#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>
long nr_pages;
struct super_block *sb;
enum writeback_sync_modes sync_mode;
- int for_kupdate;
- int range_cyclic;
+ unsigned int for_kupdate:1;
+ unsigned int range_cyclic:1;
+ unsigned int for_background:1;
+ unsigned int sb_pinned:1;
};
/*
{
clear_bit(WS_USED_B, &work->state);
smp_mb__after_clear_bit();
+ /*
+ * work can have disappeared at this point. bit waitq functions
+ * should be able to tolerate this, provided bdi_sched_wait does
+ * not dereference it's pointer argument.
+ */
wake_up_bit(&work->state, WS_USED_B);
}
static void wb_work_complete(struct bdi_work *work)
{
const enum writeback_sync_modes sync_mode = work->args.sync_mode;
+ int onstack = bdi_work_on_stack(work);
/*
* For allocated work, we can clear the done/seen bit right here.
* to after the RCU grace period, since the stack could be invalidated
* as soon as bdi_work_clear() has done the wakeup.
*/
- if (!bdi_work_on_stack(work))
+ if (!onstack)
bdi_work_clear(work);
- if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work))
+ if (sync_mode == WB_SYNC_NONE || onstack)
call_rcu(&work->rcu_head, bdi_work_free);
}
else {
struct bdi_writeback *wb = &bdi->wb;
- /*
- * End work now if this wb has no dirty IO pending. Otherwise
- * wakeup the handling thread
- */
- if (!wb_has_dirty_io(wb))
- wb_clear_pending(wb, work);
- else if (wb->task)
+ if (wb->task)
wake_up_process(wb->task);
}
}
}
static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
- struct wb_writeback_args *args)
+ struct wb_writeback_args *args,
+ int wait)
{
struct bdi_work *work;
if (work) {
bdi_work_init(work, args);
bdi_queue_work(bdi, work);
+ if (wait)
+ bdi_wait_on_work_clear(work);
} else {
struct bdi_writeback *wb = &bdi->wb;
.sync_mode = WB_SYNC_ALL,
.nr_pages = LONG_MAX,
.range_cyclic = 0,
+ /*
+ * Setting sb_pinned is not necessary for WB_SYNC_ALL, but
+ * lets make it explicitly clear.
+ */
+ .sb_pinned = 1,
};
struct bdi_work work;
/**
* 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
+ * @sb_locked: caller already holds sb umount sem.
*
* Description:
* This does WB_SYNC_NONE opportunistic writeback. The IO is only
* started when this function returns, we make no guarentees on
- * completion. Caller need not hold sb s_umount semaphore.
+ * completion. Caller specifies whether sb umount sem is held already or not.
*
*/
-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, int sb_locked)
{
struct wb_writeback_args args = {
+ .sb = sb,
.sync_mode = WB_SYNC_NONE,
.nr_pages = nr_pages,
.range_cyclic = 1,
+ .sb_pinned = sb_locked,
};
- bdi_alloc_queue_work(bdi, &args);
+ /*
+ * We treat @nr_pages=0 as the special case to do background writeback,
+ * ie. to sync pages until the background dirty threshold is reached.
+ */
+ if (!nr_pages) {
+ args.nr_pages = LONG_MAX;
+ args.for_background = 1;
+ }
+
+ bdi_alloc_queue_work(bdi, &args, sb_locked);
}
/*
* For inodes being constantly redirtied, dirtied_when can get stuck.
* It _appears_ to be in the future, but is actually in distant past.
* This test is necessary to prevent such wrapped-around relative times
- * from permanently stopping the whole pdflush writeback.
+ * from permanently stopping the whole bdi writeback.
*/
ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
struct list_head *dispatch_queue,
unsigned long *older_than_this)
{
+ LIST_HEAD(tmp);
+ struct list_head *pos, *node;
+ struct super_block *sb = NULL;
+ struct inode *inode;
+ int do_sb_sort = 0;
+
while (!list_empty(delaying_queue)) {
- struct inode *inode = list_entry(delaying_queue->prev,
- struct inode, i_list);
+ inode = list_entry(delaying_queue->prev, struct inode, i_list);
if (older_than_this &&
inode_dirtied_after(inode, *older_than_this))
break;
- list_move(&inode->i_list, dispatch_queue);
+ if (sb && sb != inode->i_sb)
+ do_sb_sort = 1;
+ sb = inode->i_sb;
+ list_move(&inode->i_list, &tmp);
+ }
+
+ /* just one sb in list, splice to dispatch_queue and we're done */
+ if (!do_sb_sort) {
+ list_splice(&tmp, dispatch_queue);
+ return;
+ }
+
+ /* Move inodes from one superblock together */
+ while (!list_empty(&tmp)) {
+ inode = list_entry(tmp.prev, struct inode, i_list);
+ sb = inode->i_sb;
+ list_for_each_prev_safe(pos, node, &tmp) {
+ inode = list_entry(pos, struct inode, i_list);
+ if (inode->i_sb == sb)
+ list_move(&inode->i_list, dispatch_queue);
+ }
}
}
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;
}
wait_queue_head_t *wqh;
wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
- do {
+ while (inode->i_state & I_SYNC) {
spin_unlock(&inode_lock);
__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
spin_lock(&inode_lock);
- } while (inode->i_state & I_SYNC);
+ }
}
/*
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;
}
BUG_ON(inode->i_state & I_SYNC);
- /* Set I_SYNC, reset I_DIRTY */
- dirty = inode->i_state & I_DIRTY;
+ /* Set I_SYNC, reset I_DIRTY_PAGES */
inode->i_state |= I_SYNC;
- inode->i_state &= ~I_DIRTY;
-
+ inode->i_state &= ~I_DIRTY_PAGES;
spin_unlock(&inode_lock);
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);
+ /*
+ * Some filesystems may redirty the inode during the writeback
+ * due to delalloc, clear dirty metadata flags right before
+ * write_inode()
+ */
+ spin_lock(&inode_lock);
+ dirty = inode->i_state & I_DIRTY;
+ inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+ spin_unlock(&inode_lock);
+ /* 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) &&
- mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
+ /*
+ * 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)) {
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything. Redirty
* 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
inode->i_state |= I_DIRTY_PAGES;
redirty_tail(inode);
}
- } else if (inode->i_state & I_DIRTY) {
- /*
- * Someone redirtied the inode while were writing back
- * the pages.
- */
- redirty_tail(inode);
} else if (atomic_read(&inode->i_count)) {
/*
* The inode is clean, inuse
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) {
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->sb_pinned) {
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;
-}
-
-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);
+ return SB_PIN_FAILED;
}
-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,
+ .sb_pinned = args->sb_pinned,
};
unsigned long oldest_jif;
long wrote = 0;
+ struct inode *inode;
if (wbc.for_kupdate) {
wbc.older_than_this = &oldest_jif;
for (;;) {
/*
- * Don't flush anything for non-integrity writeback where
- * no nr_pages was given
+ * Stop writeback when nr_pages has been consumed
*/
- if (!args->for_kupdate && args->nr_pages <= 0 &&
- args->sync_mode == WB_SYNC_NONE)
+ if (args->nr_pages <= 0)
break;
/*
- * If no specific pages were given and this is just a
- * periodic background writeout and we are below the
- * background dirty threshold, don't do anything
+ * For background writeout, stop when we are below the
+ * background dirty threshold
*/
- if (args->for_kupdate && args->nr_pages <= 0 &&
- !over_bground_thresh())
+ if (args->for_background && !over_bground_thresh())
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);
wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
/*
- * If we ran out of stuff to write, bail unless more_io got set
+ * If we consumed everything, see if we have more
*/
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- if (wbc.more_io && !wbc.for_kupdate)
- continue;
+ if (wbc.nr_to_write <= 0)
+ continue;
+ /*
+ * Didn't write everything and we don't have more IO, bail
+ */
+ if (!wbc.more_io)
break;
+ /*
+ * Did we write something? Try for more
+ */
+ if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+ continue;
+ /*
+ * Nothing written. Wait for some inode to
+ * become available for writeback. Otherwise
+ * we'll just busyloop.
