@@ -3706,19 +3706,87 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio)
return ret;
}
-static bool wp_can_reuse_anon_folio(struct folio *folio,
- struct vm_area_struct *vma)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
+ struct vm_area_struct *vma)
{
+ bool exclusive = false;
+
+ /* Let's just free up a large folio if only a single page is mapped. */
+ if (folio_large_mapcount(folio) <= 1)
+ return false;
+
/*
- * We could currently only reuse a subpage of a large folio if no
- * other subpages of the large folios are still mapped. However,
- * let's just consistently not reuse subpages even if we could
- * reuse in that scenario, and give back a large folio a bit
- * sooner.
+ * The assumption for anonymous folios is that each page can only get
+ * mapped once into each MM. The only exception are KSM folios, which
+ * are always small.
+ *
+ * Each taken mapcount must be paired with exactly one taken reference,
+ * whereby the refcount must be incremented before the mapcount when
+ * mapping a page, and the refcount must be decremented after the
+ * mapcount when unmapping a page.
+ *
+ * If all folio references are from mappings, and all mappings are in
+ * the page tables of this MM, then this folio is exclusive to this MM.
*/
- if (folio_test_large(folio))
+ if (folio_test_large_maybe_mapped_shared(folio))
+ return false;
+
+ VM_WARN_ON_ONCE(folio_test_ksm(folio));
+ VM_WARN_ON_ONCE(folio_mapcount(folio) > folio_nr_pages(folio));
+ VM_WARN_ON_ONCE(folio_entire_mapcount(folio));
+
+ if (unlikely(folio_test_swapcache(folio))) {
+ /*
+ * Note: freeing up the swapcache will fail if some PTEs are
+ * still swap entries.
+ */
+ if (!folio_trylock(folio))
+ return false;
+ folio_free_swap(folio);
+ folio_unlock(folio);
+ }
+
+ if (folio_large_mapcount(folio) != folio_ref_count(folio))
return false;
+ /* Stabilize the mapcount vs. refcount and recheck. */
+ folio_lock_large_mapcount(folio);
+ VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio));
+
+ if (folio_test_large_maybe_mapped_shared(folio))
+ goto unlock;
+ if (folio_large_mapcount(folio) != folio_ref_count(folio))
+ goto unlock;
+
+ VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id &&
+ folio_mm_id(folio, 1) != vma->vm_mm->mm_id);
+
+ /*
+ * Do we need the folio lock? Likely not. If there would have been
+ * references from page migration/swapout, we would have detected
+ * an additional folio reference and never ended up here.
+ */
+ exclusive = true;
+unlock:
+ folio_unlock_large_mapcount(folio);
+ return exclusive;
+}
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+static bool __wp_can_reuse_large_anon_folio(struct folio *folio,
+ struct vm_area_struct *vma)
+{
+ BUILD_BUG();
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static bool wp_can_reuse_anon_folio(struct folio *folio,
+ struct vm_area_struct *vma)
+{
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && folio_test_large(folio))
+ return __wp_can_reuse_large_anon_folio(folio, vma);
+ VM_WARN_ON_ONCE(folio_test_large(folio));
+
/*
* We have to verify under folio lock: these early checks are
* just an optimization to avoid locking the folio and freeing
Currently, we never end up reusing PTE-mapped THPs after fork. This wasn't really a problem with PMD-sized THPs, because they would have to be PTE-mapped first, but it's getting a problem with smaller THP sizes that are effectively always PTE-mapped. With our new "mapped exclusively" vs "maybe mapped shared" logic for large folios, implementing CoW reuse for PTE-mapped THPs is straight forward: if exclusively mapped, make sure that all references are from these (our) mappings. Add some helpful comments to explain the details. CONFIG_TRANSPARENT_HUGEPAGE selects CONFIG_MM_ID. If we spot an anon large folio without CONFIG_TRANSPARENT_HUGEPAGE in that code, something is seriously messed up. There are plenty of things we can optimize in the future: For example, we could remember that the folio is fully exclusive so we could speedup the next fault further. Also, we could try "faulting around", turning surrounding PTEs that map the same folio writable. But especially the latter might increase COW latency, so it would need further investigation. Signed-off-by: David Hildenbrand <david@redhat.com> --- mm/memory.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 76 insertions(+), 8 deletions(-)