| 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
| ||
|
Message-Id: <20220208081902.3550911-11-yuzhao@google.com>
Date: Tue, 8 Feb 2022 01:19:00 -0700
From: Yu Zhao <yuzhao@...gle.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
Johannes Weiner <hannes@...xchg.org>,
Mel Gorman <mgorman@...e.de>, Michal Hocko <mhocko@...nel.org>
Cc: Andi Kleen <ak@...ux.intel.com>,
Aneesh Kumar <aneesh.kumar@...ux.ibm.com>,
Barry Song <21cnbao@...il.com>,
Catalin Marinas <catalin.marinas@....com>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Hillf Danton <hdanton@...a.com>, Jens Axboe <axboe@...nel.dk>,
Jesse Barnes <jsbarnes@...gle.com>,
Jonathan Corbet <corbet@....net>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Matthew Wilcox <willy@...radead.org>,
Michael Larabel <Michael@...haellarabel.com>,
Mike Rapoport <rppt@...nel.org>,
Rik van Riel <riel@...riel.com>,
Vlastimil Babka <vbabka@...e.cz>,
Will Deacon <will@...nel.org>,
Ying Huang <ying.huang@...el.com>,
linux-arm-kernel@...ts.infradead.org, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
page-reclaim@...gle.com, x86@...nel.org,
Yu Zhao <yuzhao@...gle.com>, Brian Geffon <bgeffon@...gle.com>,
Jan Alexander Steffens <heftig@...hlinux.org>,
Oleksandr Natalenko <oleksandr@...alenko.name>,
Steven Barrett <steven@...uorix.net>,
Suleiman Souhlal <suleiman@...gle.com>,
Daniel Byrne <djbyrne@....edu>,
Donald Carr <d@...os-reins.com>,
"Holger Hoffstätte"
<holger@...lied-asynchrony.com>,
Konstantin Kharlamov <Hi-Angel@...dex.ru>,
Shuang Zhai <szhai2@...rochester.edu>,
Sofia Trinh <sofia.trinh@....works>
Subject: [PATCH v7 10/12] mm: multigenerational LRU: thrashing prevention
Add /sys/kernel/mm/lru_gen/min_ttl_ms for thrashing prevention, as
requested by many desktop users [1].
When set to value N, it prevents the working set of N milliseconds
from getting evicted. The OOM killer is triggered if this working set
can't be kept in memory. Based on the average human detectable lag
(~100ms), N=1000 usually eliminates intolerable lags due to thrashing.
Larger values like N=3000 make lags less noticeable at the risk of
premature OOM kills.
Compared with the size-based approach, e.g., [2], this time-based
approach has the following advantages:
1) It's easier to configure because it's agnostic to applications and
memory sizes.
2) It's more reliable because it's directly wired to the OOM killer.
[1] https://lore.kernel.org/lkml/Ydza%2FzXKY9ATRoh6@google.com/
[2] https://lore.kernel.org/lkml/20211130201652.2218636d@mail.inbox.lv/
Signed-off-by: Yu Zhao <yuzhao@...gle.com>
Acked-by: Brian Geffon <bgeffon@...gle.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@...hlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@...alenko.name>
Acked-by: Steven Barrett <steven@...uorix.net>
Acked-by: Suleiman Souhlal <suleiman@...gle.com>
Tested-by: Daniel Byrne <djbyrne@....edu>
Tested-by: Donald Carr <d@...os-reins.com>
Tested-by: Holger Hoffstätte <holger@...lied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@...dex.ru>
Tested-by: Shuang Zhai <szhai2@...rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@....works>
---
mm/vmscan.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 60 insertions(+), 4 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 700c35f2a030..4d37d63668b5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4335,7 +4335,8 @@ static long get_nr_evictable(struct lruvec *lruvec, unsigned long max_seq,
return total > 0 ? total : 0;
}
-static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc,
+ unsigned long min_ttl)
{
bool need_aging;
long nr_to_scan;
@@ -4344,14 +4345,22 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
DEFINE_MAX_SEQ(lruvec);
DEFINE_MIN_SEQ(lruvec);
+ if (min_ttl) {
+ int gen = lru_gen_from_seq(min_seq[TYPE_FILE]);
+ unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
+
+ if (time_is_after_jiffies(birth + min_ttl))
+ return false;
+ }
+
mem_cgroup_calculate_protection(NULL, memcg);
if (mem_cgroup_below_min(memcg))
- return;
+ return false;
nr_to_scan = get_nr_evictable(lruvec, max_seq, min_seq, swappiness, &need_aging);
if (!nr_to_scan)
- return;
+ return false;
nr_to_scan >>= sc->priority;
@@ -4360,11 +4369,18 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
if (nr_to_scan && need_aging && (!mem_cgroup_below_low(memcg) || sc->memcg_low_reclaim))
try_to_inc_max_seq(lruvec, max_seq, sc, swappiness, false);
+
+ return true;
}
+/* to protect the working set of the last N jiffies */
+static unsigned long lru_gen_min_ttl __read_mostly;
+
static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
{
struct mem_cgroup *memcg;
+ bool success = false;
+ unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl);
VM_BUG_ON(!current_is_kswapd());
@@ -4390,11 +4406,28 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
do {
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
- age_lruvec(lruvec, sc);
+ if (age_lruvec(lruvec, sc, min_ttl))
+ success = true;
cond_resched();
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+ /*
+ * The main goal is to OOM kill if every generation from all memcgs is
+ * younger than min_ttl. However, another theoretical possibility is all
+ * memcgs are either below min or empty.
+ */
+ if (!success && mutex_trylock(&oom_lock)) {
+ struct oom_control oc = {
+ .gfp_mask = sc->gfp_mask,
+ .order = sc->order,
+ };
+
+ out_of_memory(&oc);
+
+ mutex_unlock(&oom_lock);
+ }
+
current->reclaim_state->mm_walk = NULL;
}
@@ -5107,6 +5140,28 @@ static void lru_gen_change_state(bool enable)
* sysfs interface
******************************************************************************/
+static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
+}
+
+static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t len)
+{
+ unsigned int msecs;
+
+ if (kstrtouint(buf, 0, &msecs))
+ return -EINVAL;
+
+ WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs));
+
+ return len;
+}
+
+static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR(
+ min_ttl_ms, 0644, show_min_ttl, store_min_ttl
+);
+
static ssize_t show_enable(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
{
unsigned int caps = 0;
@@ -5155,6 +5210,7 @@ static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
);
static struct attribute *lru_gen_attrs[] = {
+ &lru_gen_min_ttl_attr.attr,
&lru_gen_enabled_attr.attr,
NULL
};
--
2.35.0.263.gb82422642f-goog
Powered by blists - more mailing lists