#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
/**
* bdi_start_writeback - start writeback
* @bdi: the backing device to write from
+ * @sb: write inodes from this super_block
* @nr_pages: the number of pages to write
*
* Description:
* completion. Caller need not hold sb s_umount semaphore.
*
*/
-void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+ long nr_pages)
{
struct wb_writeback_args args = {
+ .sb = sb,
.sync_mode = WB_SYNC_NONE,
.nr_pages = nr_pages,
.range_cyclic = 1,
move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}
-static int write_inode(struct inode *inode, int sync)
+static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, sync);
+ return inode->i_sb->s_op->write_inode(inode, wbc);
return 0;
}
writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
struct address_space *mapping = inode->i_mapping;
- int wait = wbc->sync_mode == WB_SYNC_ALL;
unsigned dirty;
int ret;
* We'll have another go at writing back this inode when we
* completed a full scan of b_io.
*/
- if (!wait) {
+ if (wbc->sync_mode != WB_SYNC_ALL) {
requeue_io(inode);
return 0;
}
ret = do_writepages(mapping, wbc);
- /* Don't write the inode if only I_DIRTY_PAGES was set */
- if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
- int err = write_inode(inode, wait);
+ /*
+ * Make sure to wait on the data before writing out the metadata.
+ * This is important for filesystems that modify metadata on data
+ * I/O completion.
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL) {
+ int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
}
- if (wait) {
- int err = filemap_fdatawait(mapping);
+ /* Don't write the inode if only I_DIRTY_PAGES was set */
+ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ int err = write_inode(inode, wbc);
if (ret == 0)
ret = err;
}
spin_lock(&inode_lock);
inode->i_state &= ~I_SYNC;
if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
- if (inode->i_state & I_DIRTY) {
+ if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
/*
- * Someone redirtied the inode while were writing back
- * the pages.
+ * More pages get dirtied by a fast dirtier.
+ */
+ goto select_queue;
+ } else if (inode->i_state & I_DIRTY) {
+ /*
+ * At least XFS will redirty the inode during the
+ * writeback (delalloc) and on io completion (isize).
*/
redirty_tail(inode);
} else if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
+select_queue:
if (wbc->nr_to_write <= 0) {
/*
* slice used up: queue for next turn
return ret;
}
+static void unpin_sb_for_writeback(struct super_block *sb)
+{
+ up_read(&sb->s_umount);
+ put_super(sb);
+}
+
+enum sb_pin_state {
+ SB_PINNED,
+ SB_NOT_PINNED,
+ SB_PIN_FAILED
+};
+
/*
* For WB_SYNC_NONE writeback, the caller does not have the sb pinned
* before calling writeback. So make sure that we do pin it, so it doesn't
* go away while we are writing inodes from it.
- *
- * Returns 0 if the super was successfully pinned (or pinning wasn't needed),
- * 1 if we failed.
*/
-static int pin_sb_for_writeback(struct writeback_control *wbc,
- struct inode *inode)
+static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc,
+ struct super_block *sb)
{
- struct super_block *sb = inode->i_sb;
-
/*
* Caller must already hold the ref for this
*/
if (wbc->sync_mode == WB_SYNC_ALL) {
WARN_ON(!rwsem_is_locked(&sb->s_umount));
- return 0;
+ return SB_NOT_PINNED;
}
-
spin_lock(&sb_lock);
sb->s_count++;
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root) {
spin_unlock(&sb_lock);
- return 0;
+ return SB_PINNED;
}
/*
* umounted, drop rwsem again and fall through to failure
*/
up_read(&sb->s_umount);
}
-
sb->s_count--;
spin_unlock(&sb_lock);
- return 1;
+ return SB_PIN_FAILED;
}
-static void unpin_sb_for_writeback(struct writeback_control *wbc,
- struct inode *inode)
-{
- struct super_block *sb = inode->i_sb;
-
- if (wbc->sync_mode == WB_SYNC_ALL)
- return;
-
- up_read(&sb->s_umount);
- put_super(sb);
-}
-
-static void writeback_inodes_wb(struct bdi_writeback *wb,
- struct writeback_control *wbc)
+/*
+ * Write a portion of b_io inodes which belong to @sb.
+ * If @wbc->sb != NULL, then find and write all such
+ * inodes. Otherwise write only ones which go sequentially
+ * in reverse order.
+ * Return 1, if the caller writeback routine should be
+ * interrupted. Otherwise return 0.
+ */
+static int writeback_sb_inodes(struct super_block *sb,
+ struct bdi_writeback *wb,
+ struct writeback_control *wbc)
{
- struct super_block *sb = wbc->sb;
- const int is_blkdev_sb = sb_is_blkdev_sb(sb);
- const unsigned long start = jiffies; /* livelock avoidance */
-
- spin_lock(&inode_lock);
-
- if (!wbc->for_kupdate || list_empty(&wb->b_io))
- queue_io(wb, wbc->older_than_this);
-
while (!list_empty(&wb->b_io)) {
- struct inode *inode = list_entry(wb->b_io.prev,
- struct inode, i_list);
long pages_skipped;
-
- /*
- * super block given and doesn't match, skip this inode
- */
- if (sb && sb != inode->i_sb) {
+ struct inode *inode = list_entry(wb->b_io.prev,
+ struct inode, i_list);
+ if (wbc->sb && sb != inode->i_sb) {
+ /* super block given and doesn't
+ match, skip this inode */
redirty_tail(inode);
continue;
}
-
- if (!bdi_cap_writeback_dirty(wb->bdi)) {
- redirty_tail(inode);
- if (is_blkdev_sb) {
- /*
- * Dirty memory-backed blockdev: the ramdisk
- * driver does this. Skip just this inode
- */
- continue;
- }
- /*
- * Dirty memory-backed inode against a filesystem other
- * than the kernel-internal bdev filesystem. Skip the
- * entire superblock.
- */
- break;
- }
-
+ if (sb != inode->i_sb)
+ /* finish with this superblock */
+ return 0;
if (inode->i_state & (I_NEW | I_WILL_FREE)) {
requeue_io(inode);
continue;
}
-
- if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
- wbc->encountered_congestion = 1;
- if (!is_blkdev_sb)
- break; /* Skip a congested fs */
- requeue_io(inode);
- continue; /* Skip a congested blockdev */
- }
-
/*
* Was this inode dirtied after sync_sb_inodes was called?
* This keeps sync from extra jobs and livelock.
*/
- if (inode_dirtied_after(inode, start))
- break;
-
- if (pin_sb_for_writeback(wbc, inode)) {
- requeue_io(inode);
- continue;
- }
+ if (inode_dirtied_after(inode, wbc->wb_start))
+ return 1;
BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
- unpin_sb_for_writeback(wbc, inode);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
spin_lock(&inode_lock);
if (wbc->nr_to_write <= 0) {
wbc->more_io = 1;
- break;
+ return 1;
}
if (!list_empty(&wb->b_more_io))
wbc->more_io = 1;
}
+ /* b_io is empty */
+ return 1;
+}
+
+static void writeback_inodes_wb(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
+{
+ int ret = 0;
+
+ wbc->wb_start = jiffies; /* livelock avoidance */
+ spin_lock(&inode_lock);
+ if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ queue_io(wb, wbc->older_than_this);
+
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = list_entry(wb->b_io.prev,
+ struct inode, i_list);
+ struct super_block *sb = inode->i_sb;
+ enum sb_pin_state state;
+
+ if (wbc->sb && sb != wbc->sb) {
+ /* super block given and doesn't
+ match, skip this inode */
+ redirty_tail(inode);
+ continue;
+ }
+ state = pin_sb_for_writeback(wbc, sb);
+
+ if (state == SB_PIN_FAILED) {
+ requeue_io(inode);
+ continue;
+ }
+ ret = writeback_sb_inodes(sb, wb, wbc);
+ if (state == SB_PINNED)
+ unpin_sb_for_writeback(sb);
+ if (ret)
+ break;
+ }
spin_unlock(&inode_lock);
/* Leave any unwritten inodes on b_io */
}
.sync_mode = args->sync_mode,
.older_than_this = NULL,
.for_kupdate = args->for_kupdate,
+ .for_background = args->for_background,
.range_cyclic = args->range_cyclic,
};
unsigned long oldest_jif;
break;
wbc.more_io = 0;
- wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
wbc.pages_skipped = 0;
writeback_inodes_wb(wb, &wbc);
nr_to_write = nr_dirty + nr_unstable +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
- bdi_writeback_all(sb, nr_to_write);
+ bdi_start_writeback(sb->s_bdi, sb, nr_to_write);
}
EXPORT_SYMBOL(writeback_inodes_sb);
/**
+ * writeback_inodes_sb_if_idle - start writeback if none underway
+ * @sb: the superblock
+ *
+ * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int writeback_inodes_sb_if_idle(struct super_block *sb)
+{
+ if (!writeback_in_progress(sb->s_bdi)) {
+ writeback_inodes_sb(sb);
+ return 1;
+ } else
+ return 0;
+}
+EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
+
+/**
* sync_inodes_sb - sync sb inode pages
* @sb: the superblock
*
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff