1 files changed, 40 insertions, 108 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d213ead95675..72b0ff0d4bae 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -41,6 +41,7 @@
 #include <trace/events/writeback.h>
 
 #include "internal.h"
+#include "swap.h"
 
 /*
  * Sleep at most 200ms at a time in balance_dirty_pages().
@@ -120,29 +121,6 @@ EXPORT_SYMBOL(laptop_mode);
 
 struct wb_domain global_wb_domain;
 
-/* consolidated parameters for balance_dirty_pages() and its subroutines */
-struct dirty_throttle_control {
-#ifdef CONFIG_CGROUP_WRITEBACK
-	struct wb_domain	*dom;
-	struct dirty_throttle_control *gdtc;	/* only set in memcg dtc's */
-#endif
-	struct bdi_writeback	*wb;
-	struct fprop_local_percpu *wb_completions;
-
-	unsigned long		avail;		/* dirtyable */
-	unsigned long		dirty;		/* file_dirty + write + nfs */
-	unsigned long		thresh;		/* dirty threshold */
-	unsigned long		bg_thresh;	/* dirty background threshold */
-
-	unsigned long		wb_dirty;	/* per-wb counterparts */
-	unsigned long		wb_thresh;
-	unsigned long		wb_bg_thresh;
-
-	unsigned long		pos_ratio;
-	bool			freerun;
-	bool			dirty_exceeded;
-};
-
 /*
  * Length of period for aging writeout fractions of bdis. This is an
  * arbitrarily chosen number. The longer the period, the slower fractions will
@@ -543,8 +521,8 @@ static int dirty_ratio_handler(const struct ctl_table *table, int write, void *b
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
-		writeback_set_ratelimit();
 		vm_dirty_bytes = 0;
+		writeback_set_ratelimit();
 	}
 	return ret;
 }
@@ -630,7 +608,7 @@ EXPORT_SYMBOL_GPL(wb_writeout_inc);
  */
 static void writeout_period(struct timer_list *t)
 {
-	struct wb_domain *dom = from_timer(dom, t, period_timer);
+	struct wb_domain *dom = timer_container_of(dom, t, period_timer);
 	int miss_periods = (jiffies - dom->period_time) /
 						 VM_COMPLETIONS_PERIOD_LEN;
 
@@ -663,7 +641,7 @@ int wb_domain_init(struct wb_domain *dom, gfp_t gfp)
 #ifdef CONFIG_CGROUP_WRITEBACK
 void wb_domain_exit(struct wb_domain *dom)
 {
-	del_timer_sync(&dom->period_timer);
+	timer_delete_sync(&dom->period_timer);
 	fprop_global_destroy(&dom->completions);
 }
 #endif
@@ -692,6 +670,8 @@ static unsigned long bdi_ratio_from_pages(unsigned long pages)
 	unsigned long ratio;
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
+	if (!dirty_thresh)
+		return -EINVAL;
 	ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh);
 
 	return ratio;
@@ -790,13 +770,15 @@ int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes)
 {
 	int ret;
 	unsigned long pages = min_bytes >> PAGE_SHIFT;
-	unsigned long min_ratio;
+	long min_ratio;
 
 	ret = bdi_check_pages_limit(pages);
 	if (ret)
 		return ret;
 
 	min_ratio = bdi_ratio_from_pages(pages);
+	if (min_ratio < 0)
+		return min_ratio;
 	return __bdi_set_min_ratio(bdi, min_ratio);
 }
 
@@ -809,13 +791,15 @@ int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes)
 {
 	int ret;
 	unsigned long pages = max_bytes >> PAGE_SHIFT;
-	unsigned long max_ratio;
+	long max_ratio;
 
 	ret = bdi_check_pages_limit(pages);
 	if (ret)
 		return ret;
 
 	max_ratio = bdi_ratio_from_pages(pages);
+	if (max_ratio < 0)
+		return max_ratio;
 	return __bdi_set_max_ratio(bdi, max_ratio);
 }
 
