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, 10 insertions, 22 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index aa0c47cb0d16..e943370107d0 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -29,6 +29,7 @@
 #include <linux/ioctl.h>
 #include <linux/security.h>
 #include <linux/hugetlb.h>
+#include <linux/swapops.h>
 
 int sysctl_unprivileged_userfaultfd __read_mostly;
 
@@ -249,9 +250,10 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
-	 * changes under us.
+	 * changes under us.  PTE markers should be handled the same as none
+	 * ptes here.
 	 */
-	if (huge_pte_none(pte))
+	if (huge_pte_none_mostly(pte))
 		ret = true;
 	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
 		ret = true;
@@ -330,9 +332,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	pte = pte_offset_map(pmd, address);
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
-	 * changes under us.
+	 * changes under us.  PTE markers should be handled the same as none
+	 * ptes here.
 	 */
-	if (pte_none(*pte))
+	if (pte_none_mostly(*pte))
 		ret = true;
 	if (!pte_write(*pte) && (reason & VM_UFFD_WP))
 		ret = true;
@@ -1255,24 +1258,6 @@ static __always_inline int validate_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags)
-{
-	/* FIXME: add WP support to hugetlbfs and shmem */
-	if (vm_flags & VM_UFFD_WP) {
-		if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
-			return false;
-	}
-
-	if (vm_flags & VM_UFFD_MINOR) {
-		if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
-			return false;
-	}
-
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	       vma_is_shmem(vma);
-}
-
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
@@ -1954,6 +1939,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
 #endif
+#ifndef CONFIG_PTE_MARKER_UFFD_WP
+	uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
+#endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
 	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))