From 937790699be9c8100e5358625e7dfa8b32bd33f2 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@google.com>
Date: Sat, 30 Nov 2019 17:58:29 -0800
Subject: [PATCH] mm/page_io.c: annotate refault stalls from swap_readpage

If a block device supports rw_page operation, it doesn't submit bios so
the annotation in submit_bio() for refault stall doesn't work.  It
happens with zram in android, especially swap read path which could
consume CPU cycle for decompress.  It is also a problem for zswap which
uses frontswap.

Annotate swap_readpage() to account the synchronous IO overhead to
prevent underreport memory pressure.

[akpm@linux-foundation.org: add comment, per Johannes]
Link: http://lkml.kernel.org/r/20191010152134.38545-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_io.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/mm/page_io.c b/mm/page_io.c
index 60a66a58b9bf..3a198deb8bb1 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -22,6 +22,7 @@
 #include <linux/writeback.h>
 #include <linux/frontswap.h>
 #include <linux/blkdev.h>
+#include <linux/psi.h>
 #include <linux/uio.h>
 #include <linux/sched/task.h>
 #include <asm/pgtable.h>
@@ -354,10 +355,19 @@ int swap_readpage(struct page *page, bool synchronous)
 	struct swap_info_struct *sis = page_swap_info(page);
 	blk_qc_t qc;
 	struct gendisk *disk;
+	unsigned long pflags;
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageUptodate(page), page);
+
+	/*
+	 * Count submission time as memory stall. When the device is congested,
+	 * or the submitting cgroup IO-throttled, submission can be a
+	 * significant part of overall IO time.
+	 */
+	psi_memstall_enter(&pflags);
+
 	if (frontswap_load(page) == 0) {
 		SetPageUptodate(page);
 		unlock_page(page);
@@ -371,7 +381,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		ret = mapping->a_ops->readpage(swap_file, page);
 		if (!ret)
 			count_vm_event(PSWPIN);
-		return ret;
+		goto out;
 	}
 
 	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
@@ -382,7 +392,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		}
 
 		count_vm_event(PSWPIN);
-		return 0;
+		goto out;
 	}
 
 	ret = 0;
@@ -418,6 +428,7 @@ int swap_readpage(struct page *page, bool synchronous)
 	bio_put(bio);
 
 out:
+	psi_memstall_leave(&pflags);
 	return ret;
 }