struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
+ unsigned long *older_than_this;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
/*
* Move expired dirty inodes from @delaying_queue to @dispatch_queue.
*/
-static void move_expired_inodes(struct list_head *delaying_queue,
+static int move_expired_inodes(struct list_head *delaying_queue,
struct list_head *dispatch_queue,
- unsigned long *older_than_this)
+ 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;
+ int moved = 0;
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
do_sb_sort = 1;
sb = inode->i_sb;
list_move(&inode->i_wb_list, &tmp);
+ moved++;
}
/* just one sb in list, splice to dispatch_queue and we're done */
if (!do_sb_sort) {
list_splice(&tmp, dispatch_queue);
- return;
+ goto out;
}
/* Move inodes from one superblock together */
list_move(&inode->i_wb_list, dispatch_queue);
}
}
+out:
+ return moved;
}
/*
*/
static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
+ int moved;
assert_spin_locked(&wb->list_lock);
list_splice_init(&wb->b_more_io, &wb->b_io);
- move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+ moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
+ trace_writeback_queue_io(wb, older_than_this, moved);
}
static int write_inode(struct inode *inode, struct writeback_control *wbc)
struct writeback_control *wbc)
{
struct address_space *mapping = inode->i_mapping;
+ long nr_to_write = wbc->nr_to_write;
unsigned dirty;
int ret;
*/
if (wbc->sync_mode != WB_SYNC_ALL) {
requeue_io(inode, wb);
+ trace_writeback_single_inode_requeue(inode, wbc,
+ nr_to_write);
return 0;
}
* No need to add it back to the LRU.
*/
list_del_init(&inode->i_wb_list);
- wbc->inodes_written++;
}
}
inode_sync_complete(inode);
+ trace_writeback_single_inode(inode, wbc, nr_to_write);
return ret;
}
-/*
- * For background 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.
- */
-static bool pin_sb_for_writeback(struct super_block *sb)
+static long writeback_chunk_size(struct backing_dev_info *bdi,
+ struct wb_writeback_work *work)
{
- spin_lock(&sb_lock);
- if (list_empty(&sb->s_instances)) {
- spin_unlock(&sb_lock);
- return false;
- }
-
- sb->s_count++;
- spin_unlock(&sb_lock);
+ long pages;
- if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root)
- return true;
- up_read(&sb->s_umount);
+ /*
+ * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+ * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+ * here avoids calling into writeback_inodes_wb() more than once.
+ *
+ * The intended call sequence for WB_SYNC_ALL writeback is:
+ *
+ * wb_writeback()
+ * writeback_sb_inodes() <== called only once
+ * write_cache_pages() <== called once for each inode
+ * (quickly) tag currently dirty pages
+ * (maybe slowly) sync all tagged pages
+ */
+ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
+ pages = LONG_MAX;
+ else {
+ pages = min(bdi->avg_write_bandwidth / 2,
+ global_dirty_limit / DIRTY_SCOPE);
+ pages = min(pages, work->nr_pages);
+ pages = round_down(pages + MIN_WRITEBACK_PAGES,
+ MIN_WRITEBACK_PAGES);
}
- put_super(sb);
- return false;
+ return pages;
}
/*
* inodes. Otherwise write only ones which go sequentially
* in reverse order.
*
- * Return 1, if the caller writeback routine should be
- * interrupted. Otherwise return 0.
+ * Return the number of pages and/or inodes written.
*/
-static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
- struct writeback_control *wbc, bool only_this_sb)
+static long writeback_sb_inodes(struct super_block *sb,
+ struct bdi_writeback *wb,
+ struct wb_writeback_work *work)
{
+ struct writeback_control wbc = {
+ .sync_mode = work->sync_mode,
+ .tagged_writepages = work->tagged_writepages,
+ .for_kupdate = work->for_kupdate,
+ .for_background = work->for_background,
+ .range_cyclic = work->range_cyclic,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
+ unsigned long start_time = jiffies;
+ long write_chunk;
+ long wrote = 0; /* count both pages and inodes */
+
while (!list_empty(&wb->b_io)) {
- long pages_skipped;
struct inode *inode = wb_inode(wb->b_io.prev);
if (inode->i_sb != sb) {
- if (only_this_sb) {
+ if (work->sb) {
/*
* We only want to write back data for this
* superblock, move all inodes not belonging
* Bounce back to the caller to unpin this and
* pin the next superblock.
