unsigned int length);
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);
+static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
+ int pextents);
/*
* Test whether an inode is a fast symlink.
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
- ext4_ioend_shutdown(inode);
+
+ WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
goto no_delete;
}
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages(&inode->i_data, 0);
- ext4_ioend_shutdown(inode);
+ WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
if (is_bad_inode(inode))
goto no_delete;
#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,
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
+ ext4_es_lru_add(inode);
+
/* 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)) {
}
}
- if (ext4_has_inline_data(inode))
- copied = ext4_write_inline_data_end(inode, pos, len,
- copied, page);
- else
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_write_inline_data_end(inode, pos, len,
+ copied, page);
+ if (ret < 0)
+ goto errout;
+ copied = ret;
+ } else
copied = block_write_end(file, mapping, pos,
len, copied, page, fsdata);
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
* 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;
+struct mpage_da_data {
+ struct inode *inode;
+ struct writeback_control *wbc;
- BUG_ON(mpd->next_page <= mpd->first_page);
- memset(&io_submit, 0, sizeof(io_submit));
+ pgoff_t first_page; /* The first page to write */
+ pgoff_t next_page; /* Current page to examine */
+ pgoff_t last_page; /* Last page to examine */
/*
- * 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.
+ * Extent to map - this can be after first_page because that can be
+ * fully mapped. We somewhat abuse m_flags to store whether the extent
+ * is delalloc or unwritten.
*/
- 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;
-}
+ struct ext4_map_blocks map;
+ struct ext4_io_submit io_submit; /* IO submission data */
+};
-static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
+static void mpage_release_unused_pages(struct mpage_da_data *mpd,
+ bool invalidate)
{
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;
+
+ /* This is necessary when next_page == 0. */
+ if (mpd->first_page >= mpd->next_page)
+ return;
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);
+ if (invalidate) {
+ ext4_lblk_t start, last;
+ 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) {
break;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
- ClearPageUptodate(page);
+ if (invalidate) {
+ block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
+ 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)
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);
"logical block %lu\n", inode->i_ino, map->m_len,
(unsigned long) map->m_lblk);
+ ext4_es_lru_add(inode);
+
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, &es)) {
* lock so we have to do some magic.
*
* This function can get called via...
- * - ext4_da_writepages after taking page lock (have journal handle)
+ * - ext4_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)
unlock_page(page);
return 0;
}
- }
-
- if (PageChecked(page) && ext4_should_journal_data(inode))
+ }
+
+ if (PageChecked(page) && ext4_should_journal_data(inode))
+ /*
+ * It's mmapped pagecache. Add buffers and journal it. There
+ * doesn't seem much point in redirtying the page here.
+ */
+ return __ext4_journalled_writepage(page, len);
+
+ ext4_io_submit_init(&io_submit, wbc);
+ io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_submit.io_end) {
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return -ENOMEM;
+ }
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ext4_io_submit(&io_submit);
+ /* Drop io_end reference we got from init */
+ ext4_put_io_end_defer(io_submit.io_end);
+ return ret;
+}
+
+#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
+
+/*
+ * mballoc gives us at most this number of blocks...
+ * XXX: That seems to be only a limitation of ext4_mb_normalize_request().
+ * The rest of mballoc seems to handle chunks upto full group size.
+ */
+#define MAX_WRITEPAGES_EXTENT_LEN 2048
+
+/*
+ * mpage_add_bh_to_extent - try to add bh to extent of blocks to map
+ *
+ * @mpd - extent of blocks
+ * @lblk - 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 int mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
+ unsigned long b_state)
+{
+ struct ext4_map_blocks *map = &mpd->map;
+
+ /* Don't go larger than mballoc is willing to allocate */
+ if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
+ return 0;
+
+ /* First block in the extent? */
+ if (map->m_len == 0) {
+ map->m_lblk = lblk;
+ map->m_len = 1;
+ map->m_flags = b_state & BH_FLAGS;
+ return 1;
+ }
+
+ /* Can we merge the block to our big extent? */
+ if (lblk == map->m_lblk + map->m_len &&
+ (b_state & BH_FLAGS) == map->m_flags) {
+ map->m_len++;
+ return 1;
+ }
+ return 0;
+}
+
+static bool add_page_bufs_to_extent(struct mpage_da_data *mpd,
+ struct buffer_head *head,
+ struct buffer_head *bh,
+ ext4_lblk_t lblk)
+{
+ struct inode *inode = mpd->inode;
+ ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+ >> inode->i_blkbits;
+
+ do {
+ BUG_ON(buffer_locked(bh));
+
+ if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
+ (!buffer_delay(bh) && !buffer_unwritten(bh)) ||
+ lblk >= blocks) {
+ /* Found extent to map? */
+ if (mpd->map.m_len)
+ return false;
+ if (lblk >= blocks)
+ return true;
+ continue;
+ }
+ if (!mpage_add_bh_to_extent(mpd, lblk, bh->b_state))
+ return false;
+ } while (lblk++, (bh = bh->b_this_page) != head);
+ return true;
+}
+
+static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
+{
+ int len;
+ loff_t size = i_size_read(mpd->inode);
+ int err;
+
+ BUG_ON(page->index != mpd->first_page);
+ if (page->index == size >> PAGE_CACHE_SHIFT)
+ len = size & ~PAGE_CACHE_MASK;
+ else
+ len = PAGE_CACHE_SIZE;
+ clear_page_dirty_for_io(page);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+ if (!err)
+ mpd->wbc->nr_to_write--;
+ mpd->first_page++;
+
+ return err;
+}
+
+/*
+ * mpage_map_buffers - update buffers corresponding to changed extent and
+ * submit fully mapped pages for IO
+ *
+ * @mpd - description of extent to map, on return next extent to map
+ *
+ * Scan buffers corresponding to changed extent (we expect corresponding pages
+ * to be already locked) and update buffer state according to new extent state.
