Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

1 files changed, 65 insertions, 27 deletions

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index fff49fec0258..d78b01524349 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -38,40 +38,55 @@
 
 extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
-/*
- * The mode of operation for __mcopy_atomic and its helpers.
- *
- * This is almost an implementation detail (mcopy_atomic below doesn't take this
- * as a parameter), but it's exposed here because memory-kind-specific
- * implementations (e.g. hugetlbfs) need to know the mode of operation.
- */
-enum mcopy_atomic_mode {
-	/* A normal copy_from_user into the destination range. */
-	MCOPY_ATOMIC_NORMAL,
-	/* Don't copy; map the destination range to the zero page. */
-	MCOPY_ATOMIC_ZEROPAGE,
-	/* Just install pte(s) with the existing page(s) in the page cache. */
-	MCOPY_ATOMIC_CONTINUE,
+/* A combined operation mode + behavior flags. */
+typedef unsigned int __bitwise uffd_flags_t;
+
+/* Mutually exclusive modes of operation. */
+enum mfill_atomic_mode {
+	MFILL_ATOMIC_COPY,
+	MFILL_ATOMIC_ZEROPAGE,
+	MFILL_ATOMIC_CONTINUE,
+	NR_MFILL_ATOMIC_MODES,
 };
 
-extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
+#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1)
+#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr))
+#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr))
+#define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1))
+
+static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected)
+{
+	return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected);
+}
+
+static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode)
+{
+	flags &= ~MFILL_ATOMIC_MODE_MASK;
+	return flags | ((__force uffd_flags_t) mode);
+}
+
+/* Flags controlling behavior. These behavior changes are mode-independent. */
+#define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0)
+
+extern int mfill_atomic_install_pte(pmd_t *dst_pmd,
 				    struct vm_area_struct *dst_vma,
 				    unsigned long dst_addr, struct page *page,
-				    bool newly_allocated, bool wp_copy);
-
-extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
-			    unsigned long src_start, unsigned long len,
-			    atomic_t *mmap_changing, __u64 mode);
-extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
-			      unsigned long dst_start,
-			      unsigned long len,
-			      atomic_t *mmap_changing);
-extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
-			      unsigned long len, atomic_t *mmap_changing);
+				    bool newly_allocated, uffd_flags_t flags);
+
+extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start,
+				 unsigned long src_start, unsigned long len,
+				 atomic_t *mmap_changing, uffd_flags_t flags);
+extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm,
+				     unsigned long dst_start,
+				     unsigned long len,
+				     atomic_t *mmap_changing);
+extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start,
+				     unsigned long len, atomic_t *mmap_changing,
+				     uffd_flags_t flags);
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
 			       bool enable_wp, atomic_t *mmap_changing);
-extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma,
+extern long uffd_wp_range(struct vm_area_struct *vma,
 			  unsigned long start, unsigned long len, bool enable_wp);
 
 /* mm helpers */
@@ -177,6 +192,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start,
 				  unsigned long end, struct list_head *uf);
 extern void userfaultfd_unmap_complete(struct mm_struct *mm,
 				       struct list_head *uf);
+extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma);
 
 #else /* CONFIG_USERFAULTFD */
 
@@ -272,8 +288,30 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
+{
+	return false;
+}
+
 #endif /* CONFIG_USERFAULTFD */
 
+static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
+{
+	/* Only wr-protect mode uses pte markers */
+	if (!userfaultfd_wp(vma))
+		return false;
+
+	/* File-based uffd-wp always need markers */
+	if (!vma_is_anonymous(vma))
+		return true;
+
+	/*
+	 * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED
+	 * enabled (to apply markers on zero pages).
+	 */
+	return userfaultfd_wp_unpopulated(vma);
+}
+
 static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry)
 {
 #ifdef CONFIG_PTE_MARKER_UFFD_WP