writeback: fix incorrect calculation of available memory for memcg domains

For memcg domains, the amount of available memory was calculated as

 min(the amount currently in use + headroom according to memcg,
     total clean memory)

This isn't quite correct as what should be capped by the amount of
clean memory is the headroom, not the sum of memory in use and
headroom.  For example, if a memcg domain has a significant amount of
dirty memory, the above can lead to a value which is lower than the
current amount in use which doesn't make much sense.  In most
circumstances, the above leads to a number which is somewhat but not
drastically lower.

As the amount of memory which can be readily allocated to the memcg
domain is capped by the amount of system-wide clean memory which is
not already assigned to the memcg itself, the number we want is

 the amount currently in use +
 min(headroom according to memcg, clean memory elsewhere in the system)

This patch updates mem_cgroup_wb_stats() to return the number of
filepages and headroom instead of the calculated available pages.
mdtc_cap_avail() is renamed to mdtc_calc_avail() and performs the
above calculation from file, headroom, dirty and globally clean pages.

v2: Dummy mem_cgroup_wb_stats() implementation wasn't updated leading
    to build failure when !CGROUP_WRITEBACK.  Fixed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: c2aa723a6093 ("writeback: implement memcg writeback domain based throttling")
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 18 insertions, 11 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 56c0bffa9f49..2c90357c34ea 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -684,13 +684,19 @@ static unsigned long hard_dirty_limit(struct wb_domain *dom,
 	return max(thresh, dom->dirty_limit);
 }
 
-/* memory available to a memcg domain is capped by system-wide clean memory */
-static void mdtc_cap_avail(struct dirty_throttle_control *mdtc)
+/*
+ * Memory which can be further allocated to a memcg domain is capped by
+ * system-wide clean memory excluding the amount being used in the domain.
+ */
+static void mdtc_calc_avail(struct dirty_throttle_control *mdtc,
+			    unsigned long filepages, unsigned long headroom)
 {
 	struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc);
-	unsigned long clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
+	unsigned long clean = filepages - min(filepages, mdtc->dirty);
+	unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
+	unsigned long other_clean = global_clean - min(global_clean, clean);
 
-	mdtc->avail = min(mdtc->avail, clean);
+	mdtc->avail = filepages + min(headroom, other_clean);
 }
 
 /**
@@ -1564,16 +1570,16 @@ static void balance_dirty_pages(struct address_space *mapping,
 		}
 
 		if (mdtc) {
-			unsigned long writeback;
+			unsigned long filepages, headroom, writeback;
 
 			/*
 			 * If @wb belongs to !root memcg, repeat the same
 			 * basic calculations for the memcg domain.
 			 */
-			mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty,
-					    &writeback);
-			mdtc_cap_avail(mdtc);
+			mem_cgroup_wb_stats(wb, &filepages, &headroom,
+					    &mdtc->dirty, &writeback);
 			mdtc->dirty += writeback;
+			mdtc_calc_avail(mdtc, filepages, headroom);
 
 			domain_dirty_limits(mdtc);
 
@@ -1895,10 +1901,11 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 		return true;
 
 	if (mdtc) {
-		unsigned long writeback;
+		unsigned long filepages, headroom, writeback;
 
-		mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback);
-		mdtc_cap_avail(mdtc);
+		mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty,
+				    &writeback);
+		mdtc_calc_avail(mdtc, filepages, headroom);
 		domain_dirty_limits(mdtc);	/* ditto, ignore writeback */
 
 		if (mdtc->dirty > mdtc->bg_thresh)