summaryrefslogtreecommitdiff
path: root/fs/mpage.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/mpage.c')
-rw-r--r--fs/mpage.c548
1 files changed, 255 insertions, 293 deletions
diff --git a/fs/mpage.c b/fs/mpage.c
index 0face1c4d4c6..7dae5afc2b9e 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* fs/mpage.c
*
@@ -24,111 +25,96 @@
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
+#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/cleancache.h>
+#include "internal.h"
/*
* I/O completion handler for multipage BIOs.
*
* The mpage code never puts partial pages into a BIO (except for end-of-file).
* If a page does not map to a contiguous run of blocks then it simply falls
- * back to block_read_full_page().
+ * back to block_read_full_folio().
*
* Why is this? If a page's completion depends on a number of different BIOs
* which can complete in any order (or at the same time) then determining the
* status of that page is hard. See end_buffer_async_read() for the details.
* There is no point in duplicating all that complexity.
*/
-static void mpage_end_io(struct bio *bio, int err)
+static void mpage_read_end_io(struct bio *bio)
{
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct folio_iter fi;
+ int err = blk_status_to_errno(bio->bi_status);
- do {
- struct page *page = bvec->bv_page;
+ bio_for_each_folio_all(fi, bio)
+ folio_end_read(fi.folio, err == 0);
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
- 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);
- }
- } while (bvec >= bio->bi_io_vec);
bio_put(bio);
}
-static struct bio *mpage_bio_submit(int rw, struct bio *bio)
+static void mpage_write_end_io(struct bio *bio)
{
- bio->bi_end_io = mpage_end_io;
- submit_bio(rw, bio);
- return NULL;
-}
+ struct folio_iter fi;
+ int err = blk_status_to_errno(bio->bi_status);
-static struct bio *
-mpage_alloc(struct block_device *bdev,
- sector_t first_sector, int nr_vecs,
- gfp_t gfp_flags)
-{
- struct bio *bio;
+ bio_for_each_folio_all(fi, bio) {
+ if (err)
+ mapping_set_error(fi.folio->mapping, err);
+ folio_end_writeback(fi.folio);
+ }
- bio = bio_alloc(gfp_flags, nr_vecs);
+ bio_put(bio);
+}
- if (bio == NULL && (current->flags & PF_MEMALLOC)) {
- while (!bio && (nr_vecs /= 2))
- bio = bio_alloc(gfp_flags, nr_vecs);
- }
+static struct bio *mpage_bio_submit_read(struct bio *bio)
+{
+ bio->bi_end_io = mpage_read_end_io;
+ guard_bio_eod(bio);
+ submit_bio(bio);
+ return NULL;
+}
- if (bio) {
- bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
- }
- return bio;
+static struct bio *mpage_bio_submit_write(struct bio *bio)
+{
+ bio->bi_end_io = mpage_write_end_io;
+ guard_bio_eod(bio);
+ submit_bio(bio);
+ return NULL;
}
/*
- * support function for mpage_readpages. The fs supplied get_block might
+ * support function for mpage_readahead. 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
+ * the page, which allows read_folio to avoid triggering a duplicate call
* to get_block.
*
* 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)
+static void map_buffer_to_folio(struct folio *folio, struct buffer_head *bh,
+ int page_block)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
struct buffer_head *page_bh, *head;
int block = 0;
- if (!page_has_buffers(page)) {
+ head = folio_buffers(folio);
+ if (!head) {
/*
* 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
+ * the folio and the folio just needs to be set up to date
*/
- if (inode->i_blkbits == PAGE_CACHE_SHIFT &&
+ if (inode->i_blkbits == folio_shift(folio) &&
buffer_uptodate(bh)) {
- SetPageUptodate(page);
+ folio_mark_uptodate(folio);
return;
}
- create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+ head = create_empty_buffers(folio, i_blocksize(inode), 0);
}
- head = page_buffers(page);
+
page_bh = head;
do {
if (block == page_block) {
@@ -142,6 +128,17 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
} while (page_bh != head);
}
+struct mpage_readpage_args {
+ struct bio *bio;
+ struct folio *folio;
+ unsigned int nr_pages;
+ bool is_readahead;
+ sector_t last_block_in_bio;
+ struct buffer_head map_bh;
+ unsigned long first_logical_block;
+ get_block_t *get_block;
+};
+
/*
* 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
@@ -151,32 +148,38 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
* 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, struct buffer_head *map_bh,
- unsigned long *first_logical_block, get_block_t get_block)
+static void do_mpage_readpage(struct mpage_readpage_args *args)
{
- struct inode *inode = page->mapping->host;
+ struct folio *folio = args->folio;
+ struct inode *inode = folio->mapping->host;
const unsigned blkbits = inode->i_blkbits;
- const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+ const unsigned blocks_per_folio = folio_size(folio) >> blkbits;
const unsigned blocksize = 1 << blkbits;
+ struct buffer_head *map_bh = &args->map_bh;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
- sector_t blocks[MAX_BUF_PER_PAGE];
+ sector_t first_block;
unsigned page_block;
- unsigned first_hole = blocks_per_page;
+ unsigned first_hole = blocks_per_folio;
struct block_device *bdev = NULL;
int length;
int fully_mapped = 1;
+ blk_opf_t opf = REQ_OP_READ;
unsigned nblocks;
unsigned relative_block;
+ gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL);
+
+ if (args->is_readahead) {
+ opf |= REQ_RAHEAD;
+ gfp |= __GFP_NORETRY | __GFP_NOWARN;
+ }
- if (page_has_buffers(page))
+ if (folio_buffers(folio))
goto confused;
- block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
- last_block = block_in_file + nr_pages * blocks_per_page;
+ block_in_file = folio_pos(folio) >> blkbits;
+ last_block = block_in_file + ((args->nr_pages * PAGE_SIZE) >> blkbits);
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
@@ -186,20 +189,20 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
* 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;
+ if (buffer_mapped(map_bh) &&
+ block_in_file > args->first_logical_block &&
+ block_in_file < (args->first_logical_block + nblocks)) {
+ unsigned map_offset = block_in_file - args->first_logical_block;
unsigned last = nblocks - map_offset;
+ first_block = map_bh->b_blocknr + map_offset;
for (relative_block = 0; ; relative_block++) {
if (relative_block == last) {
clear_buffer_mapped(map_bh);
break;
}
- if (page_block == blocks_per_page)
+ if (page_block == blocks_per_folio)
break;
- blocks[page_block] = map_bh->b_blocknr + map_offset +
- relative_block;
page_block++;
block_in_file++;
}
@@ -207,23 +210,23 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
}
/*
- * Then do more get_blocks calls until we are done with this page.
+ * Then do more get_blocks calls until we are done with this folio.
*/
- map_bh->b_page = page;
- while (page_block < blocks_per_page) {
+ map_bh->b_folio = folio;
+ while (page_block < blocks_per_folio) {
map_bh->b_state = 0;
map_bh->b_size = 0;
if (block_in_file < last_block) {
map_bh->b_size = (last_block-block_in_file) << blkbits;
- if (get_block(inode, block_in_file, map_bh, 0))
+ if (args->get_block(inode, block_in_file, map_bh, 0))
goto confused;
- *first_logical_block = block_in_file;
+ args->first_logical_block = block_in_file;
}
if (!buffer_mapped(map_bh)) {
fully_mapped = 0;
- if (first_hole == blocks_per_page)
+ if (first_hole == blocks_per_folio)
first_hole = page_block;
page_block++;
block_in_file++;
@@ -232,101 +235,91 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
/* 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
+ * read it again. map_buffer_to_folio copies the data
+ * we just collected from get_block into the folio's buffers
+ * so read_folio doesn't have to repeat the get_block call
*/
if (buffer_uptodate(map_bh)) {
- map_buffer_to_page(page, map_bh, page_block);
+ map_buffer_to_folio(folio, map_bh, page_block);
goto confused;
}
- if (first_hole != blocks_per_page)
+ if (first_hole != blocks_per_folio)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
- if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
+ if (!page_block)
+ first_block = map_bh->b_blocknr;
+ else if (first_block + page_block != map_bh->b_blocknr)
goto confused;
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)
+ } else if (page_block == blocks_per_folio)
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) {
- zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
+ if (first_hole != blocks_per_folio) {
+ folio_zero_segment(folio, first_hole << blkbits, folio_size(folio));
if (first_hole == 0) {
- SetPageUptodate(page);
- unlock_page(page);
+ folio_mark_uptodate(folio);
+ folio_unlock(folio);
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;
+ folio_set_mappedtodisk(folio);
}
/*
- * This page will go to BIO. Do we need to send this BIO off first?
+ * This folio will go to BIO. Do we need to send this BIO off first?
*/
- if (bio && (*last_block_in_bio != blocks[0] - 1))
- bio = mpage_bio_submit(READ, bio);
+ if (args->bio && (args->last_block_in_bio != first_block - 1))
+ args->bio = mpage_bio_submit_read(args->bio);
alloc_new:
- if (bio == NULL) {
- bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
- min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
- GFP_KERNEL);
- if (bio == NULL)
+ if (args->bio == NULL) {
+ args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), opf,
+ gfp);
+ if (args->bio == NULL)
goto confused;
+ args->bio->bi_iter.bi_sector = first_block << (blkbits - 9);
}
length = first_hole << blkbits;
- if (bio_add_page(bio, page, length, 0) < length) {
- bio = mpage_bio_submit(READ, bio);
+ if (!bio_add_folio(args->bio, folio, length, 0)) {
+ args->bio = mpage_bio_submit_read(args->bio);
goto alloc_new;
}
- relative_block = block_in_file - *first_logical_block;
+ relative_block = block_in_file - args->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);
+ (first_hole != blocks_per_folio))
+ args->bio = mpage_bio_submit_read(args->bio);
else
- *last_block_in_bio = blocks[blocks_per_page - 1];
+ args->last_block_in_bio = first_block + blocks_per_folio - 1;
out:
- return bio;
+ return;
confused:
- if (bio)
- bio = mpage_bio_submit(READ, bio);
- if (!PageUptodate(page))
- block_read_full_page(page, get_block);
+ if (args->bio)
+ args->bio = mpage_bio_submit_read(args->bio);
+ if (!folio_test_uptodate(folio))
+ block_read_full_folio(folio, args->get_block);
else
- unlock_page(page);
+ folio_unlock(folio);
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
+ * mpage_readahead - start reads against pages
+ * @rac: Describes which pages to read.
* @get_block: The filesystem's block mapper function.
*
* This function walks the pages and the blocks within each page, building and
@@ -340,7 +333,7 @@ confused:
*
* 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.
+ * the end-of-file on blocksize < PAGE_SIZE setups.
*
* BH_Boundary explanation:
*
@@ -350,6 +343,7 @@ confused:
*
* 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
@@ -362,59 +356,48 @@ confused:
*
* 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)
+void mpage_readahead(struct readahead_control *rac, get_block_t get_block)
{
- struct bio *bio = NULL;
- unsigned page_idx;
- sector_t last_block_in_bio = 0;
- struct buffer_head map_bh;
- unsigned long first_logical_block = 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, lru);
-
- prefetchw(&page->flags);
- 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, &map_bh,
- &first_logical_block,
- get_block);
- }
- page_cache_release(page);
+ struct folio *folio;
+ struct mpage_readpage_args args = {
+ .get_block = get_block,
+ .is_readahead = true,
+ };
+
+ while ((folio = readahead_folio(rac))) {
+ prefetchw(&folio->flags);
+ args.folio = folio;
+ args.nr_pages = readahead_count(rac);
+ do_mpage_readpage(&args);
+ /*
+ * If read ahead failed synchronously, it may cause by removed
+ * device, or some filesystem metadata error.
+ */
+ if (!folio_test_locked(folio) && !folio_test_uptodate(folio))
+ break;
}
- BUG_ON(!list_empty(pages));
- if (bio)
- mpage_bio_submit(READ, bio);
- return 0;
+ if (args.bio)
+ mpage_bio_submit_read(args.bio);
}
-EXPORT_SYMBOL(mpage_readpages);
+EXPORT_SYMBOL(mpage_readahead);
/*
* This isn't called much at all
*/
-int mpage_readpage(struct page *page, get_block_t get_block)
+int mpage_read_folio(struct folio *folio, get_block_t get_block)
{
- struct bio *bio = NULL;
- sector_t last_block_in_bio = 0;
- struct buffer_head map_bh;
- unsigned long first_logical_block = 0;
+ struct mpage_readpage_args args = {
+ .folio = folio,
+ .nr_pages = folio_nr_pages(folio),
+ .get_block = 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);
+ do_mpage_readpage(&args);
+ if (args.bio)
+ mpage_bio_submit_read(args.bio);
return 0;
}
-EXPORT_SYMBOL(mpage_readpage);
+EXPORT_SYMBOL(mpage_read_folio);
/*
* Writing is not so simple.
@@ -437,35 +420,61 @@ 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)
+/*
+ * 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.
+ */
+static void clean_buffers(struct folio *folio, unsigned first_unmapped)
+{
+ unsigned buffer_counter = 0;
+ struct buffer_head *bh, *head = folio_buffers(folio);
+
+ if (!head)
+ return;
+ bh = head;
+
+ do {
+ if (buffer_counter++ == first_unmapped)
+ break;
+ clear_buffer_dirty(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+
+ /*
+ * we cannot drop the bh if the page is not uptodate or a concurrent
+ * read_folio would fail to serialize with the bh and it would read from
+ * disk before we reach the platter.
+ */
+ if (buffer_heads_over_limit && folio_test_uptodate(folio))
+ try_to_free_buffers(folio);
+}
+
+static int mpage_write_folio(struct writeback_control *wbc, struct folio *folio,
+ struct mpage_data *mpd)
{
- struct mpage_data *mpd = data;
struct bio *bio = mpd->bio;
- struct address_space *mapping = page->mapping;
- struct inode *inode = page->mapping->host;
+ struct address_space *mapping = folio->mapping;
+ struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
- unsigned long end_index;
- const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+ const unsigned blocks_per_folio = folio_size(folio) >> blkbits;
sector_t last_block;
sector_t block_in_file;
- sector_t blocks[MAX_BUF_PER_PAGE];
+ sector_t first_block;
unsigned page_block;
- unsigned first_unmapped = blocks_per_page;
+ unsigned first_unmapped = blocks_per_folio;
struct block_device *bdev = NULL;
int boundary = 0;
sector_t boundary_block = 0;
struct block_device *boundary_bdev = NULL;
- int length;
+ size_t length;
struct buffer_head map_bh;
loff_t i_size = i_size_read(inode);
int ret = 0;
+ struct buffer_head *head = folio_buffers(folio);
- if (page_has_buffers(page)) {
- struct buffer_head *head = page_buffers(page);
+ if (head) {
struct buffer_head *bh = head;
/* If they're all mapped and dirty, do it */
@@ -475,25 +484,27 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
if (!buffer_mapped(bh)) {
/*
* unmapped dirty buffers are created by
- * __set_page_dirty_buffers -> mmapped data
+ * block_dirty_folio -> mmapped data
*/
if (buffer_dirty(bh))
goto confused;
- if (first_unmapped == blocks_per_page)
+ if (first_unmapped == blocks_per_folio)
first_unmapped = page_block;
continue;
}
- if (first_unmapped != blocks_per_page)
+ if (first_unmapped != blocks_per_folio)
goto confused; /* hole -> non-hole */
if (!buffer_dirty(bh) || !buffer_uptodate(bh))
goto confused;
if (page_block) {
- if (bh->b_blocknr != blocks[page_block-1] + 1)
+ if (bh->b_blocknr != first_block + page_block)
goto confused;
+ } else {
+ first_block = bh->b_blocknr;
}
- blocks[page_block++] = bh->b_blocknr;
+ page_block++;
boundary = buffer_boundary(bh);
if (boundary) {
boundary_block = bh->b_blocknr;
@@ -508,8 +519,8 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
/*
* Page has buffers, but they are all unmapped. The page was
* created by pagein or read over a hole which was handled by
- * block_read_full_page(). If this address_space is also
- * using mpage_readpages then this can rarely happen.
+ * block_read_full_folio(). If this address_space is also
+ * using mpage_readahead then this can rarely happen.
*/
goto confused;
}
@@ -517,28 +528,37 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
/*
* The page has no buffers: map it to disk
*/
- BUG_ON(!PageUptodate(page));
- block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+ BUG_ON(!folio_test_uptodate(folio));
+ block_in_file = folio_pos(folio) >> blkbits;
+ /*
+ * Whole page beyond EOF? Skip allocating blocks to avoid leaking
+ * space.
+ */
+ if (block_in_file >= (i_size + (1 << blkbits) - 1) >> blkbits)
+ goto page_is_mapped;
last_block = (i_size - 1) >> blkbits;
- map_bh.b_page = page;
- for (page_block = 0; page_block < blocks_per_page; ) {
+ map_bh.b_folio = folio;
+ for (page_block = 0; page_block < blocks_per_folio; ) {
map_bh.b_state = 0;
map_bh.b_size = 1 << blkbits;
if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
+ if (!buffer_mapped(&map_bh))
+ goto confused;
if (buffer_new(&map_bh))
- unmap_underlying_metadata(map_bh.b_bdev,
- map_bh.b_blocknr);
+ clean_bdev_bh_alias(&map_bh);
if (buffer_boundary(&map_bh)) {
boundary_block = map_bh.b_blocknr;
boundary_bdev = map_bh.b_bdev;
}
if (page_block) {
- if (map_bh.b_blocknr != blocks[page_block-1] + 1)
+ if (map_bh.b_blocknr != first_block + page_block)
goto confused;
+ } else {
+ first_block = map_bh.b_blocknr;
}
- blocks[page_block++] = map_bh.b_blocknr;
+ page_block++;
boundary = buffer_boundary(&map_bh);
bdev = map_bh.b_bdev;
if (block_in_file == last_block)
@@ -550,8 +570,11 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
first_unmapped = page_block;
page_is_mapped:
- end_index = i_size >> PAGE_CACHE_SHIFT;
- if (page->index >= end_index) {
+ /* Don't bother writing beyond EOF, truncate will discard the folio */
+ if (folio_pos(folio) >= i_size)
+ goto confused;
+ length = folio_size(folio);
+ if (folio_pos(folio) + length > i_size) {
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
@@ -560,25 +583,24 @@ page_is_mapped:
* 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;
- zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+ length = i_size - folio_pos(folio);
+ folio_zero_segment(folio, length, folio_size(folio));
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
- if (bio && mpd->last_block_in_bio != blocks[0] - 1)
- bio = mpage_bio_submit(WRITE, bio);
+ if (bio && mpd->last_block_in_bio != first_block - 1)
+ bio = mpage_bio_submit_write(bio);
alloc_new:
if (bio == NULL) {
- bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
- bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
- if (bio == NULL)
- goto confused;
+ bio = bio_alloc(bdev, BIO_MAX_VECS,
+ REQ_OP_WRITE | wbc_to_write_flags(wbc),
+ GFP_NOFS);
+ bio->bi_iter.bi_sector = first_block << (blkbits - 9);
+ wbc_init_bio(wbc, bio);
+ bio->bi_write_hint = inode->i_write_hint;
}
/*
@@ -586,64 +608,37 @@ alloc_new:
* the confused fail path above (OOM) will be very confused when
* it finds all bh marked clean (i.e. it will not write anything)
*/
+ wbc_account_cgroup_owner(wbc, folio, folio_size(folio));
length = first_unmapped << blkbits;
- if (bio_add_page(bio, page, length, 0) < length) {
- bio = mpage_bio_submit(WRITE, bio);
+ if (!bio_add_folio(bio, folio, length, 0)) {
+ 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.
- */
- if (page_has_buffers(page)) {
- struct buffer_head *head = page_buffers(page);
- struct buffer_head *bh = head;
- unsigned buffer_counter = 0;
+ clean_buffers(folio, first_unmapped);
- do {
- if (buffer_counter++ == first_unmapped)
- break;
- clear_buffer_dirty(bh);
- bh = bh->b_this_page;
- } while (bh != head);
-
- /*
- * 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);
- }
-
- BUG_ON(PageWriteback(page));
- set_page_writeback(page);
- unlock_page(page);
- if (boundary || (first_unmapped != blocks_per_page)) {
- bio = mpage_bio_submit(WRITE, bio);
+ BUG_ON(folio_test_writeback(folio));
+ folio_start_writeback(folio);
+ folio_unlock(folio);
+ if (boundary || (first_unmapped != blocks_per_folio)) {
+ bio = mpage_bio_submit_write(bio);
if (boundary_block) {
write_boundary_block(boundary_bdev,
boundary_block, 1 << blkbits);
}
} else {
- mpd->last_block_in_bio = blocks[blocks_per_page - 1];
+ mpd->last_block_in_bio = first_block + blocks_per_folio - 1;
}
goto out;
confused:
if (bio)
- bio = mpage_bio_submit(WRITE, bio);
+ bio = mpage_bio_submit_write(bio);
- 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
*/
+ ret = block_write_full_folio(folio, wbc, mpd->get_block);
mapping_set_error(mapping, ret);
out:
mpd->bio = bio;
@@ -655,60 +650,27 @@ out:
* @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.
- * If this is NULL then use a_ops->writepage. Otherwise, go
- * direct-to-BIO.
*
* This is a library function, which implements the writepages()
* address_space_operation.
- *
- * 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 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 mpage_data mpd = {
+ .get_block = get_block,
+ };
+ struct folio *folio = NULL;
struct blk_plug plug;
- int ret;
+ int error;
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);
- }
+ while ((folio = writeback_iter(mapping, wbc, folio, &error)))
+ error = mpage_write_folio(wbc, folio, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit_write(mpd.bio);
blk_finish_plug(&plug);
- return ret;
+ return error;
}
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);
generated by cgit (git 2.34.1) at 2025-12-22 01:48:00 +0000