Merge tag 'mm-stable-2026-02-18-19-48' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more MM  updates from Andrew Morton:

 - "mm/vmscan: fix demotion targets checks in reclaim/demotion" fixes a
   couple of issues in the demotion code - pages were failed demotion
   and were finding themselves demoted into disallowed nodes (Bing Jiao)

 - "Remove XA_ZERO from error recovery of dup_mmap()" fixes a rare
   mapledtree race and performs a number of cleanups (Liam Howlett)

 - "mm: add bitmap VMA flag helpers and convert all mmap_prepare to use
   them" implements a lot of cleanups following on from the conversion
   of the VMA flags into a bitmap (Lorenzo Stoakes)

 - "support batch checking of references and unmapping for large folios"
   implements batching to greatly improve the performance of reclaiming
   clean file-backed large folios (Baolin Wang)

 - "selftests/mm: add memory failure selftests" does as claimed (Miaohe
   Lin)

* tag 'mm-stable-2026-02-18-19-48' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (36 commits)
  mm/page_alloc: clear page->private in free_pages_prepare()
  selftests/mm: add memory failure dirty pagecache test
  selftests/mm: add memory failure clean pagecache test
  selftests/mm: add memory failure anonymous page test
  mm: rmap: support batched unmapping for file large folios
  arm64: mm: implement the architecture-specific clear_flush_young_ptes()
  arm64: mm: support batch clearing of the young flag for large folios
  arm64: mm: factor out the address and ptep alignment into a new helper
  mm: rmap: support batched checks of the references for large folios
  tools/testing/vma: add VMA userland tests for VMA flag functions
  tools/testing/vma: separate out vma_internal.h into logical headers
  tools/testing/vma: separate VMA userland tests into separate files
  mm: make vm_area_desc utilise vma_flags_t only
  mm: update all remaining mmap_prepare users to use vma_flags_t
  mm: update shmem_[kernel]_file_*() functions to use vma_flags_t
  mm: update secretmem to use VMA flags on mmap_prepare
  mm: update hugetlbfs to use VMA flags on mmap_prepare
  mm: add basic VMA flag operation helper functions
  tools: bitmap: add missing bitmap_[subset(), andnot()]
  mm: add mk_vma_flags() bitmap flag macro helper
  ...

