* Contains functions related to preparing and submitting BIOs which contain
* multiple pagecache pages.
*
- * 15May2002 akpm@zip.com.au
+ * 15May2002 Andrew Morton
* Initial version
* 27Jun2002 axboe@suse.de
* use bio_add_page() to build bio's just the right size
*/
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm.h>
#include <linux/kdev_t.h>
+#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
+#include <linux/cleancache.h>
/*
* I/O completion handler for multipage BIOs.
* status of that page is hard. See end_buffer_async_read() for the details.
* There is no point in duplicating all that complexity.
*/
-static int mpage_end_io_read(struct bio *bio, unsigned int bytes_done, int err)
+static void mpage_end_io(struct bio *bio, int err)
{
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
- if (bio->bi_size)
- return 1;
-
do {
struct page *page = bvec->bv_page;
if (--bvec >= bio->bi_io_vec)
prefetchw(&bvec->bv_page->flags);
-
- if (uptodate) {
- SetPageUptodate(page);
- } else {
- ClearPageUptodate(page);
- SetPageError(page);
+ if (bio_data_dir(bio) == READ) {
+ if (uptodate) {
+ SetPageUptodate(page);
+ } else {
+ ClearPageUptodate(page);
+ SetPageError(page);
+ }
+ unlock_page(page);
+ } else { /* bio_data_dir(bio) == WRITE */
+ if (!uptodate) {
+ SetPageError(page);
+ if (page->mapping)
+ set_bit(AS_EIO, &page->mapping->flags);
+ }
+ end_page_writeback(page);
}
- unlock_page(page);
- } while (bvec >= bio->bi_io_vec);
- bio_put(bio);
- return 0;
-}
-
-static int mpage_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
-{
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-
- if (bio->bi_size)
- return 1;
-
- do {
- struct page *page = bvec->bv_page;
-
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
- if (!uptodate)
- SetPageError(page);
- end_page_writeback(page);
} while (bvec >= bio->bi_io_vec);
bio_put(bio);
- return 0;
}
-struct bio *mpage_bio_submit(int rw, struct bio *bio)
+static struct bio *mpage_bio_submit(int rw, struct bio *bio)
{
- bio->bi_end_io = mpage_end_io_read;
- if (rw == WRITE)
- bio->bi_end_io = mpage_end_io_write;
+ bio->bi_end_io = mpage_end_io;
submit_bio(rw, bio);
return NULL;
}
static struct bio *
mpage_alloc(struct block_device *bdev,
- sector_t first_sector, int nr_vecs, int gfp_flags)
+ sector_t first_sector, int nr_vecs,
+ gfp_t gfp_flags)
{
struct bio *bio;
return bio;
}
-/**
- * mpage_readpages - populate an address space with some pages, and
- * start reads against them.
- *
- * @mapping: the address_space
- * @pages: The address of a list_head which contains the target pages. These
- * pages have their ->index populated and are otherwise uninitialised.
- *
- * The page at @pages->prev has the lowest file offset, and reads should be
- * issued in @pages->prev to @pages->next order.
- *
- * @nr_pages: The number of pages at *@pages
- * @get_block: The filesystem's block mapper function.
- *
- * This function walks the pages and the blocks within each page, building and
- * emitting large BIOs.
- *
- * If anything unusual happens, such as:
- *
- * - encountering a page which has buffers
- * - encountering a page which has a non-hole after a hole
- * - encountering a page with non-contiguous blocks
- *
- * then this code just gives up and calls the buffer_head-based read function.
- * It does handle a page which has holes at the end - that is a common case:
- * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
- *
- * BH_Boundary explanation:
- *
- * There is a problem. The mpage read code assembles several pages, gets all
- * their disk mappings, and then submits them all. That's fine, but obtaining
- * the disk mappings may require I/O. Reads of indirect blocks, for example.
+/*
+ * support function for mpage_readpages. The fs supplied get_block might
+ * return an up to date buffer. This is used to map that buffer into
+ * the page, which allows readpage to avoid triggering a duplicate call
+ * to get_block.