+ * We map delalloc buffers to their physical location, clear unwritten bits,
+ * and mark buffers as uninit when we perform writes to uninitialized extents
+ * and do extent conversion after IO is finished. If the last page is not fully
+ * mapped, we update @map to the next extent in the last page that needs
+ * mapping. Otherwise we submit the page for IO.
+ */
+static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
+{
+ struct pagevec pvec;
+ int nr_pages, i;
+ struct inode *inode = mpd->inode;
+ struct buffer_head *head, *bh;
+ int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits;
+ ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+ >> inode->i_blkbits;
+ pgoff_t start, end;
+ ext4_lblk_t lblk;
+ sector_t pblock;
+ int err;
+
+ start = mpd->map.m_lblk >> bpp_bits;
+ end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
+ lblk = start << bpp_bits;
+ pblock = mpd->map.m_pblk;
+
+ pagevec_init(&pvec, 0);
+ while (start <= end) {
+ nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start,
+ 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;
+ /* Upto 'end' pages must be contiguous */
+ BUG_ON(page->index != start);
+ bh = head = page_buffers(page);
+ do {
+ if (lblk < mpd->map.m_lblk)
+ continue;
+ if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
+ /*
+ * Buffer after end of mapped extent.
+ * Find next buffer in the page to map.
+ */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ add_page_bufs_to_extent(mpd, head, bh,
+ lblk);
+ pagevec_release(&pvec);
+ return 0;
+ }
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock++;
+ }
+ clear_buffer_unwritten(bh);
+ } while (++lblk < blocks &&
+ (bh = bh->b_this_page) != head);
+
+ /*
+ * FIXME: This is going to break if dioread_nolock
+ * supports blocksize < pagesize as we will try to
+ * convert potentially unmapped parts of inode.
+ */
+ mpd->io_submit.io_end->size += PAGE_CACHE_SIZE;
+ /* Page fully mapped - let IO run! */
+ err = mpage_submit_page(mpd, page);
+ if (err < 0) {
+ pagevec_release(&pvec);
+ return err;
+ }
+ start++;
+ }
+ pagevec_release(&pvec);
+ }
+ /* Extent fully mapped and matches with page boundary. We are done. */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ return 0;
+}
+
+static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
+{
+ struct inode *inode = mpd->inode;
+ struct ext4_map_blocks *map = &mpd->map;
+ int get_blocks_flags;
+ int err;
+
+ trace_ext4_da_write_pages_extent(inode, map);
+ /*
+ * 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). 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.
+ *
+ * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if the blocks
+ * in question are delalloc blocks. 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.
+ */
+ get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
+ EXT4_GET_BLOCKS_METADATA_NOFAIL;
+ if (ext4_should_dioread_nolock(inode))
+ get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
+ if (map->m_flags & (1 << BH_Delay))
+ get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
+
+ err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
+ if (err < 0)
+ return err;
+ if (map->m_flags & EXT4_MAP_UNINIT) {
+ if (!mpd->io_submit.io_end->handle &&
+ ext4_handle_valid(handle)) {
+ mpd->io_submit.io_end->handle = handle->h_rsv_handle;
+ handle->h_rsv_handle = NULL;
+ }
+ ext4_set_io_unwritten_flag(inode, mpd->io_submit.io_end);
+ }
+
+ BUG_ON(map->m_len == 0);
+ if (map->m_flags & EXT4_MAP_NEW) {
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ int i;
+
+ for (i = 0; i < map->m_len; i++)
+ unmap_underlying_metadata(bdev, map->m_pblk + i);
+ }
+ return 0;
+}
+
+/*
+ * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length
+ * mpd->len and submit pages underlying it for IO
+ *
+ * @handle - handle for journal operations
+ * @mpd - extent to map
+ *
+ * The function maps extent starting at mpd->lblk of length mpd->len. If it is
+ * delayed, blocks are allocated, if it is unwritten, we may need to convert
+ * them to initialized or split the described range from larger unwritten
+ * extent. Note that we need not map all the described range since allocation
+ * can return less blocks or the range is covered by more unwritten extents. We
+ * cannot map more because we are limited by reserved transaction credits. On
+ * the other hand we always make sure that the last touched page is fully
+ * mapped so that it can be written out (and thus forward progress is
+ * guaranteed). After mapping we submit all mapped pages for IO.
+ */
+static int mpage_map_and_submit_extent(handle_t *handle,
+ struct mpage_da_data *mpd)
+{
+ struct inode *inode = mpd->inode;
+ struct ext4_map_blocks *map = &mpd->map;
+ int err;
+ loff_t disksize;
+
+ mpd->io_submit.io_end->offset =
+ ((loff_t)map->m_lblk) << inode->i_blkbits;
+ while (map->m_len) {
+ err = mpage_map_one_extent(handle, mpd);
+ if (err < 0) {
+ struct super_block *sb = inode->i_sb;
+
+ /*
+ * Need to commit transaction to free blocks. Let upper
+ * layers sort it out.
