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, 34 insertions, 11 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 28e942feacc8..0fd96d6e39ce 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -123,6 +123,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
 	return ctx->features & UFFD_FEATURE_INITIALIZED;
 }
 
+/*
+ * Whether WP_UNPOPULATED is enabled on the uffd context.  It is only
+ * meaningful when userfaultfd_wp()==true on the vma and when it's
+ * anonymous.
+ */
+bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
+{
+	struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+	if (!ctx)
+		return false;
+
+	return ctx->features & UFFD_FEATURE_WP_UNPOPULATED;
+}
+
 static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
 				     vm_flags_t flags)
 {
@@ -1644,7 +1659,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 
 		/* Reset ptes for the whole vma range if wr-protected */
 		if (userfaultfd_wp(vma))
-			uffd_wp_range(mm, vma, start, vma_end - start, false);
+			uffd_wp_range(vma, start, vma_end - start, false);
 
 		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
 		prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
@@ -1729,6 +1744,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	struct uffdio_copy uffdio_copy;
 	struct uffdio_copy __user *user_uffdio_copy;
 	struct userfaultfd_wake_range range;
+	uffd_flags_t flags = 0;
 
 	user_uffdio_copy = (struct uffdio_copy __user *) arg;
 
@@ -1755,10 +1771,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 		goto out;
 	if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
 		goto out;
+	if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
+		flags |= MFILL_ATOMIC_WP;
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
-				   uffdio_copy.len, &ctx->mmap_changing,
-				   uffdio_copy.mode);
+		ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
+					uffdio_copy.len, &ctx->mmap_changing,
+					flags);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1808,9 +1826,9 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
-				     uffdio_zeropage.range.len,
-				     &ctx->mmap_changing);
+		ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start,
+					   uffdio_zeropage.range.len,
+					   &ctx->mmap_changing);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1890,6 +1908,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	struct uffdio_continue uffdio_continue;
 	struct uffdio_continue __user *user_uffdio_continue;
 	struct userfaultfd_wake_range range;
+	uffd_flags_t flags = 0;
 
 	user_uffdio_continue = (struct uffdio_continue __user *)arg;
 
@@ -1914,13 +1933,16 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 	    uffdio_continue.range.start) {
 		goto out;
 	}
-	if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
+	if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE |
+				     UFFDIO_CONTINUE_MODE_WP))
 		goto out;
+	if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP)
+		flags |= MFILL_ATOMIC_WP;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mcopy_continue(ctx->mm, uffdio_continue.range.start,
-				     uffdio_continue.range.len,
-				     &ctx->mmap_changing);
+		ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start,
+					    uffdio_continue.range.len,
+					    &ctx->mmap_changing, flags);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1988,6 +2010,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 #endif
 #ifndef CONFIG_PTE_MARKER_UFFD_WP
 	uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
+	uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
 #endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;