@@ -936,26 +920,25 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc,
 	wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio);
 
 	wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE);
-	wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
-	if (wb_thresh > wb_max_thresh)
-		wb_thresh = wb_max_thresh;
 
 	/*
-	 * With strictlimit flag, the wb_thresh is treated as
-	 * a hard limit in balance_dirty_pages() and wb_position_ratio().
-	 * It's possible that wb_thresh is close to zero, not because
-	 * the device is slow, but because it has been inactive.
-	 * To prevent occasional writes from being blocked, we raise wb_thresh.
+	 * It's very possible that wb_thresh is close to 0 not because the
+	 * device is slow, but that it has remained inactive for long time.
+	 * Honour such devices a reasonable good (hopefully IO efficient)
+	 * threshold, so that the occasional writes won't be blocked and active
+	 * writes can rampup the threshold quickly.
 	 */
-	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
-		unsigned long limit = hard_dirty_limit(dom, dtc->thresh);
-		u64 wb_scale_thresh = 0;
-
-		if (limit > dtc->dirty)
-			wb_scale_thresh = (limit - dtc->dirty) / 100;
-		wb_thresh = max(wb_thresh, min(wb_scale_thresh, wb_max_thresh / 4));
+	if (thresh > dtc->dirty) {
+		if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT))
+			wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100);
+		else
+			wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8);
 	}
 
+	wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
+	if (wb_thresh > wb_max_thresh)
+		wb_thresh = wb_max_thresh;
+
 	return wb_thresh;
 }
 
@@ -963,6 +946,7 @@ unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh)
 {
 	struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
 
+	domain_dirty_avail(&gdtc, true);
 	return __wb_calc_thresh(&gdtc, thresh);
 }
 
@@ -1089,7 +1073,7 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	struct bdi_writeback *wb = dtc->wb;
 	unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth);
 	unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh);
-	unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
+	unsigned long limit = dtc->limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh);
 	unsigned long wb_thresh = dtc->wb_thresh;
 	unsigned long x_intercept;
 	unsigned long setpoint;		/* dirty pages' target balance point */
@@ -1139,12 +1123,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		long long wb_pos_ratio;
 
-		if (dtc->wb_dirty < 8) {
-			dtc->pos_ratio = min_t(long long, pos_ratio * 2,
-					   2 << RATELIMIT_CALC_SHIFT);
-			return;
-		}
-
 		if (dtc->wb_dirty >= wb_thresh)
 			return;
 
@@ -1216,14 +1194,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	if (unlikely(wb_thresh > dtc->thresh))
 		wb_thresh = dtc->thresh;
 	/*
-	 * It's very possible that wb_thresh is close to 0 not because the
-	 * device is slow, but that it has remained inactive for long time.
-	 * Honour such devices a reasonable good (hopefully IO efficient)
-	 * threshold, so that the occasional writes won't be blocked and active
-	 * writes can rampup the threshold quickly.
-	 */
-	wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8);
-	/*
 	 * scale global setpoint to wb's:
 	 *	wb_setpoint = setpoint * wb_thresh / thresh
 	 */
@@ -1478,17 +1448,10 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	 * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
 	 * Hence, to calculate "step" properly, we have to use wb_dirty as
 	 * "dirty" and wb_setpoint as "setpoint".
-	 *
-	 * We rampup dirty_ratelimit forcibly if wb_dirty is low because
-	 * it's possible that wb_thresh is close to zero due to inactivity
-	 * of backing device.
 	 */
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		dirty = dtc->wb_dirty;
-		if (dtc->wb_dirty < 8)
-			setpoint = dtc->wb_dirty + 1;
-		else
-			setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
+		setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
 	}
 
 	if (dirty < setpoint) {
@@ -1977,11 +1940,7 @@ free_running:
 		 */
 		if (pause < min_pause) {
 			trace_balance_dirty_pages(wb,
-						  sdtc->thresh,
-						  sdtc->bg_thresh,
-						  sdtc->dirty,
-						  sdtc->wb_thresh,
-						  sdtc->wb_dirty,
+						  sdtc,
 						  dirty_ratelimit,
 						  task_ratelimit,
 						  pages_dirtied,
@@ -2006,11 +1965,7 @@ free_running:
 
