From 90abb7109644cc1d3c328750c1cf7a5818cac20a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 27 Aug 2017 13:55:12 -0700
Subject: [PATCH] Minor page waitqueue cleanups

References: bnc#971975 VM performance -- page waitqueue
Patch-mainline: v4.13-rc7
Git-commit: 3510ca20ece0150af6b10c77a74ff1b5c198e3e2

Tim Chen and Kan Liang have been battling a customer load that shows
extremely long page wakeup lists.  The cause seems to be constant NUMA
migration of a hot page that is shared across a lot of threads, but the
actual root cause for the exact behavior has not been found.

Tim has a patch that batches the wait list traversal at wakeup time, so
that we at least don't get long uninterruptible cases where we traverse
and wake up thousands of processes and get nasty latency spikes.  That
is likely 4.14 material, but we're still discussing the page waitqueue
specific parts of it.

In the meantime, I've tried to look at making the page wait queues less
expensive, and failing miserably.  If you have thousands of threads
waiting for the same page, it will be painful.  We'll need to try to
figure out the NUMA balancing issue some day, in addition to avoiding
the excessive spinlock hold times.

That said, having tried to rewrite the page wait queues, I can at least
fix up some of the braindamage in the current situation. In particular:

 (a) we don't want to continue walking the page wait list if the bit
     we're waiting for already got set again (which seems to be one of
     the patterns of the bad load).  That makes no progress and just
     causes pointless cache pollution chasing the pointers.

 (b) we don't want to put the non-locking waiters always on the front of
     the queue, and the locking waiters always on the back.  Not only is
     that unfair, it means that we wake up thousands of reading threads
     that will just end up being blocked by the writer later anyway.

Also add a comment about the layout of 'struct wait_page_key' - there is
an external user of it in the cachefiles code that means that it has to
match the layout of 'struct wait_bit_key' in the two first members.  It
so happens to match, because 'struct page *' and 'unsigned long *' end
up having the same values simply because the page flags are the first
member in struct page.

Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christopher Lameter <cl@linux.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 kernel/sched/wait.c |  7 ++++---
 mm/filemap.c        | 11 ++++++-----
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index b8c84c6dee64..58c31978391a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -70,9 +70,10 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
 
 	list_for_each_entry_safe(curr, next, &wq_head->head, entry) {
 		unsigned flags = curr->flags;
-
-		if (curr->func(curr, mode, wake_flags, key) &&
-				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+		int ret = curr->func(curr, mode, wake_flags, key);
+		if (ret < 0)
+			break;
+		if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
 			break;
 	}
 }
diff --git a/mm/filemap.c b/mm/filemap.c
index 742034e56100..1b37ca88ccac 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -791,6 +791,7 @@ void __init pagecache_init(void)
 	page_writeback_init();
 }
 
+/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
 struct wait_page_key {
 	struct page *page;
 	int bit_nr;
@@ -815,8 +816,10 @@ static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void
 
 	if (wait_page->bit_nr != key->bit_nr)
 		return 0;
+
+	/* Stop walking if it's locked */
 	if (test_bit(key->bit_nr, &key->page->flags))
-		return 0;
+		return -1;
 
 	return autoremove_wake_function(wait, mode, sync, key);
 }
@@ -870,6 +873,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 	int ret = 0;
 
 	init_wait(wait);
+	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
 	wait_page.page = page;
 	wait_page.bit_nr = bit_nr;
@@ -878,10 +882,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 		spin_lock_irq(&q->lock);
 
 		if (likely(list_empty(&wait->entry))) {
-			if (lock)
-				__add_wait_queue_entry_tail_exclusive(q, wait);
-			else
-				__add_wait_queue(q, wait);
+			__add_wait_queue_entry_tail(q, wait);
 			SetPageWaiters(page);
 		}