+ */
+ if (err == -ENOSPC && ext4_count_free_clusters(sb))
+ return -ENOSPC;
+
+ 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 %u with error %d",
+ inode->i_ino,
+ (unsigned long long)map->m_lblk,
+ (unsigned)map->m_len, err);
+ ext4_msg(sb, KERN_CRIT,
+ "This should not happen!! Data will "
+ "be lost\n");
+ if (err == -ENOSPC)
+ ext4_print_free_blocks(inode);
+ }
+ /* invalidate all the pages */
+ mpage_release_unused_pages(mpd, true);
+ return err;
+ }
/*
- * It's mmapped pagecache. Add buffers and journal it. There
- * doesn't seem much point in redirtying the page here.
+ * Update buffer state, submit mapped pages, and get us new
+ * extent to map
*/
- return __ext4_journalled_writepage(page, len);
+ err = mpage_map_and_submit_buffers(mpd);
+ if (err < 0)
+ return err;
+ }
- memset(&io_submit, 0, sizeof(io_submit));
- ret = ext4_bio_write_page(&io_submit, page, len, wbc);
- ext4_io_submit(&io_submit);
- return ret;
+ /* Update on-disk size after IO is submitted */
+ disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
+ if (disksize > i_size_read(inode))
+ disksize = i_size_read(inode);
+ if (disksize > EXT4_I(inode)->i_disksize) {
+ int err2;
+
+ ext4_update_i_disksize(inode, disksize);
+ err2 = ext4_mark_inode_dirty(handle, inode);
+ if (err2)
+ ext4_error(inode->i_sb,
+ "Failed to mark inode %lu dirty",
+ inode->i_ino);
+ if (!err)
+ err = err2;
+ }
+ return err;
}
/*
- * This is called via ext4_da_writepages() to
- * calculate 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.
+ * Calculate the total number of credits to reserve for one writepages
+ * iteration. This is called from ext4_writepages(). We map an extent of
+ * upto MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
+ * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
+ * bpp - 1 blocks in bpp different extents.
*/
-
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 (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
- (max_blocks > EXT4_MAX_TRANS_DATA))
- max_blocks = EXT4_MAX_TRANS_DATA;
+ int bpp = ext4_journal_blocks_per_page(inode);
- return ext4_chunk_trans_blocks(inode, max_blocks);
+ return ext4_meta_trans_blocks(inode,
+ MAX_WRITEPAGES_EXTENT_LEN + bpp - 1, bpp);
}
/*
- * write_cache_pages_da - walk the list of dirty pages of the given
- * address space and accumulate pages that need writing, and call
- * mpage_da_map_and_submit to map a single contiguous memory region
- * and then write them.
+ * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages
+ * and underlying extent to map
+ *
+ * @mpd - where to look for pages
+ *
+ * Walk dirty pages in the mapping. If they are fully mapped, submit them for
+ * IO immediately. When we find a page which isn't mapped we start accumulating
+ * extent of buffers underlying these pages that needs mapping (formed by
+ * either delayed or unwritten buffers). We also lock the pages containing
+ * these buffers. The extent found is returned in @mpd structure (starting at
+ * mpd->lblk with length mpd->len blocks).
+ *
+ * Note that this function can attach bios to one io_end structure which are
+ * neither logically nor physically contiguous. Although it may seem as an
+ * unnecessary complication, it is actually inevitable in blocksize < pagesize
+ * case as we need to track IO to all buffers underlying a page in one io_end.
*/
-static int write_cache_pages_da(handle_t *handle,
- struct address_space *mapping,
- struct writeback_control *wbc,
- struct mpage_da_data *mpd,
- pgoff_t *done_index)
+static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
{
- struct buffer_head *bh, *head;
- struct inode *inode = mapping->host;
- struct pagevec pvec;
- unsigned int nr_pages;
- sector_t logical;
- pgoff_t index, end;
- long nr_to_write = wbc->nr_to_write;
- int i, tag, ret = 0;
-
- memset(mpd, 0, sizeof(struct mpage_da_data));
- mpd->wbc = wbc;
- mpd->inode = inode;
- pagevec_init(&pvec, 0);
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ struct address_space *mapping = mpd->inode->i_mapping;
+ struct pagevec pvec;
+ unsigned int nr_pages;
+ pgoff_t index = mpd->first_page;
+ pgoff_t end = mpd->last_page;
+ int tag;
+ int i, err = 0;
+ int blkbits = mpd->inode->i_blkbits;
+ ext4_lblk_t lblk;
+ struct buffer_head *head;
- if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
- *done_index = index;
+ pagevec_init(&pvec, 0);
+ mpd->map.m_len = 0;
+ mpd->next_page = index;
while (index <= end) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
- return 0;
+ goto out;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page->index > end)
goto out;
- *done_index = page->index + 1;
-
- /*
- * If we can't merge this page, and we have
- * accumulated an contiguous region, write it
- */
- if ((mpd->next_page != page->index) &&
- (mpd->next_page != mpd->first_page)) {
- mpage_da_map_and_submit(mpd);
- goto ret_extent_tail;
- }
+ /* If we can't merge this page, we are done. */
+ if (mpd->map.m_len > 0 && mpd->next_page != page->index)
+ goto out;
lock_page(page);
-
/*
- * If the page is no longer dirty, or its
- * mapping no longer corresponds to inode we
- * are writing (which means it has been
- * truncated or invalidated), or the page is
- * already under writeback and we are not
- * doing a data integrity writeback, skip the page
+ * If the page is no longer dirty, or its mapping no
+ * longer corresponds to inode we are writing (which
+ * means it has been truncated or invalidated), or the
+ * page is already under writeback and we are not doing
+ * a data integrity writeback, skip the page
*/
if (!PageDirty(page) ||
(PageWriteback(page) &&
- (wbc->sync_mode == WB_SYNC_NONE)) ||
+ (mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
- /*
- * If we have inline data and arrive here, it means that
- * we will soon create the block for the 1st page, so
- * we'd better clear the inline data here.
- */
- if (ext4_has_inline_data(inode)) {
- BUG_ON(ext4_test_inode_state(inode,
- EXT4_STATE_MAY_INLINE_DATA));
- ext4_destroy_inline_data(handle, inode);
- }
-
- if (mpd->next_page != page->index)
+ if (mpd->map.m_len == 0)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
- logical = (sector_t) page->index <<
- (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
/* Add all dirty buffers to mpd */
+ lblk = ((ext4_lblk_t)page->index) <<
+ (PAGE_CACHE_SHIFT - blkbits);
head = page_buffers(page);
- bh = head;
- do {
- BUG_ON(buffer_locked(bh));
- /*
- * We need to try to allocate unmapped blocks
- * in the same page. Otherwise we won't make
- * progress with the page in ext4_writepage
- */
- if (ext4_bh_delay_or_unwritten(NULL, bh)) {
- mpage_add_bh_to_extent(mpd, logical,
- bh->b_state);
- if (mpd->io_done)
- goto ret_extent_tail;
- } else if (buffer_dirty(bh) &&
- buffer_mapped(bh)) {
- /*
- * mapped dirty buffer. We need to
- * update the b_state because we look
- * at b_state in mpage_da_map_blocks.
- * We don't update b_size because if we
- * find an unmapped buffer_head later
- * we need to use the b_state flag of
- * that buffer_head.
- */
- if (mpd->b_size == 0)
- mpd->b_state =
- bh->b_state & BH_FLAGS;
- }
- logical++;
- } while ((bh = bh->b_this_page) != head);
-
- if (nr_to_write > 0) {
- nr_to_write--;
- if (nr_to_write == 0 &&
- wbc->sync_mode == WB_SYNC_NONE)
- /*
- * We stop writing back only if we are
- * not doing integrity sync. In case of
- * integrity sync we have to keep going
- * because someone may be concurrently
- * dirtying pages, and we might have
- * synced a lot of newly appeared dirty
- * pages, but have not synced all of the
- * old dirty pages.
- */
+ if (!add_page_bufs_to_extent(mpd, head, head, lblk))
+ goto out;
+ /* So far everything mapped? Submit the page for IO. */
+ if (mpd->map.m_len == 0) {
+ err = mpage_submit_page(mpd, page);
+ if (err < 0)
goto out;
}
+
+ /*
+ * Accumulated enough dirty pages? This doesn't apply
+ * to WB_SYNC_ALL mode. For integrity sync we have to
+ * keep going because someone may be concurrently
+ * dirtying pages, and we might have synced a lot of
+ * newly appeared dirty pages, but have not synced all
+ * of the old dirty pages.
+ */
+ if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
+ mpd->next_page - mpd->first_page >=
+ mpd->wbc->nr_to_write)
+ goto out;
}
pagevec_release(&pvec);
cond_resched();
}
return 0;
-ret_extent_tail:
- ret = MPAGE_DA_EXTENT_TAIL;
out:
pagevec_release(&pvec);
- cond_resched();
- return ret;
+ return err;
}
+static int __writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
+{
+ struct address_space *mapping = data;
+ int ret = ext4_writepage(page, wbc);
+ mapping_set_error(mapping, ret);
+ return ret;
+}
-static int ext4_da_writepages(struct address_space *mapping,
- struct writeback_control *wbc)
+static int ext4_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
{
- pgoff_t index;
+ pgoff_t writeback_index = 0;
+ long nr_to_write = wbc->nr_to_write;
int range_whole = 0;
+ int cycled = 1;
handle_t *handle = NULL;
struct mpage_da_data mpd;
struct inode *inode = mapping->host;
- int pages_written = 0;
- unsigned int max_pages;
- int range_cyclic, cycled = 1, io_done = 0;
- int needed_blocks, ret = 0;
- long desired_nr_to_write, nr_to_writebump = 0;
- loff_t range_start = wbc->range_start;
+ int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
- pgoff_t done_index = 0;
- pgoff_t end;
+ bool done;
struct blk_plug plug;
- trace_ext4_da_writepages(inode, wbc);
+ trace_ext4_writepages(inode, wbc);
/*
* No pages to write? This is mainly a kludge to avoid starting
if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
return 0;
+ if (ext4_should_journal_data(inode)) {
+ struct blk_plug plug;
+ int ret;
+
+ blk_start_plug(&plug);
+ ret = write_cache_pages(mapping, wbc, __writepage, mapping);
+ blk_finish_plug(&plug);
+ return ret;
+ }
+
/*
* 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_MF_FS_ABORTED 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
+ * read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
return -EROFS;
+ if (ext4_should_dioread_nolock(inode)) {
+ /*
+ * We may need to convert upto one extent per block in
+ * the page and we may dirty the inode.
+ */
+ rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits);
+ }
+
+ /*
+ * If we have inline data and arrive here, it means that
+ * we will soon create the block for the 1st page, so
+ * we'd better clear the inline data here.
+ */
+ if (ext4_has_inline_data(inode)) {
+ /* Just inode will be modified... */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_writepages;
+ }
+ BUG_ON(ext4_test_inode_state(inode,
+ EXT4_STATE_MAY_INLINE_DATA));
+ ext4_destroy_inline_data(handle, inode);
+ ext4_journal_stop(handle);
+ }
+
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
- range_cyclic = wbc->range_cyclic;
if (wbc->range_cyclic) {
- index = mapping->writeback_index;
- if (index)
+ writeback_index = mapping->writeback_index;
+ if (writeback_index)
cycled = 0;
- wbc->range_start = index << PAGE_CACHE_SHIFT;
- wbc->range_end = LLONG_MAX;
- wbc->range_cyclic = 0;
- end = -1;
+ mpd.first_page = writeback_index;
+ mpd.last_page = -1;
} else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
- }
-
- /*
- * This works around two forms of stupidity. The first is in
- * the writeback code, which caps the maximum number of pages
- * written to be 1024 pages. This is wrong on multiple
- * levels; different architectues have a different page size,
- * which changes the maximum amount of data which gets
- * written. Secondly, 4 megabytes is way too small. XFS
- * forces this value to be 16 megabytes by multiplying
- * nr_to_write parameter by four, and then relies on its
- * allocator to allocate larger extents to make them
- * contiguous. Unfortunately this brings us to the second
- * stupidity, which is that ext4's mballoc code only allocates
- * at most 2048 blocks. So we force contiguous writes up to
- * the number of dirty blocks in the inode, or
- * sbi->max_writeback_mb_bump whichever is smaller.
- */
- max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT);
- if (!range_cyclic && range_whole) {
- if (wbc->nr_to_write == LONG_MAX)
- desired_nr_to_write = wbc->nr_to_write;
- else
- desired_nr_to_write = wbc->nr_to_write * 8;
- } else
- desired_nr_to_write = ext4_num_dirty_pages(inode, index,
- max_pages);
- if (desired_nr_to_write > max_pages)
- desired_nr_to_write = max_pages;
-
- if (wbc->nr_to_write < desired_nr_to_write) {
- nr_to_writebump = desired_nr_to_write - wbc->nr_to_write;
- wbc->nr_to_write = desired_nr_to_write;
+ mpd.first_page = wbc->range_start >> PAGE_CACHE_SHIFT;
+ mpd.last_page = wbc->range_end >> PAGE_CACHE_SHIFT;
}
+ mpd.inode = inode;
+ mpd.wbc = wbc;
+ ext4_io_submit_init(&mpd.io_submit, wbc);
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
- tag_pages_for_writeback(mapping, index, end);
-
+ tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
+ done = false;
blk_start_plug(&plug);
- while (!ret && wbc->nr_to_write > 0) {
+ while (!done && mpd.first_page <= mpd.last_page) {
+ /* For each extent of pages we use new io_end */
+ mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
+ if (!mpd.io_submit.io_end) {
+ ret = -ENOMEM;
+ break;
+ }
/*
- * we insert one extent at a time. So we need
- * credit needed for single extent allocation.
- * journalled mode is currently not supported
- * by delalloc
+ * We have two constraints: We find one extent to map and we
+ * must always write out whole page (makes a difference when
+ * blocksize < pagesize) so that we don't block on IO when we
+ * try to write out the rest of the page. Journalled mode is
+ * 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, EXT4_HT_WRITE_PAGE,
- needed_blocks);
+ /* start a new transaction */
+ handle = ext4_journal_start_with_reserve(inode,
+ EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
"%ld pages, ino %lu; err %d", __func__,
wbc->nr_to_write, inode->i_ino, ret);
- blk_finish_plug(&plug);
- goto out_writepages;
+ /* Release allocated io_end */
+ ext4_put_io_end(mpd.io_submit.io_end);
+ break;
}
- /*
- * Now call write_cache_pages_da() to find the next
- * contiguous region of logical blocks that need
- * blocks to be allocated by ext4 and submit them.
- */
- ret = write_cache_pages_da(handle, mapping,
- wbc, &mpd, &done_index);
- /*
- * If we have a contiguous extent of pages and we
- * haven't done the I/O yet, map the blocks and submit
- * them for I/O.
- */
- if (!mpd.io_done && mpd.next_page != mpd.first_page) {
- mpage_da_map_and_submit(&mpd);
- ret = MPAGE_DA_EXTENT_TAIL;
+ trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
+ ret = mpage_prepare_extent_to_map(&mpd);
+ if (!ret) {
+ if (mpd.map.m_len)
+ ret = mpage_map_and_submit_extent(handle, &mpd);
+ else {
+ /*
+ * We scanned the whole range (or exhausted
+ * nr_to_write), submitted what was mapped and
+ * didn't find anything needing mapping. We are
+ * done.
+ */
+ done = true;
+ }
}
- trace_ext4_da_write_pages(inode, &mpd);
- wbc->nr_to_write -= mpd.pages_written;
-
ext4_journal_stop(handle);
-
- if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
- /* commit the transaction which would
+ /* Submit prepared bio */
+ ext4_io_submit(&mpd.io_submit);
+ /* Unlock pages we didn't use */
+ mpage_release_unused_pages(&mpd, false);
+ /* Drop our io_end reference we got from init */
+ ext4_put_io_end(mpd.io_submit.io_end);
+
+ if (ret == -ENOSPC && sbi->s_journal) {
+ /*
+ * Commit the transaction which would
* free blocks released in the transaction
* and try again
*/
jbd2_journal_force_commit_nested(sbi->s_journal);
ret = 0;
- } else if (ret == MPAGE_DA_EXTENT_TAIL) {
- /*
- * Got one extent now try with rest of the pages.
- * If mpd.retval is set -EIO, journal is aborted.
- * So we don't need to write any more.
- */
- pages_written += mpd.pages_written;
- ret = mpd.retval;
- io_done = 1;
- } 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
- */
+ continue;
+ }
+ /* Fatal error - ENOMEM, EIO... */
+ if (ret)
break;
}
blk_finish_plug(&plug);
- if (!io_done && !cycled) {
+ if (!ret && !cycled) {
cycled = 1;
- index = 0;
- wbc->range_start = index << PAGE_CACHE_SHIFT;
- wbc->range_end = mapping->writeback_index - 1;
+ mpd.last_page = writeback_index - 1;
+ mpd.first_page = 0;
goto retry;
}
/* Update index */
- wbc->range_cyclic = range_cyclic;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
/*
- * set the writeback_index so that range_cyclic
+ * Set the writeback_index so that range_cyclic
* mode will write it back later
*/
- mapping->writeback_index = done_index;
+ mapping->writeback_index = mpd.first_page;
out_writepages:
- wbc->nr_to_write -= nr_to_writebump;
- wbc->range_start = range_start;
- trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
+ trace_ext4_writepages_result(inode, wbc, ret,
+ nr_to_write - wbc->nr_to_write);
return ret;
}
* laptop_mode, not even desirable). However, to do otherwise
* would require replicating code paths in:
*
- * ext4_da_writepages() ->
+ * ext4_writepages() ->
* write_cache_pages() ---> (via passed in callback function)
* __mpage_da_writepage() -->
* mpage_add_bh_to_extent()
struct inode *inode = file_inode(iocb->ki_filp);
ext4_io_end_t *io_end = iocb->private;
- /* if not async direct IO or dio with 0 bytes write, just return */
- if (!io_end || !size)
- goto out;
+ /* if not async direct IO just return */
+ if (!io_end) {
+ inode_dio_done(inode);
+ if (is_async)
+ aio_complete(iocb, ret, 0);
+ return;
+ }
ext_debug("ext4_end_io_dio(): io_end 0x%p "
"for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
size);
iocb->private = NULL;
-
- /* if not aio dio with unwritten extents, just free io and return */
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- ext4_free_io_end(io_end);
-out:
- inode_dio_done(inode);
- if (is_async)
- aio_complete(iocb, ret, 0);
- return;
- }
-
io_end->offset = offset;
io_end->size = size;
if (is_async) {
io_end->iocb = iocb;
io_end->result = ret;
}
-
- ext4_add_complete_io(io_end);
+ ext4_put_io_end_defer(io_end);
}
/*
get_block_t *get_block_func = NULL;
int dio_flags = 0;
loff_t final_size = offset + count;
+ ext4_io_end_t *io_end = NULL;
/* Use the old path for reads and writes beyond i_size. */
if (rw != WRITE || final_size > inode->i_size)
BUG_ON(iocb->private == NULL);
+ /*
+ * Make all waiters for direct IO properly wait also for extent
+ * conversion. This also disallows race between truncate() and
+ * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
+ */
+ if (rw == WRITE)
+ atomic_inc(&inode->i_dio_count);
+
/* If we do a overwrite dio, i_mutex locking can be released */
overwrite = *((int *)iocb->private);
if (overwrite) {
- atomic_inc(&inode->i_dio_count);
down_read(&EXT4_I(inode)->i_data_sem);
mutex_unlock(&inode->i_mutex);
}
iocb->private = NULL;
ext4_inode_aio_set(inode, NULL);
if (!is_sync_kiocb(iocb)) {
- ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
+ io_end = ext4_init_io_end(inode, GFP_NOFS);
if (!io_end) {
ret = -ENOMEM;
goto retake_lock;
}
io_end->flag |= EXT4_IO_END_DIRECT;
- iocb->private = io_end;
+ /*
+ * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
+ */
+ iocb->private = ext4_get_io_end(io_end);
/*
* we save the io structure for current async direct
* IO, so that later ext4_map_blocks() could flag the
NULL,
dio_flags);
- if (iocb->private)
- ext4_inode_aio_set(inode, NULL);
/*
- * The io_end structure takes a reference to the inode, that
- * structure needs to be destroyed and the reference to the
- * inode need to be dropped, when IO is complete, even with 0
- * byte write, or failed.
- *
- * In the successful AIO DIO case, the io_end structure will
- * be destroyed and the reference to the inode will be dropped
- * after the end_io call back function is called.
- *
- * In the case there is 0 byte write, or error case, since VFS
- * direct IO won't invoke the end_io call back function, we
- * need to free the end_io structure here.
+ * Put our reference to io_end. This can free the io_end structure e.g.
+ * in sync IO case or in case of error. It can even perform extent
+ * conversion if all bios we submitted finished before we got here.
+ * Note that in that case iocb->private can be already set to NULL
+ * here.
*/
- if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
- ext4_free_io_end(iocb->private);
- iocb->private = NULL;
- } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
+ if (io_end) {
+ ext4_inode_aio_set(inode, NULL);
+ ext4_put_io_end(io_end);
+ /*
+ * When no IO was submitted ext4_end_io_dio() was not
+ * called so we have to put iocb's reference.