8 files changed, 433 insertions, 0 deletions

diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index c2a8586e51a1..83ad9454dd9d 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -12,6 +12,7 @@ map_hugetlb
 map_populate
 thuge-gen
 compaction_test
+memory-failure
 migration
 mlock2-tests
 mrelease_test
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index dca8f590c1e6..7a5de4e9bf52 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -75,6 +75,7 @@ TEST_GEN_FILES += map_populate
 ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64 loongarch32 loongarch64))
 TEST_GEN_FILES += memfd_secret
 endif
+TEST_GEN_FILES += memory-failure
 TEST_GEN_FILES += migration
 TEST_GEN_FILES += mkdirty
 TEST_GEN_FILES += mlock-random-test
@@ -154,6 +155,7 @@ TEST_PROGS += ksft_ksm_numa.sh
 TEST_PROGS += ksft_madv_guard.sh
 TEST_PROGS += ksft_madv_populate.sh
 TEST_PROGS += ksft_memfd_secret.sh
+TEST_PROGS += ksft_memory_failure.sh
 TEST_PROGS += ksft_migration.sh
 TEST_PROGS += ksft_mkdirty.sh
 TEST_PROGS += ksft_mlock.sh
diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config
index deba93379c80..1dbe2b4558ab 100644
--- a/tools/testing/selftests/mm/config
+++ b/tools/testing/selftests/mm/config
@@ -11,3 +11,5 @@ CONFIG_ANON_VMA_NAME=y
 CONFIG_FTRACE=y
 CONFIG_PROFILING=y
 CONFIG_UPROBES=y
+CONFIG_MEMORY_FAILURE=y
+CONFIG_HWPOISON_INJECT=m
diff --git a/tools/testing/selftests/mm/ksft_memory_failure.sh b/tools/testing/selftests/mm/ksft_memory_failure.sh
new file mode 100755
index 000000000000..ae1614d4d49b
--- /dev/null
+++ b/tools/testing/selftests/mm/ksft_memory_failure.sh
@@ -0,0 +1,4 @@
+#!/bin/sh -e
+# SPDX-License-Identifier: GPL-2.0
+
+./run_vmtests.sh -t memory-failure
diff --git a/tools/testing/selftests/mm/memory-failure.c b/tools/testing/selftests/mm/memory-failure.c
new file mode 100644
index 000000000000..3d9e0b9ffb41
--- /dev/null
+++ b/tools/testing/selftests/mm/memory-failure.c
@@ -0,0 +1,359 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Memory-failure functional tests.
+ *
+ * Author(s): Miaohe Lin <linmiaohe@huawei.com>
+ */
+
+#include "../kselftest_harness.h"
+
+#include <sys/mman.h>
+#include <linux/mman.h>
+#include <linux/string.h>
+#include <unistd.h>
+#include <signal.h>
+#include <setjmp.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/vfs.h>
+#include <linux/magic.h>
+#include <errno.h>
+
+#include "vm_util.h"
+
+enum inject_type {
+	MADV_HARD,
+	MADV_SOFT,
+};
+
+enum result_type {
+	MADV_HARD_ANON,
+	MADV_HARD_CLEAN_PAGECACHE,
+	MADV_HARD_DIRTY_PAGECACHE,
+	MADV_SOFT_ANON,
+	MADV_SOFT_CLEAN_PAGECACHE,
+	MADV_SOFT_DIRTY_PAGECACHE,
+};
+
+static jmp_buf signal_jmp_buf;
+static siginfo_t siginfo;
+const char *pagemap_proc = "/proc/self/pagemap";
+const char *kpageflags_proc = "/proc/kpageflags";
+
+FIXTURE(memory_failure)
+{
+	unsigned long page_size;
+	unsigned long corrupted_size;
+	unsigned long pfn;
+	int pagemap_fd;
+	int kpageflags_fd;
+	bool triggered;
+};
+
+FIXTURE_VARIANT(memory_failure)
+{
+	enum inject_type type;
+	int (*inject)(FIXTURE_DATA(memory_failure) * self, void *vaddr);
+};
+
+static int madv_hard_inject(FIXTURE_DATA(memory_failure) * self, void *vaddr)
+{
+	return madvise(vaddr, self->page_size, MADV_HWPOISON);
+}
+
+FIXTURE_VARIANT_ADD(memory_failure, madv_hard)
+{
+	.type = MADV_HARD,
+	.inject = madv_hard_inject,
+};
+
+static int madv_soft_inject(FIXTURE_DATA(memory_failure) * self, void *vaddr)
+{
+	return madvise(vaddr, self->page_size, MADV_SOFT_OFFLINE);
+}
+
+FIXTURE_VARIANT_ADD(memory_failure, madv_soft)
+{
+	.type = MADV_SOFT,
+	.inject = madv_soft_inject,
+};
+
+static void sigbus_action(int signo, siginfo_t *si, void *args)
+{
