Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

4 files changed, 34 insertions, 11 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9dc5066654fd..1b2bdc02abf4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2260,6 +2260,7 @@ config TEST_XARRAY
 	tristate "Test the XArray code at runtime"
 
 config TEST_MAPLE_TREE
+	depends on DEBUG_KERNEL
 	select DEBUG_MAPLE_TREE
 	tristate "Test the Maple Tree code at runtime"
 
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 836f70393e22..be6ee6020290 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -181,7 +181,7 @@ config KASAN_VMALLOC
 
 config KASAN_KUNIT_TEST
 	tristate "KUnit-compatible tests of KASAN bug detection capabilities" if !KUNIT_ALL_TESTS
-	depends on KASAN && KUNIT
+	depends on KASAN && KUNIT && TRACEPOINTS
 	default KUNIT_ALL_TESTS
 	help
 	  A KUnit-based KASAN test suite. Triggers different kinds of
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index df352f6ccc24..3fe1491d2bf9 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -323,14 +323,19 @@ static inline void *mte_safe_root(const struct maple_enode *node)
 	return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE);
 }
 
-static inline void mte_set_full(const struct maple_enode *node)
+static inline void *mte_set_full(const struct maple_enode *node)
 {
-	node = (void *)((unsigned long)node & ~MAPLE_ENODE_NULL);
+	return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL);
 }
 
-static inline void mte_clear_full(const struct maple_enode *node)
+static inline void *mte_clear_full(const struct maple_enode *node)
 {
-	node = (void *)((unsigned long)node | MAPLE_ENODE_NULL);
+	return (void *)((unsigned long)node | MAPLE_ENODE_NULL);
+}
+
+static inline bool mte_has_null(const struct maple_enode *node)
+{
+	return (unsigned long)node & MAPLE_ENODE_NULL;
 }
 
 static inline bool ma_is_root(struct maple_node *node)
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index ed610b75dc32..42f729c8e56c 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -117,11 +117,8 @@ void percpu_counter_sync(struct percpu_counter *fbc)
 }
 EXPORT_SYMBOL(percpu_counter_sync);
 
-/*
- * Add up all the per-cpu counts, return the result.  This is a more accurate
- * but much slower version of percpu_counter_read_positive()
- */
-s64 __percpu_counter_sum(struct percpu_counter *fbc)
+static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc,
+			      const struct cpumask *cpu_mask)
 {
 	s64 ret;
 	int cpu;
@@ -129,15 +126,35 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 
 	raw_spin_lock_irqsave(&fbc->lock, flags);
 	ret = fbc->count;
-	for_each_online_cpu(cpu) {
+	for_each_cpu(cpu, cpu_mask) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
 	}
 	raw_spin_unlock_irqrestore(&fbc->lock, flags);
 	return ret;
 }
+
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive()
+ */
+s64 __percpu_counter_sum(struct percpu_counter *fbc)
+{
+	return __percpu_counter_sum_mask(fbc, cpu_online_mask);
+}
 EXPORT_SYMBOL(__percpu_counter_sum);
 
+/*
+ * This is slower version of percpu_counter_sum as it traverses all possible
+ * cpus. Use this only in the cases where accurate data is needed in the
+ * presense of CPUs getting offlined.
+ */
+s64 percpu_counter_sum_all(struct percpu_counter *fbc)
+{
+	return __percpu_counter_sum_mask(fbc, cpu_possible_mask);
+}
+EXPORT_SYMBOL(percpu_counter_sum_all);
+
 int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
 			  struct lock_class_key *key)
 {