void unlock_buffer(struct buffer_head *bh)
{
- smp_mb__before_clear_bit();
- clear_buffer_locked(bh);
+ clear_bit_unlock(BH_Lock, &bh->b_state);
smp_mb__after_clear_bit();
wake_up_bit(&bh->b_state, BH_Lock);
}
page_cache_release(page);
}
+
+static int quiet_error(struct buffer_head *bh)
+{
+ if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit())
+ return 0;
+ return 1;
+}
+
+
static void buffer_io_error(struct buffer_head *bh)
{
char b[BDEVNAME_SIZE];
-
printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n",
bdevname(bh->b_bdev, b),
(unsigned long long)bh->b_blocknr);
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
+ if (!buffer_eopnotsupp(bh) && !quiet_error(bh)) {
buffer_io_error(bh);
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
}
/*
- * Write out and wait upon all the dirty data associated with a block
- * device via its mapping. Does not take the superblock lock.
- */
-int sync_blockdev(struct block_device *bdev)
-{
- int ret = 0;
-
- if (bdev)
- ret = filemap_write_and_wait(bdev->bd_inode->i_mapping);
- return ret;
-}
-EXPORT_SYMBOL(sync_blockdev);
-
-/*
- * Write out and wait upon all dirty data associated with this
- * device. Filesystem data as well as the underlying block
- * device. Takes the superblock lock.
- */
-int fsync_bdev(struct block_device *bdev)
-{
- struct super_block *sb = get_super(bdev);
- if (sb) {
- int res = fsync_super(sb);
- drop_super(sb);
- return res;
- }
- return sync_blockdev(bdev);
-}
-
-/**
- * freeze_bdev -- lock a filesystem and force it into a consistent state
- * @bdev: blockdevice to lock
- *
- * This takes the block device bd_mount_sem to make sure no new mounts
- * happen on bdev until thaw_bdev() is called.
- * If a superblock is found on this device, we take the s_umount semaphore
- * on it to make sure nobody unmounts until the snapshot creation is done.
- */
-struct super_block *freeze_bdev(struct block_device *bdev)
-{
- struct super_block *sb;
-
- down(&bdev->bd_mount_sem);
- sb = get_super(bdev);
- if (sb && !(sb->s_flags & MS_RDONLY)) {
- sb->s_frozen = SB_FREEZE_WRITE;
- smp_wmb();
-
- __fsync_super(sb);
-
- sb->s_frozen = SB_FREEZE_TRANS;
- smp_wmb();
-
- sync_blockdev(sb->s_bdev);
-
- if (sb->s_op->write_super_lockfs)
- sb->s_op->write_super_lockfs(sb);
- }
-
- sync_blockdev(bdev);
- return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */
-}
-EXPORT_SYMBOL(freeze_bdev);
-
-/**
- * thaw_bdev -- unlock filesystem
- * @bdev: blockdevice to unlock
- * @sb: associated superblock
- *
- * Unlocks the filesystem and marks it writeable again after freeze_bdev().
- */
-void thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
- if (sb) {
- BUG_ON(sb->s_bdev != bdev);
-
- if (sb->s_op->unlockfs)
- sb->s_op->unlockfs(sb);
- sb->s_frozen = SB_UNFROZEN;
- smp_wmb();
- wake_up(&sb->s_wait_unfrozen);
- drop_super(sb);
- }
-
- up(&bdev->bd_mount_sem);
-}
-EXPORT_SYMBOL(thaw_bdev);
-
-/*
* Various filesystems appear to want __find_get_block to be non-blocking.
