linux-kernel - [PATCH v4 1/3] mm: call touch_nmi_watchdog() on max order boundaries in deferred init

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20200403140952.17177-2-pasha.tatashin@soleen.com>
Date:   Fri,  3 Apr 2020 10:09:50 -0400
From:   Pavel Tatashin <pasha.tatashin@...een.com>
To:     linux-kernel@...r.kernel.org, akpm@...ux-foundation.org,
        mhocko@...e.com, linux-mm@...ck.org, dan.j.williams@...el.com,
        shile.zhang@...ux.alibaba.com, daniel.m.jordan@...cle.com,
        pasha.tatashin@...een.com, ktkhai@...tuozzo.com, david@...hat.com,
        jmorris@...ei.org, sashal@...nel.org, vbabka@...e.cz
Subject: [PATCH v4 1/3] mm: call touch_nmi_watchdog() on max order boundaries in deferred init

From: Daniel Jordan <daniel.m.jordan@...cle.com>

deferred_init_memmap() disables interrupts the entire time, so it calls
touch_nmi_watchdog() periodically to avoid soft lockup splats.  Soon it
will run with interrupts enabled, at which point cond_resched() should
be used instead.

deferred_grow_zone() makes the same watchdog calls through code shared
with deferred init but will continue to run with interrupts disabled, so
it can't call cond_resched().

Pull the watchdog calls up to these two places to allow the first to be
changed later, independently of the second.  The frequency reduces from
twice per pageblock (init and free) to once per max order block.

Fixes: 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages")
Cc: stable@...r.kernel.org # 4.17+

Signed-off-by: Daniel Jordan <daniel.m.jordan@...cle.com>
Signed-off-by: Pavel Tatashin <pasha.tatashin@...een.com>
Reviewed-by: David Hildenbrand <david@...hat.com>
Acked-by: Michal Hocko <mhocko@...e.com>
Acked-by: Vlastimil Babka <vbabka@...e.cz>
---
 mm/page_alloc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e5f76da8cd4e..d95bfd328107 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1633,7 +1633,6 @@ static void __init deferred_free_pages(unsigned long pfn,
 		} else if (!(pfn & nr_pgmask)) {
 			deferred_free_range(pfn - nr_free, nr_free);
 			nr_free = 1;
-			touch_nmi_watchdog();
 		} else {
 			nr_free++;
 		}
@@ -1663,7 +1662,6 @@ static unsigned long  __init deferred_init_pages(struct zone *zone,
 			continue;
 		} else if (!page || !(pfn & nr_pgmask)) {
 			page = pfn_to_page(pfn);
-			touch_nmi_watchdog();
 		} else {
 			page++;
 		}
@@ -1803,8 +1801,10 @@ static int __init deferred_init_memmap(void *data)
 	 * that we can avoid introducing any issues with the buddy
 	 * allocator.
 	 */
-	while (spfn < epfn)
+	while (spfn < epfn) {
 		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+		touch_nmi_watchdog();
+	}
 zone_empty:
 	pgdat_resize_unlock(pgdat, &flags);
 
@@ -1888,6 +1888,7 @@ deferred_grow_zone(struct zone *zone, unsigned int order)
 		first_deferred_pfn = spfn;
 
 		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+		touch_nmi_watchdog();
 
 		/* We should only stop along section boundaries */
 		if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
-- 
2.17.1