*
- * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
- * submitted in the following order:
- * 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
- * because the indirect block has to be read to get the mappings of blocks
- * 13,14,15,16. Obviously, this impacts performance.
- *
- * So what we do it to allow the filesystem's get_block() function to set
- * BH_Boundary when it maps block 11. BH_Boundary says: mapping of the block
- * after this one will require I/O against a block which is probably close to
- * this one. So you should push what I/O you have currently accumulated.
+ * The idea is to avoid adding buffers to pages that don't already have
+ * them. So when the buffer is up to date and the page size == block size,
+ * this marks the page up to date instead of adding new buffers.
+ */
+static void
+map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
+{
+ struct inode *inode = page->mapping->host;
+ struct buffer_head *page_bh, *head;
+ int block = 0;
+
+ if (!page_has_buffers(page)) {
+ /*
+ * don't make any buffers if there is only one buffer on
+ * the page and the page just needs to be set up to date
+ */
+ if (inode->i_blkbits == PAGE_CACHE_SHIFT &&
+ buffer_uptodate(bh)) {
+ SetPageUptodate(page);
+ return;
+ }
+ create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+ }
+ head = page_buffers(page);
+ page_bh = head;
+ do {
+ if (block == page_block) {
+ page_bh->b_state = bh->b_state;
+ page_bh->b_bdev = bh->b_bdev;
+ page_bh->b_blocknr = bh->b_blocknr;
+ break;
+ }
+ page_bh = page_bh->b_this_page;
+ block++;
+ } while (page_bh != head);
+}
+
+/*
+ * This is the worker routine which does all the work of mapping the disk
+ * blocks and constructs largest possible bios, submits them for IO if the
+ * blocks are not contiguous on the disk.
*
- * This all causes the disk requests to be issued in the correct order.
+ * We pass a buffer_head back and forth and use its buffer_mapped() flag to
+ * represent the validity of its disk mapping and to decide when to do the next
+ * get_block() call.
*/
static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
- sector_t *last_block_in_bio, get_block_t get_block)
+ sector_t *last_block_in_bio, struct buffer_head *map_bh,
+ unsigned long *first_logical_block, get_block_t get_block)
{
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
+ sector_t last_block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_hole = blocks_per_page;
struct block_device *bdev = NULL;
- struct buffer_head bh;
int length;
+ int fully_mapped = 1;
+ unsigned nblocks;
+ unsigned relative_block;
if (page_has_buffers(page))
goto confused;
- block_in_file = page->index << (PAGE_CACHE_SHIFT - blkbits);
- last_block = (inode->i_size + blocksize - 1) >> blkbits;
+ block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+ last_block = block_in_file + nr_pages * blocks_per_page;
+ last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
+ if (last_block > last_block_in_file)
+ last_block = last_block_in_file;
+ page_block = 0;
+
+ /*
+ * Map blocks using the result from the previous get_blocks call first.
+ */
+ nblocks = map_bh->b_size >> blkbits;
+ if (buffer_mapped(map_bh) && block_in_file > *first_logical_block &&
+ block_in_file < (*first_logical_block + nblocks)) {
+ unsigned map_offset = block_in_file - *first_logical_block;
+ unsigned last = nblocks - map_offset;
+
+ for (relative_block = 0; ; relative_block++) {
+ if (relative_block == last) {
+ clear_buffer_mapped(map_bh);
+ break;
+ }
+ if (page_block == blocks_per_page)
+ break;
+ blocks[page_block] = map_bh->b_blocknr + map_offset +
+ relative_block;
+ page_block++;
+ block_in_file++;
+ }
+ bdev = map_bh->b_bdev;
+ }
+
+ /*
+ * Then do more get_blocks calls until we are done with this page.
+ */
+ map_bh->b_page = page;
+ while (page_block < blocks_per_page) {
+ map_bh->b_state = 0;
+ map_bh->b_size = 0;
- for (page_block = 0; page_block < blocks_per_page;
- page_block++, block_in_file++) {
- bh.b_state = 0;
if (block_in_file < last_block) {
- if (get_block(inode, block_in_file, &bh, 0))
+ map_bh->b_size = (last_block-block_in_file) << blkbits;
+ if (get_block(inode, block_in_file, map_bh, 0))
goto confused;
+ *first_logical_block = block_in_file;
}
- if (!buffer_mapped(&bh)) {
+ if (!buffer_mapped(map_bh)) {
+ fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
+ page_block++;
+ block_in_file++;
continue;
}
+
+ /* some filesystems will copy data into the page during
+ * the get_block call, in which case we don't want to
+ * read it again. map_buffer_to_page copies the data
+ * we just collected from get_block into the page's buffers
+ * so readpage doesn't have to repeat the get_block call
+ */
+ if (buffer_uptodate(map_bh)) {
+ map_buffer_to_page(page, map_bh, page_block);
+ goto confused;
+ }
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
- if (page_block && blocks[page_block-1] != bh.b_blocknr-1)
+ if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
goto confused;
- blocks[page_block] = bh.b_blocknr;
- bdev = bh.b_bdev;
+ nblocks = map_bh->b_size >> blkbits;
+ for (relative_block = 0; ; relative_block++) {
+ if (relative_block == nblocks) {
+ clear_buffer_mapped(map_bh);
+ break;
+ } else if (page_block == blocks_per_page)
+ break;
+ blocks[page_block] = map_bh->b_blocknr+relative_block;
+ page_block++;
+ block_in_file++;
+ }
+ bdev = map_bh->b_bdev;
}
if (first_hole != blocks_per_page) {
- memset(kmap(page) + (first_hole << blkbits), 0,
- PAGE_CACHE_SIZE - (first_hole << blkbits));
- flush_dcache_page(page);
- kunmap(page);
+ zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
goto out;
}
+ } else if (fully_mapped) {
+ SetPageMappedToDisk(page);
+ }
+
+ if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
+ cleancache_get_page(page) == 0) {
+ SetPageUptodate(page);
+ goto confused;
}
/*
alloc_new:
if (bio == NULL) {
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
- nr_pages, GFP_KERNEL);
+ min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
+ GFP_KERNEL);
if (bio == NULL)
goto confused;
}
goto alloc_new;
}
- if (buffer_boundary(&bh) || (first_hole != blocks_per_page))
+ relative_block = block_in_file - *first_logical_block;
+ nblocks = map_bh->b_size >> blkbits;
+ if ((buffer_boundary(map_bh) && relative_block == nblocks) ||
+ (first_hole != blocks_per_page))
bio = mpage_bio_submit(READ, bio);
else
*last_block_in_bio = blocks[blocks_per_page - 1];
confused:
if (bio)
bio = mpage_bio_submit(READ, bio);
- block_read_full_page(page, get_block);
+ if (!PageUptodate(page))
+ block_read_full_page(page, get_block);
+ else
+ unlock_page(page);
goto out;
}
+/**
+ * mpage_readpages - populate an address space with some pages & start reads against them
+ * @mapping: the address_space
+ * @pages: The address of a list_head which contains the target pages. These
+ * pages have their ->index populated and are otherwise uninitialised.
+ * The page at @pages->prev has the lowest file offset, and reads should be
+ * issued in @pages->prev to @pages->next order.
+ * @nr_pages: The number of pages at *@pages
+ * @get_block: The filesystem's block mapper function.
+ *
+ * This function walks the pages and the blocks within each page, building and
+ * emitting large BIOs.
+ *
+ * If anything unusual happens, such as:
+ *
+ * - encountering a page which has buffers
+ * - encountering a page which has a non-hole after a hole
+ * - encountering a page with non-contiguous blocks
+ *
+ * then this code just gives up and calls the buffer_head-based read function.
+ * It does handle a page which has holes at the end - that is a common case:
+ * the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
+ *
+ * BH_Boundary explanation:
+ *
+ * There is a problem. The mpage read code assembles several pages, gets all
+ * their disk mappings, and then submits them all. That's fine, but obtaining
+ * the disk mappings may require I/O. Reads of indirect blocks, for example.
+ *
+ * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
+ * submitted in the following order:
+ * 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
+ *
+ * because the indirect block has to be read to get the mappings of blocks
+ * 13,14,15,16. Obviously, this impacts performance.
+ *
+ * So what we do it to allow the filesystem's get_block() function to set
+ * BH_Boundary when it maps block 11. BH_Boundary says: mapping of the block
+ * after this one will require I/O against a block which is probably close to
+ * this one. So you should push what I/O you have currently accumulated.
+ *
+ * This all causes the disk requests to be issued in the correct order.
+ */
int
mpage_readpages(struct address_space *mapping, struct list_head *pages,
unsigned nr_pages, get_block_t get_block)
struct bio *bio = NULL;
unsigned page_idx;
sector_t last_block_in_bio = 0;
- struct pagevec lru_pvec;
+ struct buffer_head map_bh;
+ unsigned long first_logical_block = 0;
- pagevec_init(&lru_pvec, 0);
+ map_bh.b_state = 0;
+ map_bh.b_size = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
- struct page *page = list_entry(pages->prev, struct page, list);
+ struct page *page = list_entry(pages->prev, struct page, lru);
prefetchw(&page->flags);
- list_del(&page->list);
- if (!add_to_page_cache(page, mapping, page->index)) {
+ list_del(&page->lru);
+ if (!add_to_page_cache_lru(page, mapping,
+ page->index, GFP_KERNEL)) {
bio = do_mpage_readpage(bio, page,
nr_pages - page_idx,
- &last_block_in_bio, get_block);
- if (!pagevec_add(&lru_pvec, page))
- __pagevec_lru_add(&lru_pvec);
- } else {
- page_cache_release(page);
+ &last_block_in_bio, &map_bh,
+ &first_logical_block,
+ get_block);
}
+ page_cache_release(page);
}
- pagevec_lru_add(&lru_pvec);
BUG_ON(!list_empty(pages));
if (bio)
mpage_bio_submit(READ, bio);
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
+ struct buffer_head map_bh;
+ unsigned long first_logical_block = 0;
- bio = do_mpage_readpage(bio, page, 1,
- &last_block_in_bio, get_block);
+ map_bh.b_state = 0;
+ map_bh.b_size = 0;
+ bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
+ &map_bh, &first_logical_block, get_block);
if (bio)
mpage_bio_submit(READ, bio);
return 0;
* written, so it can intelligently allocate a suitably-sized BIO. For now,
* just allocate full-size (16-page) BIOs.
*/
-static struct bio *
-mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
- sector_t *last_block_in_bio, int *ret)
+
+struct mpage_data {
+ struct bio *bio;
+ sector_t last_block_in_bio;
+ get_block_t *get_block;
+ unsigned use_writepage;
+};
+
+static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
{
+ struct mpage_data *mpd = data;
+ struct bio *bio = mpd->bio;
+ struct address_space *mapping = page->mapping;
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
unsigned long end_index;
sector_t boundary_block = 0;
struct block_device *boundary_bdev = NULL;
int length;
+ struct buffer_head map_bh;
+ loff_t i_size = i_size_read(inode);
+ int ret = 0;
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
* The page has no buffers: map it to disk
*/
BUG_ON(!PageUptodate(page));
- block_in_file = page->index << (PAGE_CACHE_SHIFT - blkbits);
- last_block = (inode->i_size - 1) >> blkbits;
+ block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+ last_block = (i_size - 1) >> blkbits;
+ map_bh.b_page = page;
for (page_block = 0; page_block < blocks_per_page; ) {
- struct buffer_head map_bh;
map_bh.b_state = 0;
- if (get_block(inode, block_in_file, &map_bh, 1))
+ map_bh.b_size = 1 << blkbits;
+ if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
break;
block_in_file++;
}
- if (page_block == 0)
- buffer_error();
+ BUG_ON(page_block == 0);
first_unmapped = page_block;
- end_index = inode->i_size >> PAGE_CACHE_SHIFT;
+page_is_mapped:
+ end_index = i_size >> PAGE_CACHE_SHIFT;
if (page->index >= end_index) {
- unsigned offset = inode->i_size & (PAGE_CACHE_SIZE - 1);
+ /*
+ * The page straddles i_size. It must be zeroed out on each
+ * and every writepage invocation because it may be mmapped.
