[RFC PATCH v1 4/7] Revert "memcg/hugetlb: remove memcg hugetlb try-commit-cancel protocol"

[Ackerley Tng]

This reverts commit 1d8f136a421f26747e58c01281cba5bffae8d289.

Restore try-commit-cancel protocol for memory charging for HugeTLB, to be
used in later patches.

Signed-off-by: Ackerley Tng <ackerleytng@xxxxxxxxxx>
---
 include/linux/memcontrol.h | 22 +++++++++++++
 mm/memcontrol.c            | 65 ++++++++++++++++++++++++++++++++++++--
 2 files changed, 84 insertions(+), 3 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f29d4969c0c36..59eab4caa01fa 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -639,6 +639,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
 		page_counter_read(&memcg->memory);
 }
 
+void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg);
+
 int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp);
 
 /**
@@ -663,6 +665,9 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
 	return __mem_cgroup_charge(folio, mm, gfp);
 }
 
+int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
+		long nr_pages);
+
 int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp);
 
 int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
@@ -691,6 +696,7 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 	__mem_cgroup_uncharge_folios(folios);
 }
 
+void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages);
 void mem_cgroup_replace_folio(struct folio *old, struct folio *new);
 void mem_cgroup_migrate(struct folio *old, struct folio *new);
 
@@ -1135,12 +1141,23 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
 	return false;
 }
 
+static inline void mem_cgroup_commit_charge(struct folio *folio,
+		struct mem_cgroup *memcg)
+{
+}
+
 static inline int mem_cgroup_charge(struct folio *folio,
 		struct mm_struct *mm, gfp_t gfp)
 {
 	return 0;
 }
 
+static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg,
+		gfp_t gfp, long nr_pages)
+{
+	return 0;
+}
+
 static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp)
 {
         return 0;
@@ -1160,6 +1177,11 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 {
 }
 
+static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
+		unsigned int nr_pages)
+{
+}
+
 static inline void mem_cgroup_replace_folio(struct folio *old,
 		struct folio *new)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36ab9897b61b2..70d762ba465b1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2561,6 +2561,21 @@ static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	return try_charge_memcg(memcg, gfp_mask, nr_pages);
 }
 
+/**
+ * mem_cgroup_cancel_charge() - cancel an uncommitted try_charge() call.
+ * @memcg: memcg previously charged.
+ * @nr_pages: number of pages previously charged.
+ */
+void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
+{
+	if (mem_cgroup_is_root(memcg))
+		return;
+
+	page_counter_uncharge(&memcg->memory, nr_pages);
+	if (do_memsw_account())
+		page_counter_uncharge(&memcg->memsw, nr_pages);
+}
+
 static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 {
 	VM_BUG_ON_FOLIO(folio_memcg_charged(folio), folio);
@@ -2574,6 +2589,18 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 	folio->memcg_data = (unsigned long)memcg;
 }
 
+/**
+ * mem_cgroup_commit_charge - commit a previously successful try_charge().
+ * @folio: folio to commit the charge to.
+ * @memcg: memcg previously charged.
+ */
+void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
+{
+	css_get(&memcg->css);
+	commit_charge(folio, memcg);
+	memcg1_commit_charge(folio, memcg);
+}
+
 #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
 static inline void account_slab_nmi_safe(struct mem_cgroup *memcg,
 					 struct pglist_data *pgdat,
@@ -4777,9 +4804,7 @@ static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
 	if (ret)
 		goto out;
 
-	css_get(&memcg->css);
-	commit_charge(folio, memcg);
-	memcg1_commit_charge(folio, memcg);
+	mem_cgroup_commit_charge(folio, memcg);
 out:
 	return ret;
 }
@@ -4796,6 +4821,40 @@ int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
 	return ret;
 }
 
+/**
+ * mem_cgroup_hugetlb_try_charge - try to charge the memcg for a hugetlb folio
+ * @memcg: memcg to charge.
+ * @gfp: reclaim mode.
+ * @nr_pages: number of pages to charge.
+ *
+ * This function is called when allocating a huge page folio to determine if
+ * the memcg has the capacity for it. It does not commit the charge yet,
+ * as the hugetlb folio itself has not been obtained from the hugetlb pool.
+ *
+ * Once we have obtained the hugetlb folio, we can call
+ * mem_cgroup_commit_charge() to commit the charge. If we fail to obtain the
+ * folio, we should instead call mem_cgroup_cancel_charge() to undo the effect
+ * of try_charge().
+ *
+ * Returns 0 on success. Otherwise, an error code is returned.
+ */
+int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
+			long nr_pages)
+{
+	/*
+	 * If hugetlb memcg charging is not enabled, do not fail hugetlb allocation,
+	 * but do not attempt to commit charge later (or cancel on error) either.
+	 */
+	if (mem_cgroup_disabled() || !memcg ||
+		!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !memcg_accounts_hugetlb())
+		return -EOPNOTSUPP;
+
+	if (try_charge(memcg, gfp, nr_pages))
+		return -ENOMEM;
+
+	return 0;
+}
+
 /**
  * mem_cgroup_charge_hugetlb - charge the memcg for a hugetlb folio
  * @folio: folio being charged
-- 
2.53.0.310.g728cabbaf7-goog