* But it's the page lock which protects the buffers. To get around this,
* we get exclusion from try_to_free_buffers with the blockdev mapping's
head = page_buffers(page);
bh = head;
do {
- if (bh->b_blocknr == block) {
+ if (!buffer_mapped(bh))
+ all_mapped = 0;
+ else if (bh->b_blocknr == block) {
ret = bh;
get_bh(bh);
goto out_unlock;
}
- if (!buffer_mapped(bh))
- all_mapped = 0;
bh = bh->b_this_page;
} while (bh != head);
&zone);
if (zone)
try_to_free_pages(node_zonelist(nid, GFP_NOFS), 0,
- GFP_NOFS);
+ GFP_NOFS, NULL);
}
}
set_buffer_uptodate(bh);
} else {
clear_buffer_uptodate(bh);
- if (printk_ratelimit())
+ if (!quiet_error(bh))
buffer_io_error(bh);
SetPageError(page);
}
* Completion handler for block_write_full_page() - pages which are unlocked
* during I/O, and which have PageWriteback cleared upon I/O completion.
*/
-static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
+void end_buffer_async_write(struct buffer_head *bh, int uptodate)
{
char b[BDEVNAME_SIZE];
unsigned long flags;
if (uptodate) {
set_buffer_uptodate(bh);
} else {
- if (printk_ratelimit()) {
+ if (!quiet_error(bh)) {
buffer_io_error(bh);
printk(KERN_WARNING "lost page write due to "
"I/O error on %s\n",
set_buffer_async_read(bh);
}
-void mark_buffer_async_write(struct buffer_head *bh)
+void mark_buffer_async_write_endio(struct buffer_head *bh,
+ bh_end_io_t *handler)
{
- bh->b_end_io = end_buffer_async_write;
+ bh->b_end_io = handler;
set_buffer_async_write(bh);
}
+
+void mark_buffer_async_write(struct buffer_head *bh)
+{
+ mark_buffer_async_write_endio(bh, end_buffer_async_write);
+}
EXPORT_SYMBOL(mark_buffer_async_write);
return err;
}
+void do_thaw_all(struct work_struct *work)
+{
+ struct super_block *sb;
+ char b[BDEVNAME_SIZE];
+
+ spin_lock(&sb_lock);
+restart:
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ sb->s_count++;
+ spin_unlock(&sb_lock);
+ down_read(&sb->s_umount);
+ while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+ printk(KERN_WARNING "Emergency Thaw on %s\n",
+ bdevname(sb->s_bdev, b));
+ up_read(&sb->s_umount);
+ spin_lock(&sb_lock);
+ if (__put_super_and_need_restart(sb))
+ goto restart;
+ }
+ spin_unlock(&sb_lock);
+ kfree(work);
+ printk(KERN_WARNING "Emergency Thaw complete\n");
+}
+
+/**
+ * emergency_thaw_all -- forcibly thaw every frozen filesystem
+ *
+ * Used for emergency unfreeze of all filesystems via SysRq
+ */
+void emergency_thaw_all(void)
+{
+ struct work_struct *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(work, do_thaw_all);
+ schedule_work(work);
+ }
+}
+
/**
* sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
* @mapping: the mapping which wants those buffers written
* If warn is true, then emit a warning if the page is not uptodate and has
* not been truncated.
*/
-static int __set_page_dirty(struct page *page,
+static void __set_page_dirty(struct page *page,
struct address_space *mapping, int warn)
{
- if (unlikely(!mapping))
- return !TestSetPageDirty(page);
-
- if (TestSetPageDirty(page))
- return 0;
-
spin_lock_irq(&mapping->tree_lock);
if (page->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
-
- if (mapping_cap_account_dirty(mapping)) {
- __inc_zone_page_state(page, NR_FILE_DIRTY);
- __inc_bdi_stat(mapping->backing_dev_info,
- BDI_RECLAIMABLE);
- task_io_account_write(PAGE_CACHE_SIZE);
- }
+ account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-
- return 1;
}
/*
*/
int __set_page_dirty_buffers(struct page *page)
{
+ int newly_dirty;
struct address_space *mapping = page_mapping(page);
if (unlikely(!mapping))
bh = bh->b_this_page;
} while (bh != head);
}
+ newly_dirty = !TestSetPageDirty(page);
spin_unlock(&mapping->private_lock);
- return __set_page_dirty(page, mapping, 1);
+ if (newly_dirty)
+ __set_page_dirty(page, mapping, 1);
+ return newly_dirty;
}
EXPORT_SYMBOL(__set_page_dirty_buffers);
{
struct buffer_head *bh;
struct list_head tmp;
- struct address_space *mapping;
+ struct address_space *mapping, *prev_mapping = NULL;
int err = 0, err2;
INIT_LIST_HEAD(&tmp);
* contents - it is a noop if I/O is still in
* flight on potentially older contents.
