static void bdev_inode_switch_bdi(struct inode *inode,
struct backing_dev_info *dst)
{
- spin_lock(&inode_lock);
+ spin_lock(&inode_wb_list_lock);
+ spin_lock(&inode->i_lock);
inode->i_data.backing_dev_info = dst;
if (inode->i_state & I_DIRTY)
list_move(&inode->i_wb_list, &dst->wb.b_dirty);
- spin_unlock(&inode_lock);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&inode_wb_list_lock);
}
static sector_t max_block(struct block_device *bdev)
if (!disk)
goto out;
+ disk_block_events(disk);
mutex_lock_nested(&bdev->bd_mutex, for_part);
if (!bdev->bd_openers) {
bdev->bd_disk = disk;
*/
disk_put_part(bdev->bd_part);
bdev->bd_part = NULL;
- module_put(disk->fops->owner);
- put_disk(disk);
bdev->bd_disk = NULL;
mutex_unlock(&bdev->bd_mutex);
+ disk_unblock_events(disk);
+ module_put(disk->fops->owner);
+ put_disk(disk);
goto restart;
}
if (ret)
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
}
} else {
- module_put(disk->fops->owner);
- put_disk(disk);
- disk = NULL;
if (bdev->bd_contains == bdev) {
if (bdev->bd_disk->fops->open) {
ret = bdev->bd_disk->fops->open(bdev, mode);
if (bdev->bd_invalidated)
rescan_partitions(bdev->bd_disk, bdev);
}
+ /* only one opener holds refs to the module and disk */
+ module_put(disk->fops->owner);
+ put_disk(disk);
}
bdev->bd_openers++;
if (for_part)
bdev->bd_part_count++;
mutex_unlock(&bdev->bd_mutex);
+ disk_unblock_events(disk);
return 0;
out_clear:
bdev->bd_contains = NULL;
out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
- out:
- if (disk)
- module_put(disk->fops->owner);
+ disk_unblock_events(disk);
+ module_put(disk->fops->owner);
put_disk(disk);
+ out:
bdput(bdev);
return ret;
if (bdev_free) {
if (bdev->bd_write_holder) {
disk_unblock_events(bdev->bd_disk);
- bdev->bd_write_holder = false;
- } else
disk_check_events(bdev->bd_disk);
+ bdev->bd_write_holder = false;
+ }
}
mutex_unlock(&bdev->bd_mutex);
- } else
- disk_check_events(bdev->bd_disk);
+ }
return __blkdev_put(bdev, mode, 0);
}
static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
.writepage = blkdev_writepage,
- .sync_page = block_sync_page,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
.writepages = generic_writepages,
}
EXPORT_SYMBOL(init_buffer);
-static int sync_buffer(void *word)
+static int sleep_on_buffer(void *word)
{
- struct block_device *bd;
- struct buffer_head *bh
- = container_of(word, struct buffer_head, b_state);
-
- smp_mb();
- bd = bh->b_bdev;
- if (bd)
- blk_run_address_space(bd->bd_inode->i_mapping);
io_schedule();
return 0;
}
void __lock_buffer(struct buffer_head *bh)
{
- wait_on_bit_lock(&bh->b_state, BH_Lock, sync_buffer,
+ wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_buffer);
*/
void __wait_on_buffer(struct buffer_head * bh)
{
- wait_on_bit(&bh->b_state, BH_Lock, sync_buffer, TASK_UNINTERRUPTIBLE);
+ wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__wait_on_buffer);
{
struct buffer_head *bh;
struct list_head tmp;
- struct address_space *mapping, *prev_mapping = NULL;
+ struct address_space *mapping;
int err = 0, err2;
+ struct blk_plug plug;
INIT_LIST_HEAD(&tmp);
+ blk_start_plug(&plug);
spin_lock(lock);
while (!list_empty(list)) {
* still in flight on potentially older
* contents.
*/
- write_dirty_buffer(bh, WRITE_SYNC_PLUG);
+ write_dirty_buffer(bh, WRITE_SYNC);
/*
* Kick off IO for the previous mapping. Note
* 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(lock);
+ blk_finish_plug(&plug);
+ spin_lock(lock);
+
while (!list_empty(&tmp)) {
bh = BH_ENTRY(tmp.prev);
get_bh(bh);
* inode list.
*
* mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock,
- * mapping->tree_lock and the global inode_lock.
+ * mapping->tree_lock and mapping->host->i_lock.
*/
void mark_buffer_dirty(struct buffer_head *bh)
{
* 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.
+ * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this
+ * causes the writes to be flagged as synchronous writes.
*/
static int __block_write_full_page(struct inode *inode, struct page *page,
get_block_t *get_block, struct writeback_control *wbc,
const unsigned blocksize = 1 << inode->i_blkbits;
int nr_underway = 0;
int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
- WRITE_SYNC_PLUG : WRITE);
+ WRITE_SYNC : WRITE);
BUG_ON(!PageLocked(page));
}
EXPORT_SYMBOL(try_to_free_buffers);
-void block_sync_page(struct page *page)
-{
- struct address_space *mapping;
-
- smp_mb();
- mapping = page_mapping(page);
- if (mapping)
- blk_run_backing_dev(mapping->backing_dev_info, page);
-}
-EXPORT_SYMBOL(block_sync_page);
-
/*
* There are no bdflush tunables left. But distributions are
* still running obsolete flush daemons, so we terminate them here.
* block layer could (in theory) choose to ignore this
* request if it runs into resource problems.
* WRITE A normal async write. Device will be plugged.
- * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down
+ * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down
* the hint that someone will be waiting on this IO
- * shortly. The device must still be unplugged explicitly,
- * WRITE_SYNC_PLUG does not do this as we could be
- * submitting more writes before we actually wait on any
- * of them.
- * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device
- * immediately after submission. The write equivalent
- * of READ_SYNC.
- * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only.
+ * shortly. The write equivalent of READ_SYNC.
+ * WRITE_ODIRECT Special case write for O_DIRECT only.
* WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush.
* WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on
* non-volatile media on completion.
#define WRITE RW_MASK
#define READA RWA_MASK
-#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG)
+#define READ_SYNC (READ | REQ_SYNC)
#define READ_META (READ | REQ_META)
-#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
-#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC)
+#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT (WRITE | REQ_SYNC)
#define WRITE_META (WRITE | REQ_META)
-#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
- REQ_FLUSH)
-#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
- REQ_FUA)
-#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
- REQ_FLUSH | REQ_FUA)
+#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
+#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
#define SEL_IN 1
#define SEL_OUT 2
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*readpage)(struct file *, struct page *);
- void (*sync_page)(struct page *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
};
/*
- * Inode state bits. Protected by inode_lock.
+ * Inode state bits. Protected by inode->i_lock
*
* Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
* I_DIRTY_DATASYNC and I_DIRTY_PAGES.
static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
-
struct backing_dev_info default_backing_dev_info = {
.name = "default",
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
.state = 0,
.capabilities = BDI_CAP_MAP_COPY,
- .unplug_io_fn = default_unplug_io_fn,
};
EXPORT_SYMBOL_GPL(default_backing_dev_info);
struct inode *inode;
nr_wb = nr_dirty = nr_io = nr_more_io = 0;
- spin_lock(&inode_lock);
+ spin_lock(&inode_wb_list_lock);
list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
nr_dirty++;
list_for_each_entry(inode, &wb->b_io, i_wb_list)
nr_io++;
list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
nr_more_io++;
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_wb_list_lock);
global_dirty_limits(&background_thresh, &dirty_thresh);
bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (sb->s_bdi == bdi)
- sb->s_bdi = NULL;
+ sb->s_bdi = &default_backing_dev_info;
}
spin_unlock(&sb_lock);
}
if (bdi_has_dirty_io(bdi)) {
struct bdi_writeback *dst = &default_backing_dev_info.wb;
- spin_lock(&inode_lock);
+ spin_lock(&inode_wb_list_lock);
list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
list_splice(&bdi->wb.b_io, &dst->b_io);
list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
- spin_unlock(&inode_lock);
+ spin_unlock(&inode_wb_list_lock);
}
bdi_unregister(bdi);
* ->i_mutex
* ->i_alloc_sem (various)
*
- * ->inode_lock
- * ->sb_lock (fs/fs-writeback.c)
+ * inode_wb_list_lock
+ * sb_lock (fs/fs-writeback.c)
* ->mapping->tree_lock (__sync_single_inode)
*
* ->i_mmap_lock
* ->zone.lru_lock (check_pte_range->isolate_lru_page)
* ->private_lock (page_remove_rmap->set_page_dirty)
* ->tree_lock (page_remove_rmap->set_page_dirty)
- * ->inode_lock (page_remove_rmap->set_page_dirty)
- * ->inode_lock (zap_pte_range->set_page_dirty)
+ * inode_wb_list_lock (page_remove_rmap->set_page_dirty)
+ * ->inode->i_lock (page_remove_rmap->set_page_dirty)
+ * inode_wb_list_lock (zap_pte_range->set_page_dirty)
+ * ->inode->i_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->__set_page_dirty_buffers)
*
* (code doesn't rely on that order, so you could switch it around)
}
EXPORT_SYMBOL(delete_from_page_cache);
-static int sync_page(void *word)
+static int sleep_on_page(void *word)
{
- struct address_space *mapping;
- struct page *page;
-
- page = container_of((unsigned long *)word, struct page, flags);
-
- /*
- * page_mapping() is being called without PG_locked held.
- * Some knowledge of the state and use of the page is used to
- * reduce the requirements down to a memory barrier.
- * The danger here is of a stale page_mapping() return value
- * indicating a struct address_space different from the one it's
- * associated with when it is associated with one.
- * After smp_mb(), it's either the correct page_mapping() for
- * the page, or an old page_mapping() and the page's own
- * page_mapping() has gone NULL.
- * The ->sync_page() address_space operation must tolerate
- * page_mapping() going NULL. By an amazing coincidence,
- * this comes about because none of the users of the page
- * in the ->sync_page() methods make essential use of the
- * page_mapping(), merely passing the page down to the backing
- * device's unplug functions when it's non-NULL, which in turn
- * ignore it for all cases but swap, where only page_private(page) is
- * of interest. When page_mapping() does go NULL, the entire
- * call stack gracefully ignores the page and returns.
- * -- wli
- */
- smp_mb();
- mapping = page_mapping(page);
- if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
- mapping->a_ops->sync_page(page);
io_schedule();
return 0;
}
-static int sync_page_killable(void *word)
+static int sleep_on_page_killable(void *word)
{
- sync_page(word);
+ sleep_on_page(word);
return fatal_signal_pending(current) ? -EINTR : 0;
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif
-static int __sleep_on_page_lock(void *word)
-{
- io_schedule();
- return 0;
-}
-
/*
* In order to wait for pages to become available there must be
* waitqueues associated with pages. By using a hash table of
DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
if (test_bit(bit_nr, &page->flags))
- __wait_on_bit(page_waitqueue(page), &wait, sync_page,
+ __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_on_page_bit);
/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
- *
- * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some
- * random driver's requestfn sets TASK_RUNNING, we could busywait. However
- * chances are that on the second loop, the block layer's plug list is empty,
- * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
*/
void __lock_page(struct page *page)
{
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
- __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
+ __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_page);
DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
return __wait_on_bit_lock(page_waitqueue(page), &wait,
- sync_page_killable, TASK_KILLABLE);
+ sleep_on_page_killable, TASK_KILLABLE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
-/**
- * __lock_page_nosync - get a lock on the page, without calling sync_page()
- * @page: the page to lock
- *
- * Variant of lock_page that does not require the caller to hold a reference
- * on the page's mapping.
- */
-void __lock_page_nosync(struct page *page)
-{
- DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
- __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
- TASK_UNINTERRUPTIBLE);
-}
-
int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
+ struct blk_plug plug;
count = 0;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
+ blk_start_plug(&plug);
+
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
loff_t size;
break;
}
out:
+ blk_finish_plug(&plug);
return retval;
}
EXPORT_SYMBOL(generic_file_aio_read);
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ struct blk_plug plug;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
mutex_lock(&inode->i_mutex);
+ blk_start_plug(&plug);
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
if (err < 0 && ret > 0)
ret = err;
}
+ blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(generic_file_aio_write);