map->m_lblk - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) { retval = 0; } else { BUG_ON(1); } #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(handle, inode, map, &orig_map, flags); #endif goto found; } /* * Try to see if we can get the block without requesting a new * file system block. */ if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } if (retval > 0) { int ret; unsigned long long status; #ifdef ES_AGGRESSIVE_TEST if (retval != map->m_len) { printk("ES len assertation failed for inode: %lu " "retval %d != map->m_len %d " "in %s (lookup)\n", inode->i_ino, retval, map->m_len, __func__); } #endif status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && ext4_find_delalloc_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); if (ret < 0) retval = ret; } if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) up_read((&EXT4_I(inode)->i_data_sem)); found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { int ret = check_block_validity(inode, map); if (ret != 0) return ret; } /* If it is only a block(s) look up */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; /* * Returns if the blocks have already allocated * * Note that if blocks have been preallocated * ext4_ext_get_block() returns the create = 0 * with buffer head unmapped. */ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) return retval; /* * Here we clear m_flags because after allocating an new extent, * it will be set again. */ map->m_flags &= ~EXT4_MAP_FLAGS; /* * New blocks allocate and/or writing to uninitialized extent * will possibly result in updating i_data, so we take * the write lock of i_data_sem, and call get_blocks() * with create == 1 flag. */ down_write((&EXT4_I(inode)->i_data_sem)); /* * if the caller is from delayed allocation writeout path * we have already reserved fs blocks for allocation * let the underlying get_block() function know to * avoid double accounting */ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); /* * We need to check for EXT4 here because migrate * could have changed the inode type in between */ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags); if (retval > 0 && map->m_flags & EXT4_MAP_NEW) { /* * We allocated new blocks which will result in * i_data's format changing. Force the migrate * to fail by clearing migrate flags */ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } /* * Update reserved blocks/metadata blocks after successful * block allocation which had been deferred till now. We don't * support fallocate for non extent files. So we can update * reserve space here. */ if ((retval > 0) && (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) ext4_da_update_reserve_space(inode, retval, 1); } if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); if (retval > 0) { int ret; unsigned long long status; #ifdef ES_AGGRESSIVE_TEST if (retval != map->m_len) { printk("ES len assertation failed for inode: %lu " "retval %d != map->m_len %d " "in %s (allocation)\n", inode->i_ino, retval, map->m_len, __func__); } #endif /* * If the extent has been zeroed out, we don't need to update * extent status tree. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO) && ext4_es_lookup_extent(inode, map->m_lblk, &es)) { if (ext4_es_is_written(&es)) goto has_zeroout; } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) && ext4_find_delalloc_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); if (ret < 0) retval = ret; } has_zeroout: up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { int ret = check_block_validity(inode, map); if (ret != 0) return ret; } return retval; } /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 static int _ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int flags) { handle_t *handle = ext4_journal_current_handle(); struct ext4_map_blocks map; int ret = 0, started = 0; int dio_credits; if (ext4_has_inline_data(inode)) return -ERANGE; map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) { /* Direct IO write... */ if (map.m_len > DIO_MAX_BLOCKS) map.m_len = DIO_MAX_BLOCKS; dio_credits = ext4_chunk_trans_blocks(inode, map.m_len); handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); return ret; } started = 1; } ret = ext4_map_blocks(handle, inode, &map, flags); if (ret > 0) { map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; bh->b_size = inode->i_sb->s_blocksize * map.m_len; ret = 0; } if (started) ext4_journal_stop(handle); return ret; } int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { return _ext4_get_block(inode, iblock, bh, create ? EXT4_GET_BLOCKS_CREATE : 