*/
- ll_rw_block(SWRITE_SYNC, 1, &bh);
+ ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh);
+
+ /*
+ * Kick off IO for the previous mapping. Note
+ * that we will not run the very last mapping,
+ * wait_on_buffer() will do that for us
+ * through sync_buffer().
+ */
+ if (prev_mapping && prev_mapping != mapping)
+ blk_run_address_space(prev_mapping);
+ prev_mapping = mapping;
+
brelse(bh);
spin_lock(lock);
}
spin_unlock(&buffer_mapping->private_lock);
}
}
+EXPORT_SYMBOL(invalidate_inode_buffers);
/*
* Remove any clean buffers from the inode's buffer list. This is called
return;
}
- if (!test_set_buffer_dirty(bh))
- __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
+ if (!test_set_buffer_dirty(bh)) {
+ struct page *page = bh->b_page;
+ if (!TestSetPageDirty(page))
+ __set_page_dirty(page, page_mapping(page), 0);
+ }
}
/*
* locked buffer. This only can happen if someone has written the buffer
* directly, with submit_bh(). At the address_space level PageWriteback
* prevents this contention from occurring.
+ *
+ * If block_write_full_page() is called with wbc->sync_mode ==
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
+ * causes the writes to be flagged as synchronous writes, but the
+ * block device queue will NOT be unplugged, since usually many pages
+ * will be pushed to the out before the higher-level caller actually
+ * waits for the writes to be completed. The various wait functions,
+ * such as wait_on_writeback_range() will ultimately call sync_page()
+ * which will ultimately call blk_run_backing_dev(), which will end up
+ * unplugging the device queue.
*/
static int __block_write_full_page(struct inode *inode, struct page *page,
- get_block_t *get_block, struct writeback_control *wbc)
+ get_block_t *get_block, struct writeback_control *wbc,
+ bh_end_io_t *handler)
{
int err;
sector_t block;
struct buffer_head *bh, *head;
const unsigned blocksize = 1 << inode->i_blkbits;
int nr_underway = 0;
+ int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
+ WRITE_SYNC_PLUG : WRITE);
BUG_ON(!PageLocked(page));
continue;
}
if (test_clear_buffer_dirty(bh)) {
- mark_buffer_async_write(bh);
+ mark_buffer_async_write_endio(bh, handler);
} else {
unlock_buffer(bh);
}
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(WRITE, bh);
+ submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
if (buffer_mapped(bh) && buffer_dirty(bh) &&
!buffer_delay(bh)) {
lock_buffer(bh);
- mark_buffer_async_write(bh);
+ mark_buffer_async_write_endio(bh, handler);
} else {
/*
* The buffer may have been set dirty during
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh(WRITE, bh);
+ submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
page = *pagep;
if (page == NULL) {
ownpage = 1;
- page = __grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
status = -ENOMEM;
goto out;
if (pos + len > inode->i_size)
vmtruncate(inode, inode->i_size);
}
- goto out;
}
out:
* unlock the page.
