Merge tag 'mm-hotfixes-stable-2024-07-10-13-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "21 hotfixes, 15 of which are cc:stable.

  No identifiable theme here - all are singleton patches, 19 are for MM"

* tag 'mm-hotfixes-stable-2024-07-10-13-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
  mm/hugetlb: fix kernel NULL pointer dereference when migrating hugetlb folio
  mm/hugetlb: fix potential race in __update_and_free_hugetlb_folio()
  filemap: replace pte_offset_map() with pte_offset_map_nolock()
  arch/xtensa: always_inline get_current() and current_thread_info()
  sched.h: always_inline alloc_tag_{save|restore} to fix modpost warnings
  MAINTAINERS: mailmap: update Lorenzo Stoakes's email address
  mm: fix crashes from deferred split racing folio migration
  lib/build_OID_registry: avoid non-destructive substitution for Perl < 5.13.2 compat
  mm: gup: stop abusing try_grab_folio
  nilfs2: fix kernel bug on rename operation of broken directory
  mm/hugetlb_vmemmap: fix race with speculative PFN walkers
  cachestat: do not flush stats in recency check
  mm/shmem: disable PMD-sized page cache if needed
  mm/filemap: skip to create PMD-sized page cache if needed
  mm/readahead: limit page cache size in page_cache_ra_order()
  mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray
  mm/damon/core: merge regions aggressively when max_nr_regions is unmet
  Fix userfaultfd_api to return EINVAL as expected
  mm: vmalloc: check if a hash-index is in cpu_possible_mask
  mm: prevent derefencing NULL ptr in pfn_section_valid()
  ...

5 files changed, 24 insertions, 54 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 586a8f0104d7..1dc6248feb83 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1979,8 +1979,9 @@ static inline int subsection_map_index(unsigned long pfn)
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	int idx = subsection_map_index(pfn);
+	struct mem_section_usage *usage = READ_ONCE(ms->usage);
 
-	return test_bit(idx, READ_ONCE(ms->usage)->subsection_map);
+	return usage ? test_bit(idx, usage->subsection_map) : 0;
 }
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 1acf5bac7f50..8c236c651d1d 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -230,7 +230,13 @@ static inline int folio_ref_dec_return(struct folio *folio)
 
 static inline bool page_ref_add_unless(struct page *page, int nr, int u)
 {
-	bool ret = atomic_add_unless(&page->_refcount, nr, u);
+	bool ret = false;
+
+	rcu_read_lock();
+	/* avoid writing to the vmemmap area being remapped */
+	if (!page_is_fake_head(page) && page_ref_count(page) != u)
+		ret = atomic_add_unless(&page->_refcount, nr, u);
+	rcu_read_unlock();
 
 	if (page_ref_tracepoint_active(page_ref_mod_unless))
 		__page_ref_mod_unless(page, nr, ret);
@@ -258,54 +264,9 @@ static inline bool folio_try_get(struct folio *folio)
 	return folio_ref_add_unless(folio, 1, 0);
 }
 
-static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
-{
-#ifdef CONFIG_TINY_RCU
-	/*
-	 * The caller guarantees the folio will not be freed from interrupt
-	 * context, so (on !SMP) we only need preemption to be disabled
-	 * and TINY_RCU does that for us.
-	 */
-# ifdef CONFIG_PREEMPT_COUNT
-	VM_BUG_ON(!in_atomic() && !irqs_disabled());
-# endif
-	VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
-	folio_ref_add(folio, count);
-#else
-	if (unlikely(!folio_ref_add_unless(folio, count, 0))) {
-		/* Either the folio has been freed, or will be freed. */
-		return false;
-	}
-#endif
-	return true;
-}
-
-/**
- * folio_try_get_rcu - Attempt to increase the refcount on a folio.
- * @folio: The folio.
- *
- * This is a version of folio_try_get() optimised for non-SMP kernels.
- * If you are still holding the rcu_read_lock() after looking up the
- * page and know that the page cannot have its refcount decreased to
- * zero in interrupt context, you can use this instead of folio_try_get().
- *
- * Example users include get_user_pages_fast() (as pages are not unmapped
- * from interrupt context) and the page cache lookups (as pages are not
- * truncated from interrupt context).  We also know that pages are not
- * frozen in interrupt context for the purposes of splitting or migration.
- *
- * You can also use this function if you're holding a lock that prevents
- * pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_lock or page table lock for page tables.  In this case,
- * it will always succeed, and you could have used a plain folio_get(),
- * but it's sometimes more convenient to have a common function called
- * from both locked and RCU-protected contexts.
- *
- * Return: True if the reference count was successfully incremented.
- */
-static inline bool folio_try_get_rcu(struct folio *folio)
+static inline bool folio_ref_try_add(struct folio *folio, int count)
 {
-	return folio_ref_try_add_rcu(folio, 1);
+	return folio_ref_add_unless(folio, count, 0);
 }
 
 static inline int page_ref_freeze(struct page *page, int count)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 59f1df0cde5a..a0a026d2d244 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -354,11 +354,18 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
  * a good order (that's 1MB if you're using 4kB pages)
  */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#define PREFERRED_MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
 #else
-#define MAX_PAGECACHE_ORDER	8
+#define PREFERRED_MAX_PAGECACHE_ORDER	8
 #endif
 
+/*
+ * xas_split_alloc() does not support arbitrary orders. This implies no
+ * 512MB THP on ARM64 with 64KB base page size.
+ */
+#define MAX_XAS_ORDER		(XA_CHUNK_SHIFT * 2 - 1)
+#define MAX_PAGECACHE_ORDER	min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER)
+
 /**
  * mapping_set_large_folios() - Indicate the file supports large folios.
  * @mapping: The file.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 61591ac6eab6..a5f4b48fca18 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2192,13 +2192,13 @@ static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); }
 extern void sched_set_stop_task(int cpu, struct task_struct *stop);
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING
-static inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag)
+static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag)
 {
 	swap(current->alloc_tag, tag);
 	return tag;
 }
 
-static inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old)
+static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old)
 {
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 	WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n");
diff --git a/include/linux/swap.h b/include/linux/swap.h
index bd450023b9a4..e685e93ba354 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -354,7 +354,8 @@ static inline swp_entry_t page_swap_entry(struct page *page)
 }
 
 /* linux/mm/workingset.c */
-bool workingset_test_recent(void *shadow, bool file, bool *workingset);
+bool workingset_test_recent(void *shadow, bool file, bool *workingset,
+				bool flush);
 void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
 void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
 void workingset_refault(struct folio *folio, void *shadow);