Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

1 files changed, 36 insertions, 31 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index 313b57d55a63..2b9305ed0dda 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -102,26 +102,31 @@ static void unmap_region(struct mm_struct *mm,
  *								x: (yes) yes
  */
 pgprot_t protection_map[16] __ro_after_init = {
-	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
-	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
+	[VM_NONE]					= __P000,
+	[VM_READ]					= __P001,
+	[VM_WRITE]					= __P010,
+	[VM_WRITE | VM_READ]				= __P011,
+	[VM_EXEC]					= __P100,
+	[VM_EXEC | VM_READ]				= __P101,
+	[VM_EXEC | VM_WRITE]				= __P110,
+	[VM_EXEC | VM_WRITE | VM_READ]			= __P111,
+	[VM_SHARED]					= __S000,
+	[VM_SHARED | VM_READ]				= __S001,
+	[VM_SHARED | VM_WRITE]				= __S010,
+	[VM_SHARED | VM_WRITE | VM_READ]		= __S011,
+	[VM_SHARED | VM_EXEC]				= __S100,
+	[VM_SHARED | VM_EXEC | VM_READ]			= __S101,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= __S110,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= __S111
 };
 
-#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT
-static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
-{
-	return prot;
-}
-#endif
-
+#ifndef CONFIG_ARCH_HAS_VM_GET_PAGE_PROT
 pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
-	pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags &
-				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
-			pgprot_val(arch_vm_get_page_prot(vm_flags)));
-
-	return arch_filter_pgprot(ret);
+	return protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)];
 }
 EXPORT_SYMBOL(vm_get_page_prot);
+#endif	/* CONFIG_ARCH_HAS_VM_GET_PAGE_PROT */
 
 static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
 {
@@ -1218,7 +1223,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 					 end, prev->vm_pgoff, NULL, prev);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(prev, vm_flags);
+		khugepaged_enter_vma(prev, vm_flags);
 		return prev;
 	}
 
@@ -1245,7 +1250,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 		}
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(area, vm_flags);
+		khugepaged_enter_vma(area, vm_flags);
 		return area;
 	}
 
@@ -1280,7 +1285,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *
  * the same as 'old', the other will be the new one that is trying
  * to share the anon_vma.
  *
- * NOTE! This runs with mm_sem held for reading, so it is possible that
+ * NOTE! This runs with mmap_lock held for reading, so it is possible that
  * the anon_vma of 'old' is concurrently in the process of being set up
  * by another page fault trying to merge _that_. But that's ok: if it
  * is being set up, that automatically means that it will be a singleton
@@ -1294,7 +1299,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *
  *
  * We also make sure that the two vma's are compatible (adjacent,
  * and with the same memory policies). That's all stable, even with just
- * a read lock on the mm_sem.
+ * a read lock on the mmap_lock.
  */
 static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b)
 {
@@ -1842,6 +1847,13 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
+
+	/*
+	 * vma_merge() calls khugepaged_enter_vma() either, the below
+	 * call covers the non-merge case.
+	 */
+	khugepaged_enter_vma(vma, vma->vm_flags);
+
 	/* Once vma denies write, undo our temporary denial count */
 unmap_writable:
 	if (file && vm_flags & VM_SHARED)
@@ -2340,15 +2352,8 @@ static int acct_stack_growth(struct vm_area_struct *vma,
 		return -ENOMEM;
 
 	/* mlock limit tests */
-	if (vma->vm_flags & VM_LOCKED) {
-		unsigned long locked;
-		unsigned long limit;
-		locked = mm->locked_vm + grow;
-		limit = rlimit(RLIMIT_MEMLOCK);
-		limit >>= PAGE_SHIFT;
-		if (locked > limit && !capable(CAP_IPC_LOCK))
-			return -ENOMEM;
-	}
+	if (mlock_future_check(mm, vma->vm_flags, grow << PAGE_SHIFT))
+		return -ENOMEM;
 
 	/* Check to ensure the stack will not grow into a hugetlb-only region */
 	new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
@@ -2452,7 +2457,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		}
 	}
 	anon_vma_unlock_write(vma->anon_vma);
-	khugepaged_enter_vma_merge(vma, vma->vm_flags);
+	khugepaged_enter_vma(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
 }
@@ -2530,7 +2535,7 @@ int expand_downwards(struct vm_area_struct *vma,
 		}
 	}
 	anon_vma_unlock_write(vma->anon_vma);
-	khugepaged_enter_vma_merge(vma, vma->vm_flags);
+	khugepaged_enter_vma(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
 }
@@ -3553,7 +3558,7 @@ int mm_take_all_locks(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	struct anon_vma_chain *avc;
 
-	BUG_ON(mmap_read_trylock(mm));
+	mmap_assert_write_locked(mm);
 
 	mutex_lock(&mm_all_locks_mutex);
 
@@ -3633,7 +3638,7 @@ void mm_drop_all_locks(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 	struct anon_vma_chain *avc;
 
-	BUG_ON(mmap_read_trylock(mm));
+	mmap_assert_write_locked(mm);
 	BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));
 
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {