1 files changed, 80 insertions, 33 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e19b87049..8a1c920901 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -415,13 +415,20 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 	else
 		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
-	if (bg_thresh >= thresh)
-		bg_thresh = thresh / 2;
 	tsk = current;
 	if (rt_task(tsk)) {
 		bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
 		thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
 	}
+	/*
+	 * Dirty throttling logic assumes the limits in page units fit into
+	 * 32-bits. This gives 16TB dirty limits max which is hopefully enough.
+	 */
+	if (thresh > UINT_MAX)
+		thresh = UINT_MAX;
+	/* This makes sure bg_thresh is within 32-bits as well */
+	if (bg_thresh >= thresh)
+		bg_thresh = thresh / 2;
 	dtc->thresh = thresh;
 	dtc->bg_thresh = bg_thresh;
 
@@ -471,7 +478,11 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat)
 	if (rt_task(tsk))
 		dirty += dirty / 4;
 
-	return dirty;
+	/*
+	 * Dirty throttling logic assumes the limits in page units fit into
+	 * 32-bits. This gives 16TB dirty limits max which is hopefully enough.
+	 */
+	return min_t(unsigned long, dirty, UINT_MAX);
 }
 
 /**
@@ -508,10 +519,17 @@ static int dirty_background_bytes_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
+	unsigned long old_bytes = dirty_background_bytes;
 
 	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
-	if (ret == 0 && write)
+	if (ret == 0 && write) {
+		if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) >
+								UINT_MAX) {
+			dirty_background_bytes = old_bytes;
+			return -ERANGE;
+		}
 		dirty_background_ratio = 0;
+	}
 	return ret;
 }
 
@@ -537,6 +555,10 @@ static int dirty_bytes_handler(struct ctl_table *table, int write,
 
 	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
+		if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) {
+			vm_dirty_bytes = old_bytes;
+			return -ERANGE;
+		}
 		writeback_set_ratelimit();
 		vm_dirty_ratio = 0;
 	}
@@ -838,13 +860,15 @@ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc,
 }
 
 /**
- * __wb_calc_thresh - @wb's share of dirty throttling threshold
+ * __wb_calc_thresh - @wb's share of dirty threshold
  * @dtc: dirty_throttle_context of interest
+ * @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc
  *
- * Note that balance_dirty_pages() will only seriously take it as a hard limit
- * when sleeping max_pause per page is not enough to keep the dirty pages under
- * control. For example, when the device is completely stalled due to some error
- * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
+ * Note that balance_dirty_pages() will only seriously take dirty throttling
+ * threshold as a hard limit when sleeping max_pause per page is not enough
+ * to keep the dirty pages under control. For example, when the device is
+ * completely stalled due to some error conditions, or when there are 1000
+ * dd tasks writing to a slow 10MB/s USB key.
  * In the other normal situations, it acts more gently by throttling the tasks
  * more (rather than completely block them) when the wb dirty pages go high.
  *
@@ -855,19 +879,20 @@ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc,
  * The wb's share of dirty limit will be adapting to its throughput and
  * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
  *
- * Return: @wb's dirty limit in pages. The term "dirty" in the context of
- * dirty balancing includes all PG_dirty and PG_writeback pages.
+ * Return: @wb's dirty limit in pages. For dirty throttling limit, the term
+ * "dirty" in the context of dirty balancing includes all PG_dirty and
+ * PG_writeback pages.
  */
-static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
+static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc,
+				      unsigned long thresh)
 {
 	struct wb_domain *dom = dtc_dom(dtc);
-	unsigned long thresh = dtc->thresh;
 	u64 wb_thresh;
 	unsigned long numerator, denominator;
 	unsigned long wb_min_ratio, wb_max_ratio;
 
 	/*
-	 * Calculate this BDI's share of the thresh ratio.
+	 * Calculate this wb's share of the thresh ratio.
 	 */
 	fprop_fraction_percpu(&dom->completions, dtc->wb_completions,
 			      &numerator, &denominator);
@@ -887,9 +912,28 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc)
 
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh)
 {
-	struct dirty_throttle_control gdtc = { GDTC_INIT(wb),
-					       .thresh = thresh };
-	return __wb_calc_thresh(&gdtc);
+	struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
+
+	return __wb_calc_thresh(&gdtc, thresh);
+}
+
+unsigned long cgwb_calc_thresh(struct bdi_writeback *wb)
+{
+	struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB };
+	struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) };
+	unsigned long filepages = 0, headroom = 0, writeback = 0;
+
+	gdtc.avail = global_dirtyable_memory();
+	gdtc.dirty = global_node_page_state(NR_FILE_DIRTY) +
+		     global_node_page_state(NR_WRITEBACK);
+
+	mem_cgroup_wb_stats(wb, &filepages, &headroom,
+			    &mdtc.dirty, &writeback);
+	mdtc.dirty += writeback;
+	mdtc_calc_avail(&mdtc, filepages, headroom);
+	domain_dirty_limits(&mdtc);
+
+	return __wb_calc_thresh(&mdtc, mdtc.thresh);
 }
 
 /*
@@ -1636,9 +1680,9 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
 	 *   wb_position_ratio() will let the dirtier task progress
 	 *   at some rate <= (write_bw / 2) for bringing down wb_dirty.
 	 */
-	dtc->wb_thresh = __wb_calc_thresh(dtc);
+	dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh);
 	dtc->wb_bg_thresh = dtc->thresh ?
-		div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
+		div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
@@ -1675,7 +1719,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb,
 	struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ?
 						     &mdtc_stor : NULL;
 	struct dirty_throttle_control *sdtc;
-	unsigned long nr_reclaimable;	/* = file_dirty */
+	unsigned long nr_dirty;
 	long period;
 	long pause;
 	long max_pause;
@@ -1696,9 +1740,9 @@ static int balance_dirty_pages(struct bdi_writeback *wb,
 		unsigned long m_thresh = 0;
 		unsigned long m_bg_thresh = 0;
 
-		nr_reclaimable = global_node_page_state(NR_FILE_DIRTY);
+		nr_dirty = global_node_page_state(NR_FILE_DIRTY);
 		gdtc->avail = global_dirtyable_memory();
-		gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK);
+		gdtc->dirty = nr_dirty + global_node_page_state(NR_WRITEBACK);
 
 		domain_dirty_limits(gdtc);
 
@@ -1749,7 +1793,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb,
 		 * In normal mode, we start background writeout at the lower
 		 * background_thresh, to keep the amount of dirty memory low.
 		 */
-		if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh &&
+		if (!laptop_mode && nr_dirty > gdtc->bg_thresh &&
 		    !writeback_in_progress(wb))
 			wb_start_background_writeback(wb);
 
@@ -2095,7 +2139,7 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 	if (gdtc->dirty > gdtc->bg_thresh)
 		return true;
 
-	thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh);
+	thresh = __wb_calc_thresh(gdtc, gdtc->bg_thresh);
 	if (thresh < 2 * wb_stat_error())
 		reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
 	else
@@ -2115,7 +2159,7 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 		if (mdtc->dirty > mdtc->bg_thresh)
 			return true;
 
-		thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh);
+		thresh = __wb_calc_thresh(mdtc, mdtc->bg_thresh);
 		if (thresh < 2 * wb_stat_error())
 			reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
 		else
@@ -2291,7 +2335,6 @@ static struct ctl_table vm_page_writeback_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
-	{}
 };
 #endif
 
@@ -2546,6 +2589,7 @@ done:
 	folio_batch_release(&wbc->fbatch);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(writeback_iter);
 
 /**
  * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
@@ -2700,17 +2744,20 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb)
 }
 
 /*
- * Mark the folio dirty, and set it dirty in the page cache, and mark
- * the inode dirty.
+ * Mark the folio dirty, and set it dirty in the page cache.
  *
  * If warn is true, then emit a warning if the folio is not uptodate and has
  * not been truncated.
  *
- * The caller must hold folio_memcg_lock().  Most callers have the folio
- * locked.  A few have the folio blocked from truncation through other
- * means (eg zap_vma_pages() has it mapped and is holding the page table
- * lock).  This can also be called from mark_buffer_dirty(), which I
- * cannot prove is always protected against truncate.
+ * The caller must hold folio_memcg_lock().  It is the caller's
+ * responsibility to prevent the folio from being truncated while
+ * this function is in progress, although it may have been truncated
+ * before this function is called.  Most callers have the folio locked.
+ * A few have the folio blocked from truncation through other means (e.g.
+ * zap_vma_pages() has it mapped and is holding the page table lock).
+ * When called from mark_buffer_dirty(), the filesystem should hold a
+ * reference to the buffer_head that is being marked dirty, which causes
+ * try_to_free_buffers() to fail.
  */
 void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
 			     int warn)