+	memcpy(&siginfo, si, sizeof(siginfo_t));
+	siglongjmp(signal_jmp_buf, 1);
+}
+
+static int setup_sighandler(void)
+{
+	struct sigaction sa = {
+		.sa_sigaction = sigbus_action,
+		.sa_flags = SA_SIGINFO,
+	};
+
+	return sigaction(SIGBUS, &sa, NULL);
+}
+
+FIXTURE_SETUP(memory_failure)
+{
+	memset(self, 0, sizeof(*self));
+
+	self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
+
+	memset(&siginfo, 0, sizeof(siginfo));
+	if (setup_sighandler())
+		SKIP(return, "setup sighandler failed.\n");
+
+	self->pagemap_fd = open(pagemap_proc, O_RDONLY);
+	if (self->pagemap_fd == -1)
+		SKIP(return, "open %s failed.\n", pagemap_proc);
+
+	self->kpageflags_fd = open(kpageflags_proc, O_RDONLY);
+	if (self->kpageflags_fd == -1)
+		SKIP(return, "open %s failed.\n", kpageflags_proc);
+}
+
+static void teardown_sighandler(void)
+{
+	struct sigaction sa = {
+		.sa_handler = SIG_DFL,
+		.sa_flags = SA_SIGINFO,
+	};
+
+	sigaction(SIGBUS, &sa, NULL);
+}
+
+FIXTURE_TEARDOWN(memory_failure)
+{
+	close(self->kpageflags_fd);
+	close(self->pagemap_fd);
+	teardown_sighandler();
+}
+
+static void prepare(struct __test_metadata *_metadata, FIXTURE_DATA(memory_failure) * self,
+		    void *vaddr)
+{
+	self->pfn = pagemap_get_pfn(self->pagemap_fd, vaddr);
+	ASSERT_NE(self->pfn, -1UL);
+
+	ASSERT_EQ(get_hardware_corrupted_size(&self->corrupted_size), 0);
+}
+
+static bool check_memory(void *vaddr, unsigned long size)
+{
+	char buf[64];
+
+	memset(buf, 0xce, sizeof(buf));
+	while (size >= sizeof(buf)) {
+		if (memcmp(vaddr, buf, sizeof(buf)))
+			return false;
+		size -= sizeof(buf);
+		vaddr += sizeof(buf);
+	}
+
+	return true;
+}
+
+static void check(struct __test_metadata *_metadata, FIXTURE_DATA(memory_failure) * self,
+		  void *vaddr, enum result_type type, int setjmp)
+{
+	unsigned long size;
+	uint64_t pfn_flags;
+
+	switch (type) {
+	case MADV_SOFT_ANON:
+	case MADV_HARD_CLEAN_PAGECACHE:
+	case MADV_SOFT_CLEAN_PAGECACHE:
+	case MADV_SOFT_DIRTY_PAGECACHE:
+		/* It is not expected to receive a SIGBUS signal. */
+		ASSERT_EQ(setjmp, 0);
+
+		/* The page content should remain unchanged. */
+		ASSERT_TRUE(check_memory(vaddr, self->page_size));
+
+		/* The backing pfn of addr should have changed. */
+		ASSERT_NE(pagemap_get_pfn(self->pagemap_fd, vaddr), self->pfn);
+		break;
+	case MADV_HARD_ANON:
+	case MADV_HARD_DIRTY_PAGECACHE:
+		/* The SIGBUS signal should have been received. */
+		ASSERT_EQ(setjmp, 1);
+
+		/* Check if siginfo contains correct SIGBUS context. */
+		ASSERT_EQ(siginfo.si_signo, SIGBUS);
+		ASSERT_EQ(siginfo.si_code, BUS_MCEERR_AR);
+		ASSERT_EQ(1UL << siginfo.si_addr_lsb, self->page_size);
+		ASSERT_EQ(siginfo.si_addr, vaddr);
+
+		/* XXX Check backing pte is hwpoison entry when supported. */
+		ASSERT_TRUE(pagemap_is_swapped(self->pagemap_fd, vaddr));
+		break;
+	default:
+		SKIP(return, "unexpected inject type %d.\n", type);
+	}
+
+	/* Check if the value of HardwareCorrupted has increased. */
+	ASSERT_EQ(get_hardware_corrupted_size(&size), 0);
+	ASSERT_EQ(size, self->corrupted_size + self->page_size / 1024);
+
+	/* Check if HWPoison flag is set. */
+	ASSERT_EQ(pageflags_get(self->pfn, self->kpageflags_fd, &pfn_flags), 0);
+	ASSERT_EQ(pfn_flags & KPF_HWPOISON, KPF_HWPOISON);
+}
+
+static void cleanup(struct __test_metadata *_metadata, FIXTURE_DATA(memory_failure) * self,
+		    void *vaddr)
+{
+	unsigned long size;
+	uint64_t pfn_flags;
+
+	ASSERT_EQ(unpoison_memory(self->pfn), 0);
+
+	/* Check if HWPoison flag is cleared. */
+	ASSERT_EQ(pageflags_get(self->pfn, self->kpageflags_fd, &pfn_flags), 0);
+	ASSERT_NE(pfn_flags & KPF_HWPOISON, KPF_HWPOISON);
+
+	/* Check if the value of HardwareCorrupted has decreased. */
