mm: disable LRU pagevec during the migration temporarily

LRU pagevec holds refcount of pages until the pagevec are drained.  It
could prevent migration since the refcount of the page is greater than
the expection in migration logic.  To mitigate the issue, callers of
migrate_pages drains LRU pagevec via migrate_prep or lru_add_drain_all
before migrate_pages call.

However, it's not enough because pages coming into pagevec after the
draining call still could stay at the pagevec so it could keep
preventing page migration.  Since some callers of migrate_pages have
retrial logic with LRU draining, the page would migrate at next trail
but it is still fragile in that it doesn't close the fundamental race
between upcoming LRU pages into pagvec and migration so the migration
failure could cause contiguous memory allocation failure in the end.

To close the race, this patch disables lru caches(i.e, pagevec) during
ongoing migration until migrate is done.

Since it's really hard to reproduce, I measured how many times
migrate_pages retried with force mode(it is about a fallback to a sync
migration) with below debug code.

int migrate_pages(struct list_head *from, new_page_t get_new_page,
			..
			..

  if (rc && reason == MR_CONTIG_RANGE && pass > 2) {
         printk(KERN_ERR, "pfn 0x%lx reason %d", page_to_pfn(page), rc);
         dump_page(page, "fail to migrate");
  }

The test was repeating android apps launching with cma allocation in
background every five seconds.  Total cma allocation count was about 500
during the testing.  With this patch, the dump_page count was reduced
from 400 to 30.

The new interface is also useful for memory hotplug which currently
drains lru pcp caches after each migration failure.  This is rather
suboptimal as it has to disrupt others running during the operation.
With the new interface the operation happens only once.  This is also in
line with pcp allocator cache which are disabled for the offlining as
well.

Link: https://lkml.kernel.org/r/20210319175127.886124-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: John Dias <joaodias@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Oliver Sang <oliver.sang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 70 insertions, 14 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0cdbbfbc5757..729fba144c71 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1611,6 +1611,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 	 * in a way that pages from isolated pageblock are left on pcplists.
 	 */
 	zone_pcp_disable(zone);
+	lru_cache_disable();
 
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn,
@@ -1642,7 +1643,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 			}
 
 			cond_resched();
-			lru_add_drain_all();
 
 			ret = scan_movable_pages(pfn, end_pfn, &pfn);
 			if (!ret) {
@@ -1687,6 +1687,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 	zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages;
 	spin_unlock_irqrestore(&zone->lock, flags);
 
+	lru_cache_enable();
 	zone_pcp_enable(zone);
 
 	/* removal success */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index cd0295567a04..3b95e169e97d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1208,6 +1208,8 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 			break;
 	}
 	mmap_read_unlock(mm);
+
+	migrate_finish();
 	if (err < 0)
 		return err;
 	return busy;
@@ -1371,6 +1373,8 @@ up_out:
 	mmap_write_unlock(mm);
 mpol_out:
 	mpol_put(new);
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+		migrate_finish();
 	return err;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 47df0df8f21a..5b09567dc293 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -66,11 +66,13 @@ void migrate_prep(void)
 {
 	/*
 	 * Clear the LRU lists so pages can be isolated.
-	 * Note that pages may be moved off the LRU after we have
-	 * drained them. Those pages will fail to migrate like other
-	 * pages that may be busy.
 	 */
-	lru_add_drain_all();
+	lru_cache_disable();
+}
+
+void migrate_finish(void)
+{
+	lru_cache_enable();
 }
 
 /* Do the necessary work of migrate_prep but not if it involves other CPUs */
@@ -1838,6 +1840,7 @@ out_flush:
 	if (err >= 0)
 		err = err1;
 out:
+	migrate_finish();
 	return err;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 64d4aae2a78a..2cefb634e0d6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8715,6 +8715,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		if (ret == -ENOMEM)
 			break;
 	}
+
+	migrate_finish();
 	if (ret < 0) {
 		alloc_contig_dump_pages(&cc->migratepages);
 		putback_movable_pages(&cc->migratepages);
diff --git a/mm/swap.c b/mm/swap.c
index 31b844d4ed94..c94f55e7b649 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -235,6 +235,18 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
 	}
 }
 