+ * "A file is mapped in multiples of the page size. For a file
+ * that is not a multiple of the page size, the remaining memory
+ * is zeroed when mapped, and writes to that region are not
+ * written out to the file."
+ */
+ unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
if (page->index > end_index || !offset)
goto confused;
- memset(kmap(page) + offset, 0, PAGE_CACHE_SIZE - offset);
- flush_dcache_page(page);
- kunmap(page);
+ zero_user_segment(page, offset, PAGE_CACHE_SIZE);
}
-page_is_mapped:
-
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
- if (bio && *last_block_in_bio != blocks[0] - 1)
+ if (bio && mpd->last_block_in_bio != blocks[0] - 1)
bio = mpage_bio_submit(WRITE, bio);
alloc_new:
}
/*
+ * Must try to add the page before marking the buffer clean or
+ * the confused fail path above (OOM) will be very confused when
+ * it finds all bh marked clean (i.e. it will not write anything)
+ */
+ length = first_unmapped << blkbits;
+ if (bio_add_page(bio, page, length, 0) < length) {
+ bio = mpage_bio_submit(WRITE, bio);
+ goto alloc_new;
+ }
+
+ /*
* OK, we have our BIO, so we can now mark the buffers clean. Make
* sure to only clean buffers which we know we'll be writing.
*/
bh = bh->b_this_page;
} while (bh != head);
- if (buffer_heads_over_limit)
+ /*
+ * we cannot drop the bh if the page is not uptodate
+ * or a concurrent readpage would fail to serialize with the bh
+ * and it would read from disk before we reach the platter.
+ */
+ if (buffer_heads_over_limit && PageUptodate(page))
try_to_free_buffers(page);
}
- length = first_unmapped << blkbits;
- if (bio_add_page(bio, page, length, 0) < length) {
- bio = mpage_bio_submit(WRITE, bio);
- goto alloc_new;
- }
-
BUG_ON(PageWriteback(page));
- SetPageWriteback(page);
+ set_page_writeback(page);
unlock_page(page);
if (boundary || (first_unmapped != blocks_per_page)) {
bio = mpage_bio_submit(WRITE, bio);
boundary_block, 1 << blkbits);
}
} else {
- *last_block_in_bio = blocks[blocks_per_page - 1];
+ mpd->last_block_in_bio = blocks[blocks_per_page - 1];
}
goto out;
confused:
if (bio)
bio = mpage_bio_submit(WRITE, bio);
- *ret = page->mapping->a_ops->writepage(page);
+
+ if (mpd->use_writepage) {
+ ret = mapping->a_ops->writepage(page, wbc);
+ } else {
+ ret = -EAGAIN;
+ goto out;
+ }
+ /*
+ * The caller has a ref on the inode, so *mapping is stable
+ */
+ mapping_set_error(mapping, ret);
out:
- return bio;
+ mpd->bio = bio;
+ return ret;
}
/**
- * mpage_writepages - walk the list of dirty pages of the given
- * address space and writepage() all of them.
- *
+ * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of 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.
*
- * (The next two paragraphs refer to code which isn't here yet, but they
- * explain the presence of address_space.io_pages)
- *
- * Pages can be moved from clean_pages or locked_pages onto dirty_pages
- * at any time - it's not possible to lock against that. So pages which
- * have already been added to a BIO may magically reappear on the dirty_pages
- * list. And generic_writepages() will again try to lock those pages.
- * But I/O has not yet been started against the page. Thus deadlock.
- *
- * To avoid this, the entire contents of the dirty_pages list are moved
- * onto io_pages up-front. We then walk io_pages, locking the
- * pages and submitting them for I/O, moving them to locked_pages.
- *
- * This has the added benefit of preventing a livelock which would otherwise
- * occur if pages are being dirtied faster than we can write them out.