0); } /* * `handle' can be NULL if create is zero */ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, ext4_lblk_t block, int create, int *errp) { struct ext4_map_blocks map; struct buffer_head *bh; int fatal = 0, err; J_ASSERT(handle != NULL || create == 0); map.m_lblk = block; map.m_len = 1; err = ext4_map_blocks(handle, inode, &map, create ? EXT4_GET_BLOCKS_CREATE : 0); /* ensure we send some value back into *errp */ *errp = 0; if (create && err == 0) err = -ENOSPC; /* should never happen */ if (err < 0) *errp = err; if (err <= 0) return NULL; bh = sb_getblk(inode->i_sb, map.m_pblk); if (unlikely(!bh)) { *errp = -ENOMEM; return NULL; } if (map.m_flags & EXT4_MAP_NEW) { J_ASSERT(create != 0); J_ASSERT(handle != NULL); /* * Now that we do not always journal data, we should * keep in mind whether this should always journal the * new buffer as metadata. For now, regular file * writes use ext4_get_block instead, so it's not a * problem. */ lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); fatal = ext4_journal_get_create_access(handle, bh); if (!fatal && !buffer_uptodate(bh)) { memset(bh->b_data, 0, inode->i_sb->s_blocksize); set_buffer_uptodate(bh); } unlock_buffer(bh); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); if (!fatal) fatal = err; } else { BUFFER_TRACE(bh, "not a new buffer"); } if (fatal) { *errp = fatal; brelse(bh); bh = NULL; } return bh; } struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, ext4_lblk_t block, int create, int *err) { struct buffer_head *bh; bh = ext4_getblk(handle, inode, block, create, err); if (!bh) return bh; if (buffer_uptodate(bh)) return bh; ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; put_bh(bh); *err = -EIO; return NULL; } int ext4_walk_page_buffers(handle_t *handle, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)(handle_t *handle, struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; unsigned blocksize = head->b_size; int err, ret = 0; struct buffer_head *next; for (bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (partial && !buffer_uptodate(bh)) *partial = 1; continue; } err = (*fn)(handle, bh); if (!ret) ret = err; } return ret; } /* * To preserve ordering, it is essential that the hole instantiation and * the data write be encapsulated in a single transaction. We cannot * close off a transaction and start a new one between the ext4_get_block() * and the commit_write(). So doing the jbd2_journal_start at the start of * prepare_write() is the right place. * * Also, this function can nest inside ext4_writepage(). In that case, we * *know* that ext4_writepage() has generated enough buffer credits to do the * whole page. So we won't block on the journal in that case, which is good, * because the caller may be PF_MEMALLOC. * * By accident, ext4 can be reentered when a transaction is open via * quota file writes. If we were to commit the transaction while thus * reentered, there can be a deadlock - we would be holding a quota * lock, and the commit would never complete if another thread had a * transaction open and was blocking on the quota lock - a ranking * violation. * * So what we do is to rely on the fact that jbd2_journal_stop/journal_start * will _not_ run commit under these circumstances because handle->h_ref * is elevated. We'll still have enough credits for the tiny quotafile * write. */ int do_journal_get_write_access(handle_t *handle, struct buffer_head *bh) { int dirty = buffer_dirty(bh); int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; /* * __block_write_begin() could have dirtied some buffers. Clean * the dirty bit as jbd2_journal_get_write_access() could complain * otherwise about fs integrity issues. Setting of the dirty bit * by __block_write_begin() isn't a real problem here as we clear * the bit before releasing a page lock and thus writeback cannot * ever write the buffer. */ if (dirty) clear_buffer_dirty(bh); ret = ext4_journal_get_write_access(handle, bh); if (!ret && dirty) ret = ext4_handle_dirty_metadata(handle, NULL, bh); return ret; } static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; handle_t *handle; int retries = 0; struct page *page; pgoff_t index; unsigned from, to; trace_ext4_write_begin(inode, pos, len, flags); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason */ needed_blocks = ext4_writepage_trans_blocks(inode) + 1; index = pos >> PAGE_CACHE_SHIFT; from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, flags, pagep); if (ret < 0) return ret; if (ret == 1) return 0; } /* * grab_cache_page_write_begin() can take a long time if the * system