+ */
+ if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) {
+ WARN_ON(iocb->private != io_end);
+ WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
+ WARN_ON(io_end->iocb);
+ /*
+ * Generic code already did inode_dio_done() so we
+ * have to clear EXT4_IO_END_DIRECT to not do it for
+ * the second time.
+ */
+ io_end->flag = 0;
+ ext4_put_io_end(io_end);
+ iocb->private = NULL;
+ }
+ }
+ if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN)) {
int err;
/*
* for non AIO case, since the IO is already
* completed, we could do the conversion right here
*/
- err = ext4_convert_unwritten_extents(inode,
+ err = ext4_convert_unwritten_extents(NULL, inode,
offset, ret);
if (err < 0)
ret = err;
}
retake_lock:
+ if (rw == WRITE)
+ inode_dio_done(inode);
/* take i_mutex locking again if we do a ovewrite dio */
if (overwrite) {
- inode_dio_done(inode);
up_read(&EXT4_I(inode)->i_data_sem);
mutex_lock(&inode->i_mutex);
}
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
+ .writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_write_end,
.bmap = ext4_bmap,
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
+ .writepages = ext4_writepages,
.write_begin = ext4_write_begin,
.write_end = ext4_journalled_write_end,
.set_page_dirty = ext4_journalled_set_page_dirty,
.readpage = ext4_readpage,
.readpages = ext4_readpages,
.writepage = ext4_writepage,
- .writepages = ext4_da_writepages,
+ .writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.bmap = ext4_bmap,
inode->i_mapping->a_ops = &ext4_aops;
}
-
-/*
- * ext4_discard_partial_page_buffers()
- * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
- * This function finds and locks the page containing the offset
- * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
- * Calling functions that already have the page locked should call
- * ext4_discard_partial_page_buffers_no_lock directly.
- */
-int ext4_discard_partial_page_buffers(handle_t *handle,
- struct address_space *mapping, loff_t from,
- loff_t length, int flags)
-{
- struct inode *inode = mapping->host;
- struct page *page;
- int err = 0;
-
- page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
- mapping_gfp_mask(mapping) & ~__GFP_FS);
- if (!page)
- return -ENOMEM;
-
- err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
- from, length, flags);
-
- unlock_page(page);
- page_cache_release(page);
- return err;
-}
-
-/*
- * ext4_discard_partial_page_buffers_no_lock()
- * Zeros a page range of length 'length' starting from offset 'from'.
- * Buffer heads that correspond to the block aligned regions of the
- * zeroed range will be unmapped. Unblock aligned regions
- * will have the corresponding buffer head mapped if needed so that
- * that region of the page can be updated with the partial zero out.
- *
- * This function assumes that the page has already been locked. The
- * The range to be discarded must be contained with in the given page.
- * If the specified range exceeds the end of the page it will be shortened
- * to the end of the page that corresponds to 'from'. This function is
- * appropriate for updating a page and it buffer heads to be unmapped and
- * zeroed for blocks that have been either released, or are going to be
- * released.
- *
- * handle: The journal handle
- * inode: The files inode
- * page: A locked page that contains the offset "from"
- * from: The starting byte offset (from the beginning of the file)
- * to begin discarding
- * len: The length of bytes to discard
- * flags: Optional flags that may be used:
- *
- * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
- * Only zero the regions of the page whose buffer heads
- * have already been unmapped. This flag is appropriate
- * for updating the contents of a page whose blocks may
- * have already been released, and we only want to zero
- * out the regions that correspond to those released blocks.
- *
- * Returns zero on success or negative on failure.
- */
-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)
-{
- ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
- unsigned int offset = from & (PAGE_CACHE_SIZE-1);
- unsigned int blocksize, max, pos;
- ext4_lblk_t iblock;
- struct buffer_head *bh;
- int err = 0;
-
- blocksize = inode->i_sb->s_blocksize;
- max = PAGE_CACHE_SIZE - offset;
-
- if (index != page->index)
- return -EINVAL;
-
- /*
- * correct length if it does not fall between
- * 'from' and the end of the page
- */
- if (length > max || length < 0)
- length = max;
-
- iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
-
- if (!page_has_buffers(page))
- create_empty_buffers(page, blocksize, 0);
-
- /* Find the buffer that contains "offset" */
- bh = page_buffers(page);
- pos = blocksize;
- while (offset >= pos) {
- bh = bh->b_this_page;
- iblock++;
- pos += blocksize;
- }
-
- pos = offset;
- while (pos < offset + length) {
- unsigned int end_of_block, range_to_discard;
-
- err = 0;
-
- /* The length of space left to zero and unmap */
- range_to_discard = offset + length - pos;
-
- /* The length of space until the end of the block */
- end_of_block = blocksize - (pos & (blocksize-1));
-
- /*
- * Do not unmap or zero past end of block
- * for this buffer head
- */
- if (range_to_discard > end_of_block)
- range_to_discard = end_of_block;
-
-
- /*
- * Skip this buffer head if we are only zeroing unampped
- * regions of the page
- */
- if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
- buffer_mapped(bh))
- goto next;
-
- /* If the range is block aligned, unmap */
- if (range_to_discard == blocksize) {
- clear_buffer_dirty(bh);
- bh->b_bdev = NULL;
- clear_buffer_mapped(bh);
- clear_buffer_req(bh);
- clear_buffer_new(bh);
- clear_buffer_delay(bh);
- clear_buffer_unwritten(bh);
- clear_buffer_uptodate(bh);
- zero_user(page, pos, range_to_discard);
- BUFFER_TRACE(bh, "Buffer discarded");
- goto next;
- }
-
- /*
- * If this block is not completely contained in the range
- * to be discarded, then it is not going to be released. Because
- * we need to keep this block, we need to make sure this part
- * of the page is uptodate before we modify it by writeing
- * partial zeros on it.