*/
- return 0;
+ break;
}
/*
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
spin_unlock(&inode->i_lock);
- requeue_io(inode, wb);
+ redirty_tail(inode, wb);
continue;
}
-
__iget(inode);
+ write_chunk = writeback_chunk_size(wb->bdi, work);
+ wbc.nr_to_write = write_chunk;
+ wbc.pages_skipped = 0;
+
+ writeback_single_inode(inode, wb, &wbc);
- pages_skipped = wbc->pages_skipped;
- writeback_single_inode(inode, wb, wbc);
- if (wbc->pages_skipped != pages_skipped) {
+ work->nr_pages -= write_chunk - wbc.nr_to_write;
+ wrote += write_chunk - wbc.nr_to_write;
+ if (!(inode->i_state & I_DIRTY))
+ wrote++;
+ if (wbc.pages_skipped) {
/*
* writeback is not making progress due to locked
* buffers. Skip this inode for now.
iput(inode);
cond_resched();
spin_lock(&wb->list_lock);
- if (wbc->nr_to_write <= 0)
- return 1;
+ /*
+ * bail out to wb_writeback() often enough to check
+ * background threshold and other termination conditions.
+ */
+ if (wrote) {
+ if (time_is_before_jiffies(start_time + HZ / 10UL))
+ break;
+ if (work->nr_pages <= 0)
+ break;
+ }
}
- /* b_io is empty */
- return 1;
+ return wrote;
}
-static void __writeback_inodes_wb(struct bdi_writeback *wb,
- struct writeback_control *wbc)
+static long __writeback_inodes_wb(struct bdi_writeback *wb,
+ struct wb_writeback_work *work)
{
- int ret = 0;
+ unsigned long start_time = jiffies;
+ long wrote = 0;
while (!list_empty(&wb->b_io)) {
struct inode *inode = wb_inode(wb->b_io.prev);
struct super_block *sb = inode->i_sb;
- if (!pin_sb_for_writeback(sb)) {
- requeue_io(inode, wb);
+ if (!grab_super_passive(sb)) {
+ /*
+ * grab_super_passive() may fail consistently due to
+ * s_umount being grabbed by someone else. Don't use
+ * requeue_io() to avoid busy retrying the inode/sb.
+ */
+ redirty_tail(inode, wb);
continue;
}
- ret = writeback_sb_inodes(sb, wb, wbc, false);
+ wrote += writeback_sb_inodes(sb, wb, work);
drop_super(sb);
- if (ret)
- break;
+ /* refer to the same tests at the end of writeback_sb_inodes */
+ if (wrote) {
+ if (time_is_before_jiffies(start_time + HZ / 10UL))
+ break;
+ if (work->nr_pages <= 0)
+ break;
+ }
}
/* Leave any unwritten inodes on b_io */
+ return wrote;
}
-void writeback_inodes_wb(struct bdi_writeback *wb,
- struct writeback_control *wbc)
+long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages)
{
+ struct wb_writeback_work work = {
+ .nr_pages = nr_pages,
+ .sync_mode = WB_SYNC_NONE,
+ .range_cyclic = 1,
+ };
+
spin_lock(&wb->list_lock);
if (list_empty(&wb->b_io))
- queue_io(wb, wbc->older_than_this);
- __writeback_inodes_wb(wb, wbc);
+ queue_io(wb, NULL);
+ __writeback_inodes_wb(wb, &work);
spin_unlock(&wb->list_lock);
-}
-/*
- * The maximum number of pages to writeout in a single bdi flush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
+ return nr_pages - work.nr_pages;
+}
static inline bool over_bground_thresh(void)
{
global_page_state(NR_UNSTABLE_NFS) > background_thresh);
}
+/*
+ * Called under wb->list_lock. If there are multiple wb per bdi,
+ * only the flusher working on the first wb should do it.
