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, 91 insertions, 6 deletions

diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index d8b5b4930412..7bc9fc17c9f0 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -15,8 +15,10 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <sys/mman.h>
+#include <sys/prctl.h>
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
+#include <sys/wait.h>
 #include <linux/userfaultfd.h>
 
 #include "../kselftest.h"
@@ -178,7 +180,6 @@ unmap:
 static void test_unmerge_uffd_wp(void)
 {
 	struct uffdio_writeprotect uffd_writeprotect;
-	struct uffdio_register uffdio_register;
 	const unsigned int size = 2 * MiB;
 	struct uffdio_api uffdio_api;
 	char *map;
@@ -210,10 +211,7 @@ static void test_unmerge_uffd_wp(void)
 	}
 
 	/* Register UFFD-WP, no need for an actual handler. */
-	uffdio_register.range.start = (unsigned long) map;
-	uffdio_register.range.len = size;
-	uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) {
+	if (uffd_register(uffd, map, size, false, true, false)) {
 		ksft_test_result_fail("UFFDIO_REGISTER_MODE_WP failed\n");
 		goto close_uffd;
 	}
@@ -241,9 +239,93 @@ unmap:
 }
 #endif
 
+/* Verify that KSM can be enabled / queried with prctl. */
+static void test_prctl(void)
+{
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0);
+	if (ret < 0 && errno == EINVAL) {
+		ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n");
+		return;
+	} else if (ret) {
+		ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n");
+		return;
+	}
+
+	ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0);
+	if (ret < 0) {
+		ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n");
+		return;
+	} else if (ret != 1) {
+		ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 not effective\n");
+		return;
+	}
+
+	ret = prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0);
+	if (ret) {
+		ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n");
+		return;
+	}
+
+	ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0);
+	if (ret < 0) {
+		ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n");
+		return;
+	} else if (ret != 0) {
+		ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 not effective\n");
+		return;
+	}
+
+	ksft_test_result_pass("Setting/clearing PR_SET_MEMORY_MERGE works\n");
+}
+
+/* Verify that prctl ksm flag is inherited. */
+static void test_prctl_fork(void)
+{
+	int ret, status;
+	pid_t child_pid;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0);
+	if (ret < 0 && errno == EINVAL) {
+		ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n");
+		return;
+	} else if (ret) {
+		ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n");
+		return;
+	}
+
+	child_pid = fork();
+	if (!child_pid) {
+		exit(prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0));
+	} else if (child_pid < 0) {
+		ksft_test_result_fail("fork() failed\n");
+		return;
+	}
+
+	if (waitpid(child_pid, &status, 0) < 0) {
+		ksft_test_result_fail("waitpid() failed\n");
+		return;
+	} else if (WEXITSTATUS(status) != 1) {
+		ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n");
+		return;
+	}
+
+	if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) {
+		ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n");
+		return;
+	}
+
+	ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n");
+}
+
 int main(int argc, char **argv)
 {
-	unsigned int tests = 2;
+	unsigned int tests = 4;
 	int err;
 
 #ifdef __NR_userfaultfd
@@ -271,6 +353,9 @@ int main(int argc, char **argv)
 	test_unmerge_uffd_wp();
 #endif
 
+	test_prctl();
+	test_prctl_fork();
+
 	err = ksft_get_fail_cnt();
 	if (err)
 		ksft_exit_fail_msg("%d out of %d tests failed\n",