mm/vmscan: throttle reclaim and compaction when too may pages are isolated

Page reclaim throttles on congestion if too many parallel reclaim
instances have isolated too many pages.  This makes no sense, excessive
parallelisation has nothing to do with writeback or congestion.

This patch creates an additional workqueue to sleep on when too many
pages are isolated.  The throttled tasks are woken when the number of
isolated pages is reduced or a timeout occurs.  There may be some false
positive wakeups for GFP_NOIO/GFP_NOFS callers but the tasks will
throttle again if necessary.

[shy828301@gmail.com: Wake up from compaction context]
[vbabka@suse.cz: Account number of throttled tasks only for writeback]

Link: https://lkml.kernel.org/r/20211022144651.19914-3-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: "Darrick J . Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 35 insertions, 8 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index bfc93da1c2c7..7359093d8ac0 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -761,6 +761,8 @@ isolate_freepages_range(struct compact_control *cc,
 /* Similar to reclaim, but different enough that they don't share logic */
 static bool too_many_isolated(pg_data_t *pgdat)
 {
+	bool too_many;
+
 	unsigned long active, inactive, isolated;
 
 	inactive = node_page_state(pgdat, NR_INACTIVE_FILE) +
@@ -770,7 +772,11 @@ static bool too_many_isolated(pg_data_t *pgdat)
 	isolated = node_page_state(pgdat, NR_ISOLATED_FILE) +
 			node_page_state(pgdat, NR_ISOLATED_ANON);
 
-	return isolated > (inactive + active) / 2;
+	too_many = isolated > (inactive + active) / 2;
+	if (!too_many)
+		wake_throttle_isolated(pgdat);
+
+	return too_many;
 }
 
 /**
@@ -822,7 +828,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (cc->mode == MIGRATE_ASYNC)
 			return -EAGAIN;
 
-		congestion_wait(BLK_RW_ASYNC, HZ/10);
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10);
 
 		if (fatal_signal_pending(current))
 			return -EINTR;
diff --git a/mm/internal.h b/mm/internal.h
index a59b5626f968..7dfe74f827bf 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -45,6 +45,15 @@ static inline void acct_reclaim_writeback(struct page *page)
 		__acct_reclaim_writeback(pgdat, page, nr_throttled);
 }
 
+static inline void wake_throttle_isolated(pg_data_t *pgdat)
+{
+	wait_queue_head_t *wqh;
+
+	wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED];
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+
 vm_fault_t do_swap_page(struct vm_fault *vmf);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
@@ -121,6 +130,8 @@ extern unsigned long highest_memmap_pfn;
  */
 extern int isolate_lru_page(struct page *page);
 extern void putback_lru_page(struct page *page);
+extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
+								long timeout);
 
 /*
  * in mm/rmap.c:
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 09beeb55546c..7bfd62f81e16 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1006,12 +1006,12 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
-static void
-reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
+void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
 							long timeout)
 {
 	wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
 	long ret;
+	bool acct_writeback = (reason == VMSCAN_THROTTLE_WRITEBACK);
 	DEFINE_WAIT(wait);
 
 	/*
@@ -1023,7 +1023,8 @@ reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
 	    current->flags & (PF_IO_WORKER|PF_KTHREAD))
 		return;
 
-	if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
+	if (acct_writeback &&
+	    atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
 		WRITE_ONCE(pgdat->nr_reclaim_start,
 			node_page_state(pgdat, NR_THROTTLED_WRITTEN));
 	}
@@ -1031,7 +1032,9 @@ reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = schedule_timeout(timeout);
 	finish_wait(wqh, &wait);
-	atomic_dec(&pgdat->nr_writeback_throttled);
+
+	if (acct_writeback)
+		atomic_dec(&pgdat->nr_writeback_throttled);
 
 	trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
 				jiffies_to_usecs(timeout - ret),
@@ -2175,6 +2178,7 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 		struct scan_control *sc)
 {
 	unsigned long inactive, isolated;
+	bool too_many;
 
 	if (current_is_kswapd())
 		return 0;
@@ -2198,7 +2202,13 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 	if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
 		inactive >>= 3;
 
-	return isolated > inactive;
+	too_many = isolated > inactive;
+
+	/* Wake up tasks throttled due to too_many_isolated. */
+	if (!too_many)
+		wake_throttle_isolated(pgdat);
+
+	return too_many;
 }
 
 /*
@@ -2307,8 +2317,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 			return 0;
 
 		/* wait a bit for the reclaimer. */
-		msleep(100);
 		stalled = true;
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10);
 
 		/* We are about to die and free our memory. Return now. */
 		if (fatal_signal_pending(current))