+ */
+static void wb_update_bandwidth(struct bdi_writeback *wb,
+ unsigned long start_time)
+{
+ __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time);
+}
+
/*
* Explicit flushing or periodic writeback of "old" data.
*
static long wb_writeback(struct bdi_writeback *wb,
struct wb_writeback_work *work)
{
- struct writeback_control wbc = {
- .sync_mode = work->sync_mode,
- .tagged_writepages = work->tagged_writepages,
- .older_than_this = NULL,
- .for_kupdate = work->for_kupdate,
- .for_background = work->for_background,
- .range_cyclic = work->range_cyclic,
- };
+ unsigned long wb_start = jiffies;
+ long nr_pages = work->nr_pages;
unsigned long oldest_jif;
- long wrote = 0;
- long write_chunk = MAX_WRITEBACK_PAGES;
struct inode *inode;
-
- if (!wbc.range_cyclic) {
- wbc.range_start = 0;
- wbc.range_end = LLONG_MAX;
- }
-
- /*
- * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
- * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
- * here avoids calling into writeback_inodes_wb() more than once.
- *
- * The intended call sequence for WB_SYNC_ALL writeback is:
- *
- * wb_writeback()
- * writeback_sb_inodes() <== called only once
- * write_cache_pages() <== called once for each inode
- * (quickly) tag currently dirty pages
- * (maybe slowly) sync all tagged pages
- */
- if (wbc.sync_mode == WB_SYNC_ALL || wbc.tagged_writepages)
- write_chunk = LONG_MAX;
+ long progress;
oldest_jif = jiffies;
- wbc.older_than_this = &oldest_jif;
+ work->older_than_this = &oldest_jif;
spin_lock(&wb->list_lock);
for (;;) {
if (work->for_kupdate) {
oldest_jif = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
- wbc.older_than_this = &oldest_jif;
+ work->older_than_this = &oldest_jif;
}
- wbc.nr_to_write = write_chunk;
- wbc.pages_skipped = 0;
- wbc.inodes_written = 0;
-
- trace_wbc_writeback_start(&wbc, wb->bdi);
+ trace_writeback_start(wb->bdi, work);
if (list_empty(&wb->b_io))
- queue_io(wb, wbc.older_than_this);
+ queue_io(wb, work->older_than_this);
if (work->sb)
- writeback_sb_inodes(work->sb, wb, &wbc, true);
+ progress = writeback_sb_inodes(work->sb, wb, work);
else
- __writeback_inodes_wb(wb, &wbc);
- trace_wbc_writeback_written(&wbc, wb->bdi);
+ progress = __writeback_inodes_wb(wb, work);
+ trace_writeback_written(wb->bdi, work);
- work->nr_pages -= write_chunk - wbc.nr_to_write;
- wrote += write_chunk - wbc.nr_to_write;
+ wb_update_bandwidth(wb, wb_start);
/*
* Did we write something? Try for more
* mean the overall work is done. So we keep looping as long
* as made some progress on cleaning pages or inodes.
*/
- if (wbc.nr_to_write < write_chunk)
- continue;
- if (wbc.inodes_written)
+ if (progress)
continue;
/*
* No more inodes for IO, bail
* we'll just busyloop.
*/
if (!list_empty(&wb->b_more_io)) {
+ trace_writeback_wait(wb->bdi, work);
inode = wb_inode(wb->b_more_io.prev);
- trace_wbc_writeback_wait(&wbc, wb->bdi);
spin_lock(&inode->i_lock);
inode_wait_for_writeback(inode, wb);
spin_unlock(&inode->i_lock);
}
spin_unlock(&wb->list_lock);
- return wrote;
+ return nr_pages - work->nr_pages;
}
/*