[PATCH] mlock: fix mlock count can not decrease in race condition

[Yisheng Xie]

Kefeng reported that when run the follow test the mlock count in meminfo
cannot be decreased:
 [1] testcase
 linux:~ # cat test_mlockal
 grep Mlocked /proc/meminfo
  for j in `seq 0 10`
  do
 	for i in `seq 4 15`
 	do
 		./p_mlockall >> log &
 	done
 	sleep 0.2
 done
 sleep 5 # wait some time to let mlock decrease
 grep Mlocked /proc/meminfo

 linux:~ # cat p_mlockall.c
 #include <sys/mman.h>
 #include <stdlib.h>
 #include <stdio.h>

 #define SPACE_LEN	4096

 int main(int argc, char ** argv)
 {
 	int ret;
 	void *adr = malloc(SPACE_LEN);
 	if (!adr)
 		return -1;

 	ret = mlockall(MCL_CURRENT | MCL_FUTURE);
 	printf("mlcokall ret = %d\n", ret);

 	ret = munlockall();
 	printf("munlcokall ret = %d\n", ret);

 	free(adr);
 	return 0;
 }

When __munlock_pagevec, we ClearPageMlock but isolation_failed in race
condition, and we do not count these page into delta_munlocked, which cause mlock
counter incorrect for we had Clear the PageMlock and cannot count down
the number in the feture.

Fix it by count the number of page whoes PageMlock flag is cleared.

Reported-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Signed-off-by: Yisheng Xie <xieyisheng1@xxxxxxxxxx>
---
 mm/mlock.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/mlock.c b/mm/mlock.c
index c483c5c..71ba5cf 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -284,7 +284,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked;
+	int munlocked = 0;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;

@@ -296,6 +296,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		struct page *page = pvec->pages[i];

 		if (TestClearPageMlocked(page)) {
+			munlocked --;
 			/*
 			 * We already have pin from follow_page_mask()
 			 * so we can spare the get_page() here.
@@ -315,8 +316,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	delta_munlocked = -nr + pagevec_count(&pvec_putback);
-	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
+	if (munlocked)
+		__mod_zone_page_state(zone, NR_MLOCK, munlocked);
 	spin_unlock_irq(zone_lru_lock(zone));

 	/* Now we can release pins of pages that we are not munlocking */
-- 
1.7.12.4





Thanks
On 2017/5/23 22:41, Kefeng Wang wrote:
> Hi All,
> 
> Mlocked in meminfo will be increasing with an small testcase, and never be released in mainline,
> here is a testcase[1] to reproduce the issue, but the centos7.2/7.3 will not increase.
> 
> Is it normal?
> 
> Thanks,
> Kefeng
> 
> 
> 
> 
> [1] testcase
> linux:~ # cat test_mlockal
> grep Mlocked /proc/meminfo
>  for j in `seq 0 10`
>  do
> 	for i in `seq 4 15`
> 	do
> 		./p_mlockall >> log &
> 	done
> 	sleep 0.2
> done
> grep Mlocked /proc/meminfo
> 
> 
> linux:~ # cat p_mlockall.c
> #include <sys/mman.h>
> #include <stdlib.h>
> #include <stdio.h>
> 
> #define SPACE_LEN	4096
> 
> int main(int argc, char ** argv)
> {
> 	int ret;
> 	void *adr = malloc(SPACE_LEN);
> 	if (!adr)
> 		return -1;
> 	
> 	ret = mlockall(MCL_CURRENT | MCL_FUTURE);
> 	printf("mlcokall ret = %d\n", ret);
> 
> 	ret = munlockall();
> 	printf("munlcokall ret = %d\n", ret);
> 
> 	free(adr);
> 	return 0;
> }
> 
> 
> .
>