is thrashing due to memory pressure, or if the page * is being written back. So grab it first before we start * the transaction handle. This also allows us to allocate * the page (if needed) without using GFP_NOFS. */ retry_grab: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; unlock_page(page); retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { page_cache_release(page); return PTR_ERR(handle); } lock_page(page); if (page->mapping != mapping) { /* The page got truncated from under us */ unlock_page(page); page_cache_release(page); ext4_journal_stop(handle); goto retry_grab; } wait_on_page_writeback(page); if (ext4_should_dioread_nolock(inode)) ret = __block_write_begin(page, pos, len, ext4_get_block_write); else ret = __block_write_begin(page, pos, len, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); } if (ret) { unlock_page(page); /* * __block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_mutex. * * Add inode to orphan list in case we crash before * truncate finishes */ if (pos + len > inode->i_size && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; page_cache_release(page); return ret; } *pagep = page; return ret; } /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct buffer_head *bh) { int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; set_buffer_uptodate(bh); ret = ext4_handle_dirty_metadata(handle, NULL, bh); clear_buffer_meta(bh); clear_buffer_prio(bh); return ret; } /* * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). * * ext4 never places buffers on inode->i_mapping->private_list. metadata * buffers are managed internally. */ static int ext4_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; int ret = 0, ret2; int i_size_changed = 0; trace_ext4_write_end(inode, pos, len, copied); if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) { ret = ext4_jbd2_file_inode(handle, inode); if (ret) { unlock_page(page); page_cache_release(page); goto errout; } } if (ext4_has_inline_data(inode)) copied = ext4_write_inline_data_end(inode, pos, len, copied, page); else copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size * cannot change under us because we hole i_mutex. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = 1; } if (pos + copied > EXT4_I(inode)->i_disksize) { /* We need to mark inode dirty even if * new_i_size is less that inode->i_size * but greater than i_disksize. (hint delalloc) */ ext4_update_i_disksize(inode, (pos + copied)); i_size_changed = 1; } unlock_page(page); page_cache_release(page); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) ext4_mark_inode_dirty(handle, inode); if (copied < 0) ret = copied; if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; } static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; int ret = 0, ret2; int partial = 0; unsigned from, to; loff_t new_i_size; trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; BUG_ON(!ext4_handle_valid(handle)); if (ext4_has_inline_data(inode)) copied = ext4_write_inline_data_end(inode, pos, len, copied, page); else { if (copied < len) { if (!PageUptodate(page)) copied = 0; page_zero_new_buffers(page, from+copied, to); } ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, &partial, write_end_fn); if (!partial) SetPageUptodate(page); } new_i_size = pos + copied; if (new_i_size > inode->i_size) i_size_write(inode, pos+copied); ext4_set_inode_state(inode, EXT4_STATE_JDATA); EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; if (new_i_size > EXT4_I(inode)->i_disksize) { ext4_update_i_disksize(inode, new_i_size); ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; } unlock_page(page); page_cache_release(page); if (pos + len > inode->i_size && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; } /* * Reserve a metadata for a single block located at lblock */ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock) { int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; ext4_lblk_t save_last_lblock; int save_len; /* * recalculate the amount of metadata blocks to reserve * in order to allocate nrblocks * worse case is one extent per block */ repeat: spin_lock(&ei->i_block_reservation_lock); /* * ext4_calc_metadata_amount() has side effects, which we have * to be prepared undo if we fail to claim space. */ save_len = ei->i_da_metadata_calc_len; save_last_lblock = ei->i_da_metadata_calc_last_lblock; md_needed = EXT4_NUM_B2C(sbi, ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); /* * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ if (ext4_claim_free_clusters(sbi, md_needed, 0)) { ei->i_da_metadata_calc_len = save_len; ei->i_da_metadata_calc_last_lblock = save_last_lblock; spin_unlock(&ei->i_block_reservation_lock); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { cond_resched(); goto repeat; } return -ENOSPC; } ei->i_reserved_meta_blocks += md_needed; spin_unlock(&ei->i_block_reservation_lock); return 0; /* success */ } /* * Reserve a single cluster located at lblock */ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; int ret; ext4_lblk_t save_last_lblock; int save_len; /* * We will charge metadata quota at writeout time; this saves * us from metadata over-estimation, though we may go over by * a small amount in the end. Here we just reserve for data. */ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); if (ret) return ret; /* * recalculate the amount of metadata blocks to reserve * in order to allocate nrblocks * worse case is one extent per block */ repeat: spin_lock(&ei->i_block_reservation_lock); /* * ext4_calc_metadata_amount() has side effects, which we have * to be prepared undo if we fail to claim space. */ save_len = ei->i_da_metadata_calc_len; save_last_lblock = ei->i_da_metadata_calc_last_lblock; md_needed = EXT4_NUM_B2C(sbi, ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); /* * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { ei->i_da_metadata_calc_len = save_len; ei->i_da_metadata_calc_last_lblock = save_last_lblock; spin_unlock(&ei->i_block_reservation_lock); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { cond_resched(); goto repeat; } dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } ei->i_reserved_data_blocks++; ei->i_reserved_meta_blocks += md_needed; spin_unlock(&ei->i_block_reservation_lock); return 0; /* success */ } static void ext4_da_release_space(struct inode *inode, int to_free) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); if (!to_free) return; /* Nothing to release, exit */ spin_lock(&EXT4_I(inode)->i_block_reservation_lock); trace_ext4_da_release_space(inode, to_free); if (unlikely(to_free > ei->i_reserved_data_blocks)) { /* * if there aren't enough reserved blocks, then the * counter is messed up somewhere. Since this * function is called from invalidate page, it's * harmless to return without any action. */ ext4_warning(inode->i_sb, "ext4_da_release_space: " "ino %lu, to_free %d with only %d reserved " "data blocks", inode->i_ino, to_free, ei->i_reserved_data_blocks); WARN_ON(1); to_free = ei->i_reserved_data_blocks; } ei->i_reserved_data_blocks -= to_free; if (ei->i_reserved_data_blocks == 0) { /* * We can release all of the reserved metadata blocks * only when we have written all of the delayed * allocation blocks. * Note that in case of bigalloc, i_reserved_meta_blocks, * i_reserved_data_blocks, etc. refer to number of clusters. */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); ei->i_reserved_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; } /* update fs dirty data blocks counter */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); } static void ext4_da_page_release_reservation(struct page *page, unsigned long offset) { int to_release = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; struct inode *inode = page->mapping->host; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int num_clusters; ext4_fsblk_t lblk; head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; clear_buffer_delay(bh); } curr_off = next_off; } while ((bh = bh->b_this_page) != head); if (to_release) { lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); ext4_es_remove_extent(inode, lblk, to_release); } /* If we have released all the blocks belonging to a cluster, then we * need to release the reserved space for that cluster. */ num_clusters = EXT4_NUM_B2C(sbi, to_release); while (num_clusters > 0) { lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + ((num_clusters - 1) << sbi->s_cluster_bits); if (sbi->s_cluster_ratio == 1 || !ext4_find_delalloc_cluster(inode, lblk)) ext4_da_release_space(inode, 1); num_clusters--; } } /* * Delayed allocation stuff */ /* * mpage_da_submit_io - walks through extent of pages and try to write * them with writepage() call back * * @mpd->inode: inode * @mpd->first_page: first page of the extent * @mpd->next_page: page after the last page of the extent * * By the time mpage_da_submit_io() is called we expect all blocks * to be allocated. this may be wrong if allocation failed. * * As pages are already locked by write_cache_pages(), we can't use it */ static int mpage_da_submit_io(struct mpage_da_data *mpd, struct ext4_map_blocks *map) { struct pagevec pvec; unsigned long index, end; int ret = 0, err, nr_pages, i; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; loff_t size = i_size_read(inode); unsigned int len, block_start; struct buffer_head *bh, *page_bufs = NULL; sector_t pblock = 0, cur_logical = 0; struct ext4_io_submit io_submit; BUG_ON(mpd->next_page <= mpd->first_page); memset(&io_submit, 0, sizeof(io_submit)); /* * We need to start from the first_page to the next_page - 1 * to make sure we also write the mapped dirty buffer_heads. * If we look at mpd->b_blocknr we would only be looking * at the currently mapped buffer_heads. */ index = mpd->first_page; end = mpd->next_page - 1; pagevec_init(&pvec, 0); while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { int skip_page = 0; struct page *page = pvec.pages[i]; index = page->index; if (index > end) break; if (index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; else len = PAGE_CACHE_SIZE; if (map) { cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); pblock = map->m_pblk + (cur_logical - map->m_lblk); } index++; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); bh = page_bufs = page_buffers(page); block_start = 0; do { if (map && (cur_logical >= map->m_lblk) && (cur_logical <= (map->m_lblk + (map->m_len - 1)))) { if (buffer_delay(bh)) { clear_buffer_delay(bh); bh->b_blocknr = pblock; } if (buffer_unwritten(bh) || buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); if (map->m_flags & EXT4_MAP_UNINIT) set_buffer_uninit(bh); clear_buffer_unwritten(bh); } /* * skip page if block allocation undone and * block is dirty */ if (ext4_bh_delay_or_unwritten(NULL, bh)) skip_page = 1; bh = bh->b_this_page; block_start += bh->b_size; cur_logical++; pblock++; } while (bh != page_bufs); if (skip_page) { unlock_page(page); continue; } clear_page_dirty_for_io(page); err = ext4_bio_write_page(&io_submit, page, len, mpd->wbc); if (!err) mpd->pages_written++; /* * In error case, we have to continue because * remaining pages are still locked */ if (ret == 0) ret = err; } pagevec_release(&pvec); } ext4_io_submit(&io_submit); return ret; } static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) { int nr_pages, i; pgoff_t index, end; struct pagevec pvec; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; ext4_lblk_t start, last; index = mpd->first_page; end = mpd->next_page - 1; start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); ext4_es_remove_extent(inode, start, last - start + 1); pagevec_init(&pvec, 0); while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; if (page->index > end) break; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); block_invalidatepage(page, 0); ClearPageUptodate(page); unlock_page(page); } index = pvec.pages[nr_pages - 1]->index + 1; pagevec_release(&pvec); } return; } static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld", EXT4_C2B(EXT4_SB(inode->i_sb), ext4_count_free_clusters(sb))); ext4_msg(sb, KERN_CRIT, "Free/Dirty block details"); ext4_msg(sb, KERN_CRIT, "free_blocks=%lld", (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld", (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_dirtyclusters_counter))); ext4_msg(sb, KERN_CRIT, "Block reservation details"); ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u", ei->i_reserved_data_blocks); ext4_msg(sb, KERN_CRIT, "i_reserved_meta_blocks=%u", ei->i_reserved_meta_blocks); ext4_msg(sb, KERN_CRIT, "i_allocated_meta_blocks=%u", ei->i_allocated_meta_blocks); return; } /* * mpage_da_map_and_submit - go through given space, map them * if necessary, and then submit them for I/O * * @mpd - bh describing space * * The function skips space we know is already mapped to disk blocks. * */ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) { int err, blks, get_blocks_flags; struct ext4_map_blocks map, *mapp = NULL; sector_t next = mpd->b_blocknr; unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits; loff_t disksize = EXT4_I(mpd->inode)->i_disksize; handle_t *handle = NULL; /* * If the blocks are mapped already, or we couldn't accumulate * any blocks, then proceed immediately to the submission stage. */ if ((mpd->b_size == 0) || ((mpd->b_state & (1 << BH_Mapped)) && !(mpd->b_state & (1 << BH_Delay)) && !