From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Qian Cai <cai@lca.pw>, Andrew Morton <akpm@linux-foundation.org>,
Marco Elver <elver@google.com>,
Matthew Wilcox <willy@infradead.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Sasha Levin <sashal@kernel.org>,
linux-mm@kvack.org
Subject: [PATCH AUTOSEL 4.19 139/206] mm/vmscan.c: fix data races using kswapd_classzone_idx
Date: Thu, 17 Sep 2020 22:06:55 -0400 [thread overview]
Message-ID: <20200918020802.2065198-139-sashal@kernel.org> (raw)
In-Reply-To: <20200918020802.2065198-1-sashal@kernel.org>
From: Qian Cai <cai@lca.pw>
[ Upstream commit 5644e1fbbfe15ad06785502bbfe5751223e5841d ]
pgdat->kswapd_classzone_idx could be accessed concurrently in
wakeup_kswapd(). Plain writes and reads without any lock protection
result in data races. Fix them by adding a pair of READ|WRITE_ONCE() as
well as saving a branch (compilers might well optimize the original code
in an unintentional way anyway). While at it, also take care of
pgdat->kswapd_order and non-kswapd threads in allow_direct_reclaim(). The
data races were reported by KCSAN,
BUG: KCSAN: data-race in wakeup_kswapd / wakeup_kswapd
write to 0xffff9f427ffff2dc of 4 bytes by task 7454 on cpu 13:
wakeup_kswapd+0xf1/0x400
wakeup_kswapd at mm/vmscan.c:3967
wake_all_kswapds+0x59/0xc0
wake_all_kswapds at mm/page_alloc.c:4241
__alloc_pages_slowpath+0xdcc/0x1290
__alloc_pages_slowpath at mm/page_alloc.c:4512
__alloc_pages_nodemask+0x3bb/0x450
alloc_pages_vma+0x8a/0x2c0
do_anonymous_page+0x16e/0x6f0
__handle_mm_fault+0xcd5/0xd40
handle_mm_fault+0xfc/0x2f0
do_page_fault+0x263/0x6f9
page_fault+0x34/0x40
1 lock held by mtest01/7454:
#0: ffff9f425afe8808 (&mm->mmap_sem#2){++++}, at:
do_page_fault+0x143/0x6f9
do_user_addr_fault at arch/x86/mm/fault.c:1405
(inlined by) do_page_fault at arch/x86/mm/fault.c:1539
irq event stamp: 6944085
count_memcg_event_mm+0x1a6/0x270
count_memcg_event_mm+0x119/0x270
__do_softirq+0x34c/0x57c
irq_exit+0xa2/0xc0
read to 0xffff9f427ffff2dc of 4 bytes by task 7472 on cpu 38:
wakeup_kswapd+0xc8/0x400
wake_all_kswapds+0x59/0xc0
__alloc_pages_slowpath+0xdcc/0x1290
__alloc_pages_nodemask+0x3bb/0x450
alloc_pages_vma+0x8a/0x2c0
do_anonymous_page+0x16e/0x6f0
__handle_mm_fault+0xcd5/0xd40
handle_mm_fault+0xfc/0x2f0
do_page_fault+0x263/0x6f9
page_fault+0x34/0x40
1 lock held by mtest01/7472:
#0: ffff9f425a9ac148 (&mm->mmap_sem#2){++++}, at:
do_page_fault+0x143/0x6f9
irq event stamp: 6793561
count_memcg_event_mm+0x1a6/0x270
count_memcg_event_mm+0x119/0x270
__do_softirq+0x34c/0x57c
irq_exit+0xa2/0xc0
BUG: KCSAN: data-race in kswapd / wakeup_kswapd
write to 0xffff90973ffff2dc of 4 bytes by task 820 on cpu 6:
kswapd+0x27c/0x8d0
kthread+0x1e0/0x200
ret_from_fork+0x27/0x50
read to 0xffff90973ffff2dc of 4 bytes by task 6299 on cpu 0:
wakeup_kswapd+0xf3/0x450
wake_all_kswapds+0x59/0xc0
__alloc_pages_slowpath+0xdcc/0x1290
__alloc_pages_nodemask+0x3bb/0x450
alloc_pages_vma+0x8a/0x2c0
do_anonymous_page+0x170/0x700
__handle_mm_fault+0xc9f/0xd00
handle_mm_fault+0xfc/0x2f0
do_page_fault+0x263/0x6f9
page_fault+0x34/0x40
Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Marco Elver <elver@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Link: http://lkml.kernel.org/r/1582749472-5171-1-git-send-email-cai@lca.pw
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
mm/vmscan.c | 45 ++++++++++++++++++++++++++-------------------
1 file changed, 26 insertions(+), 19 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bc2ecd43251ad..da09b741d08a0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3101,8 +3101,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
/* kswapd must be awake if processes are being throttled */
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
- pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
- (enum zone_type)ZONE_NORMAL);
+ if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
+ WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+
wake_up_interruptible(&pgdat->kswapd_wait);
}
@@ -3618,9 +3619,9 @@ out:
static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
enum zone_type prev_classzone_idx)
{
- if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
- return prev_classzone_idx;
- return pgdat->kswapd_classzone_idx;
+ enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+ return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3664,8 +3665,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
* the previous request that slept prematurely.
*/
if (remaining) {
- pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
- pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+ WRITE_ONCE(pgdat->kswapd_classzone_idx,
+ kswapd_classzone_idx(pgdat, classzone_idx));
+
+ if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
+ WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
}
finish_wait(&pgdat->kswapd_wait, &wait);
@@ -3747,12 +3751,12 @@ static int kswapd(void *p)
tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
set_freezable();
- pgdat->kswapd_order = 0;
- pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+ WRITE_ONCE(pgdat->kswapd_order, 0);
+ WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
for ( ; ; ) {
bool ret;
- alloc_order = reclaim_order = pgdat->kswapd_order;
+ alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
kswapd_try_sleep:
@@ -3760,10 +3764,10 @@ kswapd_try_sleep:
classzone_idx);
/* Read the new order and classzone_idx */
- alloc_order = reclaim_order = pgdat->kswapd_order;
+ alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
- pgdat->kswapd_order = 0;
- pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+ WRITE_ONCE(pgdat->kswapd_order, 0);
+ WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
ret = try_to_freeze();
if (kthread_should_stop())
@@ -3808,20 +3812,23 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
enum zone_type classzone_idx)
{
pg_data_t *pgdat;
+ enum zone_type curr_idx;
if (!managed_zone(zone))
return;
if (!cpuset_zone_allowed(zone, gfp_flags))
return;
+
pgdat = zone->zone_pgdat;
+ curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+ if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
+ WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+
+ if (READ_ONCE(pgdat->kswapd_order) < order)
+ WRITE_ONCE(pgdat->kswapd_order, order);
- if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
- pgdat->kswapd_classzone_idx = classzone_idx;
- else
- pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
- classzone_idx);
- pgdat->kswapd_order = max(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
--
2.25.1
next prev parent reply other threads:[~2020-09-18 2:10 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20200918020802.2065198-1-sashal@kernel.org>
2020-09-18 2:04 ` [PATCH AUTOSEL 4.19 006/206] mm: fix double page fault on arm64 if PTE_AF is cleared Sasha Levin
2020-09-18 2:05 ` [PATCH AUTOSEL 4.19 066/206] mm/swapfile.c: swap_next should increase position index Sasha Levin
2020-09-18 2:05 ` [PATCH AUTOSEL 4.19 067/206] mm: pagewalk: fix termination condition in walk_pte_range() Sasha Levin
2020-09-18 2:06 ` [PATCH AUTOSEL 4.19 099/206] mm: avoid data corruption on CoW fault into PFN-mapped VMA Sasha Levin
2020-09-18 2:06 ` [PATCH AUTOSEL 4.19 137/206] mm/kmemleak.c: use address-of operator on section symbols Sasha Levin
2020-09-18 2:06 ` [PATCH AUTOSEL 4.19 138/206] mm/filemap.c: clear page error before actual read Sasha Levin
2020-09-18 2:06 ` Sasha Levin [this message]
2020-09-18 2:06 ` [PATCH AUTOSEL 4.19 141/206] mm/mmap.c: initialize align_offset explicitly for vm_unmapped_area Sasha Levin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200918020802.2065198-139-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=cai@lca.pw \
--cc=elver@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=stable@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox