From: Muchun Song <songmuchun@bytedance.com>
To: hannes@cmpxchg.org, mhocko@kernel.org, roman.gushchin@linux.dev,
shakeelb@google.com, akpm@linux-foundation.org
Cc: cgroups@vger.kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, duanxiongchun@bytedance.com,
longman@redhat.com, Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v5 04/11] mm: memcontrol: make lruvec lock safe when LRU pages are reparented
Date: Mon, 30 May 2022 15:49:12 +0800 [thread overview]
Message-ID: <20220530074919.46352-5-songmuchun@bytedance.com> (raw)
In-Reply-To: <20220530074919.46352-1-songmuchun@bytedance.com>
The diagram below shows how to make the folio lruvec lock safe when LRU
pages are reparented.
folio_lruvec_lock(folio)
rcu_read_lock();
retry:
lruvec = folio_lruvec(folio);
// The folio is reparented at this time.
spin_lock(&lruvec->lru_lock);
if (unlikely(lruvec_memcg(lruvec) != folio_memcg(folio)))
// Acquired the wrong lruvec lock and need to retry.
// Because this folio is on the parent memcg lruvec list.
spin_unlock(&lruvec->lru_lock);
goto retry;
// If we reach here, it means that folio_memcg(folio) is stable.
memcg_reparent_objcgs(memcg)
// lruvec belongs to memcg and lruvec_parent belongs to parent memcg.
spin_lock(&lruvec->lru_lock);
spin_lock(&lruvec_parent->lru_lock);
// Move all the pages from the lruvec list to the parent lruvec list.
spin_unlock(&lruvec_parent->lru_lock);
spin_unlock(&lruvec->lru_lock);
After we acquire the lruvec lock, we need to check whether the folio is
reparented. If so, we need to reacquire the new lruvec lock. On the
routine of the LRU pages reparenting, we will also acquire the lruvec
lock (will be implemented in the later patch). So folio_memcg() cannot
be changed when we hold the lruvec lock.
Since lruvec_memcg(lruvec) is always equal to folio_memcg(folio) after
we hold the lruvec lock, lruvec_memcg_debug() check is pointless. So
remove it.
This is a preparation for reparenting the LRU pages.
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
include/linux/memcontrol.h | 18 +++-------------
mm/compaction.c | 27 +++++++++++++++++++----
mm/memcontrol.c | 53 ++++++++++++++++++++++++++--------------------
mm/swap.c | 5 +++++
4 files changed, 61 insertions(+), 42 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 27f3171f42a1..e390aaa46776 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -752,7 +752,9 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
* folio_lruvec - return lruvec for isolating/putting an LRU folio
* @folio: Pointer to the folio.
*
- * This function relies on folio->mem_cgroup being stable.
+ * The lruvec can be changed to its parent lruvec when the page reparented.
+ * The caller need to recheck if it cares about this changes (just like
+ * folio_lruvec_lock() does).
*/
static inline struct lruvec *folio_lruvec(struct folio *folio)
{
@@ -771,15 +773,6 @@ struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flags);
-#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio);
-#else
-static inline
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
-{
-}
-#endif
-
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
return css ? container_of(css, struct mem_cgroup, css) : NULL;
@@ -1240,11 +1233,6 @@ static inline struct lruvec *folio_lruvec(struct folio *folio)
return &pgdat->__lruvec;
}
-static inline
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
-{
-}
-
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
return NULL;
diff --git a/mm/compaction.c b/mm/compaction.c
index 4f155df6b39c..29ff111e5711 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -509,6 +509,25 @@ static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags,
return true;
}
+static struct lruvec *
+compact_folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags,
+ struct compact_control *cc)
+{
+ struct lruvec *lruvec;
+
+ rcu_read_lock();
+retry:
+ lruvec = folio_lruvec(folio);
+ compact_lock_irqsave(&lruvec->lru_lock, flags, cc);
+ if (unlikely(lruvec_memcg(lruvec) != folio_memcg(folio))) {
+ spin_unlock_irqrestore(&lruvec->lru_lock, *flags);
+ goto retry;
+ }
+ rcu_read_unlock();
+
+ return lruvec;
+}
+
/*
* Compaction requires the taking of some coarse locks that are potentially
* very heavily contended. The lock should be periodically unlocked to avoid
@@ -844,6 +863,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
/* Time to isolate some pages for migration */
for (; low_pfn < end_pfn; low_pfn++) {
+ struct folio *folio;
if (skip_on_failure && low_pfn >= next_skip_pfn) {
/*
@@ -1065,18 +1085,17 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
if (!TestClearPageLRU(page))
goto isolate_fail_put;
- lruvec = folio_lruvec(page_folio(page));
+ folio = page_folio(page);
+ lruvec = folio_lruvec(folio);
/* If we already hold the lock, we can skip some rechecking */
if (lruvec != locked) {
if (locked)
lruvec_unlock_irqrestore(locked, flags);
- compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
+ lruvec = compact_folio_lruvec_lock_irqsave(folio, &flags, cc);
locked = lruvec;
- lruvec_memcg_debug(lruvec, page_folio(page));
-
/* Try get exclusive access under lock */
if (!skip_updated) {
skip_updated = true;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 739a1d58ce97..9d98a791353c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1199,23 +1199,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
return ret;
}
-#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
-{
- struct mem_cgroup *memcg;
-
- if (mem_cgroup_disabled())
- return;
-
- memcg = folio_memcg(folio);
-
- if (!memcg)
- VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio);
- else
- VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
-}
-#endif
-
/**
* folio_lruvec_lock - Lock the lruvec for a folio.
* @folio: Pointer to the folio.
@@ -1230,10 +1213,18 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
*/
struct lruvec *folio_lruvec_lock(struct folio *folio)
{
- struct lruvec *lruvec = folio_lruvec(folio);
+ struct lruvec *lruvec;
+ rcu_read_lock();
+retry:
+ lruvec = folio_lruvec(folio);
spin_lock(&lruvec->lru_lock);
- lruvec_memcg_debug(lruvec, folio);
+
+ if (unlikely(lruvec_memcg(lruvec) != folio_memcg(folio))) {
+ spin_unlock(&lruvec->lru_lock);
+ goto retry;
+ }
+ rcu_read_unlock();
return lruvec;
}
@@ -1253,10 +1244,18 @@ struct lruvec *folio_lruvec_lock(struct folio *folio)
*/
struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
- struct lruvec *lruvec = folio_lruvec(folio);
+ struct lruvec *lruvec;
+ rcu_read_lock();
+retry:
+ lruvec = folio_lruvec(folio);
spin_lock_irq(&lruvec->lru_lock);
- lruvec_memcg_debug(lruvec, folio);
+
+ if (unlikely(lruvec_memcg(lruvec) != folio_memcg(folio))) {
+ spin_unlock_irq(&lruvec->lru_lock);
+ goto retry;
+ }
+ rcu_read_unlock();
return lruvec;
}
@@ -1278,10 +1277,18 @@ struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flags)
{
- struct lruvec *lruvec = folio_lruvec(folio);
+ struct lruvec *lruvec;
+ rcu_read_lock();
+retry:
+ lruvec = folio_lruvec(folio);
spin_lock_irqsave(&lruvec->lru_lock, *flags);
- lruvec_memcg_debug(lruvec, folio);
+
+ if (unlikely(lruvec_memcg(lruvec) != folio_memcg(folio))) {
+ spin_unlock_irqrestore(&lruvec->lru_lock, *flags);
+ goto retry;
+ }
+ rcu_read_unlock();
return lruvec;
}
diff --git a/mm/swap.c b/mm/swap.c
index 0a8ee33116c5..6cea469b6ff2 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -303,6 +303,11 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
void lru_note_cost_folio(struct folio *folio)
{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ /*
+ * The rcu read lock is held by the caller, so we do not need to
+ * care about the lruvec returned by folio_lruvec() being released.
+ */
lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
folio_nr_pages(folio));
}
--
2.11.0
next prev parent reply other threads:[~2022-05-30 7:50 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-30 7:49 [PATCH v5 00/11] Use obj_cgroup APIs to charge the LRU pages Muchun Song
2022-05-30 7:49 ` [PATCH v5 01/11] mm: memcontrol: remove dead code and comments Muchun Song
2022-06-10 23:01 ` Roman Gushchin
2022-05-30 7:49 ` [PATCH v5 02/11] mm: rename unlock_page_lruvec{_irq, _irqrestore} to lruvec_unlock{_irq, _irqrestore} Muchun Song
2022-06-10 23:08 ` Roman Gushchin
2022-05-30 7:49 ` [PATCH v5 03/11] mm: memcontrol: prepare objcg API for non-kmem usage Muchun Song
2022-06-01 17:34 ` Michal Koutný
2022-06-01 18:33 ` Roman Gushchin
2022-06-02 10:48 ` Muchun Song
2022-06-02 3:06 ` Muchun Song
2022-06-10 23:13 ` Roman Gushchin
2022-05-30 7:49 ` Muchun Song [this message]
2022-05-30 7:49 ` [PATCH v5 05/11] mm: vmscan: rework move_pages_to_lru() Muchun Song
2022-05-30 7:49 ` [PATCH v5 06/11] mm: thp: make split queue lock safe when LRU pages are reparented Muchun Song
2022-05-30 7:49 ` [PATCH v5 07/11] mm: memcontrol: make all the callers of {folio,page}_memcg() safe Muchun Song
2022-06-19 19:37 ` Roman Gushchin
2022-06-20 6:13 ` Muchun Song
2022-05-30 7:49 ` [PATCH v5 08/11] mm: memcontrol: introduce memcg_reparent_ops Muchun Song
2022-06-19 19:47 ` Roman Gushchin
2022-06-20 7:14 ` Muchun Song
2022-05-30 7:49 ` [PATCH v5 09/11] mm: memcontrol: use obj_cgroup APIs to charge the LRU pages Muchun Song
2022-06-01 17:34 ` Michal Koutný
2022-06-02 4:14 ` Muchun Song
2022-06-19 20:32 ` Roman Gushchin
2022-05-30 7:49 ` [PATCH v5 10/11] mm: lru: add VM_BUG_ON_FOLIO to lru maintenance function Muchun Song
2022-06-19 19:49 ` Roman Gushchin
2022-05-30 7:49 ` [PATCH v5 11/11] mm: lru: use lruvec lock to serialize memcg changes Muchun Song
2022-05-30 21:17 ` [PATCH v5 00/11] Use obj_cgroup APIs to charge the LRU pages Andrew Morton
2022-05-31 2:26 ` Muchun Song
2022-05-31 2:46 ` Roman Gushchin
2022-05-31 2:41 ` Waiman Long
2022-05-31 7:29 ` Muchun Song
2022-06-09 2:43 ` Muchun Song
2022-06-09 2:53 ` Roman Gushchin
2022-06-09 3:09 ` Muchun Song
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=20220530074919.46352-5-songmuchun@bytedance.com \
--to=songmuchun@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=duanxiongchun@bytedance.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=longman@redhat.com \
--cc=mhocko@kernel.org \
--cc=roman.gushchin@linux.dev \
--cc=shakeelb@google.com \
/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;
as well as URLs for NNTP newsgroup(s).