+ */
+ spin_lock(&inode_lock);
+ if (!list_empty(&wb->b_more_io)) {
+ inode = list_entry(wb->b_more_io.prev,
+ struct inode, i_list);
+ inode_wait_for_writeback(inode);
}
+ spin_unlock(&inode_lock);
}
return wrote;
unsigned long expired;
long nr_pages;
+ /*
+ * When set to zero, disable periodic writeback
+ */
+ if (!dirty_writeback_interval)
+ return 0;
+
expired = wb->last_old_flush +
msecs_to_jiffies(dirty_writeback_interval * 10);
if (time_before(jiffies, expired))
while ((work = get_next_work_item(bdi, wb)) != NULL) {
struct wb_writeback_args args = work->args;
+ int post_clear;
/*
* Override sync mode, in case we must wait for completion
if (force_wait)
work->args.sync_mode = args.sync_mode = WB_SYNC_ALL;
+ post_clear = WB_SYNC_ALL || args.sb_pinned;
+
/*
* If this isn't a data integrity operation, just notify
* that we have seen this work and we are now starting it.
*/
- if (args.sync_mode == WB_SYNC_NONE)
+ if (!post_clear)
wb_clear_pending(wb, work);
wrote += wb_writeback(wb, &args);
* This is a data integrity writeback, so only do the
* notification when we have completed the work.
*/
- if (args.sync_mode == WB_SYNC_ALL)
+ if (post_clear)
wb_clear_pending(wb, work);
}
break;
}
- wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
- schedule_timeout_interruptible(wait_jiffies);
+ if (dirty_writeback_interval) {
+ wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+ schedule_timeout_interruptible(wait_jiffies);
+ } else {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (list_empty_careful(&wb->bdi->work_list) &&
+ !kthread_should_stop())
+ schedule();
+ __set_current_state(TASK_RUNNING);
+ }
+
try_to_freeze();
}
if (!bdi_has_dirty_io(bdi))
continue;
- bdi_alloc_queue_work(bdi, &args);
+ bdi_alloc_queue_work(bdi, &args, 0);
}
rcu_read_unlock();
* If older_than_this is non-NULL, then only write out inodes which
* had their first dirtying at a time earlier than *older_than_this.
*
- * If we're a pdlfush thread, then implement pdflush collision avoidance
- * against the entire list.
- *
* If `bdi' is non-zero then we're being asked to writeback a specific queue.
* This function assumes that the blockdev superblock's inodes are backed by
* a variety of queues, so all inodes are searched. For other superblocks,
iput(old_inode);
}
+static void __writeback_inodes_sb(struct super_block *sb, int sb_locked)
+{
+ unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+ unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+ long nr_to_write;
+
+ nr_to_write = nr_dirty + nr_unstable +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ bdi_start_writeback(sb->s_bdi, sb, nr_to_write, sb_locked);
+}
+
/**
* writeback_inodes_sb - writeback dirty inodes from given super_block
* @sb: the superblock
*/
void writeback_inodes_sb(struct super_block *sb)
{
- unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
- unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
- long nr_to_write;
+ __writeback_inodes_sb(sb, 0);
+}
+EXPORT_SYMBOL(writeback_inodes_sb);
- nr_to_write = nr_dirty + nr_unstable +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+/**
+ * writeback_inodes_sb_locked - writeback dirty inodes from given super_block
+ * @sb: the superblock
+ *
+ * Like writeback_inodes_sb(), except the caller already holds the
+ * sb umount sem.
+ */
+void writeback_inodes_sb_locked(struct super_block *sb)
+{
+ __writeback_inodes_sb(sb, 1);
+}
- bdi_writeback_all(sb, nr_to_write);
+/**
+ * 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);
+EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
/**
* sync_inodes_sb - sync sb inode pages
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff