#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
+#include <linux/mpage.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static void invalidate_bh_lrus(void);
sb = get_super(bdev);
if (sb && !(sb->s_flags & MS_RDONLY)) {
sb->s_frozen = SB_FREEZE_WRITE;
- wmb();
+ smp_wmb();
sync_inodes_sb(sb, 0);
DQUOT_SYNC(sb);
sync_inodes_sb(sb, 1);
sb->s_frozen = SB_FREEZE_TRANS;
- wmb();
+ smp_wmb();
sync_blockdev(sb->s_bdev);
if (sb->s_op->unlockfs)
sb->s_op->unlockfs(sb);
sb->s_frozen = SB_UNFROZEN;
- wmb();
+ smp_wmb();
wake_up(&sb->s_wait_unfrozen);
drop_super(sb);
}
/**
* sync_mapping_buffers - write out and wait upon a mapping's "associated"
* buffers
- * @buffer_mapping - the mapping which backs the buffers' data
- * @mapping - the mapping which wants those buffers written
+ * @mapping: the mapping which wants those buffers written
*
* Starts I/O against the buffers at mapping->private_list, and waits upon
* that I/O.
*
- * Basically, this is a convenience function for fsync(). @buffer_mapping is
- * the blockdev which "owns" the buffers and @mapping is a file or directory
- * which needs those buffers to be written for a successful fsync().
+ * Basically, this is a convenience function for fsync().
+ * @mapping is a file or directory which needs those buffers to be written for
+ * a successful fsync().
*/
int sync_mapping_buffers(struct address_space *mapping)
{
spin_unlock(&mapping->private_lock);
if (!TestSetPageDirty(page)) {
- spin_lock_irq(&mapping->tree_lock);
+ write_lock_irq(&mapping->tree_lock);
if (page->mapping) { /* Race with truncate? */
- if (!mapping->backing_dev_info->memory_backed)
+ if (mapping_cap_account_dirty(mapping))
inc_page_state(nr_dirty);
radix_tree_tag_set(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
}
- spin_unlock_irq(&mapping->tree_lock);
+ write_unlock_irq(&mapping->tree_lock);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
-struct buffer_head *
+static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
/* Size must be multiple of hard sectorsize */
/**
* mark_buffer_dirty - mark a buffer_head as needing writeout
+ * @bh: the buffer_head to mark dirty
*
* mark_buffer_dirty() will set the dirty bit against the buffer, then set its
* backing page dirty, then tag the page as dirty in its address_space's radix
/**
* __bread() - reads a specified block and returns the bh
+ * @bdev: the block_device to read from
* @block: number of block
* @size: size (in bytes) to read
*
} while (bh != head);
do {
- get_bh(bh);
if (!buffer_mapped(bh))
continue;
/*
*/
BUG_ON(PageWriteback(page));
set_page_writeback(page);
- unlock_page(page);
do {
struct buffer_head *next = bh->b_this_page;
submit_bh(WRITE, bh);
nr_underway++;
}
- put_bh(bh);
bh = next;
} while (bh != head);
+ unlock_page(page);
err = 0;
done:
bh = head;
/* Recovery: lock and submit the mapped buffers */
do {
- get_bh(bh);
if (buffer_mapped(bh) && buffer_dirty(bh)) {
lock_buffer(bh);
mark_buffer_async_write(bh);
submit_bh(WRITE, bh);
nr_underway++;
}
- put_bh(bh);
bh = next;
} while (bh != head);
goto done;
if (!buffer_mapped(bh)) {
err = get_block(inode, block, bh, 1);
if (err)
- goto out;
+ break;
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev,
while(wait_bh > wait) {
wait_on_buffer(*--wait_bh);
if (!buffer_uptodate(*wait_bh))
- return -EIO;
+ err = -EIO;
}
- return 0;
-out:
+ if (!err)
+ return err;
+
+ /* Error case: */
/*
* Zero out any newly allocated blocks to avoid exposing stale
* data. If BH_New is set, we know that the block was newly
int nr, i;
int fully_mapped = 1;
- if (!PageLocked(page))
- PAGE_BUG(page);
+ BUG_ON(!PageLocked(page));
blocksize = 1 << inode->i_blkbits;
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
continue;
if (!buffer_mapped(bh)) {
+ int err = 0;
+
fully_mapped = 0;
if (iblock < lblock) {
- if (get_block(inode, iblock, bh, 0))
+ err = get_block(inode, iblock, bh, 0);
+ if (err)
SetPageError(page);
}
if (!buffer_mapped(bh)) {
memset(kaddr + i * blocksize, 0, blocksize);
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
- set_buffer_uptodate(bh);
+ if (!err)
+ set_buffer_uptodate(bh);
continue;
}
/*
}
EXPORT_SYMBOL(nobh_commit_write);
+/*
+ * nobh_writepage() - based on block_full_write_page() except
+ * that it tries to operate without attaching bufferheads to
+ * the page.
+ */
+int nobh_writepage(struct page *page, get_block_t *get_block,
+ struct writeback_control *wbc)
+{
+ struct inode * const inode = page->mapping->host;
+ loff_t i_size = i_size_read(inode);
+ const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+ unsigned offset;
+ void *kaddr;
+ int ret;
+
+ /* Is the page fully inside i_size? */
+ if (page->index < end_index)
+ goto out;
+
+ /* Is the page fully outside i_size? (truncate in progress) */
+ offset = i_size & (PAGE_CACHE_SIZE-1);
+ if (page->index >= end_index+1 || !offset) {
+ /*
+ * The page may have dirty, unmapped buffers. For example,
+ * they may have been added in ext3_writepage(). Make them
+ * freeable here, so the page does not leak.
+ */
+#if 0
+ /* Not really sure about this - do we need this ? */
+ if (page->mapping->a_ops->invalidatepage)
+ page->mapping->a_ops->invalidatepage(page, offset);
+#endif
+ unlock_page(page);
+ return 0; /* don't care */
+ }
+
+ /*
+ * 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."
+ */
+ kaddr = kmap_atomic(page, KM_USER0);
+ memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
+ flush_dcache_page(page);
+ kunmap_atomic(kaddr, KM_USER0);
+out:
+ ret = mpage_writepage(page, get_block, wbc);
+ if (ret == -EAGAIN)
+ ret = __block_write_full_page(inode, page, get_block, wbc);
+ return ret;
+}
+EXPORT_SYMBOL(nobh_writepage);
+
/*
* This function assumes that ->prepare_write() uses nobh_prepare_write().
*/
get_bh(bh);
if (rw == WRITE) {
- bh->b_end_io = end_buffer_write_sync;
if (test_clear_buffer_dirty(bh)) {
+ bh->b_end_io = end_buffer_write_sync;
submit_bh(WRITE, bh);
continue;
}
} else {
- bh->b_end_io = end_buffer_read_sync;
if (!buffer_uptodate(bh)) {
+ bh->b_end_io = end_buffer_read_sync;
submit_bh(rw, bh);
continue;
}
bh = head;
do {
- if (buffer_write_io_error(bh))
+ if (buffer_write_io_error(bh) && page->mapping)
set_bit(AS_EIO, &page->mapping->flags);
if (buffer_busy(bh))
goto failed;
buffer_heads_over_limit = (tot > max_buffer_heads);
}
-struct buffer_head *alloc_buffer_head(int gfp_flags)
+struct buffer_head *alloc_buffer_head(unsigned int __nocast gfp_flags)
{
struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags);
if (ret) {
bh_cachep = kmem_cache_create("buffer_head",
sizeof(struct buffer_head), 0,
- SLAB_PANIC, init_buffer_head, NULL);
+ SLAB_RECLAIM_ACCOUNT|SLAB_PANIC, init_buffer_head, NULL);
/*
* Limit the bh occupancy to 10% of ZONE_NORMAL