(mpd->b_state & (1 << BH_Unwritten)))) goto submit_io; handle = ext4_journal_current_handle(); BUG_ON(!handle); /* * Call ext4_map_blocks() to allocate any delayed allocation * blocks, or to convert an uninitialized extent to be * initialized (in the case where we have written into * one or more preallocated blocks). * * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to * indicate that we are on the delayed allocation path. This * affects functions in many different parts of the allocation * call path. This flag exists primarily because we don't * want to change *many* call functions, so ext4_map_blocks() * will set the EXT4_STATE_DELALLOC_RESERVED flag once the * inode's allocation semaphore is taken. * * If the blocks in questions were delalloc blocks, set * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting * variables are updated after the blocks have been allocated. */ map.m_lblk = next; map.m_len = max_blocks; /* * We're in delalloc path and it is possible that we're going to * need more metadata blocks than previously reserved. However * we must not fail because we're in writeback and there is * nothing we can do about it so it might result in data loss. * So use reserved blocks to allocate metadata if possible. */ get_blocks_flags = EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL; if (ext4_should_dioread_nolock(mpd->inode)) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; if (mpd->b_state & (1 << BH_Delay)) get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags); if (blks < 0) { struct super_block *sb = mpd->inode->i_sb; err = blks; /* * If get block returns EAGAIN or ENOSPC and there * appears to be free blocks we will just let * mpage_da_submit_io() unlock all of the pages. */ if (err == -EAGAIN) goto submit_io; if (err == -ENOSPC && ext4_count_free_clusters(sb)) { mpd->retval = err; goto submit_io; } /* * get block failure will cause us to loop in * writepages, because a_ops->writepage won't be able * to make progress. The page will be redirtied by * writepage and writepages will again try to write * the same. */ if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) { ext4_msg(sb, KERN_CRIT, "delayed block allocation failed for inode %lu " "at logical offset %llu with max blocks %zd " "with error %d", mpd->inode->i_ino, (unsigned long long) next, mpd->b_size >> mpd->inode->i_blkbits, err); ext4_msg(sb, KERN_CRIT, "This should not happen!! Data will be lost"); if (err == -ENOSPC) ext4_print_free_blocks(mpd->inode); } /* invalidate all the pages */ ext4_da_block_invalidatepages(mpd); /* Mark this page range as having been completed */ mpd->io_done = 1; return; } BUG_ON(blks == 0); mapp = ↦ if (map.m_flags & EXT4_MAP_NEW) { struct block_device *bdev = mpd->inode->i_sb->s_bdev; int i; for (i = 0; i < map.m_len; i++) unmap_underlying_metadata(bdev, map.m_pblk + i); } /* * Update on-disk size along with block allocation. */ disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits; if (disksize > i_size_read(mpd->inode)) disksize = i_size_read(mpd->inode); if (disksize > EXT4_I(mpd->inode)->i_disksize) { ext4_update_i_disksize(mpd->inode, disksize); err = ext4_mark_inode_dirty(handle, mpd->inode); if (err) ext4_error(mpd->inode->i_sb, "Failed to mark inode %lu dirty", mpd->inode->i_ino); } submit_io: mpage_da_submit_io(mpd, mapp); mpd->io_done = 1; } #define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \ (1 << BH_Delay) | (1 << BH_Unwritten)) /* * mpage_add_bh_to_extent - try to add one more block to extent of blocks * * @mpd->lbh - extent of blocks * @logical - logical number of the block in the file * @b_state - b_state of the buffer head added * * the function is used to collect contig. blocks in same state */ static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, sector_t logical, unsigned long b_state) { sector_t next; int blkbits = mpd->inode->i_blkbits; int nrblocks = mpd->b_size >> blkbits; /* * XXX Don't go larger than mballoc is willing to allocate * This is a stopgap solution. We eventually need to fold * mpage_da_submit_io() into this function and then call * ext4_map_blocks() multiple times in a loop */ if (nrblocks >= (8*1024*1024 >> blkbits)) goto flush_it; /* check if the reserved journal credits might overflow */ if (!ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS)) { if (nrblocks >= EXT4_MAX_TRANS_DATA) { /* * With non-extent format we are limited by the journal * credit available. Total credit needed to insert * nrblocks contiguous blocks is dependent on the * nrblocks. So limit nrblocks. */ goto flush_it; } } /* * First block in the extent */ if (mpd->b_size == 0) { mpd->b_blocknr = logical; mpd->b_size = 1 << blkbits; mpd->b_state = b_state & BH_FLAGS; return; } next = mpd->b_blocknr + nrblocks; /* * Can we merge the block to our big extent? */ if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) { mpd->b_size += 1 << blkbits; return; } flush_it: /* * We couldn't merge the block to our extent, so we * need to flush current extent and start new one */ mpage_da_map_and_submit(mpd); return; } static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) { return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); } /* * This function is grabs code from the very beginning of * ext4_map_blocks, but assumes that the caller is from delayed write * time. This function looks up the requested blocks and sets the * buffer delay bit under the protection of i_data_sem. */ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, struct ext4_map_blocks *map, struct buffer_head *bh) { struct extent_status es; int retval; sector_t invalid_block = ~((sector_t) 0xffff); #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) invalid_block = ~0; map->m_flags = 0; ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u," "logical block %lu\n", inode->i_ino, map->m_len, (unsigned long) map->m_lblk); /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, &es)) { if (ext4_es_is_hole(&es)) { retval = 0; down_read((&EXT4_I(inode)->i_data_sem)); goto add_delayed; } /* * Delayed extent could be allocated by fallocate. * So we need to check it. */ if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); return 0; } map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk; retval = es.es_len - (iblock - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; if (ext4_es_is_written(&es)) map->m_flags |= EXT4_MAP_MAPPED; else if (ext4_es_is_unwritten(&es)) map->m_flags |= EXT4_MAP_UNWRITTEN; else BUG_ON(1); #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0); #endif return retval; } /* * Try to see if we can get the block without requesting a new * file system block. */ down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_has_inline_data(inode)) { /* * We will soon create blocks for this page, and let * us pretend as if the blocks aren't allocated yet. * In case of clusters, we have to handle the work * of mapping from cluster so that the reserved space * is calculated properly. */ if ((EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) && ext4_find_delalloc_cluster(inode, map->m_lblk)) map->m_flags |= EXT4_MAP_FROM_CLUSTER; retval = 0; } else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) retval = ext4_ext_map_blocks(NULL, inode, map, EXT4_GET_BLOCKS_NO_PUT_HOLE); else retval = ext4_ind_map_blocks(NULL, inode, map, EXT4_GET_BLOCKS_NO_PUT_HOLE); add_delayed: if (retval == 0) { int ret; /* * XXX: __block_prepare_write() unmaps passed block, * is it OK? */ /* * If the block was allocated from previously allocated cluster, * then we don't need to reserve it again. However we still need * to reserve metadata for every block we're going to write. */ if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) { ret = ext4_da_reserve_space(inode, iblock); if (ret) { /* not enough space to reserve */ retval = ret; goto out_unlock; } } else { ret = ext4_da_reserve_metadata(inode, iblock); if (ret) { /* not enough space to reserve */ retval = ret; goto out_unlock; } } ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, ~0, EXTENT_STATUS_DELAYED); if (ret) { retval = ret; goto out_unlock; } /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served * and it should not appear on the bh->b_state. */ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); } else if (retval > 0) { int ret; unsigned long long status; #ifdef ES_AGGRESSIVE_TEST if (retval != map->m_len) { printk("ES len assertation failed for inode: %lu " "retval %d != map->m_len %d " "in %s (lookup)\n", inode->i_ino, retval, map->m_len, __func__); } #endif status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); if (ret != 0) retval = ret; } out_unlock: up_read((&EXT4_I(inode)->i_data_sem)); return retval; } /* * This is a special get_blocks_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or * reserve space for a single block. * * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. * We also have b_blocknr = -1 and b_bdev initialized properly * * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev * initialized properly. */ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { struct ext4_map_blocks map; int ret = 0; BUG_ON(create == 0); BUG_ON(bh->b_size != inode->i_sb->s_blocksize); map.m_lblk = iblock; map.m_len = 1; /* * first, we need to know whether the block is allocated already * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ ret = ext4_da_map_blocks(inode, iblock, &map, bh); if (ret <= 0) return ret; map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked * new and