[PATCH v2] mm: annotate refault stalls from swap_readpage

[Minchan Kim]

If block device supports rw_page operation, it doesn't submit bio
so 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.

Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
---
 mm/page_io.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/mm/page_io.c b/mm/page_io.c
index 24ee600f9131..18f1f8e1d27f 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 +355,20 @@ 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, the submitting cgroup IO-throttled, or backing
+	 * device works synchronously(e.g., zram), 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 +382,7 @@ 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 +393,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		}
 
 		count_vm_event(PSWPIN);
-		return 0;
+		goto out;
 	}
 
 	ret = 0;
@@ -418,6 +429,7 @@ int swap_readpage(struct page *page, bool synchronous)
 	bio_put(bio);
 
 out:
+	psi_memstall_leave(&pflags);
 	return ret;
 }
 
-- 
2.23.0.581.g78d2f28ef7-goog