mm: folio_may_be_lru_cached() unless folio_test_large()

commit 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 upstream.

mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as a
large folio is added: so collect_longterm_unpinnable_folios() just wastes
effort when calling lru_add_drain[_all]() on a large folio.

But although there is good reason not to batch up PMD-sized folios, we
might well benefit from batching a small number of low-order mTHPs (though
unclear how that "small number" limitation will be implemented).

So ask if folio_may_be_lru_cached() rather than !folio_test_large(), to
insulate those particular checks from future change.  Name preferred to
"folio_is_batchable" because large folios can well be put on a batch: it's
just the per-CPU LRU caches, drained much later, which need care.

Marked for stable, to counter the increase in lru_add_drain_all()s from
"mm/gup: check ref_count instead of lru before migration".

Link: https://lkml.kernel.org/r/57d2eaf8-3607-f318-e0c5-be02dce61ad0@google.com
Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region")
Signed-off-by: Hugh Dickins <hughd@google.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Keir Fraser <keirf@google.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Li Zhe <lizhe.67@bytedance.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Shivank Garg <shivankg@amd.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Xu <weixugc@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: yangge <yangge1116@126.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/swap.h b/include/linux/swap.h
index bc0e1c275fc0478e55eb326ed8d273300d86deb0..8b56b2bbaa4f07bcaf66950b9f5575584012313e 100644 (file)
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -384,6 +384,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *);
 void mark_page_accessed(struct page *);
 void folio_mark_accessed(struct folio *);
 
+static inline bool folio_may_be_lru_cached(struct folio *folio)
+{
+       /*
+        * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting.
+        * Holding small numbers of low-order mTHP folios in per-CPU LRU cache
+        * will be sensible, but nobody has implemented and tested that yet.
+        */
+       return !folio_test_large(folio);
+}
+
 extern atomic_t lru_disable_count;
 
 static inline bool lru_cache_disabled(void)

diff --git a/mm/gup.c b/mm/gup.c
index f1d0218d770fb7bb4560838f4e063adf0c11fb49..10e46ff0904b05e6f734e42a49edc27bcc7a51d3 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2353,13 +2353,13 @@ static unsigned long collect_longterm_unpinnable_folios(
                        continue;
                }
 
-               if (drained == 0 &&
+               if (drained == 0 && folio_may_be_lru_cached(folio) &&
                                folio_ref_count(folio) !=
                                folio_expected_ref_count(folio) + 1) {
                        lru_add_drain();
                        drained = 1;
                }
-               if (drained == 1 &&
+               if (drained == 1 && folio_may_be_lru_cached(folio) &&
                                folio_ref_count(folio) !=
                                folio_expected_ref_count(folio) + 1) {
                        lru_add_drain_all();

diff --git a/mm/mlock.c b/mm/mlock.c
index 3cb72b579ffd3304f52579e22f61e5c1a8e6b08f..2f454ed6e510414de5bfaac58451e688e6c1c352 100644 (file)
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio)
 
        folio_get(folio);
        if (!folio_batch_add(fbatch, mlock_lru(folio)) ||
-           folio_test_large(folio) || lru_cache_disabled())
+           !folio_may_be_lru_cached(folio) || lru_cache_disabled())
                mlock_folio_batch(fbatch);
        local_unlock(&mlock_fbatch.lock);
 }
@@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio)
 
        folio_get(folio);
        if (!folio_batch_add(fbatch, mlock_new(folio)) ||
-           folio_test_large(folio) || lru_cache_disabled())
+           !folio_may_be_lru_cached(folio) || lru_cache_disabled())
                mlock_folio_batch(fbatch);
        local_unlock(&mlock_fbatch.lock);
 }
@@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio)
         */
        folio_get(folio);
        if (!folio_batch_add(fbatch, folio) ||
-           folio_test_large(folio) || lru_cache_disabled())
+           !folio_may_be_lru_cached(folio) || lru_cache_disabled())
                mlock_folio_batch(fbatch);
        local_unlock(&mlock_fbatch.lock);
 }

diff --git a/mm/swap.c b/mm/swap.c
index 99ec595988d3eb23f18294fc04889178386cb06a..a524736323c8b759fd3cadf004da72b97335ce6b 100644 (file)
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
                local_lock(&cpu_fbatches.lock);
 
        if (!folio_batch_add(this_cpu_ptr(fbatch), folio) ||
-                       folio_test_large(folio) || lru_cache_disabled())
+                       !folio_may_be_lru_cached(folio) || lru_cache_disabled())
                folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
 
        if (disable_irq)