+	ASSERT_EQ(get_hardware_corrupted_size(&size), 0);
+	ASSERT_EQ(size, self->corrupted_size);
+}
+
+TEST_F(memory_failure, anon)
+{
+	char *addr;
+	int ret;
+
+	addr = mmap(0, self->page_size, PROT_READ | PROT_WRITE,
+		    MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (addr == MAP_FAILED)
+		SKIP(return, "mmap failed, not enough memory.\n");
+	memset(addr, 0xce, self->page_size);
+
+	prepare(_metadata, self, addr);
+
+	ret = sigsetjmp(signal_jmp_buf, 1);
+	if (!self->triggered) {
+		self->triggered = true;
+		ASSERT_EQ(variant->inject(self, addr), 0);
+		FORCE_READ(*addr);
+	}
+
+	if (variant->type == MADV_HARD)
+		check(_metadata, self, addr, MADV_HARD_ANON, ret);
+	else
+		check(_metadata, self, addr, MADV_SOFT_ANON, ret);
+
+	cleanup(_metadata, self, addr);
+
+	ASSERT_EQ(munmap(addr, self->page_size), 0);
+}
+
+static int prepare_file(const char *fname, unsigned long size)
+{
+	int fd;
+
+	fd = open(fname, O_RDWR | O_CREAT, 0664);
+	if (fd >= 0) {
+		unlink(fname);
+		ftruncate(fd, size);
+	}
+	return fd;
+}
+
+/* Borrowed from mm/gup_longterm.c. */
+static int get_fs_type(int fd)
+{
+	struct statfs fs;
+	int ret;
+
+	do {
+		ret = fstatfs(fd, &fs);
+	} while (ret && errno == EINTR);
+
+	return ret ? 0 : (int)fs.f_type;
+}
+
+TEST_F(memory_failure, clean_pagecache)
+{
+	int fd;
+	char *addr;
+	int ret;
+	int fs_type;
+
+	fd = prepare_file("./clean-page-cache-test-file", self->page_size);
+	if (fd < 0)
+		SKIP(return, "failed to open test file.\n");
+	fs_type = get_fs_type(fd);
+	if (!fs_type || fs_type == TMPFS_MAGIC)
+		SKIP(return, "unsupported filesystem :%x\n", fs_type);
+
+	addr = mmap(0, self->page_size, PROT_READ | PROT_WRITE,
+		    MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED)
+		SKIP(return, "mmap failed, not enough memory.\n");
+	memset(addr, 0xce, self->page_size);
+	fsync(fd);
+
+	prepare(_metadata, self, addr);
+
+	ret = sigsetjmp(signal_jmp_buf, 1);
+	if (!self->triggered) {
+		self->triggered = true;
+		ASSERT_EQ(variant->inject(self, addr), 0);
+		FORCE_READ(*addr);
+	}
+
+	if (variant->type == MADV_HARD)
+		check(_metadata, self, addr, MADV_HARD_CLEAN_PAGECACHE, ret);
+	else
+		check(_metadata, self, addr, MADV_SOFT_CLEAN_PAGECACHE, ret);
+
+	cleanup(_metadata, self, addr);
+
+	ASSERT_EQ(munmap(addr, self->page_size), 0);
+
+	ASSERT_EQ(close(fd), 0);
+}
+
+TEST_F(memory_failure, dirty_pagecache)
+{
+	int fd;
+	char *addr;
+	int ret;
+	int fs_type;
+
+	fd = prepare_file("./dirty-page-cache-test-file", self->page_size);
+	if (fd < 0)
+		SKIP(return, "failed to open test file.\n");
+	fs_type = get_fs_type(fd);
+	if (!fs_type || fs_type == TMPFS_MAGIC)
+		SKIP(return, "unsupported filesystem :%x\n", fs_type);
+
+	addr = mmap(0, self->page_size, PROT_READ | PROT_WRITE,
+		    MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED)
+		SKIP(return, "mmap failed, not enough memory.\n");
+	memset(addr, 0xce, self->page_size);
+
+	prepare(_metadata, self, addr);
+
+	ret = sigsetjmp(signal_jmp_buf, 1);
+	if (!self->triggered) {
+		self->triggered = true;
+		ASSERT_EQ(variant->inject(self, addr), 0);
+		FORCE_READ(*addr);
+	}
+
+	if (variant->type == MADV_HARD)
+		check(_metadata, self, addr, MADV_HARD_DIRTY_PAGECACHE, ret);
+	else
+		check(_metadata, self, addr, MADV_SOFT_DIRTY_PAGECACHE, ret);
+
+	cleanup(_metadata, self, addr);
+
+	ASSERT_EQ(munmap(addr, self->page_size), 0);
+
+	ASSERT_EQ(close(fd), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 29be9038bfb0..afdcfd0d7cef 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -91,6 +91,8 @@ separated by spaces:
 	test VMA merge cases behave as expected
 - rmap
 	test rmap behaves as expected
+- memory-failure
+	test memory-failure behaves as expected
 