- *
* If a page is already under I/O, generic_writepages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
- * and msync() need to guarentee that all the data which was dirty at the time
- * the call was made get new I/O started against them. The way to do this is
- * to run filemap_fdatawait() before calling filemap_fdatawrite().
- *
- * It's fairly rare for PageWriteback pages to be on ->dirty_pages. It
- * means that someone redirtied the page while it was under I/O.
+ * and msync() need to guarantee that all the data which was dirty at the time
+ * the call was made get new I/O started against them. If wbc->sync_mode is
+ * WB_SYNC_ALL then we were called for data integrity and we must wait for
+ * existing IO to complete.
*/
int
mpage_writepages(struct address_space *mapping,
struct writeback_control *wbc, get_block_t get_block)
{
- struct backing_dev_info *bdi = mapping->backing_dev_info;
- struct bio *bio = NULL;
- sector_t last_block_in_bio = 0;
- int ret = 0;
- int done = 0;
- int sync = called_for_sync();
- struct pagevec pvec;
- int (*writepage)(struct page *);
-
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- blk_run_queues();
- wbc->encountered_congestion = 1;
- return 0;
- }
-
- writepage = NULL;
- if (get_block == NULL)
- writepage = mapping->a_ops->writepage;
-
- pagevec_init(&pvec, 0);
- write_lock(&mapping->page_lock);
-
- list_splice_init(&mapping->dirty_pages, &mapping->io_pages);
-
- while (!list_empty(&mapping->io_pages) && !done) {
- struct page *page = list_entry(mapping->io_pages.prev,
- struct page, list);
- list_del(&page->list);
- if (PageWriteback(page) && !sync) {
- if (PageDirty(page)) {
- list_add(&page->list, &mapping->dirty_pages);
- continue;
- }
- list_add(&page->list, &mapping->locked_pages);
- continue;
- }
- if (!PageDirty(page)) {
- list_add(&page->list, &mapping->clean_pages);
- continue;
- }
- list_add(&page->list, &mapping->locked_pages);
-
- page_cache_get(page);
- write_unlock(&mapping->page_lock);
-
- lock_page(page);
-
- if (sync)
- wait_on_page_writeback(page);
-
- if (page->mapping && !PageWriteback(page) &&
- test_clear_page_dirty(page)) {
- if (writepage) {
- ret = (*writepage)(page);
- if (ret == -EAGAIN) {
- __set_page_dirty_nobuffers(page);
- ret = 0;
- }
- } else {
- bio = mpage_writepage(bio, page, get_block,
- &last_block_in_bio, &ret);
- }
- if ((current->flags & PF_MEMALLOC) &&
- !PageActive(page) && PageLRU(page)) {
- if (!pagevec_add(&pvec, page))
- pagevec_deactivate_inactive(&pvec);
- page = NULL;
- }
- if (ret || (--(wbc->nr_to_write) <= 0))
- done = 1;
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- blk_run_queues();
- wbc->encountered_congestion = 1;
- done = 1;
- }
- } else {
- unlock_page(page);
- }
-
- if (page)
- page_cache_release(page);
- write_lock(&mapping->page_lock);
+ struct blk_plug plug;
+ int ret;
+
+ blk_start_plug(&plug);
+
+ if (!get_block)
+ ret = generic_writepages(mapping, wbc);
+ else {
+ struct mpage_data mpd = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = get_block,
+ .use_writepage = 1,
+ };
+
+ ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit(WRITE, mpd.bio);
}
- /*
- * Leave any remaining dirty pages on ->io_pages
- */
- write_unlock(&mapping->page_lock);
- pagevec_deactivate_inactive(&pvec);
- if (bio)
- mpage_bio_submit(WRITE, bio);
+ blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(mpage_writepages);
+
+int mpage_writepage(struct page *page, get_block_t get_block,
+ struct writeback_control *wbc)
+{
+ struct mpage_data mpd = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = get_block,
+ .use_writepage = 0,
+ };
+ int ret = __mpage_writepage(page, wbc, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit(WRITE, mpd.bio);
+ return ret;
+}
+EXPORT_SYMBOL(mpage_writepage);
projects / linux-flexiantxendom0-3.2.10.git / blobdiff