WSL2-Linux-Kernel/fs/mpage.c

834 строки
23 KiB
C
Исходник Обычный вид История

/*
* fs/mpage.c
*
* Copyright (C) 2002, Linus Torvalds.
*
* Contains functions related to preparing and submitting BIOs which contain
* multiple pagecache pages.
*
* 15May2002 akpm@zip.com.au
* 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/mm.h>
#include <linux/kdev_t.h>
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/prefetch.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.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().
*
* 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 int mpage_end_io_read(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) {
SetPageUptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(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);
if (page->mapping)
set_bit(AS_EIO, &page->mapping->flags);
}
end_page_writeback(page);
} while (bvec >= bio->bi_io_vec);
bio_put(bio);
return 0;
}
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;
submit_bio(rw, bio);
return NULL;
}
static struct bio *
mpage_alloc(struct block_device *bdev,
sector_t first_sector, int nr_vecs,
gfp_t gfp_flags)
{
struct bio *bio;
bio = bio_alloc(gfp_flags, nr_vecs);
if (bio == NULL && (current->flags & PF_MEMALLOC)) {
while (!bio && (nr_vecs /= 2))
bio = bio_alloc(gfp_flags, nr_vecs);
}
if (bio) {
bio->bi_bdev = bdev;
bio->bi_sector = first_sector;
}
return bio;
}
/*
* 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.
*
* 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.
*
* 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, 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 blocks_per_page = PAGE_CACHE_SIZE >> 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;
int length;
int fully_mapped = 1;
unsigned nblocks;
unsigned relative_block;
if (page_has_buffers(page))
goto confused;
[PATCH] fix possible PAGE_CACHE_SHIFT overflows We've had two instances recently of overflows when doing 64_bit_value = (32_bit_value << PAGE_CACHE_SHIFT) I did a tree-wide grep of `<<.*PAGE_CACHE_SHIFT' and this is the result. - afs_rxfs_fetch_descriptor.offset is of type off_t, which seems broken. - jfs and jffs are limited to 4GB anyway. - reiserfs map_block_for_writepage() takes an unsigned long for the block - it should take sector_t. (It'll fail for huge filesystems with blocksize<PAGE_CACHE_SIZE) - cramfs_read() needs to use sector_t (I think cramsfs is busted on large filesystems anyway) - affs is limited in file size anyway. - I generally didn't fix 32-bit overflows in directory operations. - arm's __flush_dcache_page() is peculiar. What if the page lies beyond 4G? - gss_wrap_req_priv() needs checking (snd_buf->page_base) Cc: Oleg Drokin <green@linuxhacker.ru> Cc: David Howells <dhowells@redhat.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: <reiserfs-dev@namesys.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: <linux-fsdevel@vger.kernel.org> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 12:03:05 +03:00
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;
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))
goto confused;
*first_logical_block = block_in_file;
}
if (!buffer_mapped(map_bh)) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
clear_buffer_mapped(map_bh);
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] != map_bh->b_blocknr-1)
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)
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) {
char *kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr + (first_hole << blkbits), 0,
PAGE_CACHE_SIZE - (first_hole << blkbits));
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
goto out;
}
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
/*
* This page 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);
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)
goto confused;
}
length = first_hole << blkbits;
if (bio_add_page(bio, page, length, 0) < length) {
bio = mpage_bio_submit(READ, bio);
goto alloc_new;
}
if (buffer_boundary(map_bh) || (first_hole != blocks_per_page))
bio = mpage_bio_submit(READ, bio);
else
*last_block_in_bio = blocks[blocks_per_page - 1];
out:
return bio;
confused:
if (bio)
bio = mpage_bio_submit(READ, bio);
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, 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.
*
* 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;
clear_buffer_mapped(&map_bh);
pagevec_init(&lru_pvec, 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(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);
if (!pagevec_add(&lru_pvec, page))
__pagevec_lru_add(&lru_pvec);
} else {
page_cache_release(page);
}
}
pagevec_lru_add(&lru_pvec);
BUG_ON(!list_empty(pages));
if (bio)
mpage_bio_submit(READ, bio);
return 0;
}
EXPORT_SYMBOL(mpage_readpages);
/*
* This isn't called much at all
*/
int mpage_readpage(struct page *page, 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;
clear_buffer_mapped(&map_bh);
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;
}
EXPORT_SYMBOL(mpage_readpage);
/*
* Writing is not so simple.
*
* If the page has buffers then they will be used for obtaining the disk
* mapping. We only support pages which are fully mapped-and-dirty, with a
* special case for pages which are unmapped at the end: end-of-file.
*
* If the page has no buffers (preferred) then the page is mapped here.
*
* If all blocks are found to be contiguous then the page can go into the
* BIO. Otherwise fall back to the mapping's writepage().
*
* FIXME: This code wants an estimate of how many pages are still to be
* 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 writeback_control *wbc,
writepage_t writepage_fn)
{
struct address_space *mapping = page->mapping;
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
unsigned long end_index;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
sector_t last_block;
sector_t block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_unmapped = blocks_per_page;
struct block_device *bdev = NULL;
int boundary = 0;
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);
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
/* If they're all mapped and dirty, do it */
page_block = 0;
do {
BUG_ON(buffer_locked(bh));
if (!buffer_mapped(bh)) {
/*
* unmapped dirty buffers are created by
* __set_page_dirty_buffers -> mmapped data
*/
if (buffer_dirty(bh))
goto confused;
if (first_unmapped == blocks_per_page)
first_unmapped = page_block;
continue;
}
if (first_unmapped != blocks_per_page)
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)
goto confused;
}
blocks[page_block++] = bh->b_blocknr;
boundary = buffer_boundary(bh);
if (boundary) {
boundary_block = bh->b_blocknr;
boundary_bdev = bh->b_bdev;
}
bdev = bh->b_bdev;
} while ((bh = bh->b_this_page) != head);
if (first_unmapped)
goto page_is_mapped;
/*
* 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.
*/
goto confused;
}
/*
* The page has no buffers: map it to disk
*/
BUG_ON(!PageUptodate(page));
[PATCH] fix possible PAGE_CACHE_SHIFT overflows We've had two instances recently of overflows when doing 64_bit_value = (32_bit_value << PAGE_CACHE_SHIFT) I did a tree-wide grep of `<<.*PAGE_CACHE_SHIFT' and this is the result. - afs_rxfs_fetch_descriptor.offset is of type off_t, which seems broken. - jfs and jffs are limited to 4GB anyway. - reiserfs map_block_for_writepage() takes an unsigned long for the block - it should take sector_t. (It'll fail for huge filesystems with blocksize<PAGE_CACHE_SIZE) - cramfs_read() needs to use sector_t (I think cramsfs is busted on large filesystems anyway) - affs is limited in file size anyway. - I generally didn't fix 32-bit overflows in directory operations. - arm's __flush_dcache_page() is peculiar. What if the page lies beyond 4G? - gss_wrap_req_priv() needs checking (snd_buf->page_base) Cc: Oleg Drokin <green@linuxhacker.ru> Cc: David Howells <dhowells@redhat.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: <reiserfs-dev@namesys.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: <linux-fsdevel@vger.kernel.org> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 12:03:05 +03:00
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; ) {
map_bh.b_state = 0;
map_bh.b_size = 1 << blkbits;
if (get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
map_bh.b_blocknr);
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)
goto confused;
}
blocks[page_block++] = map_bh.b_blocknr;
boundary = buffer_boundary(&map_bh);
bdev = map_bh.b_bdev;
if (block_in_file == last_block)
break;
block_in_file++;
}
BUG_ON(page_block == 0);
first_unmapped = page_block;
page_is_mapped:
end_index = i_size >> PAGE_CACHE_SHIFT;
if (page->index >= end_index) {
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invokation 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);
char *kaddr;
if (page->index > end_index || !offset)
goto confused;
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
}
/*
* This page 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(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;
}
/*
* 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.
*/
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
unsigned buffer_counter = 0;
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);
if (boundary_block) {
write_boundary_block(boundary_bdev,
boundary_block, 1 << blkbits);
}
} else {
*last_block_in_bio = blocks[blocks_per_page - 1];
}
goto out;
confused:
if (bio)
bio = mpage_bio_submit(WRITE, bio);
if (writepage_fn) {
*ret = (*writepage_fn)(page, wbc);
} else {
*ret = -EAGAIN;
goto out;
}
/*
* The caller has a ref on the inode, so *mapping is stable
*/
if (*ret) {
if (*ret == -ENOSPC)
set_bit(AS_ENOSPC, &mapping->flags);
else
set_bit(AS_EIO, &mapping->flags);
}
out:
return bio;
}
/**
* mpage_writepages - walk the list of dirty pages of the given
* address space and 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.
* 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 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 (*writepage)(struct page *page, struct writeback_control *wbc);
struct pagevec pvec;
int nr_pages;
pgoff_t index;
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
pgoff_t end; /* Inclusive */
int scanned = 0;
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
int range_whole = 0;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
writepage = NULL;
if (get_block == NULL)
writepage = mapping->a_ops->writepage;
pagevec_init(&pvec, 0);
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
end = -1;
} else {
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
scanned = 1;
}
retry:
while (!done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
unsigned i;
scanned = 1;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point we hold neither mapping->tree_lock nor
* lock on the page itself: the page may be truncated or
* invalidated (changing page->mapping to NULL), or even
* swizzled back from swapper_space to tmpfs file
* mapping
*/
lock_page(page);
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
if (!wbc->range_cyclic && page->index > end) {
done = 1;
unlock_page(page);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
if (PageWriteback(page) ||
!clear_page_dirty_for_io(page)) {
unlock_page(page);
continue;
}
if (writepage) {
ret = (*writepage)(page, wbc);
if (ret) {
if (ret == -ENOSPC)
set_bit(AS_ENOSPC,
&mapping->flags);
else
set_bit(AS_EIO,
&mapping->flags);
}
} else {
bio = __mpage_writepage(bio, page, get_block,
&last_block_in_bio, &ret, wbc,
page->mapping->a_ops->writepage);
}
if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
unlock_page(page);
if (ret || (--(wbc->nr_to_write) <= 0))
done = 1;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
goto retry;
}
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:03:26 +04:00
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = index;
if (bio)
mpage_bio_submit(WRITE, bio);
return ret;
}
EXPORT_SYMBOL(mpage_writepages);
int mpage_writepage(struct page *page, get_block_t get_block,
struct writeback_control *wbc)
{
int ret = 0;
struct bio *bio;
sector_t last_block_in_bio = 0;
bio = __mpage_writepage(NULL, page, get_block,
&last_block_in_bio, &ret, wbc, NULL);
if (bio)
mpage_bio_submit(WRITE, bio);
return ret;
}
EXPORT_SYMBOL(mpage_writepage);