mm: mglru: prevent memory cgroup release in mglru

In the near future, a folio will no longer pin its corresponding memory
cgroup.  To ensure safety, it will only be appropriate to hold the rcu
read lock or acquire a reference to the memory cgroup returned by
folio_memcg(), thereby preventing it from being released.

In the current patch, the rcu read lock is employed to safeguard against
the release of the memory cgroup in mglru.

This serves as a preparatory measure for the reparenting of the LRU pages.

Link: https://lore.kernel.org/9d887662a9d39c425742dd8468e3123316bccfe3.1772711148.git.zhengqi.arch@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Allen Pais <apais@linux.microsoft.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Chen Ridong <chenridong@huawei.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Hamza Mahfooz <hamzamahfooz@linux.microsoft.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Imran Khan <imran.f.khan@oracle.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kamalesh Babulal <kamalesh.babulal@oracle.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Yosry Ahmed <yosry@kernel.org>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 031fbd35ae100d928f692ad67168e96bea2b662c..6f3f9e20ff67549746f27616b91779b2da46d1a1 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3440,8 +3440,10 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
        if (folio_nid(folio) != pgdat->node_id)
                return NULL;
 
+       rcu_read_lock();
        if (folio_memcg(folio) != memcg)
-               return NULL;
+               folio = NULL;
+       rcu_read_unlock();
 
        return folio;
 }
@@ -4211,12 +4213,12 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr)
        unsigned long addr = pvmw->address;
        struct vm_area_struct *vma = pvmw->vma;
        struct folio *folio = pfn_folio(pvmw->pfn);
-       struct mem_cgroup *memcg = folio_memcg(folio);
+       struct mem_cgroup *memcg;
        struct pglist_data *pgdat = folio_pgdat(folio);
-       struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
-       struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
-       DEFINE_MAX_SEQ(lruvec);
-       int gen = lru_gen_from_seq(max_seq);
+       struct lruvec *lruvec;
+       struct lru_gen_mm_state *mm_state;
+       unsigned long max_seq;
+       int gen;
 
        lockdep_assert_held(pvmw->ptl);
        VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
@@ -4251,6 +4253,12 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr)
                }
        }
 
+       memcg = get_mem_cgroup_from_folio(folio);
+       lruvec = mem_cgroup_lruvec(memcg, pgdat);
+       max_seq = READ_ONCE((lruvec)->lrugen.max_seq);
+       gen = lru_gen_from_seq(max_seq);
+       mm_state = get_mm_state(lruvec);
+
        lazy_mmu_mode_enable();
 
        pte -= (addr - start) / PAGE_SIZE;
@@ -4300,6 +4308,8 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw, unsigned int nr)
        if (mm_state && suitable_to_scan(i, young))
                update_bloom_filter(mm_state, max_seq, pvmw->pmd);
 
+       mem_cgroup_put(memcg);
+
        return true;
 }