+/* return true if pagevec needs to drain */
+static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page)
+{
+	bool ret = false;
+
+	if (!pagevec_add(pvec, page) || PageCompound(page) ||
+			lru_cache_disabled())
+		ret = true;
+
+	return ret;
+}
+
 /*
  * Writeback is about to end against a page which has been marked for immediate
  * reclaim.  If it still appears to be reclaimable, move it to the tail of the
@@ -252,7 +264,7 @@ void rotate_reclaimable_page(struct page *page)
 		get_page(page);
 		local_lock_irqsave(&lru_rotate.lock, flags);
 		pvec = this_cpu_ptr(&lru_rotate.pvec);
-		if (!pagevec_add(pvec, page) || PageCompound(page))
+		if (pagevec_add_and_need_flush(pvec, page))
 			pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
 		local_unlock_irqrestore(&lru_rotate.lock, flags);
 	}
@@ -343,7 +355,7 @@ static void activate_page(struct page *page)
 		local_lock(&lru_pvecs.lock);
 		pvec = this_cpu_ptr(&lru_pvecs.activate_page);
 		get_page(page);
-		if (!pagevec_add(pvec, page) || PageCompound(page))
+		if (pagevec_add_and_need_flush(pvec, page))
 			pagevec_lru_move_fn(pvec, __activate_page);
 		local_unlock(&lru_pvecs.lock);
 	}
@@ -458,7 +470,7 @@ void lru_cache_add(struct page *page)
 	get_page(page);
 	local_lock(&lru_pvecs.lock);
 	pvec = this_cpu_ptr(&lru_pvecs.lru_add);
-	if (!pagevec_add(pvec, page) || PageCompound(page))
+	if (pagevec_add_and_need_flush(pvec, page))
 		__pagevec_lru_add(pvec);
 	local_unlock(&lru_pvecs.lock);
 }
@@ -654,7 +666,7 @@ void deactivate_file_page(struct page *page)
 		local_lock(&lru_pvecs.lock);
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file);
 
-		if (!pagevec_add(pvec, page) || PageCompound(page))
+		if (pagevec_add_and_need_flush(pvec, page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn);
 		local_unlock(&lru_pvecs.lock);
 	}
@@ -676,7 +688,7 @@ void deactivate_page(struct page *page)
 		local_lock(&lru_pvecs.lock);
 		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate);
 		get_page(page);
-		if (!pagevec_add(pvec, page) || PageCompound(page))
+		if (pagevec_add_and_need_flush(pvec, page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_fn);
 		local_unlock(&lru_pvecs.lock);
 	}
@@ -698,7 +710,7 @@ void mark_page_lazyfree(struct page *page)
 		local_lock(&lru_pvecs.lock);
 		pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree);
 		get_page(page);
-		if (!pagevec_add(pvec, page) || PageCompound(page))
+		if (pagevec_add_and_need_flush(pvec, page))
 			pagevec_lru_move_fn(pvec, lru_lazyfree_fn);
 		local_unlock(&lru_pvecs.lock);
 	}
@@ -735,7 +747,7 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy)
  * Calling this function with cpu hotplug locks held can actually lead
  * to obscure indirect dependencies via WQ context.
  */
-void lru_add_drain_all(void)
+inline void __lru_add_drain_all(bool force_all_cpus)
 {
 	/*
 	 * lru_drain_gen - Global pages generation number
@@ -780,7 +792,7 @@ void lru_add_drain_all(void)
 	 * (C) Exit the draining operation if a newer generation, from another
 	 * lru_add_drain_all(), was already scheduled for draining. Check (A).
 	 */
-	if (unlikely(this_gen != lru_drain_gen))
+	if (unlikely(this_gen != lru_drain_gen && !force_all_cpus))
 		goto done;
 
 	/*
@@ -810,7 +822,8 @@ void lru_add_drain_all(void)
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
-		if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
+		if (force_all_cpus ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) ||
 		    data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) ||
 		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) ||
@@ -828,6 +841,11 @@ void lru_add_drain_all(void)
 done:
 	mutex_unlock(&lock);
 }
+
+void lru_add_drain_all(void)
+{
+	__lru_add_drain_all(false);
+}
 #else
 void lru_add_drain_all(void)
 {
@@ -835,6 +853,34 @@ void lru_add_drain_all(void)
 }
 #endif /* CONFIG_SMP */
 
+atomic_t lru_disable_count = ATOMIC_INIT(0);
+
+/*
+ * lru_cache_disable() needs to be called before we start compiling
+ * a list of pages to be migrated using isolate_lru_page().
+ * It drains pages on LRU cache and then disable on all cpus until
+ * lru_cache_enable is called.
+ *
+ * Must be paired with a call to lru_cache_enable().
+ */
+void lru_cache_disable(void)
+{
+	atomic_inc(&lru_disable_count);
+#ifdef CONFIG_SMP
+	/*
+	 * lru_add_drain_all in the force mode will schedule draining on
+	 * all online CPUs so any calls of lru_cache_disabled wrapped by
+	 * local_lock or preemption disabled would be ordered by that.
+	 * The atomic operation doesn't need to have stronger ordering
+	 * requirements because that is enforeced by the scheduling
+	 * guarantees.
+	 */
+	__lru_add_drain_all(true);
+#else
+	lru_add_drain();
+#endif
+}
+
 /**
  * release_pages - batched put_page()
  * @pages: array of pages to release