- */
- if (!buffer_mapped(bh)) {
- /*
- * Buffer head must be mapped before we can read
- * from the block
- */
- BUFFER_TRACE(bh, "unmapped");
- ext4_get_block(inode, iblock, bh, 0);
- /* unmapped? It's a hole - nothing to do */
- if (!buffer_mapped(bh)) {
- BUFFER_TRACE(bh, "still unmapped");
- goto next;
- }
- }
-
- /* Ok, it's mapped. Make sure it's up-to-date */
- if (PageUptodate(page))
- set_buffer_uptodate(bh);
-
- if (!buffer_uptodate(bh)) {
- err = -EIO;
- ll_rw_block(READ, 1, &bh);
- wait_on_buffer(bh);
- /* Uhhuh. Read error. Complain and punt.*/
- if (!buffer_uptodate(bh))
- goto next;
- }
-
- if (ext4_should_journal_data(inode)) {
- BUFFER_TRACE(bh, "get write access");
- err = ext4_journal_get_write_access(handle, bh);
- if (err)
- goto next;
- }
-
- zero_user(page, pos, range_to_discard);
-
- err = 0;
- if (ext4_should_journal_data(inode)) {
- err = ext4_handle_dirty_metadata(handle, inode, bh);
- } else
- mark_buffer_dirty(bh);
-
- BUFFER_TRACE(bh, "Partial buffer zeroed");
-next:
- bh = bh->b_this_page;
- iblock++;
- pos += range_to_discard;
- }
-
- return err;
-}
-
/*
* ext4_block_truncate_page() zeroes out a mapping from file offset `from'
* up to the end of the block which corresponds to `from'.
iblock++;
pos += blocksize;
}
-
- err = 0;
if (buffer_freed(bh)) {
BUFFER_TRACE(bh, "freed: skip");
goto unlock;
}
-
if (!buffer_mapped(bh)) {
BUFFER_TRACE(bh, "unmapped");
ext4_get_block(inode, iblock, bh, 0);
if (!buffer_uptodate(bh))
goto unlock;
}
-
if (ext4_should_journal_data(inode)) {
BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
goto unlock;
}
-
zero_user(page, offset, length);
-
BUFFER_TRACE(bh, "zeroed end of block");
- err = 0;
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
} else {
+ err = 0;
mark_buffer_dirty(bh);
if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE))
err = ext4_jbd2_file_inode(handle, inode);
* Returns: 0 on success or negative on failure
*/
-int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
+int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
{
- struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
ext4_lblk_t first_block, stop_block;
struct address_space *mapping = inode->i_mapping;
/* Wait all existing dio workers, newcomers will block on i_mutex */
ext4_inode_block_unlocked_dio(inode);
- ret = ext4_flush_unwritten_io(inode);
- if (ret)
- goto out_dio;
inode_dio_wait(inode);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return;
}
- /*
- * finish any pending end_io work so we won't run the risk of
- * converting any truncated blocks to initialized later
- */
- ext4_flush_unwritten_io(inode);
-
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
else
struct kstat *stat)
{
struct inode *inode;
- unsigned long delalloc_blocks;
+ unsigned long long delalloc_blocks;
inode = dentry->d_inode;
generic_fillattr(inode, stat);
delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
EXT4_I(inode)->i_reserved_data_blocks);
- stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+ stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
return 0;
}
-static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+static int ext4_index_trans_blocks(struct inode *inode, int lblocks,
+ int pextents)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return ext4_ind_trans_blocks(inode, nrblocks, chunk);
- return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
+ return ext4_ind_trans_blocks(inode, lblocks);
+ return ext4_ext_index_trans_blocks(inode, pextents);
}
/*
*
* Also account for superblock, inode, quota and xattr blocks
*/
-static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
+ int pextents)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
int ret = 0;
/*
- * How many index blocks need to touch to modify nrblocks?
- * The "Chunk" flag indicating whether the nrblocks is
- * physically contiguous on disk
- *
- * For Direct IO and fallocate, they calls get_block to allocate
- * one single extent at a time, so they could set the "Chunk" flag
+ * How many index blocks need to touch to map @lblocks logical blocks
+ * to @pextents physical extents?
*/
- idxblocks = ext4_index_trans_blocks(inode, nrblocks, chunk);
+ idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents);
ret = idxblocks;
* Now let's see how many group bitmaps and group descriptors need
* to account
*/
- groups = idxblocks;
- if (chunk)
- groups += 1;
- else
- groups += nrblocks;
-
+ groups = idxblocks + pextents;
gdpblocks = groups;
if (groups > ngroups)
groups = ngroups;
int bpp = ext4_journal_blocks_per_page(inode);
int ret;
- ret = ext4_meta_trans_blocks(inode, bpp, 0);
+ ret = ext4_meta_trans_blocks(inode, bpp, bpp);
/* Account for data blocks for journalled mode */
if (ext4_should_journal_data(inode))
projects / ~andy / linux / blobdiff