hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9DN5Z CVE: NA
--------------------------------
Implement the buffered writeback iomap path, including the map_blocks() and the prepare_ioend() callback in iomap_writeback_ops and the corresponding end io path. Add ext4_iomap_map_blocks() to dirty map status before writeback, start journal handle and allocate new blocks if it's not been allocated. Add ext4_iomap_prepare_ioend() to register the end io handler of converting unwritten extents to mapped extents.
Note that current iomap call iomap_do_writepage() to write back dirty folios one by one, but we can't map or allocate block(s) for dirty folio one by one because it's expensive if folio size is small. In order to reduce the number of blocks mapping times, we can calculate the length through wbc->range_end carefully and map an entire delayed extent on the first call.
Besides, since we always allocate unwritten extents for the new allocated blocks, there are other 4 processes are different from the buffered_head writeback path, which could be more simple.
1. We have to allow splitting extents in endio during the unwritten to written conversion. 2. We don't need to write back the data before the metadata, there is no risk of exposing stale data, the data=ordered journal mode becomes useless. So we don't need to attach data to the jinode, and the journal thread doesn't need to write data. 3. Since data=ordered is not used, we don't need to reserve journal credits and use reserved handle for the extent status conversion. 4. We can postpone the i_disksize updating to endio path.
Signed-off-by: Zhang Yi yi.zhang@huawei.com --- fs/ext4/ext4.h | 4 + fs/ext4/ext4_jbd2.c | 6 ++ fs/ext4/extents.c | 23 +++--- fs/ext4/inode.c | 190 +++++++++++++++++++++++++++++++++++++++++++- fs/ext4/page-io.c | 107 +++++++++++++++++++++++++ fs/ext4/super.c | 2 + 6 files changed, 322 insertions(+), 10 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 04a38d548fac..c4ac78cbb212 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1148,6 +1148,8 @@ struct ext4_inode_info { */ struct list_head i_rsv_conversion_list; struct work_struct i_rsv_conversion_work; + struct list_head i_iomap_ioend_list; + struct work_struct i_iomap_ioend_work; atomic_t i_unwritten; /* Nr. of inflight conversions pending */
spinlock_t i_block_reservation_lock; @@ -3755,6 +3757,8 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page, size_t len); extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end); extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end); +extern void ext4_iomap_end_io(struct work_struct *work); +extern void ext4_iomap_end_bio(struct bio *bio);
/* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index d1a2e6624401..94c8073b49e7 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -11,6 +11,12 @@ int ext4_inode_journal_mode(struct inode *inode) { if (EXT4_JOURNAL(inode) == NULL) return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ + /* + * Ordered mode is no longer needed for the inode that use the + * iomap path, always use writeback mode. + */ + if (ext4_test_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP)) + return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ /* We do not support data journalling with delayed allocation */ if (!S_ISREG(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a3eb1465d3c2..caa718d5f5c4 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3719,18 +3719,23 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len);
- /* If extent is larger than requested it is a clear sign that we still - * have some extent state machine issues left. So extent_split is still - * required. - * TODO: Once all related issues will be fixed this situation should be - * illegal. + /* + * For the inodes that use the buffered iomap path need to split + * extents in endio, other inodes not. + * + * TODO: Reserve enough sapce for splitting extents, always split + * extents here, and totally remove this warning. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { #ifdef CONFIG_EXT4_DEBUG - ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," - " len %u; IO logical block %llu, len %u", - inode->i_ino, (unsigned long long)ee_block, ee_len, - (unsigned long long)map->m_lblk, map->m_len); + if (!ext4_test_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP)) { + ext4_warning(inode->i_sb, + "Inode (%ld) finished: extent logical block %llu, " + "len %u; IO logical block %llu, len %u", + inode->i_ino, (unsigned long long)ee_block, + ee_len, (unsigned long long)map->m_lblk, + map->m_len); + } #endif err = ext4_split_convert_extents(handle, inode, map, ppath, EXT4_GET_BLOCKS_CONVERT | diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 055f8f7f2c6a..6c960e0eb553 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -43,6 +43,7 @@ #include <linux/iversion.h>
#include "ext4_jbd2.h" +#include "ext4_extents.h" #include "xattr.h" #include "acl.h" #include "truncate.h" @@ -3752,10 +3753,197 @@ static void ext4_iomap_readahead(struct readahead_control *rac) iomap_readahead(rac, &ext4_iomap_buffered_read_ops); }
+struct ext4_writeback_ctx { + struct iomap_writepage_ctx ctx; + struct writeback_control *wbc; + unsigned int data_seq; +}; + +static int ext4_iomap_map_one_extent(struct inode *inode, + struct ext4_map_blocks *map) +{ + struct extent_status es; + handle_t *handle = NULL; + int credits, map_flags; + int retval; + + credits = ext4_da_writepages_trans_blocks(inode); + handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + map->m_flags = 0; + /* + * In order to protect from the race of truncate, we have to lookup + * extent stats and map blocks under i_data_sem, otherwise the + * delalloc extent could be stale. + */ + down_write(&EXT4_I(inode)->i_data_sem); + if (likely(ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es))) { + retval = es.es_len - (map->m_lblk - es.es_lblk); + map->m_len = min_t(unsigned int, retval, map->m_len); + + if (likely(ext4_es_is_delonly(&es))) { + trace_ext4_da_write_pages_extent(inode, map); + /* + * Call ext4_map_create_blocks() to allocate any delayed + * allocation blocks. It is possible that we're going to + * need more metadata blocks, however we must not fail + * because we're in writeback and there is nothing we + * can do so it might result in data loss. So use + * reserved blocks to allocate metadata if possible. + * + * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE + * indicates that the blocks and quotas has already been + * checked when the data was copied into the page cache. + */ + map_flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT | + EXT4_GET_BLOCKS_METADATA_NOFAIL | + EXT4_GET_BLOCKS_DELALLOC_RESERVE; + + retval = ext4_map_create_blocks(handle, inode, map, + map_flags); + } + 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; + } + } else { + retval = ext4_map_query_blocks(handle, inode, map); + } + + up_write(&EXT4_I(inode)->i_data_sem); + ext4_journal_stop(handle); + return retval < 0 ? retval : 0; +} + +static int ext4_iomap_map_blocks(struct iomap_writepage_ctx *wpc, + struct inode *inode, loff_t offset, + unsigned int dirty_len) +{ + struct ext4_writeback_ctx *ewpc = + container_of(wpc, struct ext4_writeback_ctx, ctx); + struct super_block *sb = inode->i_sb; + struct journal_s *journal = EXT4_SB(sb)->s_journal; + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_map_blocks map; + unsigned int blkbits = inode->i_blkbits; + unsigned int index = offset >> blkbits; + unsigned int end, len; + int ret; + + if (unlikely(ext4_forced_shutdown(inode->i_sb))) + return -EIO; + + /* Check validity of the cached writeback mapping. */ + if (offset >= wpc->iomap.offset && + offset < wpc->iomap.offset + wpc->iomap.length && + ewpc->data_seq == READ_ONCE(ei->i_es_seq)) + return 0; + + end = min_t(unsigned int, + (ewpc->wbc->range_end >> blkbits), (UINT_MAX - 1)); + len = (end > index + dirty_len) ? end - index + 1 : dirty_len; + +retry: + map.m_lblk = index; + map.m_len = min_t(unsigned int, MAX_WRITEPAGES_EXTENT_LEN, len); + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; + + /* + * The map isn't a delalloc extent, it must be a hole or have + * already been allocated. + */ + if (!(map.m_flags & EXT4_MAP_DELAYED)) + goto out; + + /* Map one delalloc extent. */ + ret = ext4_iomap_map_one_extent(inode, &map); + if (ret < 0) { + if (ext4_forced_shutdown(sb)) + return ret; + + /* + * Retry transient ENOSPC errors, if + * ext4_count_free_blocks() is non-zero, a commit + * should free up blocks. + */ + if (ret == -ENOSPC && ext4_count_free_clusters(sb)) { + jbd2_journal_force_commit_nested(journal); + goto retry; + } + + ext4_msg(sb, KERN_CRIT, + "Delayed block allocation failed for " + "inode %lu at logical offset %llu with " + "max blocks %u with error %d", + inode->i_ino, (unsigned long long)map.m_lblk, + (unsigned int)map.m_len, -ret); + ext4_msg(sb, KERN_CRIT, + "This should not happen!! Data will " + "be lost\n"); + if (ret == -ENOSPC) + ext4_print_free_blocks(inode); + return ret; + } +out: + ewpc->data_seq = READ_ONCE(ei->i_es_seq); + ext4_set_iomap(inode, &wpc->iomap, &map, offset, + map.m_len << blkbits, 0); + return 0; +} + +static int ext4_iomap_prepare_ioend(struct iomap_ioend *ioend, int status) +{ + struct ext4_inode_info *ei = EXT4_I(ioend->io_inode); + + /* Need to convert unwritten extents when I/Os are completed. */ + if (ioend->io_type == IOMAP_UNWRITTEN || + ioend->io_offset + ioend->io_size > READ_ONCE(ei->i_disksize)) + ioend->io_bio.bi_end_io = ext4_iomap_end_bio; + + return status; +} + +static void ext4_iomap_discard_folio(struct folio *folio, loff_t pos) +{ + struct inode *inode = folio->mapping->host; + + ext4_iomap_punch_delalloc(inode, pos, + folio_pos(folio) + folio_size(folio) - pos); +} + +static const struct iomap_writeback_ops ext4_writeback_ops = { + .map_blocks = ext4_iomap_map_blocks, + .prepare_ioend = ext4_iomap_prepare_ioend, + .discard_folio = ext4_iomap_discard_folio, +}; + static int ext4_iomap_writepages(struct address_space *mapping, struct writeback_control *wbc) { - return 0; + struct inode *inode = mapping->host; + struct super_block *sb = inode->i_sb; + long nr = wbc->nr_to_write; + int alloc_ctx, ret; + struct ext4_writeback_ctx ewpc = { + .wbc = wbc, + }; + + if (unlikely(ext4_forced_shutdown(sb))) + return -EIO; + + alloc_ctx = ext4_writepages_down_read(sb); + trace_ext4_writepages(inode, wbc); + ret = iomap_writepages(mapping, wbc, &ewpc.ctx, &ext4_writeback_ops); + trace_ext4_writepages_result(inode, wbc, ret, nr - wbc->nr_to_write); + ext4_writepages_up_read(sb, alloc_ctx); + + return ret; }
/* diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index dfdd7e5cf038..a499208500e4 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -22,6 +22,7 @@ #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/kernel.h> +#include <linux/iomap.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/sched/mm.h> @@ -565,3 +566,109 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
return 0; } + +static void ext4_iomap_finish_ioend(struct iomap_ioend *ioend) +{ + struct inode *inode = ioend->io_inode; + struct ext4_inode_info *ei = EXT4_I(inode); + loff_t pos = ioend->io_offset; + size_t size = ioend->io_size; + loff_t new_disksize; + handle_t *handle; + int credits; + int ret, err; + + ret = blk_status_to_errno(ioend->io_bio.bi_status); + if (unlikely(ret)) + goto out; + + /* + * We may need to convert up to one extent per block in + * the page and we may dirty the inode. + */ + credits = ext4_chunk_trans_blocks(inode, + EXT4_MAX_BLOCKS(size, pos, inode->i_blkbits)); + handle = ext4_journal_start(inode, EXT4_HT_EXT_CONVERT, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_err; + } + + if (ioend->io_type == IOMAP_UNWRITTEN) { + ret = ext4_convert_unwritten_extents(handle, inode, pos, size); + if (ret) + goto out_journal; + } + + /* + * Update on-disk size after IO is completed. Races with + * truncate are avoided by checking i_size under i_data_sem. + */ + new_disksize = pos + size; + if (new_disksize > READ_ONCE(ei->i_disksize)) { + down_write(&ei->i_data_sem); + new_disksize = min(new_disksize, i_size_read(inode)); + if (new_disksize > ei->i_disksize) + ei->i_disksize = new_disksize; + up_write(&ei->i_data_sem); + ret = ext4_mark_inode_dirty(handle, inode); + if (ret) + EXT4_ERROR_INODE_ERR(inode, -ret, + "Failed to mark inode dirty"); + } + +out_journal: + err = ext4_journal_stop(handle); + if (!ret) + ret = err; +out_err: + if (ret < 0 && !ext4_forced_shutdown(inode->i_sb)) { + ext4_msg(inode->i_sb, KERN_EMERG, + "failed to convert unwritten extents to " + "written extents or update inode size -- " + "potential data loss! (inode %lu, error %d)", + inode->i_ino, ret); + } +out: + iomap_finish_ioends(ioend, ret); +} + +/* + * Work on buffered iomap completed IO, to convert unwritten extents to + * mapped extents + */ +void ext4_iomap_end_io(struct work_struct *work) +{ + struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info, + i_iomap_ioend_work); + struct iomap_ioend *ioend; + struct list_head ioend_list; + unsigned long flags; + + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + list_replace_init(&ei->i_iomap_ioend_list, &ioend_list); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + + iomap_sort_ioends(&ioend_list); + while (!list_empty(&ioend_list)) { + ioend = list_entry(ioend_list.next, struct iomap_ioend, io_list); + list_del_init(&ioend->io_list); + iomap_ioend_try_merge(ioend, &ioend_list); + ext4_iomap_finish_ioend(ioend); + } +} + +void ext4_iomap_end_bio(struct bio *bio) +{ + struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); + struct ext4_inode_info *ei = EXT4_I(ioend->io_inode); + struct ext4_sb_info *sbi = EXT4_SB(ioend->io_inode->i_sb); + unsigned long flags; + + /* Only reserved conversions from writeback should enter here */ + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + if (list_empty(&ei->i_iomap_ioend_list)) + queue_work(sbi->rsv_conversion_wq, &ei->i_iomap_ioend_work); + list_add_tail(&ioend->io_list, &ei->i_iomap_ioend_list); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); +} diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 3ee144386292..799e06b5e574 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1484,11 +1484,13 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); + INIT_LIST_HEAD(&ei->i_iomap_ioend_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_unwritten, 0); INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); + INIT_WORK(&ei->i_iomap_ioend_work, ext4_iomap_end_io); ext4_fc_init_inode(&ei->vfs_inode); mutex_init(&ei->i_fc_lock); return &ei->vfs_inode;