mapped. Mapped ensures that we don't do * get_block multiple times when we write to the same * offset and new ensures that we do proper zero out * for partial write. */ set_buffer_new(bh); set_buffer_mapped(bh); } return 0; } static int bget_one(handle_t *handle, struct buffer_head *bh) { get_bh(bh); return 0; } static int bput_one(handle_t *handle, struct buffer_head *bh) { put_bh(bh); return 0; } static int __ext4_journalled_writepage(struct page *page, unsigned int len) { struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; struct buffer_head *page_bufs = NULL; handle_t *handle = NULL; int ret = 0, err = 0; int inline_data = ext4_has_inline_data(inode); struct buffer_head *inode_bh = NULL; ClearPageChecked(page); if (inline_data) { BUG_ON(page->index != 0); BUG_ON(len > ext4_get_max_inline_size(inode)); inode_bh = ext4_journalled_write_inline_data(inode, len, page); if (inode_bh == NULL) goto out; } else { page_bufs = page_buffers(page); if (!page_bufs) { BUG(); goto out; } ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); } /* As soon as we unlock the page, it can go away, but we have * references to buffers so we are safe */ unlock_page(page); handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, ext4_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } BUG_ON(!ext4_handle_valid(handle)); if (inline_data) { ret = ext4_journal_get_write_access(handle, inode_bh); err = ext4_handle_dirty_metadata(handle, inode, inode_bh); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); err = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, write_end_fn); } if (ret == 0) ret = err; EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; err = ext4_journal_stop(handle); if (!ret) ret = err; if (!ext4_has_inline_data(inode)) ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: brelse(inode_bh); return ret; } /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't * need to file the inode to the transaction's list in ordered mode because if * we are writing back data added by write(), the inode is already there and if * we are writing back data modified via mmap(), no one guarantees in which * transaction the data will hit the disk. In case we are journaling data, we * cannot start transaction directly because transaction start ranks above page * lock so we have to do some magic. * * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with * multiple blocks we need to write those buffer_heads that are mapped. This * is important for mmaped based write. So if we do with blocksize 1K * truncate(f, 1024); * a = mmap(f, 0, 4096); * a[0] = 'a'; * truncate(f, 4096); * we have in the page first buffer_head mapped via page_mkwrite call back * but other buffer_heads would be unmapped but dirty (dirty done via the * do_wp_page). So writepage should write the first block. If we modify * the mmap area beyond 1024 we will again get a page_fault and the * page_mkwrite callback will do the block allocation and mark the * buffer_heads mapped. * * We redirty the page if we have any buffer_heads that is either delay or * unwritten in the page. * * We can get recursively called as show below. * * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> * ext4_writepage() * * But since we don't do any block allocation we should not deadlock. * Page also have the dirty flag cleared so we don't get recurive page_lock. */ static int ext4_writepage(struct page *page, struct writeback_control *wbc) { int ret = 0; loff_t size; unsigned int len; struct buffer_head *page_bufs = NULL; struct inode *inode = page->mapping->host; struct ext4_io_submit io_submit; trace_ext4_writepage(page); size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; else len = PAGE_CACHE_SIZE; page_bufs = page_buffers(page); /* * We cannot do block allocation or other extent handling in this * function. If there are buffers needing that, we have to redirty * the page. But we may reach here when we do a journal commit via * journal_submit_inode_data_buffers() and in that case we must write * allocated buffers to achieve data=ordered mode guarantees. */ if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); if (current->flags & PF_MEMALLOC) { /* * For memory cleaning there's no point in writing only * some buffers. So just bail out. Warn if we came here * from direct reclaim. */ WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC); unlock_page(page); return 0; } } if (PageChecked(page) && ext4_should_journal_data(inode)) /* * It's mmapped pagecache. Add buffers and journal it. There * doesn't seem much point in redir