in dm-writecache.c [1919:2087]
static void writecache_writeback(struct work_struct *work)
{
struct dm_writecache *wc = container_of(work, struct dm_writecache, writeback_work);
struct blk_plug plug;
struct wc_entry *f, *g, *e = NULL;
struct rb_node *node, *next_node;
struct list_head skipped;
struct writeback_list wbl;
unsigned long n_walked;
if (!WC_MODE_PMEM(wc)) {
/* Wait for any active kcopyd work on behalf of ssd writeback */
dm_kcopyd_client_flush(wc->dm_kcopyd);
}
if (likely(wc->pause != 0)) {
while (1) {
unsigned long idle;
if (unlikely(wc->cleaner) || unlikely(wc->writeback_all) ||
unlikely(dm_suspended(wc->ti)))
break;
idle = dm_iot_idle_time(&wc->iot);
if (idle >= wc->pause)
break;
idle = wc->pause - idle;
if (idle > HZ)
idle = HZ;
schedule_timeout_idle(idle);
}
}
wc_lock(wc);
restart:
if (writecache_has_error(wc)) {
wc_unlock(wc);
return;
}
if (unlikely(wc->writeback_all)) {
if (writecache_wait_for_writeback(wc))
goto restart;
}
if (wc->overwrote_committed) {
writecache_wait_for_ios(wc, WRITE);
}
n_walked = 0;
INIT_LIST_HEAD(&skipped);
INIT_LIST_HEAD(&wbl.list);
wbl.size = 0;
while (!list_empty(&wc->lru) &&
(wc->writeback_all ||
wc->freelist_size + wc->writeback_size <= wc->freelist_low_watermark ||
(jiffies - container_of(wc->lru.prev, struct wc_entry, lru)->age >=
wc->max_age - wc->max_age / MAX_AGE_DIV))) {
n_walked++;
if (unlikely(n_walked > WRITEBACK_LATENCY) &&
likely(!wc->writeback_all)) {
if (likely(!dm_suspended(wc->ti)))
queue_work(wc->writeback_wq, &wc->writeback_work);
break;
}
if (unlikely(wc->writeback_all)) {
if (unlikely(!e)) {
writecache_flush(wc);
e = container_of(rb_first(&wc->tree), struct wc_entry, rb_node);
} else
e = g;
} else
e = container_of(wc->lru.prev, struct wc_entry, lru);
BUG_ON(e->write_in_progress);
if (unlikely(!writecache_entry_is_committed(wc, e))) {
writecache_flush(wc);
}
node = rb_prev(&e->rb_node);
if (node) {
f = container_of(node, struct wc_entry, rb_node);
if (unlikely(read_original_sector(wc, f) ==
read_original_sector(wc, e))) {
BUG_ON(!f->write_in_progress);
list_move(&e->lru, &skipped);
cond_resched();
continue;
}
}
wc->writeback_size++;
list_move(&e->lru, &wbl.list);
wbl.size++;
e->write_in_progress = true;
e->wc_list_contiguous = 1;
f = e;
while (1) {
next_node = rb_next(&f->rb_node);
if (unlikely(!next_node))
break;
g = container_of(next_node, struct wc_entry, rb_node);
if (unlikely(read_original_sector(wc, g) ==
read_original_sector(wc, f))) {
f = g;
continue;
}
if (read_original_sector(wc, g) !=
read_original_sector(wc, f) + (wc->block_size >> SECTOR_SHIFT))
break;
if (unlikely(g->write_in_progress))
break;
if (unlikely(!writecache_entry_is_committed(wc, g)))
break;
if (!WC_MODE_PMEM(wc)) {
if (g != f + 1)
break;
}
n_walked++;
//if (unlikely(n_walked > WRITEBACK_LATENCY) && likely(!wc->writeback_all))
// break;
wc->writeback_size++;
list_move(&g->lru, &wbl.list);
wbl.size++;
g->write_in_progress = true;
g->wc_list_contiguous = BIO_MAX_VECS;
f = g;
e->wc_list_contiguous++;
if (unlikely(e->wc_list_contiguous == BIO_MAX_VECS)) {
if (unlikely(wc->writeback_all)) {
next_node = rb_next(&f->rb_node);
if (likely(next_node))
g = container_of(next_node, struct wc_entry, rb_node);
}
break;
}
}
cond_resched();
}
if (!list_empty(&skipped)) {
list_splice_tail(&skipped, &wc->lru);
/*
* If we didn't do any progress, we must wait until some
* writeback finishes to avoid burning CPU in a loop
*/
if (unlikely(!wbl.size))
writecache_wait_for_writeback(wc);
}
wc_unlock(wc);
blk_start_plug(&plug);
if (WC_MODE_PMEM(wc))
__writecache_writeback_pmem(wc, &wbl);
else
__writecache_writeback_ssd(wc, &wbl);
blk_finish_plug(&plug);
if (unlikely(wc->writeback_all)) {
wc_lock(wc);
while (writecache_wait_for_writeback(wc));
wc_unlock(wc);
}
}