+ * the function goes through all passed space and put actual disk
+ * block numbers into buffer heads, dropping BH_Delay
+ */
+static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
+ struct buffer_head *exbh)
+{
+ struct inode *inode = mpd->inode;
+ struct address_space *mapping = inode->i_mapping;
+ int blocks = exbh->b_size >> inode->i_blkbits;
+ sector_t pblock = exbh->b_blocknr, cur_logical;
+ struct buffer_head *head, *bh;
+ pgoff_t index, end;
+ struct pagevec pvec;
+ int nr_pages, i;
+
+ index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (logical + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+
+ while (index <= end) {
+ /* XXX: optimize tail */
+ 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];
+
+ index = page->index;
+ if (index > end)
+ break;
+ index++;
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(PageWriteback(page));
+ BUG_ON(!page_has_buffers(page));
+
+ bh = page_buffers(page);
+ head = bh;
+
+ /* skip blocks out of the range */
+ do {
+ if (cur_logical >= logical)
+ break;
+ cur_logical++;
+ } while ((bh = bh->b_this_page) != head);
+
+ do {
+ if (cur_logical >= logical + blocks)
+ break;
+ if (buffer_delay(bh)) {
+ bh->b_blocknr = pblock;
+ clear_buffer_delay(bh);
+ bh->b_bdev = inode->i_sb->s_bdev;
+ } else if (buffer_unwritten(bh)) {
+ bh->b_blocknr = pblock;
+ clear_buffer_unwritten(bh);
+ set_buffer_mapped(bh);
+ set_buffer_new(bh);
+ bh->b_bdev = inode->i_sb->s_bdev;
+ } else if (buffer_mapped(bh))
+ BUG_ON(bh->b_blocknr != pblock);
+
+ cur_logical++;
+ pblock++;
+ } while ((bh = bh->b_this_page) != head);
+ }
+ pagevec_release(&pvec);
+ }
+}
+
+
+/*
+ * __unmap_underlying_blocks - just a helper function to unmap
+ * set of blocks described by @bh
+ */
+static inline void __unmap_underlying_blocks(struct inode *inode,
+ struct buffer_head *bh)
+{
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ int blocks, i;
+
+ blocks = bh->b_size >> inode->i_blkbits;
+ for (i = 0; i < blocks; i++)
+ unmap_underlying_metadata(bdev, bh->b_blocknr + i);
+}
+
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
+ sector_t logical, long blk_cnt)
+{
+ int nr_pages, i;
+ pgoff_t index, end;
+ struct pagevec pvec;
+ struct inode *inode = mpd->inode;
+ struct address_space *mapping = inode->i_mapping;
+
+ index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (logical + blk_cnt - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ 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];
+ index = page->index;
+ if (index > end)
+ break;
+ index++;
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(PageWriteback(page));
+ block_invalidatepage(page, 0);
+ ClearPageUptodate(page);
+ unlock_page(page);
+ }
+ }
+ return;
+}
+
+static void ext4_print_free_blocks(struct inode *inode)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ printk(KERN_EMERG "Total free blocks count %lld\n",
+ ext4_count_free_blocks(inode->i_sb));
+ printk(KERN_EMERG "Free/Dirty block details\n");
+ printk(KERN_EMERG "free_blocks=%lld\n",
+ (long long)percpu_counter_sum(&sbi->s_freeblocks_counter));
+ printk(KERN_EMERG "dirty_blocks=%lld\n",
+ (long long)percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ printk(KERN_EMERG "Block reservation details\n");
+ printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+ EXT4_I(inode)->i_reserved_data_blocks);
+ printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+ EXT4_I(inode)->i_reserved_meta_blocks);
+ return;
+}
+
+/*
+ * mpage_da_map_blocks - go through given space
+ *
+ * @mpd->lbh - bh describing space
+ * @mpd->get_block - the filesystem's block mapper function
+ *
+ * The function skips space we know is already mapped to disk blocks.
+ *
+ */
+static int mpage_da_map_blocks(struct mpage_da_data *mpd)
+{
+ int err = 0;
+ struct buffer_head new;
+ struct buffer_head *lbh = &mpd->lbh;
+ sector_t next;
+
+ /*
+ * We consider only non-mapped and non-allocated blocks
+ */
+ if (buffer_mapped(lbh) && !buffer_delay(lbh))
+ return 0;
+ new.b_state = lbh->b_state;
+ new.b_blocknr = 0;
+ new.b_size = lbh->b_size;
+ next = lbh->b_blocknr;
+ /*
+ * If we didn't accumulate anything
+ * to write simply return
+ */
+ if (!new.b_size)
+ return 0;
+ err = mpd->get_block(mpd->inode, next, &new, 1);
+ if (err) {
+
+ /* If get block returns with error
+ * we simply return. Later writepage
+ * will redirty the page and writepages
+ * will find the dirty page again
+ */
+ if (err == -EAGAIN)
+ return 0;
+
+ if (err == -ENOSPC &&
+ ext4_count_free_blocks(mpd->inode->i_sb)) {
+ mpd->retval = err;
+ return 0;
+ }
+
+ /*
+ * 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.
+ */
+ printk(KERN_EMERG "%s block allocation failed for inode %lu "
+ "at logical offset %llu with max blocks "
+ "%zd with error %d\n",
+ __func__, mpd->inode->i_ino,
+ (unsigned long long)next,
+ lbh->b_size >> mpd->inode->i_blkbits, err);
+ printk(KERN_EMERG "This should not happen.!! "
+ "Data will be lost\n");
+ if (err == -ENOSPC) {
+ ext4_print_free_blocks(mpd->inode);
+ }
+ /* invlaidate all the pages */
+ ext4_da_block_invalidatepages(mpd, next,
+ lbh->b_size >> mpd->inode->i_blkbits);
+ return err;
+ }
+ BUG_ON(new.b_size == 0);
+
+ if (buffer_new(&new))
+ __unmap_underlying_blocks(mpd->inode, &new);
+
+ /*
+ * If blocks are delayed marked, we need to
+ * put actual blocknr and drop delayed bit
+ */
+ if (buffer_delay(lbh) || buffer_unwritten(lbh))
+ mpage_put_bnr_to_bhs(mpd, next, &new);
+
+ return 0;
+}
+
+#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
+ * @bh - bh of the block (used to access block's state)
+ *
+ * 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, struct buffer_head *bh)
+{
+ sector_t next;
+ size_t b_size = bh->b_size;
+ struct buffer_head *lbh = &mpd->lbh;
+ int nrblocks = lbh->b_size >> mpd->inode->i_blkbits;
+
+ /* check if thereserved journal credits might overflow */
+ if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
+ 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;
+ } else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) >
+ EXT4_MAX_TRANS_DATA) {
+ /*
+ * Adding the new buffer_head would make it cross the
+ * allowed limit for which we have journal credit
+ * reserved. So limit the new bh->b_size
+ */
+ b_size = (EXT4_MAX_TRANS_DATA - nrblocks) <<
+ mpd->inode->i_blkbits;
+ /* we will do mpage_da_submit_io in the next loop */
+ }
+ }
+ /*
+ * First block in the extent
+ */
+ if (lbh->b_size == 0) {
+ lbh->b_blocknr = logical;
+ lbh->b_size = b_size;
+ lbh->b_state = bh->b_state & BH_FLAGS;
+ return;
+ }
+
+ next = lbh->b_blocknr + nrblocks;
+ /*
+ * Can we merge the block to our big extent?
+ */
+ if (logical == next && (bh->b_state & BH_FLAGS) == lbh->b_state) {
+ lbh->b_size += b_size;
+ return;
+ }
+
+flush_it:
+ /*
+ * We couldn't merge the block to our extent, so we
+ * need to flush current extent and start new one
+ */
+ if (mpage_da_map_blocks(mpd) == 0)
+ mpage_da_submit_io(mpd);
+ mpd->io_done = 1;
+ return;
+}
+
+/*
+ * __mpage_da_writepage - finds extent of pages and blocks
+ *
+ * @page: page to consider
+ * @wbc: not used, we just follow rules
+ * @data: context
+ *
+ * The function finds extents of pages and scan them for all blocks.
+ */
+static int __mpage_da_writepage(struct page *page,
+ struct writeback_control *wbc, void *data)
+{
+ struct mpage_da_data *mpd = data;
+ struct inode *inode = mpd->inode;
+ struct buffer_head *bh, *head, fake;
+ sector_t logical;
+
+ if (mpd->io_done) {
+ /*
+ * Rest of the page in the page_vec
+ * redirty then and skip then. We will
+ * try to to write them again after
+ * starting a new transaction
+ */
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return MPAGE_DA_EXTENT_TAIL;
+ }
+ /*
+ * Can we merge this page to current extent?
+ */
+ if (mpd->next_page != page->index) {
+ /*
+ * Nope, we can't. So, we map non-allocated blocks
+ * and start IO on them using writepage()
+ */
+ if (mpd->next_page != mpd->first_page) {
+ if (mpage_da_map_blocks(mpd) == 0)
+ mpage_da_submit_io(mpd);
+ /*
+ * skip rest of the page in the page_vec
+ */
+ mpd->io_done = 1;
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return MPAGE_DA_EXTENT_TAIL;
+ }
+
+ /*
+ * Start next extent of pages ...
+ */
+ mpd->first_page = page->index;
+
+ /*
+ * ... and blocks
+ */
+ mpd->lbh.b_size = 0;
+ mpd->lbh.b_state = 0;
+ mpd->lbh.b_blocknr = 0;
+ }
+
+ mpd->next_page = page->index + 1;
+ logical = (sector_t) page->index <<
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ if (!page_has_buffers(page)) {
+ /*
+ * There is no attached buffer heads yet (mmap?)
+ * we treat the page asfull of dirty blocks
+ */
+ bh = &fake;
+ bh->b_size = PAGE_CACHE_SIZE;
+ bh->b_state = 0;
+ set_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ mpage_add_bh_to_extent(mpd, logical, bh);
+ if (mpd->io_done)
+ return MPAGE_DA_EXTENT_TAIL;
+ } else {
+ /*
+ * Page with regular buffer heads, just add all dirty ones
+ */
+ head = page_buffers(page);
+ bh = head;
+ do {
+ BUG_ON(buffer_locked(bh));
+ if (buffer_dirty(bh) &&
+ (!buffer_mapped(bh) || buffer_delay(bh))) {
+ mpage_add_bh_to_extent(mpd, logical, bh);
+ if (mpd->io_done)
+ return MPAGE_DA_EXTENT_TAIL;
+ }
+ logical++;
+ } while ((bh = bh->b_this_page) != head);
+ }
+
+ return 0;
+}
+
+/*
+ * mpage_da_writepages - walk the list of dirty pages of the given
+ * address space, allocates non-allocated blocks, maps newly-allocated
+ * blocks to existing bhs and issue IO them
+ *
+ * @mapping: address space structure to write
+ * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ * @get_block: the filesystem's block mapper function.
+ *
+ * This is a library function, which implements the writepages()
+ * address_space_operation.
+ */
+static int mpage_da_writepages(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct mpage_da_data *mpd)
+{
+ int ret;
+
+ if (!mpd->get_block)
+ return generic_writepages(mapping, wbc);
+
+ mpd->lbh.b_size = 0;
+ mpd->lbh.b_state = 0;
+ mpd->lbh.b_blocknr = 0;
+ mpd->first_page = 0;
+ mpd->next_page = 0;
+ mpd->io_done = 0;
+ mpd->pages_written = 0;
+ mpd->retval = 0;
+
+ ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
+ /*
+ * Handle last extent of pages
+ */
+ if (!mpd->io_done && mpd->next_page != mpd->first_page) {
+ if (mpage_da_map_blocks(mpd) == 0)
+ mpage_da_submit_io(mpd);
+
+ mpd->io_done = 1;
+ ret = MPAGE_DA_EXTENT_TAIL;
+ }
+ wbc->nr_to_write -= mpd->pages_written;
+ return ret;
+}
+
+/*
+ * this is a special callback for ->write_begin() only
+ * it's intention is to return mapped block or reserve space
+ */
+static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret = 0;
+
+ BUG_ON(create == 0);
+ BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+
+ /*
+ * 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_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0);
+ if ((ret == 0) && !buffer_delay(bh_result)) {
+ /* the block isn't (pre)allocated yet, let's reserve space */
+ /*
+ * XXX: __block_prepare_write() unmaps passed block,
+ * is it OK?
+ */
+ ret = ext4_da_reserve_space(inode, 1);
+ if (ret)
+ /* not enough space to reserve */
+ return ret;
+
+ map_bh(bh_result, inode->i_sb, 0);
+ set_buffer_new(bh_result);
+ set_buffer_delay(bh_result);
+ } else if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+
+ return ret;
+}
+#define EXT4_DELALLOC_RSVED 1
+static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+ loff_t disksize = EXT4_I(inode)->i_disksize;
+ handle_t *handle = NULL;
+
+ handle = ext4_journal_current_handle();
+ BUG_ON(!handle);
+ ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
+ bh_result, create, 0, EXT4_DELALLOC_RSVED);
+ if (ret > 0) {
+
+ bh_result->b_size = (ret << inode->i_blkbits);
+
+ if (ext4_should_order_data(inode)) {
+ int retval;
+ retval = ext4_jbd2_file_inode(handle, inode);
+ if (retval)
+ /*
+ * Failed to add inode for ordered
+ * mode. Don't update file size
+ */
+ return retval;
+ }
+
+ /*
+ * Update on-disk size along with block allocation
+ * we don't use 'extend_disksize' as size may change
+ * within already allocated block -bzzz
+ */
+ disksize = ((loff_t) iblock + ret) << inode->i_blkbits;
+ if (disksize > i_size_read(inode))
+ disksize = i_size_read(inode);
+ if (disksize > EXT4_I(inode)->i_disksize) {
+ ext4_update_i_disksize(inode, disksize);
+ ret = ext4_mark_inode_dirty(handle, inode);
+ return ret;
+ }
+ ret = 0;
+ }
+ return ret;
+}
+
+static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+{
+ /*
+ * unmapped buffer is possible for holes.
+ * delay buffer is possible with delayed allocation
+ */
+ return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh));
+}
+
+static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ int ret = 0;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+
+ /*
+ * we don't want to do block allocation in writepage
+ * so call get_block_wrap with create = 0
+ */
+ ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks,
+ bh_result, 0, 0, 0);
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+ return ret;
+}
+
+/*
+ * get called vi ext4_da_writepages after taking page lock (have journal handle)
+ * get called via journal_submit_inode_data_buffers (no journal handle)
+ * get called via shrink_page_list via pdflush (no journal handle)
+ * or grab_page_cache when doing write_begin (have journal handle)
+ */
+static int ext4_da_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ int ret = 0;
+ loff_t size;
+ unsigned long len;
+ struct buffer_head *page_bufs;
+ struct inode *inode = page->mapping->host;
+
+ size = i_size_read(inode);
+ if (page->index == size >> PAGE_CACHE_SHIFT)
+ len = size & ~PAGE_CACHE_MASK;
+ else
+ len = PAGE_CACHE_SIZE;
+
+ if (page_has_buffers(page)) {
+ page_bufs = page_buffers(page);
+ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+ ext4_bh_unmapped_or_delay)) {
+ /*
+ * We don't want to do block allocation
+ * So redirty the page and return
+ * We may reach here when we do a journal commit
+ * via journal_submit_inode_data_buffers.
+ * If we don't have mapping block we just ignore
+ * them. We can also reach here via shrink_page_list
+ */
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return 0;
+ }
+ } else {
+ /*
+ * The test for page_has_buffers() is subtle:
+ * We know the page is dirty but it lost buffers. That means
+ * that at some moment in time after write_begin()/write_end()
+ * has been called all buffers have been clean and thus they
+ * must have been written at least once. So they are all
+ * mapped and we can happily proceed with mapping them
+ * and writing the page.
+ *
+ * Try to initialize the buffer_heads and check whether
+ * all are mapped and non delay. We don't want to
+ * do block allocation here.