 example: ./run_vmtests.sh -t "hmm mmap ksm"
 EOF
@@ -527,6 +529,25 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
 
 CATEGORY="rmap" run_test ./rmap
 
+# Try to load hwpoison_inject if not present.
+HWPOISON_DIR=/sys/kernel/debug/hwpoison/
+if [ ! -d "$HWPOISON_DIR" ]; then
+	if ! modprobe -q -R hwpoison_inject; then
+		echo "Module hwpoison_inject not found, skipping..."
+	else
+		modprobe hwpoison_inject > /dev/null 2>&1
+		LOADED_MOD=1
+	fi
+fi
+
+if [ -d "$HWPOISON_DIR" ]; then
+	CATEGORY="memory-failure" run_test ./memory-failure
+fi
+
+if [ -n "${LOADED_MOD}" ]; then
+	modprobe -r hwpoison_inject > /dev/null 2>&1
+fi
+
 if [ "${HAVE_HUGEPAGES}" = 1 ]; then
 	echo "$orig_nr_hugepgs" > /proc/sys/vm/nr_hugepages
 fi
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index d954bf91afd5..a6d4ff7dfdc0 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -723,3 +723,44 @@ int ksm_stop(void)
 	close(ksm_fd);
 	return ret == 1 ? 0 : -errno;
 }
+
+int get_hardware_corrupted_size(unsigned long *val)
+{
+	unsigned long size;
+	char *line = NULL;
+	size_t linelen = 0;
+	FILE *f = fopen("/proc/meminfo", "r");
+	int ret = -1;
+
+	if (!f)
+		return ret;
+
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "HardwareCorrupted: %12lu kB", &size) == 1) {
+			*val = size;
+			ret = 0;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(f);
+	return ret;
+}
+
+int unpoison_memory(unsigned long pfn)
+{
+	int unpoison_fd, len;
+	char buf[32];
+	ssize_t ret;
+
+	unpoison_fd = open("/sys/kernel/debug/hwpoison/unpoison-pfn", O_WRONLY);
+	if (unpoison_fd < 0)
+		return -errno;
+
+	len = sprintf(buf, "0x%lx\n", pfn);
+	ret = write(unpoison_fd, buf, len);
+	close(unpoison_fd);
+
+	return ret > 0 ? 0 : -errno;
+}
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 522f7f9050f5..e9c4e24769c1 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -20,6 +20,7 @@
 
 #define KPF_COMPOUND_HEAD             BIT_ULL(15)
 #define KPF_COMPOUND_TAIL             BIT_ULL(16)
+#define KPF_HWPOISON                  BIT_ULL(19)
 #define KPF_THP                       BIT_ULL(22)
 /*
  * Ignore the checkpatch warning, we must read from x but don't want to do
@@ -154,6 +155,8 @@ long ksm_get_full_scans(void);
 int ksm_use_zero_pages(void);
 int ksm_start(void);
 int ksm_stop(void);
+int get_hardware_corrupted_size(unsigned long *val);
+int unpoison_memory(unsigned long pfn);
 
 /*
  * On ppc64 this will only work with radix 2M hugepage size