| 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: <20211120201230.920082-1-shakeelb@google.com>
Date: Sat, 20 Nov 2021 12:12:30 -0800
From: Shakeel Butt <shakeelb@...gle.com>
To: David Hildenbrand <david@...hat.com>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
Yang Shi <shy828301@...il.com>, Zi Yan <ziy@...dia.com>,
Matthew Wilcox <willy@...radead.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, Shakeel Butt <shakeelb@...gle.com>
Subject: [PATCH] mm: split thp synchronously on MADV_DONTNEED
Many applications do sophisticated management of their heap memory for
better performance but with low cost. We have a bunch of such
applications running on our production and examples include caching and
data storage services. These applications keep their hot data on the
THPs for better performance and release the cold data through
MADV_DONTNEED to keep the memory cost low.
The kernel defers the split and release of THPs until there is memory
pressure. This causes complicates the memory management of these
sophisticated applications which then needs to look into low level
kernel handling of THPs to better gauge their headroom for expansion. In
addition these applications are very latency sensitive and would prefer
to not face memory reclaim due to non-deterministic nature of reclaim.
This patch let such applications not worry about the low level handling
of THPs in the kernel and splits the THPs synchronously on
MADV_DONTNEED.
Signed-off-by: Shakeel Butt <shakeelb@...gle.com>
---
include/linux/mmzone.h | 5 ++++
include/linux/sched.h | 4 ++++
include/linux/sched/mm.h | 11 +++++++++
kernel/fork.c | 3 +++
mm/huge_memory.c | 50 ++++++++++++++++++++++++++++++++++++++++
mm/madvise.c | 8 +++++++
6 files changed, 81 insertions(+)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 58e744b78c2c..7fa0035128b9 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -795,6 +795,11 @@ struct deferred_split {
struct list_head split_queue;
unsigned long split_queue_len;
};
+void split_local_deferred_list(struct list_head *defer_list);
+#else
+static inline void split_local_deferred_list(struct list_head *defer_list)
+{
+}
#endif
/*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9d27fd0ce5df..a984bb6509d9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1412,6 +1412,10 @@ struct task_struct {
struct mem_cgroup *active_memcg;
#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ struct list_head *deferred_split_list;
+#endif
+
#ifdef CONFIG_BLK_CGROUP
struct request_queue *throttle_queue;
#endif
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index fdf742e15e27..9b438c7e811e 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -374,6 +374,17 @@ set_active_memcg(struct mem_cgroup *memcg)
}
#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void set_local_deferred_list(struct list_head *list)
+{
+ current->deferred_split_list = list;
+}
+#else
+static inline void set_local_deferred_list(struct list_head *list)
+{
+}
+#endif
+
#ifdef CONFIG_MEMBARRIER
enum {
MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0),
diff --git a/kernel/fork.c b/kernel/fork.c
index 01af6129aa38..8197b8ed4b7a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1019,6 +1019,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
#ifdef CONFIG_MEMCG
tsk->active_memcg = NULL;
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ tsk->deferred_split_list = NULL;
#endif
return tsk;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e5483347291c..2f73eeecb857 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2754,6 +2754,7 @@ void free_transhuge_page(struct page *page)
void deferred_split_huge_page(struct page *page)
{
struct deferred_split *ds_queue = get_deferred_split_queue(page);
+ struct list_head *list = current->deferred_split_list;
#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg = page_memcg(compound_head(page));
#endif
@@ -2774,7 +2775,14 @@ void deferred_split_huge_page(struct page *page)
if (PageSwapCache(page))
return;
+ if (list && list_empty(page_deferred_list(page))) {
+ /* corresponding put in split_local_deferred_list. */
+ get_page(page);
+ list_add(page_deferred_list(page), list);
+ }
+
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+
if (list_empty(page_deferred_list(page))) {
count_vm_event(THP_DEFERRED_SPLIT_PAGE);
list_add_tail(page_deferred_list(page), &ds_queue->split_queue);
@@ -2801,6 +2809,48 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
return READ_ONCE(ds_queue->split_queue_len);
}
+void split_local_deferred_list(struct list_head *defer_list)
+{
+ struct list_head *pos, *next;
+ struct page *page;
+
+ /* First iteration for split. */
+ list_for_each_safe(pos, next, defer_list) {
+ page = list_entry((void *)pos, struct page, deferred_list);
+ page = compound_head(page);
+
+ if (!trylock_page(page))
+ continue;
+
+ if (split_huge_page(page)) {
+ unlock_page(page);
+ continue;
+ }
+ /* split_huge_page() removes page from list on success */
+ unlock_page(page);
+
+ /* corresponding get in deferred_split_huge_page. */
+ put_page(page);
+ }
+
+ /* Second iteration to putback failed pages. */
+ list_for_each_safe(pos, next, defer_list) {
+ struct deferred_split *ds_queue;
+ unsigned long flags;
+
+ page = list_entry((void *)pos, struct page, deferred_list);
+ page = compound_head(page);
+ ds_queue = get_deferred_split_queue(page);
+
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+ list_move(page_deferred_list(page), &ds_queue->split_queue);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+
+ /* corresponding get in deferred_split_huge_page. */
+ put_page(page);
+ }
+}
+
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
diff --git a/mm/madvise.c b/mm/madvise.c
index 8c927202bbe6..15614115e359 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -762,7 +762,15 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
+ LIST_HEAD(list);
+
+ set_local_deferred_list(&list);
+
zap_page_range(vma, start, end - start);
+
+ set_local_deferred_list(NULL);
+ split_local_deferred_list(&list);
+
return 0;
}
--
2.34.0.rc2.393.gf8c9666880-goog
Powered by blists - more mailing lists