 pause:
 		trace_balance_dirty_pages(wb,
-					  sdtc->thresh,
-					  sdtc->bg_thresh,
-					  sdtc->dirty,
-					  sdtc->wb_thresh,
-					  sdtc->wb_dirty,
+					  sdtc,
 					  dirty_ratelimit,
 					  task_ratelimit,
 					  pages_dirtied,
@@ -2248,7 +2203,7 @@ static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int
 void laptop_mode_timer_fn(struct timer_list *t)
 {
 	struct backing_dev_info *backing_dev_info =
-		from_timer(backing_dev_info, t, laptop_mode_wb_timer);
+		timer_container_of(backing_dev_info, t, laptop_mode_wb_timer);
 
 	wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER);
 }
@@ -2275,7 +2230,7 @@ void laptop_sync_completion(void)
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
-		del_timer(&bdi->laptop_mode_wb_timer);
+		timer_delete(&bdi->laptop_mode_wb_timer);
 
 	rcu_read_unlock();
 }
@@ -2313,7 +2268,7 @@ static int page_writeback_cpu_online(unsigned int cpu)
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 
-static struct ctl_table vm_page_writeback_sysctls[] = {
+static const struct ctl_table vm_page_writeback_sysctls[] = {
 	{
 		.procname   = "dirty_background_ratio",
 		.data       = &dirty_background_ratio,
@@ -2610,11 +2565,11 @@ struct folio *writeback_iter(struct address_space *mapping,
 	if (!folio) {
 		/*
 		 * To avoid deadlocks between range_cyclic writeback and callers
-		 * that hold pages in PageWriteback to aggregate I/O until
+		 * that hold folios in writeback to aggregate I/O until
 		 * the writeback iteration finishes, we do not loop back to the
-		 * start of the file.  Doing so causes a page lock/page
+		 * start of the file.  Doing so causes a folio lock/folio
 		 * writeback access order inversion - we should only ever lock
-		 * multiple pages in ascending page->index order, and looping
+		 * multiple folios in ascending folio->index order, and looping
 		 * back to the start of the file violates that rule and causes
 		 * deadlocks.
 		 */
@@ -2667,27 +2622,6 @@ int write_cache_pages(struct address_space *mapping,
 }
 EXPORT_SYMBOL(write_cache_pages);
 
-static int writeback_use_writepage(struct address_space *mapping,
-		struct writeback_control *wbc)
-{
-	struct folio *folio = NULL;
-	struct blk_plug plug;
-	int err;
-
-	blk_start_plug(&plug);
-	while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
-		err = mapping->a_ops->writepage(&folio->page, wbc);
-		if (err == AOP_WRITEPAGE_ACTIVATE) {
-			folio_unlock(folio);
-			err = 0;
-		}
-		mapping_set_error(mapping, err);
-	}
-	blk_finish_plug(&plug);
-
-	return err;
-}
-
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	int ret;
@@ -2698,14 +2632,11 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	wb = inode_to_wb_wbc(mapping->host, wbc);
 	wb_bandwidth_estimate_start(wb);
 	while (1) {
-		if (mapping->a_ops->writepages) {
+		if (mapping->a_ops->writepages)
 			ret = mapping->a_ops->writepages(mapping, wbc);
-		} else if (mapping->a_ops->writepage) {
-			ret = writeback_use_writepage(mapping, wbc);
-		} else {
+		else
 			/* deal with chardevs and other special files */
 			ret = 0;
-		}
 		if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL)
 			break;
 
@@ -3124,6 +3055,7 @@ void __folio_start_writeback(struct folio *folio, bool keep_write)
 	int access_ret;
 
 	VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
 	if (mapping && mapping_use_writeback_tags(mapping)) {
 		XA_STATE(xas, &mapping->i_pages, folio_index(folio));