#include <linux/syscalls.h>
#include <linux/buffer_head.h>
#include <linux/pagevec.h>
+#include <trace/events/writeback.h>
/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
for (;;) {
struct writeback_control wbc = {
- .bdi = bdi,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = write_chunk,
* threshold otherwise wait until the disk writes catch
* up.
*/
+ trace_wbc_balance_dirty_start(&wbc, bdi);
if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes_wbc(&wbc);
+ writeback_inodes_wb(&bdi->wb, &wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
+ trace_wbc_balance_dirty_written(&wbc, bdi);
}
/*
if (pages_written >= write_chunk)
break; /* We've done our duty */
- schedule_timeout_interruptible(pause);
+ trace_wbc_balance_dirty_wait(&wbc, bdi);
+ __set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule_timeout(pause);
/*
* Increase the delay for each loop, up to our previous
(!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS))
> background_thresh)))
- bdi_start_writeback(bdi, 0);
+ bdi_start_background_writeback(bdi);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
}
}
-static void laptop_timer_fn(unsigned long unused);
-
-static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
-
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, buffer, length, ppos);
+ bdi_arm_supers_timer();
return 0;
}
-static void do_laptop_sync(struct work_struct *work)
-{
- wakeup_flusher_threads(0);
- kfree(work);
-}
-
-static void laptop_timer_fn(unsigned long unused)
+#ifdef CONFIG_BLOCK
+void laptop_mode_timer_fn(unsigned long data)
{
- struct work_struct *work;
+ struct request_queue *q = (struct request_queue *)data;
+ int nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
- work = kmalloc(sizeof(*work), GFP_ATOMIC);
- if (work) {
- INIT_WORK(work, do_laptop_sync);
- schedule_work(work);
- }
+ /*
+ * We want to write everything out, not just down to the dirty
+ * threshold
+ */
+ if (bdi_has_dirty_io(&q->backing_dev_info))
+ bdi_start_writeback(&q->backing_dev_info, nr_pages);
}
/*
* of all dirty data a few seconds from now. If the flush is already scheduled
* then push it back - the user is still using the disk.
*/
-void laptop_io_completion(void)
+void laptop_io_completion(struct backing_dev_info *info)
{
- mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
+ mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode);
}
/*
*/
void laptop_sync_completion(void)
{
- del_timer(&laptop_mode_wb_timer);
+ struct backing_dev_info *bdi;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
+ del_timer(&bdi->laptop_mode_wb_timer);
+
+ rcu_read_unlock();
}
+#endif
/*
* If ratelimit_pages is too high then we can get into dirty-data overload
prop_descriptor_init(&vm_dirties, shift);
}
+/**
+ * tag_pages_for_writeback - tag pages to be written by write_cache_pages
+ * @mapping: address space structure to write
+ * @start: starting page index
+ * @end: ending page index (inclusive)
+ *
+ * This function scans the page range from @start to @end (inclusive) and tags
+ * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is
+ * that write_cache_pages (or whoever calls this function) will then use
+ * TOWRITE tag to identify pages eligible for writeback. This mechanism is
+ * used to avoid livelocking of writeback by a process steadily creating new
+ * dirty pages in the file (thus it is important for this function to be quick
+ * so that it can tag pages faster than a dirtying process can create them).
+ */
+/*
+ * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce tree_lock latency.
+ */
+#define WRITEBACK_TAG_BATCH 4096
+void tag_pages_for_writeback(struct address_space *mapping,
+ pgoff_t start, pgoff_t end)
+{
+ unsigned long tagged;
+
+ do {
+ spin_lock_irq(&mapping->tree_lock);
+ tagged = radix_tree_range_tag_if_tagged(&mapping->page_tree,
+ &start, end, WRITEBACK_TAG_BATCH,
+ PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE);
+ spin_unlock_irq(&mapping->tree_lock);
+ WARN_ON_ONCE(tagged > WRITEBACK_TAG_BATCH);
+ cond_resched();
+ } while (tagged >= WRITEBACK_TAG_BATCH);
+}
+EXPORT_SYMBOL(tag_pages_for_writeback);
+
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
+ *
+ * To avoid livelocks (when other process dirties new pages), we first tag
+ * pages which should be written back with TOWRITE tag and only then start
+ * writing them. For data-integrity sync we have to be careful so that we do
+ * not miss some pages (e.g., because some other process has cleared TOWRITE
+ * tag we set). The rule we follow is that TOWRITE tag can be cleared only
+ * by the process clearing the DIRTY tag (and submitting the page for IO).
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
- struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
pgoff_t done_index;
int cycled;
int range_whole = 0;
- long nr_to_write = wbc->nr_to_write;
-
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- return 0;
- }
+ int tag;
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ tag = PAGECACHE_TAG_TOWRITE;
+ else
+ tag = PAGECACHE_TAG_DIRTY;
retry:
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
int i;
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
break;
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
+ trace_wbc_writepage(wbc, mapping->backing_dev_info);
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
done = 1;
break;
}
- }
+ }
- if (nr_to_write > 0) {
- nr_to_write--;
- if (nr_to_write == 0 &&
+ if (wbc->nr_to_write > 0) {
+ if (--wbc->nr_to_write == 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
/*
* We stop writing back only if we are
break;
}
}
-
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- done = 1;
- break;
- }
}
pagevec_release(&pvec);
cond_resched();
end = writeback_index - 1;
goto retry;
}
- if (!wbc->no_nrwrite_index_update) {
- if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
- mapping->writeback_index = done_index;
- wbc->nr_to_write = nr_to_write;
- }
+ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+ mapping->writeback_index = done_index;
return ret;
}
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
+ radix_tree_tag_clear(&mapping->page_tree,
+ page_index(page),
+ PAGECACHE_TAG_TOWRITE);
spin_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestSetPageWriteback(page);