[PATCH v6 2/4] mm: distinguish large folio swap allocation failures

[Xueyuan Chen]

folio_alloc_swap() reports most failures with generic negative error
codes. Reclaim callers consequently cannot tell whether splitting a large
folio could make progress, or whether no swap space is available for even
a single page.

Classify failures using both the global free swap count and the remaining
capacity in the folio's memcg swap hierarchy. Return -ENOSPC when global
swap space is exhausted, -ENOMEM when splitting cannot overcome the
failure, and -E2BIG for a large folio when allocating or charging a
smaller folio might still succeed.

Use this classification for all folio_alloc_swap() failure paths,
including capability rejection, swap slot allocation failure, and memcg
swap charge failure. Callers are updated separately to split large folios
only on -E2BIG.

Suggested-by: Kairui Song <ryncsn@xxxxxxxxx>
Suggested-by: Barry Song <baohua@xxxxxxxxxx>
Suggested-by: Youngjun Park <youngjun.park@xxxxxxx>
Signed-off-by: Xueyuan Chen <xueyuan.chen21@xxxxxxxxx>
Acked-by: David Hildenbrand (Arm) <david@xxxxxxxxxx>
---
 include/linux/swap.h |  6 ++++++
 mm/memcontrol.c      | 23 +++++++++++++++++++++++
 mm/swapfile.c        | 26 +++++++++++++++++++-------
 3 files changed, 48 insertions(+), 7 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0544b2ec4c56..b23108d992aa 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -525,6 +525,7 @@ static inline void mem_cgroup_uncharge_swap(unsigned short id, unsigned int nr_p
 	__mem_cgroup_uncharge_swap(id, nr_pages);
 }
 
+long mem_cgroup_get_folio_swap_margin(struct folio *folio);
 extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
 extern bool mem_cgroup_swap_full(struct folio *folio);
 #else
@@ -538,6 +539,11 @@ static inline void mem_cgroup_uncharge_swap(unsigned short id,
 {
 }
 
+static inline long mem_cgroup_get_folio_swap_margin(struct folio *folio)
+{
+	return PAGE_COUNTER_MAX;
+}
+
 static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
 {
 	return get_nr_swap_pages();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 109c08be91cf..4b42f3fc6075 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5676,6 +5676,29 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
 	return nr_swap_pages;
 }
 
+/**
+ * mem_cgroup_get_folio_swap_margin - get a folio's memcg swap margin
+ * @folio: folio whose memcg margin is queried
+ *
+ * Return: Remaining chargeable pages in the folio's memcg hierarchy.
+ */
+long mem_cgroup_get_folio_swap_margin(struct folio *folio)
+{
+	struct mem_cgroup *memcg;
+	long margin;
+
+	if (mem_cgroup_disabled() || do_memsw_account() ||
+	    !folio_memcg_charged(folio))
+		return PAGE_COUNTER_MAX;
+
+	rcu_read_lock();
+	memcg = folio_memcg(folio);
+	margin = page_counter_margin(&memcg->swap);
+	rcu_read_unlock();
+
+	return margin;
+}
+
 bool mem_cgroup_swap_full(struct folio *folio)
 {
 	struct mem_cgroup *memcg;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 70b90fa9c2a0..651682b1fe63 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1735,7 +1735,9 @@ static int swap_dup_entries_cluster(struct swap_info_struct *si,
  * swap cache.
  *
  * Context: Caller needs to hold the folio lock.
- * Return: Whether the folio was added to the swap cache.
+ * Return: %0 on success, %-E2BIG if splitting the folio might allow swapout,
+ * %-ENOSPC if no global swap space is available, or %-ENOMEM if splitting
+ * would not help.
  */
 int folio_alloc_swap(struct folio *folio)
 {
@@ -1747,11 +1749,11 @@ int folio_alloc_swap(struct folio *folio)
 
 	if (order) {
 		/*
-		 * Reject large allocation when THP_SWAP is disabled,
-		 * the caller should split the folio and try again.
+		 * Reject large allocation when THP_SWAP is disabled. Check below
+		 * whether splitting and retrying can make progress.
 		 */
 		if (!IS_ENABLED(CONFIG_THP_SWAP))
-			return -EAGAIN;
+			goto failed;
 
 		/*
 		 * Allocation size should never exceed cluster size
@@ -1759,7 +1761,7 @@ int folio_alloc_swap(struct folio *folio)
 		 */
 		if (size > SWAPFILE_CLUSTER) {
 			VM_WARN_ON_ONCE(1);
-			return -EINVAL;
+			goto failed;
 		}
 	}
 
@@ -1775,13 +1777,23 @@ int folio_alloc_swap(struct folio *folio)
 	}
 
 	/* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */
-	if (unlikely(mem_cgroup_try_charge_swap(folio)))
+	if (unlikely(mem_cgroup_try_charge_swap(folio))) {
 		swap_cache_del_folio(folio);
+		goto failed;
+	}
 
 	if (unlikely(!folio_test_swapcache(folio)))
-		return -ENOMEM;
+		goto failed;
 
 	return 0;
+
+failed:
+	if (get_nr_swap_pages() <= 0)
+		return -ENOSPC;
+	if (mem_cgroup_get_folio_swap_margin(folio) <= 0)
+		return -ENOMEM;
+
+	return order ? -E2BIG : -ENOMEM;
 }
 
 /**
-- 
2.47.3