+ */
+ ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
+ ext4_normal_get_block_write);
+ if (!ret) {
+ page_bufs = page_buffers(page);
+ /* check whether all are mapped and non delay */
+ if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+ ext4_bh_unmapped_or_delay)) {
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return 0;
+ }
+ } else {
+ /*
+ * We can't do block allocation here
+ * so just redity the page and unlock
+ * and return
+ */
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return 0;
+ }
+ /* now mark the buffer_heads as dirty and uptodate */
+ block_commit_write(page, 0, PAGE_CACHE_SIZE);
+ }
+
+ if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
+ ret = nobh_writepage(page, ext4_normal_get_block_write, wbc);
+ else
+ ret = block_write_full_page(page,
+ ext4_normal_get_block_write,
+ wbc);
+
+ return ret;
+}
+
+/*
+ * This is called via ext4_da_writepages() to
+ * calulate the total number of credits to reserve to fit
+ * a single extent allocation into a single transaction,
+ * ext4_da_writpeages() will loop calling this before
+ * the block allocation.
+ */
+
+static int ext4_da_writepages_trans_blocks(struct inode *inode)
+{
+ int max_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+
+ /*
+ * With non-extent format the journal credit needed to
+ * insert nrblocks contiguous block is dependent on
+ * number of contiguous block. So we will limit
+ * number of contiguous block to a sane value
+ */
+ if (!(inode->i_flags & EXT4_EXTENTS_FL) &&
+ (max_blocks > EXT4_MAX_TRANS_DATA))
+ max_blocks = EXT4_MAX_TRANS_DATA;
+
+ return ext4_chunk_trans_blocks(inode, max_blocks);
+}
+
+static int ext4_da_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ pgoff_t index;
+ int range_whole = 0;
+ handle_t *handle = NULL;
+ struct mpage_da_data mpd;
+ struct inode *inode = mapping->host;
+ int no_nrwrite_index_update;
+ long pages_written = 0, pages_skipped;
+ int needed_blocks, ret = 0, nr_to_writebump = 0;
+ struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+
+ /*
+ * No pages to write? This is mainly a kludge to avoid starting
+ * a transaction for special inodes like journal inode on last iput()
+ * because that could violate lock ordering on umount
+ */
+ if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ return 0;
+
+ /*
+ * If the filesystem has aborted, it is read-only, so return
+ * right away instead of dumping stack traces later on that
+ * will obscure the real source of the problem. We test
+ * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+ * the latter could be true if the filesystem is mounted
+ * read-only, and in that case, ext4_da_writepages should
+ * *never* be called, so if that ever happens, we would want
+ * the stack trace.
+ */
+ if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+ return -EROFS;
+
+ /*
+ * Make sure nr_to_write is >= sbi->s_mb_stream_request
+ * This make sure small files blocks are allocated in
+ * single attempt. This ensure that small files
+ * get less fragmented.
+ */
+ if (wbc->nr_to_write < sbi->s_mb_stream_request) {
+ nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
+ wbc->nr_to_write = sbi->s_mb_stream_request;
+ }
+ if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+ range_whole = 1;
+
+ if (wbc->range_cyclic)
+ index = mapping->writeback_index;
+ else
+ index = wbc->range_start >> PAGE_CACHE_SHIFT;
+
+ mpd.wbc = wbc;
+ mpd.inode = mapping->host;
+
+ /*
+ * we don't want write_cache_pages to update
+ * nr_to_write and writeback_index
+ */
+ no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+ wbc->no_nrwrite_index_update = 1;
+ pages_skipped = wbc->pages_skipped;
+
+ while (!ret && wbc->nr_to_write > 0) {
+
+ /*
+ * we insert one extent at a time. So we need
+ * credit needed for single extent allocation.
+ * journalled mode is currently not supported
+ * by delalloc
+ */
+ BUG_ON(ext4_should_journal_data(inode));
+ needed_blocks = ext4_da_writepages_trans_blocks(inode);
+
+ /* start a new transaction*/
+ handle = ext4_journal_start(inode, needed_blocks);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ printk(KERN_CRIT "%s: jbd2_start: "
+ "%ld pages, ino %lu; err %d\n", __func__,
+ wbc->nr_to_write, inode->i_ino, ret);
+ dump_stack();
+ goto out_writepages;
+ }
+ mpd.get_block = ext4_da_get_block_write;
+ ret = mpage_da_writepages(mapping, wbc, &mpd);
+
+ ext4_journal_stop(handle);
+
+ if (mpd.retval == -ENOSPC) {
+ /* commit the transaction which would
+ * free blocks released in the transaction
+ * and try again
+ */
+ jbd2_journal_force_commit_nested(sbi->s_journal);
+ wbc->pages_skipped = pages_skipped;
+ ret = 0;
+ } else if (ret == MPAGE_DA_EXTENT_TAIL) {
+ /*
+ * got one extent now try with
+ * rest of the pages
+ */
+ pages_written += mpd.pages_written;
+ wbc->pages_skipped = pages_skipped;
+ ret = 0;
+ } else if (wbc->nr_to_write)
+ /*
+ * There is no more writeout needed
+ * or we requested for a noblocking writeout
+ * and we found the device congested
+ */
+ break;
+ }
+ if (pages_skipped != wbc->pages_skipped)
+ printk(KERN_EMERG "This should not happen leaving %s "
+ "with nr_to_write = %ld ret = %d\n",
+ __func__, wbc->nr_to_write, ret);
+
+ /* Update index */
+ index += pages_written;
+ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+ /*
+ * set the writeback_index so that range_cyclic
+ * mode will write it back later
+ */
+ mapping->writeback_index = index;
+
+out_writepages:
+ if (!no_nrwrite_index_update)
+ wbc->no_nrwrite_index_update = 0;
+ wbc->nr_to_write -= nr_to_writebump;
+ return ret;
+}
+
+#define FALL_BACK_TO_NONDELALLOC 1
+static int ext4_nonda_switch(struct super_block *sb)
+{
+ s64 free_blocks, dirty_blocks;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ /*
+ * switch to non delalloc mode if we are running low
+ * on free block. The free block accounting via percpu
+ * counters can get slightly wrong with FBC_BATCH getting
+ * accumulated on each CPU without updating global counters
+ * Delalloc need an accurate free block accounting. So switch
+ * to non delalloc when we are near to error range.
+ */
+ free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+ dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+ if (2 * free_blocks < 3 * dirty_blocks ||
+ free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+ /*
+ * free block count is less that 150% of dirty blocks
+ * or free blocks is less that watermark
+ */
+ return 1;
+ }
+ return 0;
+}
+
+static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
+{
+ int ret, retries = 0;
+ struct page *page;
+ pgoff_t index;
+ unsigned from, to;
+ struct inode *inode = mapping->host;
+ handle_t *handle;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
+
+ if (ext4_nonda_switch(inode->i_sb)) {
+ *fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
+ return ext4_write_begin(file, mapping, pos,
+ len, flags, pagep, fsdata);
+ }
+ *fsdata = (void *)0;
+retry:
+ /*
+ * With delayed allocation, we don't log the i_disksize update
+ * if there is delayed block allocation. But we still need
+ * to journalling the i_disksize update if writes to the end
+ * of file which has an already mapped buffer.
+ */
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ if (!page) {
+ ext4_journal_stop(handle);
+ ret = -ENOMEM;
+ goto out;
+ }
+ *pagep = page;
+
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+ ext4_da_get_block_prep);
+ if (ret < 0) {
+ unlock_page(page);
+ ext4_journal_stop(handle);
+ page_cache_release(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.
+ */
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
+ }
+
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+out:
+ return ret;
+}
+
+/*
+ * Check if we should update i_disksize
+ * when write to the end of file but not require block allocation
+ */
+static int ext4_da_should_update_i_disksize(struct page *page,
+ unsigned long offset)
+{
+ struct buffer_head *bh;
+ struct inode *inode = page->mapping->host;
+ unsigned int idx;
+ int i;
+
+ bh = page_buffers(page);
+ idx = offset >> inode->i_blkbits;
+
+ for (i = 0; i < idx; i++)
+ bh = bh->b_this_page;
+
+ if (!buffer_mapped(bh) || (buffer_delay(bh)))
+ return 0;
+ return 1;
+}
+
+static int ext4_da_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = mapping->host;
+ int ret = 0, ret2;
+ handle_t *handle = ext4_journal_current_handle();
+ loff_t new_i_size;
+ unsigned long start, end;
+ int write_mode = (int)(unsigned long)fsdata;
+
+ if (write_mode == FALL_BACK_TO_NONDELALLOC) {
+ if (ext4_should_order_data(inode)) {
+ return ext4_ordered_write_end(file, mapping, pos,
+ len, copied, page, fsdata);
+ } else if (ext4_should_writeback_data(inode)) {
+ return ext4_writeback_write_end(file, mapping, pos,
+ len, copied, page, fsdata);
+ } else {
+ BUG();
+ }
+ }
+
+ start = pos & (PAGE_CACHE_SIZE - 1);
+ end = start + copied - 1;
+
+ /*
+ * generic_write_end() will run mark_inode_dirty() if i_size
+ * changes. So let's piggyback the i_disksize mark_inode_dirty
+ * into that.
