mm: memcontrol: make lruvec lock safe when LRU pages are reparented

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 <[email protected]>

Link: https://lore.kernel.org/all/[email protected]/

Orabug: 37405594

 Conflicts:
	mm/compaction.c
	mm/memcontrol.c
	(Due to the presence of following commits in UEK-8:
	 i. 'commit 56ae0bb mm: compaction: convert to use a folio in
	     isolate_migratepages_block()'
	 ii. 'commit 590ccea mm: compaction: update pageblock skip when
	      first migration candidate is not at the start'

Signed-off-by: Imran Khan <[email protected]>
Reviewed-by: Kamalesh Babulal <[email protected]>

Author: Muchun Song

include/linux/memcontrol.h

@@ -781,7 +781,9 @@ 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)
 {
@@ -804,15 +806,6 @@ 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;
@@ -1257,11 +1250,6 @@ 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;

mm/compaction.c

@@ -550,6 +550,25 @@ 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
@@ -1231,10 +1250,9 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			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, folio);
 
 			/*
 			 * Try get exclusive access under lock. If marked for

mm/memcontrol.c

@@ -1175,23 +1175,6 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 	}
 }
 
-#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(!mem_cgroup_is_root(lruvec_memcg(lruvec)), 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.
@@ -1206,10 +1189,18 @@ 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;
 }
@@ -1229,10 +1220,18 @@ 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;
 }
@@ -1254,10 +1253,18 @@ 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;
 }

mm/swap.c

@@ -322,6 +322,11 @@ void lru_note_cost(struct lruvec *lruvec, bool file,
 
 void lru_note_cost_refault(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), 0);
 }