*/
int
-block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block)
{
+ struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
unsigned long end;
loff_t size;
- int ret = -EINVAL;
+ int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
lock_page(page);
size = i_size_read(inode);
if ((page->mapping != inode->i_mapping) ||
(page_offset(page) > size)) {
/* page got truncated out from underneath us */
- goto out_unlock;
+ unlock_page(page);
+ goto out;
}
/* page is wholly or partially inside EOF */
if (!ret)
ret = block_commit_write(page, 0, end);
-out_unlock:
- unlock_page(page);
+ if (unlikely(ret)) {
+ unlock_page(page);
+ if (ret == -ENOMEM)
+ ret = VM_FAULT_OOM;
+ else /* -ENOSPC, -EIO, etc */
+ ret = VM_FAULT_SIGBUS;
+ } else
+ ret = VM_FAULT_LOCKED;
+
+out:
return ret;
}
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
- page = __grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
struct buffer_head *bh;
BUG_ON(fsdata != NULL && page_has_buffers(page));
- if (unlikely(copied < len) && !page_has_buffers(page))
+ if (unlikely(copied < len) && head)
attach_nobh_buffers(page, head);
if (page_has_buffers(page))
return generic_write_end(file, mapping, pos, len,
out:
ret = mpage_writepage(page, get_block, wbc);
if (ret == -EAGAIN)
- ret = __block_write_full_page(inode, page, get_block, wbc);
+ ret = __block_write_full_page(inode, page, get_block, wbc,
+ end_buffer_async_write);
return ret;
}
EXPORT_SYMBOL(nobh_writepage);
/*
* The generic ->writepage function for buffer-backed address_spaces
+ * this form passes in the end_io handler used to finish the IO.
*/
-int block_write_full_page(struct page *page, get_block_t *get_block,
- struct writeback_control *wbc)
+int block_write_full_page_endio(struct page *page, get_block_t *get_block,
+ struct writeback_control *wbc, bh_end_io_t *handler)
{
struct inode * const inode = page->mapping->host;
loff_t i_size = i_size_read(inode);
/* Is the page fully inside i_size? */
if (page->index < end_index)
- return __block_write_full_page(inode, page, get_block, wbc);
+ return __block_write_full_page(inode, page, get_block, wbc,
+ handler);
/* Is the page fully outside i_size? (truncate in progress) */
offset = i_size & (PAGE_CACHE_SIZE-1);
* writes to that region are not written out to the file."
*/
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
- return __block_write_full_page(inode, page, get_block, wbc);
+ return __block_write_full_page(inode, page, get_block, wbc, handler);
}
+/*
+ * The generic ->writepage function for buffer-backed address_spaces
+ */
+int block_write_full_page(struct page *page, get_block_t *get_block,
+ struct writeback_control *wbc)
+{
+ return block_write_full_page_endio(page, get_block, wbc,
+ end_buffer_async_write);
+}
+
+
sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
get_block_t *get_block)
{
set_bit(BH_Eopnotsupp, &bh->b_state);
}
+ if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
+ set_bit(BH_Quiet, &bh->b_state);
+
bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
bio_put(bio);
}
for (i = 0; i < nr; i++) {
struct buffer_head *bh = bhs[i];
- if (rw == SWRITE || rw == SWRITE_SYNC)
+ if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG)
lock_buffer(bh);
else if (!trylock_buffer(bh))
continue;
- if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
+ if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC ||
+ rw == SWRITE_SYNC_PLUG) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
* Use of bdflush() is deprecated and will be removed in a future kernel.
* The `pdflush' kernel threads fully replace bdflush daemons and this call.
*/
-asmlinkage long sys_bdflush(int func, long data)
+SYSCALL_DEFINE2(bdflush, int, func, long, data)
{
static int msg_count;
EXPORT_SYMBOL(block_sync_page);
EXPORT_SYMBOL(block_truncate_page);
EXPORT_SYMBOL(block_write_full_page);
+EXPORT_SYMBOL(block_write_full_page_endio);
EXPORT_SYMBOL(cont_write_begin);
EXPORT_SYMBOL(end_buffer_read_sync);
EXPORT_SYMBOL(end_buffer_write_sync);
+EXPORT_SYMBOL(end_buffer_async_write);
EXPORT_SYMBOL(file_fsync);
-EXPORT_SYMBOL(fsync_bdev);
EXPORT_SYMBOL(generic_block_bmap);
EXPORT_SYMBOL(generic_cont_expand_simple);
EXPORT_SYMBOL(init_buffer);