+ */
+
+ new_i_size = pos + copied;
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ if (ext4_da_should_update_i_disksize(page, end)) {
+ down_write(&EXT4_I(inode)->i_data_sem);
+ if (new_i_size > EXT4_I(inode)->i_disksize) {
+ /*
+ * Updating i_disksize when extending file
+ * without needing block allocation
+ */
+ if (ext4_should_order_data(inode))
+ ret = ext4_jbd2_file_inode(handle,
+ inode);
+
+ EXT4_I(inode)->i_disksize = new_i_size;
+ }
+ up_write(&EXT4_I(inode)->i_data_sem);
+ /* We need to mark inode dirty even if
+ * new_i_size is less that inode->i_size
+ * bu greater than i_disksize.(hint delalloc)
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+ }
+ ret2 = generic_write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ copied = ret2;
+ if (ret2 < 0)
+ ret = ret2;
+ ret2 = ext4_journal_stop(handle);
+ if (!ret)
+ ret = ret2;
+
+ return ret ? ret : copied;
+}
+
+static void ext4_da_invalidatepage(struct page *page, unsigned long offset)
+{
+ /*
+ * Drop reserved blocks
+ */
+ BUG_ON(!PageLocked(page));
+ if (!page_has_buffers(page))
+ goto out;
+
+ ext4_da_page_release_reservation(page, offset);
+
+out:
+ ext4_invalidatepage(page, offset);
+
+ return;
+}
+
+
+/*
+ * bmap() is special. It gets used by applications such as lilo and by
+ * the swapper to find the on-disk block of a specific piece of data.
+ *
+ * Naturally, this is dangerous if the block concerned is still in the
+ * journal. If somebody makes a swapfile on an ext4 data-journaling
+ * filesystem and enables swap, then they may get a nasty shock when the
+ * data getting swapped to that swapfile suddenly gets overwritten by
+ * the original zero's written out previously to the journal and
+ * awaiting writeback in the kernel's buffer cache.
+ *
+ * So, if we see any bmap calls here on a modified, data-journaled file,
+ * take extra steps to flush any blocks which might be in the cache.
+ */
+static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
+{
+ struct inode *inode = mapping->host;
+ journal_t *journal;
+ int err;
+
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+ test_opt(inode->i_sb, DELALLOC)) {
+ /*
+ * With delalloc we want to sync the file
+ * so that we can make sure we allocate
+ * blocks for file
+ */
+ filemap_write_and_wait(mapping);
+ }
+
+ if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ /*
+ * This is a REALLY heavyweight approach, but the use of
+ * bmap on dirty files is expected to be extremely rare:
+ * only if we run lilo or swapon on a freshly made file
+ * do we expect this to happen.
+ *
+ * (bmap requires CAP_SYS_RAWIO so this does not
+ * represent an unprivileged user DOS attack --- we'd be
+ * in trouble if mortal users could trigger this path at
+ * will.)
+ *
+ * NB. EXT4_STATE_JDATA is not set on files other than
+ * regular files. If somebody wants to bmap a directory
+ * or symlink and gets confused because the buffer
+ * hasn't yet been flushed to disk, they deserve
+ * everything they get.
+ */
+
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_JDATA;
+ journal = EXT4_JOURNAL(inode);
+ jbd2_journal_lock_updates(journal);
+ err = jbd2_journal_flush(journal);
+ jbd2_journal_unlock_updates(journal);
+
+ if (err)
+ return 0;
+ }
+
+ return generic_block_bmap(mapping, block, ext4_get_block);
+}
+
+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;
+}
+
+/*
+ * 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(), noone 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.
+ *
+ * In all journaling modes block_write_full_page() will start the I/O.
+ *
+ * Problem:
+ *
+ * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->