/*
* When balance_dirty_pages decides that the caller needs to perform some
* non-background writeback, this is how many pages it will attempt to write.
- * It should be somewhat larger than RATELIMIT_PAGES to ensure that reasonably
+ * It should be somewhat larger than dirtied pages to ensure that reasonably
* large amounts of I/O are submitted.
*/
-static inline long sync_writeback_pages(void)
+static inline long sync_writeback_pages(unsigned long dirtied)
{
- return ratelimit_pages + ratelimit_pages / 2;
+ if (dirtied < ratelimit_pages)
+ dirtied = ratelimit_pages;
+
+ return dirtied + dirtied / 2;
}
/* The following parameters are exported via /proc/sys/vm */
/*
- * Start background writeback (via pdflush) at this percentage
+ * Start background writeback (via writeback threads) at this percentage
*/
int dirty_background_ratio = 10;
}
int dirty_background_ratio_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
- ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
dirty_background_bytes = 0;
return ret;
}
int dirty_background_bytes_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
- ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
dirty_background_ratio = 0;
return ret;
}
int dirty_ratio_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int old_ratio = vm_dirty_ratio;
int ret;
- ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
update_completion_period();
vm_dirty_bytes = 0;
int dirty_bytes_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
unsigned long old_bytes = vm_dirty_bytes;
int ret;
- ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
update_completion_period();
vm_dirty_ratio = 0;
struct zone *z =
&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
- x += zone_page_state(z, NR_FREE_PAGES) + zone_lru_pages(z);
+ x += zone_page_state(z, NR_FREE_PAGES) +
+ zone_reclaimable_pages(z);
}
/*
* Make sure that the number of highmem pages is never larger
{
unsigned long x;
- x = global_page_state(NR_FREE_PAGES) + global_lru_pages();
+ x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
* balance_dirty_pages() must be called by processes which are generating dirty
* data. It looks at the number of dirty pages in the machine and will force
* the caller to perform writeback if the system is over `vm_dirty_ratio'.
- * If we're over `background_thresh' then pdflush is woken to perform some
- * writeout.
+ * If we're over `background_thresh' then the writeback threads are woken to
+ * perform some writeout.
*/
-static void balance_dirty_pages(struct address_space *mapping)
+static void balance_dirty_pages(struct address_space *mapping,
+ unsigned long write_chunk)
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
unsigned long pages_written = 0;
- unsigned long write_chunk = sync_writeback_pages();
+ unsigned long pause = 1;
struct backing_dev_info *bdi = mapping->backing_dev_info;
if (pages_written >= write_chunk)
break; /* We've done our duty */
- schedule_timeout(1);
+ __set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule_timeout(pause);
+
+ /*
+ * Increase the delay for each loop, up to our previous
+ * default of taking a 100ms nap.
+ */
+ pause <<= 1;
+ if (pause > HZ / 10)
+ pause = HZ / 10;
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
bdi->dirty_exceeded = 0;
if (writeback_in_progress(bdi))
- return; /* pdflush is already working this queue */
+ return;
/*
* In laptop mode, we wait until hitting the higher threshold before
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
- (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY)
- + global_page_state(NR_UNSTABLE_NFS))
- > background_thresh))) {
- struct writeback_control wbc = {
- .bdi = bdi,
- .sync_mode = WB_SYNC_NONE,
- .nr_to_write = nr_writeback,
- };
-
-
- bdi_start_writeback(&wbc);
- }
+ (!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
+ + global_page_state(NR_UNSTABLE_NFS))
+ > background_thresh)))
+ bdi_start_writeback(bdi, NULL, 0);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
p = &__get_cpu_var(bdp_ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
+ ratelimit = sync_writeback_pages(*p);
*p = 0;
preempt_enable();
- balance_dirty_pages(mapping);
+ balance_dirty_pages(mapping, ratelimit);
return;
}
preempt_enable();
}
}
-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
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec(table, write, file, buffer, length, ppos);
+ proc_dointvec(table, write, buffer, length, ppos);
+ bdi_arm_supers_timer();
return 0;
}
-static void do_laptop_sync(struct work_struct *work)
+#ifdef CONFIG_BLOCK
+void laptop_mode_timer_fn(unsigned long data)
{
- wakeup_flusher_threads(0);
- kfree(work);
-}
+ struct request_queue *q = (struct request_queue *)data;
+ int nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
-static void laptop_timer_fn(unsigned long unused)
-{
- struct work_struct *work;
+ /*
+ * We want to write everything out, not just down to the dirty
+ * threshold
+ */
- work = kmalloc(sizeof(*work), GFP_ATOMIC);
- if (work) {
- INIT_WORK(work, do_laptop_sync);
- schedule_work(work);
- }
+ if (bdi_has_dirty_io(&q->backing_dev_info))
+ bdi_start_writeback(&q->backing_dev_info, NULL, 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
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;
- }
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
+
+ /*
+ * If this is a data integrity sync, cap the writeback to the
+ * current end of file. Any extension to the file that occurs
+ * after this is a new write and we don't need to write those
+ * pages out to fulfil our data integrity requirements. If we
+ * try to write them out, we can get stuck in this scan until
+ * the concurrent writer stops adding dirty pages and extending
+ * EOF.
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL &&
+ wbc->range_end == LLONG_MAX) {
+ end = i_size_read(mapping->host) >> PAGE_CACHE_SHIFT;
+ }
}
+
retry:
done_index = index;
while (!done && (index <= end)) {
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;
}
EXPORT_SYMBOL(redirty_page_for_writepage);
/*
+ * Dirty a page.
+ *
+ * For pages with a mapping this should be done under the page lock
+ * for the benefit of asynchronous memory errors who prefer a consistent
+ * dirty state. This rule can be broken in some special cases,
+ * but should be better not to.
+ *
* If the mapping doesn't provide a set_page_dirty a_op, then
* just fall through and assume that it wants buffer_heads.
*/