Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "190 patches.

  Subsystems affected by this patch series: mm (hugetlb, userfaultfd,
  vmscan, kconfig, proc, z3fold, zbud, ras, mempolicy, memblock,
  migration, thp, nommu, kconfig, madvise, memory-hotplug, zswap,
  zsmalloc, zram, cleanups, kfence, and hmm), procfs, sysctl, misc,
  core-kernel, lib, lz4, checkpatch, init, kprobes, nilfs2, hfs,
  signals, exec, kcov, selftests, compress/decompress, and ipc"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
  ipc/util.c: use binary search for max_idx
  ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock
  ipc: use kmalloc for msg_queue and shmid_kernel
  ipc sem: use kvmalloc for sem_undo allocation
  lib/decompressors: remove set but not used variabled 'level'
  selftests/vm/pkeys: exercise x86 XSAVE init state
  selftests/vm/pkeys: refill shadow register after implicit kernel write
  selftests/vm/pkeys: handle negative sys_pkey_alloc() return code
  selftests/vm/pkeys: fix alloc_random_pkey() to make it really, really random
  kcov: add __no_sanitize_coverage to fix noinstr for all architectures
  exec: remove checks in __register_bimfmt()
  x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned
  hfsplus: report create_date to kstat.btime
  hfsplus: remove unnecessary oom message
  nilfs2: remove redundant continue statement in a while-loop
  kprobes: remove duplicated strong free_insn_page in x86 and s390
  init: print out unknown kernel parameters
  checkpatch: do not complain about positive return values starting with EPOLL
  checkpatch: improve the indented label test
  checkpatch: scripts/spdxcheck.py now requires python3
  ...

9 files changed, 1125 insertions, 543 deletions

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 1f651e85ed60..d683a49d07d5 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -12,6 +12,9 @@ mremap_test
 on-fault-limit
 transhuge-stress
 protection_keys
+protection_keys_32
+protection_keys_64
+madv_populate
 userfaultfd
 mlock-intersect-test
 mlock-random-test
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 73e1cc96d7c2..812bc03e3142 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -31,6 +31,7 @@ TEST_GEN_FILES += hmm-tests
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-shm
 TEST_GEN_FILES += khugepaged
+TEST_GEN_FILES += madv_populate
 TEST_GEN_FILES += map_fixed_noreplace
 TEST_GEN_FILES += map_hugetlb
 TEST_GEN_FILES += map_populate
@@ -100,7 +101,7 @@ $(1) $(1)_64: $(OUTPUT)/$(1)_64
 endef
 
 ifeq ($(CAN_BUILD_I386),1)
-$(BINARIES_32): CFLAGS += -m32
+$(BINARIES_32): CFLAGS += -m32 -mxsave
 $(BINARIES_32): LDLIBS += -lrt -ldl -lm
 $(BINARIES_32): $(OUTPUT)/%_32: %.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
@@ -108,7 +109,7 @@ $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
 endif
 
 ifeq ($(CAN_BUILD_X86_64),1)
-$(BINARIES_64): CFLAGS += -m64
+$(BINARIES_64): CFLAGS += -m64 -mxsave
 $(BINARIES_64): LDLIBS += -lrt -ldl
 $(BINARIES_64): $(OUTPUT)/%_64: %.c
 	$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 5d1ac691b9f4..864f126ffd78 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -1485,4 +1485,162 @@ TEST_F(hmm2, double_map)
 	hmm_buffer_free(buffer);
 }
 
+/*
+ * Basic check of exclusive faulting.
+ */
+TEST_F(hmm, exclusive)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Map memory exclusively for device access. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_EXCLUSIVE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Fault pages back to system memory and check them. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i]++, i);
+
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i+1);
+
+	/* Check atomic access revoked */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_CHECK_EXCLUSIVE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+
+	hmm_buffer_free(buffer);
+}
+
+TEST_F(hmm, exclusive_mprotect)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Map memory exclusively for device access. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_EXCLUSIVE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	ret = mprotect(buffer->ptr, size, PROT_READ);
+	ASSERT_EQ(ret, 0);
+
+	/* Simulate a device writing system memory. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages);
+	ASSERT_EQ(ret, -EPERM);
+
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Check copy-on-write works.
+ */
+TEST_F(hmm, exclusive_cow)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+
+	npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift;
+	ASSERT_NE(npages, 0);
+	size = npages << self->page_shift;
+
+	buffer = malloc(sizeof(*buffer));
+	ASSERT_NE(buffer, NULL);
+
+	buffer->fd = -1;
+	buffer->size = size;
+	buffer->mirror = malloc(size);
+	ASSERT_NE(buffer->mirror, NULL);
+
+	buffer->ptr = mmap(NULL, size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS,
+			   buffer->fd, 0);
+	ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+	/* Initialize buffer in system memory. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Map memory exclusively for device access. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_EXCLUSIVE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	fork();
+
+	/* Fault pages back to system memory and check them. */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i]++, i);
+
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i+1);
+
+	hmm_buffer_free(buffer);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c
index 8b75821302a7..155120b67a16 100644
--- a/tools/testing/selftests/vm/khugepaged.c
+++ b/tools/testing/selftests/vm/khugepaged.c
@@ -86,7 +86,6 @@ struct settings {
 	enum thp_enabled thp_enabled;
 	enum thp_defrag thp_defrag;
 	enum shmem_enabled shmem_enabled;
-	bool debug_cow;
 	bool use_zero_page;
 	struct khugepaged_settings khugepaged;
 };
@@ -95,7 +94,6 @@ static struct settings default_settings = {
 	.thp_enabled = THP_MADVISE,
 	.thp_defrag = THP_DEFRAG_ALWAYS,
 	.shmem_enabled = SHMEM_NEVER,
-	.debug_cow = 0,
 	.use_zero_page = 0,
 	.khugepaged = {
 		.defrag = 1,
@@ -268,7 +266,6 @@ static void write_settings(struct settings *settings)
 	write_string("defrag", thp_defrag_strings[settings->thp_defrag]);
 	write_string("shmem_enabled",
 			shmem_enabled_strings[settings->shmem_enabled]);
-	write_num("debug_cow", settings->debug_cow);
 	write_num("use_zero_page", settings->use_zero_page);
 
 	write_num("khugepaged/defrag", khugepaged->defrag);
@@ -304,7 +301,6 @@ static void save_settings(void)
 		.thp_defrag = read_string("defrag", thp_defrag_strings),
 		.shmem_enabled =
 			read_string("shmem_enabled", shmem_enabled_strings),
-		.debug_cow = read_num("debug_cow"),
 		.use_zero_page = read_num("use_zero_page"),
 	};
 	saved_settings.khugepaged = (struct khugepaged_settings) {
diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/vm/madv_populate.c
new file mode 100644
index 000000000000..b959e4ebdad4
--- /dev/null
+++ b/tools/testing/selftests/vm/madv_populate.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
+ *
+ * Copyright 2021, Red Hat, Inc.
+ *
+ * Author(s): David Hildenbrand <david@redhat.com>
+ */
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+
+#include "../kselftest.h"
+
+#if defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE)
+
+/*
+ * For now, we're using 2 MiB of private anonymous memory for all tests.
+ */
+#define SIZE (2 * 1024 * 1024)
+
+static size_t pagesize;
+
+static uint64_t pagemap_get_entry(int fd, char *start)
+{
+	const unsigned long pfn = (unsigned long)start / pagesize;
+	uint64_t entry;
+	int ret;
+
+	ret = pread(fd, &entry, sizeof(entry), pfn * sizeof(entry));
+	if (ret != sizeof(entry))
+		ksft_exit_fail_msg("reading pagemap failed\n");
+	return entry;
+}
+
+static bool pagemap_is_populated(int fd, char *start)
+{
+	uint64_t entry = pagemap_get_entry(fd, start);
+
+	/* Present or swapped. */
+	return entry & 0xc000000000000000ull;
+}
+
+static bool pagemap_is_softdirty(int fd, char *start)
+{
+	uint64_t entry = pagemap_get_entry(fd, start);
+
+	return entry & 0x0080000000000000ull;
+}
+
+static void sense_support(void)
+{
+	char *addr;
+	int ret;
+
+	addr = mmap(0, pagesize, PROT_READ | PROT_WRITE,
+		    MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (!addr)
+		ksft_exit_fail_msg("mmap failed\n");
+
+	ret = madvise(addr, pagesize, MADV_POPULATE_READ);
+	if (ret)
+		ksft_exit_skip("MADV_POPULATE_READ is not available\n");
+
+	ret = madvise(addr, pagesize, MADV_POPULATE_WRITE);
+	if (ret)
+		ksft_exit_skip("MADV_POPULATE_WRITE is not available\n");
+
+	munmap(addr, pagesize);
+}
+
+static void test_prot_read(void)
+{
+	char *addr;
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	addr = mmap(0, SIZE, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap failed\n");
+
+	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
+	ksft_test_result(!ret, "MADV_POPULATE_READ with PROT_READ\n");
+
+	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
+	ksft_test_result(ret == -1 && errno == EINVAL,
+			 "MADV_POPULATE_WRITE with PROT_READ\n");
+
+	munmap(addr, SIZE);
+}
+
+static void test_prot_write(void)
+{
+	char *addr;
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	addr = mmap(0, SIZE, PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap failed\n");
+
+	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
+	ksft_test_result(ret == -1 && errno == EINVAL,
+			 "MADV_POPULATE_READ with PROT_WRITE\n");
+
+	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
+	ksft_test_result(!ret, "MADV_POPULATE_WRITE with PROT_WRITE\n");
+
+	munmap(addr, SIZE);
+}
+
+static void test_holes(void)
+{
+	char *addr;
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	addr = mmap(0, SIZE, PROT_READ | PROT_WRITE,
+		    MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap failed\n");
+	ret = munmap(addr + pagesize, pagesize);
+	if (ret)
+		ksft_exit_fail_msg("munmap failed\n");
+
+	/* Hole in the middle */
+	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
+	ksft_test_result(ret == -1 && errno == ENOMEM,
+			 "MADV_POPULATE_READ with holes in the middle\n");
+	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
+	ksft_test_result(ret == -1 && errno == ENOMEM,
+			 "MADV_POPULATE_WRITE with holes in the middle\n");
+
+	/* Hole at end */
+	ret = madvise(addr, 2 * pagesize, MADV_POPULATE_READ);
+	ksft_test_result(ret == -1 && errno == ENOMEM,
+			 "MADV_POPULATE_READ with holes at the end\n");
+	ret = madvise(addr, 2 * pagesize, MADV_POPULATE_WRITE);
+	ksft_test_result(ret == -1 && errno == ENOMEM,
+			 "MADV_POPULATE_WRITE with holes at the end\n");
+
+	/* Hole at beginning */
+	ret = madvise(addr + pagesize, pagesize, MADV_POPULATE_READ);
+	ksft_test_result(ret == -1 && errno == ENOMEM,
+			 "MADV_POPULATE_READ with holes at the beginning\n");
+	ret = madvise(addr + pagesize, pagesize, MADV_POPULATE_WRITE);
+	ksft_test_result(ret == -1 && errno == ENOMEM,
+			 "MADV_POPULATE_WRITE with holes at the beginning\n");
+
+	munmap(addr, SIZE);
+}
+
+static bool range_is_populated(char *start, ssize_t size)
+{
+	int fd = open("/proc/self/pagemap", O_RDONLY);
+	bool ret = true;
+
+	if (fd < 0)
+		ksft_exit_fail_msg("opening pagemap failed\n");
+	for (; size > 0 && ret; size -= pagesize, start += pagesize)
+		if (!pagemap_is_populated(fd, start))
+			ret = false;
+	close(fd);
+	return ret;
+}
+
+static bool range_is_not_populated(char *start, ssize_t size)
+{
+	int fd = open("/proc/self/pagemap", O_RDONLY);
+	bool ret = true;
+
+	if (fd < 0)
+		ksft_exit_fail_msg("opening pagemap failed\n");
+	for (; size > 0 && ret; size -= pagesize, start += pagesize)
+		if (pagemap_is_populated(fd, start))
+			ret = false;
+	close(fd);
+	return ret;
+}
+
+static void test_populate_read(void)
+{
+	char *addr;
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	addr = mmap(0, SIZE, PROT_READ | PROT_WRITE,
+		    MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap failed\n");
+	ksft_test_result(range_is_not_populated(addr, SIZE),
+			 "range initially not populated\n");
+
+	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
+	ksft_test_result(!ret, "MADV_POPULATE_READ\n");
+	ksft_test_result(range_is_populated(addr, SIZE),
+			 "range is populated\n");
+
+	munmap(addr, SIZE);
+}
+
+static void test_populate_write(void)
+{
+	char *addr;
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	addr = mmap(0, SIZE, PROT_READ | PROT_WRITE,
+		    MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap failed\n");
+	ksft_test_result(range_is_not_populated(addr, SIZE),
+			 "range initially not populated\n");
+
+	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
+	ksft_test_result(!ret, "MADV_POPULATE_WRITE\n");
+	ksft_test_result(range_is_populated(addr, SIZE),
+			 "range is populated\n");
+
+	munmap(addr, SIZE);
+}
+
+static bool range_is_softdirty(char *start, ssize_t size)
+{
+	int fd = open("/proc/self/pagemap", O_RDONLY);
+	bool ret = true;
+
+	if (fd < 0)
+		ksft_exit_fail_msg("opening pagemap failed\n");
+	for (; size > 0 && ret; size -= pagesize, start += pagesize)
+		if (!pagemap_is_softdirty(fd, start))
+			ret = false;
+	close(fd);
+	return ret;
+}
+
+static bool range_is_not_softdirty(char *start, ssize_t size)
+{
+	int fd = open("/proc/self/pagemap", O_RDONLY);
+	bool ret = true;
+
+	if (fd < 0)
+		ksft_exit_fail_msg("opening pagemap failed\n");
+	for (; size > 0 && ret; size -= pagesize, start += pagesize)
+		if (pagemap_is_softdirty(fd, start))
+			ret = false;
+	close(fd);
+	return ret;
+}
+
+static void clear_softdirty(void)
+{
+	int fd = open("/proc/self/clear_refs", O_WRONLY);
+	const char *ctrl = "4";
+	int ret;
+
+	if (fd < 0)
+		ksft_exit_fail_msg("opening clear_refs failed\n");
+	ret = write(fd, ctrl, strlen(ctrl));
+	if (ret != strlen(ctrl))
+		ksft_exit_fail_msg("writing clear_refs failed\n");
+	close(fd);
+}
+
+static void test_softdirty(void)
+{
+	char *addr;
+	int ret;
+
+	ksft_print_msg("[RUN] %s\n", __func__);
+
+	addr = mmap(0, SIZE, PROT_READ | PROT_WRITE,
+		    MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (addr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap failed\n");
+
+	/* Clear any softdirty bits. */
+	clear_softdirty();
+	ksft_test_result(range_is_not_softdirty(addr, SIZE),
+			 "range is not softdirty\n");
+
+	/* Populating READ should set softdirty. */
+	ret = madvise(addr, SIZE, MADV_POPULATE_READ);
+	ksft_test_result(!ret, "MADV_POPULATE_READ\n");
+	ksft_test_result(range_is_not_softdirty(addr, SIZE),
+			 "range is not softdirty\n");
+
+	/* Populating WRITE should set softdirty. */
+	ret = madvise(addr, SIZE, MADV_POPULATE_WRITE);
+	ksft_test_result(!ret, "MADV_POPULATE_WRITE\n");
+	ksft_test_result(range_is_softdirty(addr, SIZE),
+			 "range is softdirty\n");
+
+	munmap(addr, SIZE);
+}
+
+int main(int argc, char **argv)
+{
+	int err;
+
+	pagesize = getpagesize();
+
+	ksft_print_header();
+	ksft_set_plan(21);
+
+	sense_support();
+	test_prot_read();
+	test_prot_write();
+	test_holes();
+	test_populate_read();
+	test_populate_write();
+	test_softdirty();
+
+	err = ksft_get_fail_cnt();
+	if (err)
+		ksft_exit_fail_msg("%d out of %d tests failed\n",
+				   err, ksft_test_num());
+	return ksft_exit_pass();
+}
+
+#else /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */
+
+#warning "missing MADV_POPULATE_READ or MADV_POPULATE_WRITE definition"
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	ksft_exit_skip("MADV_POPULATE_READ or MADV_POPULATE_WRITE not defined\n");
+}
+
+#endif /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */
diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h
index 3be20f5d5275..e4a4ce2b826d 100644
--- a/tools/testing/selftests/vm/pkey-x86.h
+++ b/tools/testing/selftests/vm/pkey-x86.h
@@ -126,6 +126,7 @@ static inline u32 pkey_bit_position(int pkey)
 
 #define XSTATE_PKEY_BIT	(9)
 #define XSTATE_PKEY	0x200
+#define XSTATE_BV_OFFSET	512
 
 int pkey_reg_xstate_offset(void)
 {
diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c
index fdbb602ecf32..2d0ae88665db 100644
--- a/tools/testing/selftests/vm/protection_keys.c
+++ b/tools/testing/selftests/vm/protection_keys.c
@@ -510,7 +510,7 @@ int alloc_pkey(void)
 			" shadow: 0x%016llx\n",
 			__func__, __LINE__, ret, __read_pkey_reg(),
 			shadow_pkey_reg);
-	if (ret) {
+	if (ret > 0) {
 		/* clear both the bits: */
 		shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, ret,
 						~PKEY_MASK);
@@ -561,7 +561,6 @@ int alloc_random_pkey(void)
 	int nr_alloced = 0;
 	int random_index;
 	memset(alloced_pkeys, 0, sizeof(alloced_pkeys));
-	srand((unsigned int)time(NULL));
 
 	/* allocate every possible key and make a note of which ones we got */
 	max_nr_pkey_allocs = NR_PKEYS;
@@ -1278,6 +1277,78 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	}
 }
 
+void arch_force_pkey_reg_init(void)
+{
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+	u64 *buf;
+
+	/*
+	 * All keys should be allocated and set to allow reads and
+	 * writes, so the register should be all 0.  If not, just
+	 * skip the test.
+	 */
+	if (read_pkey_reg())
+		return;
+
+	/*
+	 * Just allocate an absurd about of memory rather than
+	 * doing the XSAVE size enumeration dance.
+	 */
+	buf = mmap(NULL, 1*MB, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+
+	/* These __builtins require compiling with -mxsave */
+
+	/* XSAVE to build a valid buffer: */
+	__builtin_ia32_xsave(buf, XSTATE_PKEY);
+	/* Clear XSTATE_BV[PKRU]: */
+	buf[XSTATE_BV_OFFSET/sizeof(u64)] &= ~XSTATE_PKEY;
+	/* XRSTOR will likely get PKRU back to the init state: */
+	__builtin_ia32_xrstor(buf, XSTATE_PKEY);
+
+	munmap(buf, 1*MB);
+#endif
+}
+
+
+/*
+ * This is mostly useless on ppc for now.  But it will not
+ * hurt anything and should give some better coverage as
+ * a long-running test that continually checks the pkey
+ * register.
+ */
+void test_pkey_init_state(int *ptr, u16 pkey)
+{
+	int err;
+	int allocated_pkeys[NR_PKEYS] = {0};
+	int nr_allocated_pkeys = 0;
+	int i;
+
+	for (i = 0; i < NR_PKEYS; i++) {
+		int new_pkey = alloc_pkey();
+
+		if (new_pkey < 0)
+			continue;
+		allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
+	}
+
+	dprintf3("%s()::%d\n", __func__, __LINE__);
+
+	arch_force_pkey_reg_init();
+
+	/*
+	 * Loop for a bit, hoping to get exercise the kernel
+	 * context switch code.
+	 */
+	for (i = 0; i < 1000000; i++)
+		read_pkey_reg();
+
+	for (i = 0; i < nr_allocated_pkeys; i++) {
+		err = sys_pkey_free(allocated_pkeys[i]);
+		pkey_assert(!err);
+		read_pkey_reg(); /* for shadow checking */
+	}
+}
+
 /*
  * pkey 0 is special.  It is allocated by default, so you do not
  * have to call pkey_alloc() to use it first.  Make sure that it
@@ -1449,6 +1520,13 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
 	ret = mprotect(p1, PAGE_SIZE, PROT_EXEC);
 	pkey_assert(!ret);
 
+	/*
+	 * Reset the shadow, assuming that the above mprotect()
+	 * correctly changed PKRU, but to an unknown value since
+	 * the actual alllocated pkey is unknown.
+	 */
+	shadow_pkey_reg = __read_pkey_reg();
+
 	dprintf2("pkey_reg: %016llx\n", read_pkey_reg());
 
 	/* Make sure this is an *instruction* fault */
@@ -1502,6 +1580,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
 	test_implicit_mprotect_exec_only_memory,
 	test_mprotect_with_pkey_0,
 	test_ptrace_of_child,
+	test_pkey_init_state,
 	test_pkey_syscalls_on_non_allocated_pkey,
 	test_pkey_syscalls_bad_args,
 	test_pkey_alloc_exhaust,
@@ -1552,6 +1631,8 @@ int main(void)
 	int nr_iterations = 22;
 	int pkeys_supported = is_pkeys_supported();
 
+	srand((unsigned int)time(NULL));
+
 	setup_handlers();
 
 	printf("has pkeys: %d\n", pkeys_supported);
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index e953f3cd9664..955782d138ab 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -346,4 +346,20 @@ else
 	exitcode=1
 fi
 
+echo "--------------------------------------------------------"
+echo "running MADV_POPULATE_READ and MADV_POPULATE_WRITE tests"
+echo "--------------------------------------------------------"
+./madv_populate
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+	echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+	echo "[SKIP]"
+	exitcode=$ksft_skip
+else
+	echo "[FAIL]"
+	exitcode=1
+fi
+
 exit $exitcode
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index f5ab5e0312e7..e363bdaff59d 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -85,10 +85,12 @@ static bool test_uffdio_wp = false;
 static bool test_uffdio_minor = false;
 
 static bool map_shared;
+static int shm_fd;
 static int huge_fd;
 static char *huge_fd_off0;
 static unsigned long long *count_verify;
-static int uffd, uffd_flags, finished, *pipefd;
+static int uffd = -1;
+static int uffd_flags, finished, *pipefd;
 static char *area_src, *area_src_alias, *area_dst, *area_dst_alias;
 static char *zeropage;
 pthread_attr_t attr;
@@ -140,11 +142,18 @@ static void usage(void)
 	exit(1);
 }
 
-#define uffd_error(code, fmt, ...)                                             \
-	do {                                                                   \
-		fprintf(stderr, fmt, ##__VA_ARGS__);                           \
-		fprintf(stderr, ": %" PRId64 "\n", (int64_t)(code));           \
-		exit(1);                                                       \
+#define _err(fmt, ...)						\
+	do {							\
+		int ret = errno;				\
+		fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__);	\
+		fprintf(stderr, " (errno=%d, line=%d)\n",	\
+			ret, __LINE__);				\
+	} while (0)
+
+#define err(fmt, ...)				\
+	do {					\
+		_err(fmt, ##__VA_ARGS__);	\
+		exit(1);			\
 	} while (0)
 
 static void uffd_stats_reset(struct uffd_stats *uffd_stats,
@@ -171,56 +180,50 @@ static void uffd_stats_report(struct uffd_stats *stats, int n_cpus)
 		minor_total += stats[i].minor_faults;
 	}
 
-	printf("userfaults: %llu missing (", miss_total);
-	for (i = 0; i < n_cpus; i++)
-		printf("%lu+", stats[i].missing_faults);
-	printf("\b), %llu wp (", wp_total);
-	for (i = 0; i < n_cpus; i++)
-		printf("%lu+", stats[i].wp_faults);
-	printf("\b), %llu minor (", minor_total);
-	for (i = 0; i < n_cpus; i++)
-		printf("%lu+", stats[i].minor_faults);
-	printf("\b)\n");
+	printf("userfaults: ");
+	if (miss_total) {
+		printf("%llu missing (", miss_total);
+		for (i = 0; i < n_cpus; i++)
+			printf("%lu+", stats[i].missing_faults);
+		printf("\b) ");
+	}
+	if (wp_total) {
+		printf("%llu wp (", wp_total);
+		for (i = 0; i < n_cpus; i++)
+			printf("%lu+", stats[i].wp_faults);
+		printf("\b) ");
+	}
+	if (minor_total) {
+		printf("%llu minor (", minor_total);
+		for (i = 0; i < n_cpus; i++)
+			printf("%lu+", stats[i].minor_faults);
+		printf("\b)");
+	}
+	printf("\n");
 }
 
-static int anon_release_pages(char *rel_area)
+static void anon_release_pages(char *rel_area)
 {
-	int ret = 0;
-
-	if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) {
-		perror("madvise");
-		ret = 1;
-	}
-
-	return ret;
+	if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED))
+		err("madvise(MADV_DONTNEED) failed");
 }
 
 static void anon_allocate_area(void **alloc_area)
 {
-	if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) {
-		fprintf(stderr, "out of memory\n");
-		*alloc_area = NULL;
-	}
+	if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
+		err("posix_memalign() failed");
 }
 
 static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
 {
 }
 
-/* HugeTLB memory */
-static int hugetlb_release_pages(char *rel_area)
+static void hugetlb_release_pages(char *rel_area)
 {
-	int ret = 0;
-
 	if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
-				rel_area == huge_fd_off0 ? 0 :
-				nr_pages * page_size,
-				nr_pages * page_size)) {
-		perror("fallocate");
-		ret = 1;
-	}
-
-	return ret;
+		      rel_area == huge_fd_off0 ? 0 : nr_pages * page_size,
+		      nr_pages * page_size))
+		err("fallocate() failed");
 }
 
 static void hugetlb_allocate_area(void **alloc_area)
@@ -233,20 +236,16 @@ static void hugetlb_allocate_area(void **alloc_area)
 			   MAP_HUGETLB,
 			   huge_fd, *alloc_area == area_src ? 0 :
 			   nr_pages * page_size);
-	if (*alloc_area == MAP_FAILED) {
-		perror("mmap of hugetlbfs file failed");
-		goto fail;
-	}
+	if (*alloc_area == MAP_FAILED)
+		err("mmap of hugetlbfs file failed");
 
 	if (map_shared) {
 		area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
 				  MAP_SHARED | MAP_HUGETLB,
 				  huge_fd, *alloc_area == area_src ? 0 :
 				  nr_pages * page_size);
-		if (area_alias == MAP_FAILED) {
-			perror("mmap of hugetlb file alias failed");
-			goto fail_munmap;
-		}
+		if (area_alias == MAP_FAILED)
+			err("mmap of hugetlb file alias failed");
 	}
 
 	if (*alloc_area == area_src) {
@@ -257,16 +256,6 @@ static void hugetlb_allocate_area(void **alloc_area)
 	}
 	if (area_alias)
 		*alloc_area_alias = area_alias;
-
-	return;
-
-fail_munmap:
-	if (munmap(*alloc_area, nr_pages * page_size) < 0) {
-		perror("hugetlb munmap");
-		exit(1);
-	}
-fail:
-	*alloc_area = NULL;
 }
 
 static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset)
@@ -282,33 +271,43 @@ static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset
 	*start = (unsigned long) area_dst_alias + offset;
 }
 
-/* Shared memory */
-static int shmem_release_pages(char *rel_area)
+static void shmem_release_pages(char *rel_area)
 {
-	int ret = 0;
-
-	if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) {
-		perror("madvise");
-		ret = 1;
-	}
-
-	return ret;
+	if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE))
+		err("madvise(MADV_REMOVE) failed");
 }
 
 static void shmem_allocate_area(void **alloc_area)
 {
+	void *area_alias = NULL;
+	bool is_src = alloc_area == (void **)&area_src;
+	unsigned long offset = is_src ? 0 : nr_pages * page_size;
+
 	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
-			   MAP_ANONYMOUS | MAP_SHARED, -1, 0);
-	if (*alloc_area == MAP_FAILED) {
-		fprintf(stderr, "shared memory mmap failed\n");
-		*alloc_area = NULL;
-	}
+			   MAP_SHARED, shm_fd, offset);
+	if (*alloc_area == MAP_FAILED)
+		err("mmap of memfd failed");
+
+	area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+			  MAP_SHARED, shm_fd, offset);
+	if (area_alias == MAP_FAILED)
+		err("mmap of memfd alias failed");
+
+	if (is_src)
+		area_src_alias = area_alias;
+	else
+		area_dst_alias = area_alias;
+}
+
+static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset)
+{
+	*start = (unsigned long)area_dst_alias + offset;
 }
 
 struct uffd_test_ops {
 	unsigned long expected_ioctls;
 	void (*allocate_area)(void **alloc_area);
-	int (*release_pages)(char *rel_area);
+	void (*release_pages)(char *rel_area);
 	void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset);
 };
 
@@ -332,7 +331,7 @@ static struct uffd_test_ops shmem_uffd_test_ops = {
 	.expected_ioctls = SHMEM_EXPECTED_IOCTLS,
 	.allocate_area	= shmem_allocate_area,
 	.release_pages	= shmem_release_pages,
-	.alias_mapping = noop_alias_mapping,
+	.alias_mapping = shmem_alias_mapping,
 };
 
 static struct uffd_test_ops hugetlb_uffd_test_ops = {
@@ -344,6 +343,111 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = {
 
 static struct uffd_test_ops *uffd_test_ops;
 
+static void userfaultfd_open(uint64_t *features)
+{
+	struct uffdio_api uffdio_api;
+
+	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
+	if (uffd < 0)
+		err("userfaultfd syscall not available in this kernel");
+	uffd_flags = fcntl(uffd, F_GETFD, NULL);
+
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = *features;
+	if (ioctl(uffd, UFFDIO_API, &uffdio_api))
+		err("UFFDIO_API failed.\nPlease make sure to "
+		    "run with either root or ptrace capability.");
+	if (uffdio_api.api != UFFD_API)
+		err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api);
+
+	*features = uffdio_api.features;
+}
+
+static inline void munmap_area(void **area)
+{
+	if (*area)
+		if (munmap(*area, nr_pages * page_size))
+			err("munmap");
+
+	*area = NULL;
+}
+
+static void uffd_test_ctx_clear(void)
+{
+	size_t i;
+
+	if (pipefd) {
+		for (i = 0; i < nr_cpus * 2; ++i) {
+			if (close(pipefd[i]))
+				err("close pipefd");
+		}
+		free(pipefd);
+		pipefd = NULL;
+	}
+
+	if (count_verify) {
+		free(count_verify);
+		count_verify = NULL;
+	}
+
+	if (uffd != -1) {
+		if (close(uffd))
+			err("close uffd");
+		uffd = -1;
+	}
+
+	huge_fd_off0 = NULL;
+	munmap_area((void **)&area_src);
+	munmap_area((void **)&area_src_alias);
+	munmap_area((void **)&area_dst);
+	munmap_area((void **)&area_dst_alias);
+}
+
+static void uffd_test_ctx_init_ext(uint64_t *features)
+{
+	unsigned long nr, cpu;
+
+	uffd_test_ctx_clear();
+
+	uffd_test_ops->allocate_area((void **)&area_src);
+	uffd_test_ops->allocate_area((void **)&area_dst);
+
+	uffd_test_ops->release_pages(area_src);
+	uffd_test_ops->release_pages(area_dst);
+
+	userfaultfd_open(features);
+
+	count_verify = malloc(nr_pages * sizeof(unsigned long long));
+	if (!count_verify)
+		err("count_verify");
+
+	for (nr = 0; nr < nr_pages; nr++) {
+		*area_mutex(area_src, nr) =
+			(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER;
+		count_verify[nr] = *area_count(area_src, nr) = 1;
+		/*
+		 * In the transition between 255 to 256, powerpc will
+		 * read out of order in my_bcmp and see both bytes as
+		 * zero, so leave a placeholder below always non-zero
+		 * after the count, to avoid my_bcmp to trigger false
+		 * positives.
+		 */
+		*(area_count(area_src, nr) + 1) = 1;
+	}
+
+	pipefd = malloc(sizeof(int) * nr_cpus * 2);
+	if (!pipefd)
+		err("pipefd");
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK))
+			err("pipe");
+}
+
+static inline void uffd_test_ctx_init(uint64_t features)
+{
+	uffd_test_ctx_init_ext(&features);
+}
+
 static int my_bcmp(char *str1, char *str2, size_t n)
 {
 	unsigned long i;
@@ -363,27 +467,33 @@ static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
 	/* Undo write-protect, do wakeup after that */
 	prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0;
 
-	if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) {
-		fprintf(stderr, "clear WP failed for address 0x%" PRIx64 "\n",
-			(uint64_t)start);
-		exit(1);
-	}
+	if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms))
+		err("clear WP failed: address=0x%"PRIx64, (uint64_t)start);
 }
 
 static void continue_range(int ufd, __u64 start, __u64 len)
 {
 	struct uffdio_continue req;
+	int ret;
 
 	req.range.start = start;
 	req.range.len = len;
 	req.mode = 0;
 
-	if (ioctl(ufd, UFFDIO_CONTINUE, &req)) {
-		fprintf(stderr,
-			"UFFDIO_CONTINUE failed for address 0x%" PRIx64 "\n",
-			(uint64_t)start);
-		exit(1);
-	}
+	if (ioctl(ufd, UFFDIO_CONTINUE, &req))
+		err("UFFDIO_CONTINUE failed for address 0x%" PRIx64,
+		    (uint64_t)start);
+
+	/*
+	 * Error handling within the kernel for continue is subtly different
+	 * from copy or zeropage, so it may be a source of bugs. Trigger an
+	 * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG.
+	 */
+	req.mapped = 0;
+	ret = ioctl(ufd, UFFDIO_CONTINUE, &req);
+	if (ret >= 0 || req.mapped != -EEXIST)
+		err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64,
+		    ret, (int64_t) req.mapped);
 }
 
 static void *locking_thread(void *arg)
@@ -395,7 +505,6 @@ static void *locking_thread(void *arg)
 	unsigned long long count;
 	char randstate[64];
 	unsigned int seed;
-	time_t start;
 
 	if (bounces & BOUNCE_RANDOM) {
 		seed = (unsigned int) time(NULL) - bounces;
@@ -403,10 +512,8 @@ static void *locking_thread(void *arg)
 			seed += cpu;
 		bzero(&rand, sizeof(rand));
 		bzero(&randstate, sizeof(randstate));
-		if (initstate_r(seed, randstate, sizeof(randstate), &rand)) {
-			fprintf(stderr, "srandom_r error\n");
-			exit(1);
-		}
+		if (initstate_r(seed, randstate, sizeof(randstate), &rand))
+			err("initstate_r failed");
 	} else {
 		page_nr = -bounces;
 		if (!(bounces & BOUNCE_RACINGFAULTS))
@@ -415,92 +522,26 @@ static void *locking_thread(void *arg)
 
 	while (!finished) {
 		if (bounces & BOUNCE_RANDOM) {
-			if (random_r(&rand, &rand_nr)) {
-				fprintf(stderr, "random_r 1 error\n");
-				exit(1);
-			}
+			if (random_r(&rand, &rand_nr))
+				err("random_r failed");
 			page_nr = rand_nr;
 			if (sizeof(page_nr) > sizeof(rand_nr)) {
-				if (random_r(&rand, &rand_nr)) {
-					fprintf(stderr, "random_r 2 error\n");
-					exit(1);
-				}
+				if (random_r(&rand, &rand_nr))
+					err("random_r failed");
 				page_nr |= (((unsigned long) rand_nr) << 16) <<
 					   16;
 			}
 		} else
 			page_nr += 1;
 		page_nr %= nr_pages;
-
-		start = time(NULL);
-		if (bounces & BOUNCE_VERIFY) {
-			count = *area_count(area_dst, page_nr);
-			if (!count) {
-				fprintf(stderr,
-					"page_nr %lu wrong count %Lu %Lu\n",
-					page_nr, count,
-					count_verify[page_nr]);
-				exit(1);
-			}
-
-
-			/*
-			 * We can't use bcmp (or memcmp) because that
-			 * returns 0 erroneously if the memory is
-			 * changing under it (even if the end of the
-			 * page is never changing and always
-			 * different).
-			 */
-#if 1
-			if (!my_bcmp(area_dst + page_nr * page_size, zeropage,
-				     page_size)) {
-				fprintf(stderr,
-					"my_bcmp page_nr %lu wrong count %Lu %Lu\n",
-					page_nr, count, count_verify[page_nr]);
-				exit(1);
-			}
-#else
-			unsigned long loops;
-
-			loops = 0;
-			/* uncomment the below line to test with mutex */
-			/* pthread_mutex_lock(area_mutex(area_dst, page_nr)); */
-			while (!bcmp(area_dst + page_nr * page_size, zeropage,
-				     page_size)) {
-				loops += 1;
-				if (loops > 10)
-					break;
-			}
-			/* uncomment below line to test with mutex */
-			/* pthread_mutex_unlock(area_mutex(area_dst, page_nr)); */
-			if (loops) {
-				fprintf(stderr,
-					"page_nr %lu all zero thread %lu %p %lu\n",
-					page_nr, cpu, area_dst + page_nr * page_size,
-					loops);
-				if (loops > 10)
-					exit(1);
-			}
-#endif
-		}
-
 		pthread_mutex_lock(area_mutex(area_dst, page_nr));
 		count = *area_count(area_dst, page_nr);
-		if (count != count_verify[page_nr]) {
-			fprintf(stderr,
-				"page_nr %lu memory corruption %Lu %Lu\n",
-				page_nr, count,
-				count_verify[page_nr]); exit(1);
-		}
+		if (count != count_verify[page_nr])
+			err("page_nr %lu memory corruption %llu %llu",
+			    page_nr, count, count_verify[page_nr]);
 		count++;
 		*area_count(area_dst, page_nr) = count_verify[page_nr] = count;
 		pthread_mutex_unlock(area_mutex(area_dst, page_nr));
-
-		if (time(NULL) - start > 1)
-			fprintf(stderr,
-				"userfault too slow %ld "
-				"possible false positive with overcommit\n",
-				time(NULL) - start);
 	}
 
 	return NULL;
@@ -514,22 +555,21 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
 				     offset);
 	if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) {
 		/* real retval in ufdio_copy.copy */
-		if (uffdio_copy->copy != -EEXIST) {
-			uffd_error(uffdio_copy->copy,
-				   "UFFDIO_COPY retry error");
-		}
-	} else
-		uffd_error(uffdio_copy->copy, "UFFDIO_COPY retry unexpected");
+		if (uffdio_copy->copy != -EEXIST)
+			err("UFFDIO_COPY retry error: %"PRId64,
+			    (int64_t)uffdio_copy->copy);
+	} else {
+		err("UFFDIO_COPY retry unexpected: %"PRId64,
+		    (int64_t)uffdio_copy->copy);
+	}
 }
 
 static int __copy_page(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_copy uffdio_copy;
 
-	if (offset >= nr_pages * page_size) {
-		fprintf(stderr, "unexpected offset %lu\n", offset);
-		exit(1);
-	}
+	if (offset >= nr_pages * page_size)
+		err("unexpected offset %lu\n", offset);
 	uffdio_copy.dst = (unsigned long) area_dst + offset;
 	uffdio_copy.src = (unsigned long) area_src + offset;
 	uffdio_copy.len = page_size;
@@ -541,9 +581,10 @@ static int __copy_page(int ufd, unsigned long offset, bool retry)
 	if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
 		/* real retval in ufdio_copy.copy */
 		if (uffdio_copy.copy != -EEXIST)
-			uffd_error(uffdio_copy.copy, "UFFDIO_COPY error");
+			err("UFFDIO_COPY error: %"PRId64,
+			    (int64_t)uffdio_copy.copy);
 	} else if (uffdio_copy.copy != page_size) {
-		uffd_error(uffdio_copy.copy, "UFFDIO_COPY unexpected copy");
+		err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy);
 	} else {
 		if (test_uffdio_copy_eexist && retry) {
 			test_uffdio_copy_eexist = false;
@@ -572,11 +613,10 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg)
 		if (ret < 0) {
 			if (errno == EAGAIN)
 				return 1;
-			perror("blocking read error");
+			err("blocking read error");
 		} else {
-			fprintf(stderr, "short read\n");
+			err("short read");
 		}
-		exit(1);
 	}
 
 	return 0;
@@ -587,10 +627,8 @@ static void uffd_handle_page_fault(struct uffd_msg *msg,
 {
 	unsigned long offset;
 
-	if (msg->event != UFFD_EVENT_PAGEFAULT) {
-		fprintf(stderr, "unexpected msg event %u\n", msg->event);
-		exit(1);
-	}
+	if (msg->event != UFFD_EVENT_PAGEFAULT)
+		err("unexpected msg event %u", msg->event);
 
 	if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) {
 		/* Write protect page faults */
@@ -621,11 +659,8 @@ static void uffd_handle_page_fault(struct uffd_msg *msg,
 		stats->minor_faults++;
 	} else {
 		/* Missing page faults */
-		if (bounces & BOUNCE_VERIFY &&
-		    msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) {
-			fprintf(stderr, "unexpected write fault\n");
-			exit(1);
-		}
+		if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
+			err("unexpected write fault");
 
 		offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
 		offset &= ~(page_size-1);
@@ -652,32 +687,20 @@ static void *uffd_poll_thread(void *arg)
 
 	for (;;) {
 		ret = poll(pollfd, 2, -1);
-		if (!ret) {
-			fprintf(stderr, "poll error %d\n", ret);
-			exit(1);
-		}
-		if (ret < 0) {
-			perror("poll");
-			exit(1);
-		}
+		if (ret <= 0)
+			err("poll error: %d", ret);
 		if (pollfd[1].revents & POLLIN) {
-			if (read(pollfd[1].fd, &tmp_chr, 1) != 1) {
-				fprintf(stderr, "read pipefd error\n");
-				exit(1);
-			}
+			if (read(pollfd[1].fd, &tmp_chr, 1) != 1)
+				err("read pipefd error");
 			break;
 		}
-		if (!(pollfd[0].revents & POLLIN)) {
-			fprintf(stderr, "pollfd[0].revents %d\n",
-				pollfd[0].revents);
-			exit(1);
-		}
+		if (!(pollfd[0].revents & POLLIN))
+			err("pollfd[0].revents %d", pollfd[0].revents);
 		if (uffd_read_msg(uffd, &msg))
 			continue;
 		switch (msg.event) {
 		default:
-			fprintf(stderr, "unexpected msg event %u\n",
-				msg.event); exit(1);
+			err("unexpected msg event %u\n", msg.event);
 			break;
 		case UFFD_EVENT_PAGEFAULT:
 			uffd_handle_page_fault(&msg, stats);
@@ -691,10 +714,8 @@ static void *uffd_poll_thread(void *arg)
 			uffd_reg.range.start = msg.arg.remove.start;
 			uffd_reg.range.len = msg.arg.remove.end -
 				msg.arg.remove.start;
-			if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) {
-				fprintf(stderr, "remove failure\n");
-				exit(1);
-			}
+			if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range))
+				err("remove failure");
 			break;
 		case UFFD_EVENT_REMAP:
 			area_dst = (char *)(unsigned long)msg.arg.remap.to;
@@ -797,9 +818,7 @@ static int stress(struct uffd_stats *uffd_stats)
 	 * UFFDIO_COPY without writing zero pages into area_dst
 	 * because the background threads already completed).
 	 */
-	if (uffd_test_ops->release_pages(area_src))
-		return 1;
-
+	uffd_test_ops->release_pages(area_src);
 
 	finished = 1;
 	for (cpu = 0; cpu < nr_cpus; cpu++)
@@ -809,10 +828,8 @@ static int stress(struct uffd_stats *uffd_stats)
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		char c;
 		if (bounces & BOUNCE_POLL) {
-			if (write(pipefd[cpu*2+1], &c, 1) != 1) {
-				fprintf(stderr, "pipefd write error\n");
-				return 1;
-			}
+			if (write(pipefd[cpu*2+1], &c, 1) != 1)
+				err("pipefd write error");
 			if (pthread_join(uffd_threads[cpu],
 					 (void *)&uffd_stats[cpu]))
 				return 1;
@@ -827,40 +844,6 @@ static int stress(struct uffd_stats *uffd_stats)
 	return 0;
 }
 
-static int userfaultfd_open_ext(uint64_t *features)
-{
-	struct uffdio_api uffdio_api;
-
-	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
-	if (uffd < 0) {
-		fprintf(stderr,
-			"userfaultfd syscall not available in this kernel\n");
-		return 1;
-	}
-	uffd_flags = fcntl(uffd, F_GETFD, NULL);
-
-	uffdio_api.api = UFFD_API;
-	uffdio_api.features = *features;
-	if (ioctl(uffd, UFFDIO_API, &uffdio_api)) {
-		fprintf(stderr, "UFFDIO_API failed.\nPlease make sure to "
-			"run with either root or ptrace capability.\n");
-		return 1;
-	}
-	if (uffdio_api.api != UFFD_API) {
-		fprintf(stderr, "UFFDIO_API error: %" PRIu64 "\n",
-			(uint64_t)uffdio_api.api);
-		return 1;
-	}
-
-	*features = uffdio_api.features;
-	return 0;
-}
-
-static int userfaultfd_open(uint64_t features)
-{
-	return userfaultfd_open_ext(&features);
-}
-
 sigjmp_buf jbuf, *sigbuf;
 
 static void sighndl(int sig, siginfo_t *siginfo, void *ptr)
@@ -912,10 +895,8 @@ static int faulting_process(int signal_test)
 		memset(&act, 0, sizeof(act));
 		act.sa_sigaction = sighndl;
 		act.sa_flags = SA_SIGINFO;
-		if (sigaction(SIGBUS, &act, 0)) {
-			perror("sigaction");
-			return 1;
-		}
+		if (sigaction(SIGBUS, &act, 0))
+			err("sigaction");
 		lastnr = (unsigned long)-1;
 	}
 
@@ -925,10 +906,8 @@ static int faulting_process(int signal_test)
 
 		if (signal_test) {
 			if (sigsetjmp(*sigbuf, 1) != 0) {
-				if (steps == 1 && nr == lastnr) {
-					fprintf(stderr, "Signal repeated\n");
-					return 1;
-				}
+				if (steps == 1 && nr == lastnr)
+					err("Signal repeated");
 
 				lastnr = nr;
 				if (signal_test == 1) {
@@ -953,12 +932,9 @@ static int faulting_process(int signal_test)
 		}
 
 		count = *area_count(area_dst, nr);
-		if (count != count_verify[nr]) {
-			fprintf(stderr,
-				"nr %lu memory corruption %Lu %Lu\n",
-				nr, count,
-				count_verify[nr]);
-	        }
+		if (count != count_verify[nr])
+			err("nr %lu memory corruption %llu %llu\n",
+			    nr, count, count_verify[nr]);
 		/*
 		 * Trigger write protection if there is by writing
 		 * the same value back.
@@ -974,18 +950,16 @@ static int faulting_process(int signal_test)
 
 	area_dst = mremap(area_dst, nr_pages * page_size,  nr_pages * page_size,
 			  MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
-	if (area_dst == MAP_FAILED) {
-		perror("mremap");
-		exit(1);
-	}
+	if (area_dst == MAP_FAILED)
+		err("mremap");
+	/* Reset area_src since we just clobbered it */
+	area_src = NULL;
 
 	for (; nr < nr_pages; nr++) {
 		count = *area_count(area_dst, nr);
 		if (count != count_verify[nr]) {
-			fprintf(stderr,
-				"nr %lu memory corruption %Lu %Lu\n",
-				nr, count,
-				count_verify[nr]); exit(1);
+			err("nr %lu memory corruption %llu %llu\n",
+			    nr, count, count_verify[nr]);
 		}
 		/*
 		 * Trigger write protection if there is by writing
@@ -994,15 +968,11 @@ static int faulting_process(int signal_test)
 		*area_count(area_dst, nr) = count;
 	}
 
-	if (uffd_test_ops->release_pages(area_dst))
-		return 1;
+	uffd_test_ops->release_pages(area_dst);
 
-	for (nr = 0; nr < nr_pages; nr++) {
-		if (my_bcmp(area_dst + nr * page_size, zeropage, page_size)) {
-			fprintf(stderr, "nr %lu is not zero\n", nr);
-			exit(1);
-		}
-	}
+	for (nr = 0; nr < nr_pages; nr++)
+		if (my_bcmp(area_dst + nr * page_size, zeropage, page_size))
+			err("nr %lu is not zero", nr);
 
 	return 0;
 }
@@ -1015,13 +985,12 @@ static void retry_uffdio_zeropage(int ufd,
 				     uffdio_zeropage->range.len,
 				     offset);
 	if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
-		if (uffdio_zeropage->zeropage != -EEXIST) {
-			uffd_error(uffdio_zeropage->zeropage,
-				   "UFFDIO_ZEROPAGE retry error");
-		}
+		if (uffdio_zeropage->zeropage != -EEXIST)
+			err("UFFDIO_ZEROPAGE error: %"PRId64,
+			    (int64_t)uffdio_zeropage->zeropage);
 	} else {
-		uffd_error(uffdio_zeropage->zeropage,
-			   "UFFDIO_ZEROPAGE retry unexpected");
+		err("UFFDIO_ZEROPAGE error: %"PRId64,
+		    (int64_t)uffdio_zeropage->zeropage);
 	}
 }
 
@@ -1034,10 +1003,8 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 
 	has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE);
 
-	if (offset >= nr_pages * page_size) {
-		fprintf(stderr, "unexpected offset %lu\n", offset);
-		exit(1);
-	}
+	if (offset >= nr_pages * page_size)
+		err("unexpected offset %lu", offset);
 	uffdio_zeropage.range.start = (unsigned long) area_dst + offset;
 	uffdio_zeropage.range.len = page_size;
 	uffdio_zeropage.mode = 0;
@@ -1045,14 +1012,13 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 	res = uffdio_zeropage.zeropage;
 	if (ret) {
 		/* real retval in ufdio_zeropage.zeropage */
-		if (has_zeropage) {
-			uffd_error(res, "UFFDIO_ZEROPAGE %s",
-				   res == -EEXIST ? "-EEXIST" : "error");
-		} else if (res != -EINVAL)
-			uffd_error(res, "UFFDIO_ZEROPAGE not -EINVAL");
+		if (has_zeropage)
+			err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res);
+		else if (res != -EINVAL)
+			err("UFFDIO_ZEROPAGE not -EINVAL");
 	} else if (has_zeropage) {
 		if (res != page_size) {
-			uffd_error(res, "UFFDIO_ZEROPAGE unexpected");
+			err("UFFDIO_ZEROPAGE unexpected size");
 		} else {
 			if (test_uffdio_zeropage_eexist && retry) {
 				test_uffdio_zeropage_eexist = false;
@@ -1062,7 +1028,7 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 			return 1;
 		}
 	} else
-		uffd_error(res, "UFFDIO_ZEROPAGE succeeded");
+		err("UFFDIO_ZEROPAGE succeeded");
 
 	return 0;
 }
@@ -1081,37 +1047,24 @@ static int userfaultfd_zeropage_test(void)
 	printf("testing UFFDIO_ZEROPAGE: ");
 	fflush(stdout);
 
-	if (uffd_test_ops->release_pages(area_dst))
-		return 1;
+	uffd_test_ctx_init(0);
 
-	if (userfaultfd_open(0))
-		return 1;
 	uffdio_register.range.start = (unsigned long) area_dst;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
 	if (test_uffdio_wp)
 		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
-		fprintf(stderr, "register failure\n");
-		exit(1);
-	}
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+		err("register failure");
 
 	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) !=
-	    expected_ioctls) {
-		fprintf(stderr,
-			"unexpected missing ioctl for anon memory\n");
-		exit(1);
-	}
+	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
+		err("unexpected missing ioctl for anon memory");
 
-	if (uffdio_zeropage(uffd, 0)) {
-		if (my_bcmp(area_dst, zeropage, page_size)) {
-			fprintf(stderr, "zeropage is not zero\n");
-			exit(1);
-		}
-	}
+	if (uffdio_zeropage(uffd, 0))
+		if (my_bcmp(area_dst, zeropage, page_size))
+			err("zeropage is not zero");
 
-	close(uffd);
 	printf("done.\n");
 	return 0;
 }
@@ -1129,13 +1082,10 @@ static int userfaultfd_events_test(void)
 	printf("testing events (fork, remap, remove): ");
 	fflush(stdout);
 
-	if (uffd_test_ops->release_pages(area_dst))
-		return 1;
-
 	features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
 		UFFD_FEATURE_EVENT_REMOVE;
-	if (userfaultfd_open(features))
-		return 1;
+	uffd_test_ctx_init(features);
+
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
 	uffdio_register.range.start = (unsigned long) area_dst;
@@ -1143,46 +1093,31 @@ static int userfaultfd_events_test(void)
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
 	if (test_uffdio_wp)
 		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
-		fprintf(stderr, "register failure\n");
-		exit(1);
-	}
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+		err("register failure");
 
 	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) {
-		fprintf(stderr, "unexpected missing ioctl for anon memory\n");
-		exit(1);
-	}
+	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
+		err("unexpected missing ioctl for anon memory");
 
-	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) {
-		perror("uffd_poll_thread create");
-		exit(1);
-	}
+	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
+		err("uffd_poll_thread create");
 
 	pid = fork();
-	if (pid < 0) {
-		perror("fork");
-		exit(1);
-	}
+	if (pid < 0)
+		err("fork");
 
 	if (!pid)
 		exit(faulting_process(0));
 
 	waitpid(pid, &err, 0);
-	if (err) {
-		fprintf(stderr, "faulting process failed\n");
-		exit(1);
-	}
-
-	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) {
-		perror("pipe write");
-		exit(1);
-	}
+	if (err)
+		err("faulting process failed");
+	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+		err("pipe write");
 	if (pthread_join(uffd_mon, NULL))
 		return 1;
 
-	close(uffd);
-
 	uffd_stats_report(&stats, 1);
 
 	return stats.missing_faults != nr_pages;
@@ -1202,12 +1137,9 @@ static int userfaultfd_sig_test(void)
 	printf("testing signal delivery: ");
 	fflush(stdout);
 
-	if (uffd_test_ops->release_pages(area_dst))
-		return 1;
-
 	features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS;
-	if (userfaultfd_open(features))
-		return 1;
+	uffd_test_ctx_init(features);
+
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
 	uffdio_register.range.start = (unsigned long) area_dst;
@@ -1215,57 +1147,40 @@ static int userfaultfd_sig_test(void)
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
 	if (test_uffdio_wp)
 		uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
-		fprintf(stderr, "register failure\n");
-		exit(1);
-	}
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+		err("register failure");
 
 	expected_ioctls = uffd_test_ops->expected_ioctls;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) {
-		fprintf(stderr, "unexpected missing ioctl for anon memory\n");
-		exit(1);
-	}
+	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
+		err("unexpected missing ioctl for anon memory");
 
-	if (faulting_process(1)) {
-		fprintf(stderr, "faulting process failed\n");
-		exit(1);
-	}
+	if (faulting_process(1))
+		err("faulting process failed");
 
-	if (uffd_test_ops->release_pages(area_dst))
-		return 1;
+	uffd_test_ops->release_pages(area_dst);
 
-	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) {
-		perror("uffd_poll_thread create");
-		exit(1);
-	}
+	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
+		err("uffd_poll_thread create");
 
 	pid = fork();
-	if (pid < 0) {
-		perror("fork");
-		exit(1);
-	}
+	if (pid < 0)
+		err("fork");
 
 	if (!pid)
 		exit(faulting_process(2));
 
 	waitpid(pid, &err, 0);
-	if (err) {
-		fprintf(stderr, "faulting process failed\n");
-		exit(1);
-	}
-
-	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) {
-		perror("pipe write");
-		exit(1);
-	}
+	if (err)
+		err("faulting process failed");
+	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+		err("pipe write");
 	if (pthread_join(uffd_mon, (void **)&userfaults))
 		return 1;
 
 	printf("done.\n");
 	if (userfaults)
-		fprintf(stderr, "Signal test failed, userfaults: %ld\n",
-			userfaults);
-	close(uffd);
+		err("Signal test failed, userfaults: %ld", userfaults);
+
 	return userfaults != 0;
 }
 
@@ -1279,7 +1194,7 @@ static int userfaultfd_minor_test(void)
 	void *expected_page;
 	char c;
 	struct uffd_stats stats = { 0 };
-	uint64_t features = UFFD_FEATURE_MINOR_HUGETLBFS;
+	uint64_t req_features, features_out;
 
 	if (!test_uffdio_minor)
 		return 0;
@@ -1287,13 +1202,17 @@ static int userfaultfd_minor_test(void)
 	printf("testing minor faults: ");
 	fflush(stdout);
 
-	if (uffd_test_ops->release_pages(area_dst))
+	if (test_type == TEST_HUGETLB)
+		req_features = UFFD_FEATURE_MINOR_HUGETLBFS;
+	else if (test_type == TEST_SHMEM)
+		req_features = UFFD_FEATURE_MINOR_SHMEM;
+	else
 		return 1;
 
-	if (userfaultfd_open_ext(&features))
-		return 1;
-	/* If kernel reports the feature isn't supported, skip the test. */
-	if (!(features & UFFD_FEATURE_MINOR_HUGETLBFS)) {
+	features_out = req_features;
+	uffd_test_ctx_init_ext(&features_out);
+	/* If kernel reports required features aren't supported, skip test. */
+	if ((features_out & req_features) != req_features) {
 		printf("skipping test due to lack of feature support\n");
 		fflush(stdout);
 		return 0;
@@ -1302,17 +1221,13 @@ static int userfaultfd_minor_test(void)
 	uffdio_register.range.start = (unsigned long)area_dst_alias;
 	uffdio_register.range.len = nr_pages * page_size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR;
-	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
-		fprintf(stderr, "register failure\n");
-		exit(1);
-	}
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+		err("register failure");
 
 	expected_ioctls = uffd_test_ops->expected_ioctls;
 	expected_ioctls |= 1 << _UFFDIO_CONTINUE;
-	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) {
-		fprintf(stderr, "unexpected missing ioctl(s)\n");
-		exit(1);
-	}
+	if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls)
+		err("unexpected missing ioctl(s)");
 
 	/*
 	 * After registering with UFFD, populate the non-UFFD-registered side of
@@ -1323,10 +1238,8 @@ static int userfaultfd_minor_test(void)
 		       page_size);
 	}
 
-	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) {
-		perror("uffd_poll_thread create");
-		exit(1);
-	}
+	if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats))
+		err("uffd_poll_thread create");
 
 	/*
 	 * Read each of the pages back using the UFFD-registered mapping. We
@@ -1335,92 +1248,173 @@ static int userfaultfd_minor_test(void)
 	 * page's contents, and then issuing a CONTINUE ioctl.
 	 */
 
-	if (posix_memalign(&expected_page, page_size, page_size)) {
-		fprintf(stderr, "out of memory\n");
-		return 1;
-	}
+	if (posix_memalign(&expected_page, page_size, page_size))
+		err("out of memory");
 
 	for (p = 0; p < nr_pages; ++p) {
 		expected_byte = ~((uint8_t)(p % ((uint8_t)-1)));
 		memset(expected_page, expected_byte, page_size);
 		if (my_bcmp(expected_page, area_dst_alias + (p * page_size),
-			    page_size)) {
-			fprintf(stderr,
-				"unexpected page contents after minor fault\n");
-			exit(1);
-		}
+			    page_size))
+			err("unexpected page contents after minor fault");
 	}
 
-	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) {
-		perror("pipe write");
-		exit(1);
-	}
+	if (write(pipefd[1], &c, sizeof(c)) != sizeof(c))
+		err("pipe write");
 	if (pthread_join(uffd_mon, NULL))
 		return 1;
 
-	close(uffd);
-
 	uffd_stats_report(&stats, 1);
 
 	return stats.missing_faults != 0 || stats.minor_faults != nr_pages;
 }
 
-static int userfaultfd_stress(void)
+#define BIT_ULL(nr)                   (1ULL << (nr))
+#define PM_SOFT_DIRTY                 BIT_ULL(55)
+#define PM_MMAP_EXCLUSIVE             BIT_ULL(56)
+#define PM_UFFD_WP                    BIT_ULL(57)
+#define PM_FILE                       BIT_ULL(61)
+#define PM_SWAP                       BIT_ULL(62)
+#define PM_PRESENT                    BIT_ULL(63)
+
+static int pagemap_open(void)
 {
-	void *area;
-	char *tmp_area;
-	unsigned long nr;
-	struct uffdio_register uffdio_register;
-	unsigned long cpu;
-	int err;
-	struct uffd_stats uffd_stats[nr_cpus];
+	int fd = open("/proc/self/pagemap", O_RDONLY);
 
-	uffd_test_ops->allocate_area((void **)&area_src);
-	if (!area_src)
-		return 1;
-	uffd_test_ops->allocate_area((void **)&area_dst);
-	if (!area_dst)
-		return 1;
+	if (fd < 0)
+		err("open pagemap");
 
-	if (userfaultfd_open(0))
-		return 1;
+	return fd;
+}
 
-	count_verify = malloc(nr_pages * sizeof(unsigned long long));
-	if (!count_verify) {
-		perror("count_verify");
-		return 1;
-	}
+static uint64_t pagemap_read_vaddr(int fd, void *vaddr)
+{
+	uint64_t value;
+	int ret;
 
-	for (nr = 0; nr < nr_pages; nr++) {
-		*area_mutex(area_src, nr) = (pthread_mutex_t)
-			PTHREAD_MUTEX_INITIALIZER;
-		count_verify[nr] = *area_count(area_src, nr) = 1;
+	ret = pread(fd, &value, sizeof(uint64_t),
+		    ((uint64_t)vaddr >> 12) * sizeof(uint64_t));
+	if (ret != sizeof(uint64_t))
+		err("pread() on pagemap failed");
+
+	return value;
+}
+
+/* This macro let __LINE__ works in err() */
+#define  pagemap_check_wp(value, wp) do {				\
+		if (!!(value & PM_UFFD_WP) != wp)			\
+			err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \
+	} while (0)
+
+static int pagemap_test_fork(bool present)
+{
+	pid_t child = fork();
+	uint64_t value;
+	int fd, result;
+
+	if (!child) {
+		/* Open the pagemap fd of the child itself */
+		fd = pagemap_open();
+		value = pagemap_read_vaddr(fd, area_dst);
 		/*
-		 * In the transition between 255 to 256, powerpc will
-		 * read out of order in my_bcmp and see both bytes as
-		 * zero, so leave a placeholder below always non-zero
-		 * after the count, to avoid my_bcmp to trigger false
-		 * positives.
+		 * After fork() uffd-wp bit should be gone as long as we're
+		 * without UFFD_FEATURE_EVENT_FORK
 		 */
-		*(area_count(area_src, nr) + 1) = 1;
+		pagemap_check_wp(value, false);
+		/* Succeed */
+		exit(0);
 	}
+	waitpid(child, &result, 0);
+	return result;
+}
 
-	pipefd = malloc(sizeof(int) * nr_cpus * 2);
-	if (!pipefd) {
-		perror("pipefd");
-		return 1;
-	}
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (pipe2(&pipefd[cpu*2], O_CLOEXEC | O_NONBLOCK)) {
-			perror("pipe");
-			return 1;
-		}
-	}
+static void userfaultfd_pagemap_test(unsigned int test_pgsize)
+{
+	struct uffdio_register uffdio_register;
+	int pagemap_fd;
+	uint64_t value;
 
-	if (posix_memalign(&area, page_size, page_size)) {
-		fprintf(stderr, "out of memory\n");
-		return 1;
+	/* Pagemap tests uffd-wp only */
+	if (!test_uffdio_wp)
+		return;
+
+	/* Not enough memory to test this page size */
+	if (test_pgsize > nr_pages * page_size)
+		return;
+
+	printf("testing uffd-wp with pagemap (pgsize=%u): ", test_pgsize);
+	/* Flush so it doesn't flush twice in parent/child later */
+	fflush(stdout);
+
+	uffd_test_ctx_init(0);
+
+	if (test_pgsize > page_size) {
+		/* This is a thp test */
+		if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE))
+			err("madvise(MADV_HUGEPAGE) failed");
+	} else if (test_pgsize == page_size) {
+		/* This is normal page test; force no thp */
+		if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE))
+			err("madvise(MADV_NOHUGEPAGE) failed");
 	}
+
+	uffdio_register.range.start = (unsigned long) area_dst;
+	uffdio_register.range.len = nr_pages * page_size;
+	uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+		err("register failed");
+
+	pagemap_fd = pagemap_open();
+
+	/* Touch the page */
+	*area_dst = 1;
+	wp_range(uffd, (uint64_t)area_dst, test_pgsize, true);
+	value = pagemap_read_vaddr(pagemap_fd, area_dst);
+	pagemap_check_wp(value, true);
+	/* Make sure uffd-wp bit dropped when fork */
+	if (pagemap_test_fork(true))
+		err("Detected stall uffd-wp bit in child");
+
+	/* Exclusive required or PAGEOUT won't work */
+	if (!(value & PM_MMAP_EXCLUSIVE))
+		err("multiple mapping detected: 0x%"PRIx64, value);
+
+	if (madvise(area_dst, test_pgsize, MADV_PAGEOUT))
+		err("madvise(MADV_PAGEOUT) failed");
+
+	/* Uffd-wp should persist even swapped out */
+	value = pagemap_read_vaddr(pagemap_fd, area_dst);
+	pagemap_check_wp(value, true);
+	/* Make sure uffd-wp bit dropped when fork */
+	if (pagemap_test_fork(false))
+		err("Detected stall uffd-wp bit in child");
+
+	/* Unprotect; this tests swap pte modifications */
+	wp_range(uffd, (uint64_t)area_dst, page_size, false);
+	value = pagemap_read_vaddr(pagemap_fd, area_dst);
+	pagemap_check_wp(value, false);
+
+	/* Fault in the page from disk */
+	*area_dst = 2;
+	value = pagemap_read_vaddr(pagemap_fd, area_dst);
+	pagemap_check_wp(value, false);
+
+	close(pagemap_fd);
+	printf("done\n");
+}
+
+static int userfaultfd_stress(void)
+{
+	void *area;
+	char *tmp_area;
+	unsigned long nr;
+	struct uffdio_register uffdio_register;
+	struct uffd_stats uffd_stats[nr_cpus];
+
+	uffd_test_ctx_init(0);
+
+	if (posix_memalign(&area, page_size, page_size))
+		err("out of memory");
 	zeropage = area;
 	bzero(zeropage, page_size);
 
@@ -1429,7 +1423,6 @@ static int userfaultfd_stress(void)
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
-	err = 0;
 	while (bounces--) {
 		unsigned long expected_ioctls;
 
@@ -1458,25 +1451,18 @@ static int userfaultfd_stress(void)
 		uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
 		if (test_uffdio_wp)
 			uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP;
-		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
-			fprintf(stderr, "register failure\n");
-			return 1;
-		}
+		if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+			err("register failure");
 		expected_ioctls = uffd_test_ops->expected_ioctls;
 		if ((uffdio_register.ioctls & expected_ioctls) !=
-		    expected_ioctls) {
-			fprintf(stderr,
-				"unexpected missing ioctl for anon memory\n");
-			return 1;
-		}
+		    expected_ioctls)
+			err("unexpected missing ioctl for anon memory");
 
 		if (area_dst_alias) {
 			uffdio_register.range.start = (unsigned long)
 				area_dst_alias;
-			if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) {
-				fprintf(stderr, "register failure alias\n");
-				return 1;
-			}
+			if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register))
+				err("register failure alias");
 		}
 
 		/*
@@ -1503,8 +1489,7 @@ static int userfaultfd_stress(void)
 		 * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's
 		 * required to MADV_DONTNEED here.
 		 */
-		if (uffd_test_ops->release_pages(area_dst))
-			return 1;
+		uffd_test_ops->release_pages(area_dst);
 
 		uffd_stats_reset(uffd_stats, nr_cpus);
 
@@ -1518,33 +1503,22 @@ static int userfaultfd_stress(void)
 				 nr_pages * page_size, false);
 
 		/* unregister */
-		if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) {
-			fprintf(stderr, "unregister failure\n");
-			return 1;
-		}
+		if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range))
+			err("unregister failure");
 		if (area_dst_alias) {
 			uffdio_register.range.start = (unsigned long) area_dst;
 			if (ioctl(uffd, UFFDIO_UNREGISTER,
-				  &uffdio_register.range)) {
-				fprintf(stderr, "unregister failure alias\n");
-				return 1;
-			}
+				  &uffdio_register.range))
+				err("unregister failure alias");
 		}
 
 		/* verification */
-		if (bounces & BOUNCE_VERIFY) {
-			for (nr = 0; nr < nr_pages; nr++) {
-				if (*area_count(area_dst, nr) != count_verify[nr]) {
-					fprintf(stderr,
-						"error area_count %Lu %Lu %lu\n",
-						*area_count(area_src, nr),
-						count_verify[nr],
-						nr);
-					err = 1;
-					bounces = 0;
-				}
-			}
-		}
+		if (bounces & BOUNCE_VERIFY)
+			for (nr = 0; nr < nr_pages; nr++)
+				if (*area_count(area_dst, nr) != count_verify[nr])
+					err("error area_count %llu %llu %lu\n",
+					    *area_count(area_src, nr),
+					    count_verify[nr], nr);
 
 		/* prepare next bounce */
 		tmp_area = area_src;
@@ -1558,10 +1532,21 @@ static int userfaultfd_stress(void)
 		uffd_stats_report(uffd_stats, nr_cpus);
 	}
 
-	if (err)
-		return err;
+	if (test_type == TEST_ANON) {
+		/*
+		 * shmem/hugetlb won't be able to run since they have different
+		 * behavior on fork() (file-backed memory normally drops ptes
+		 * directly when fork), meanwhile the pagemap test will verify
+		 * pgtable entry of fork()ed child.
+		 */
+		userfaultfd_pagemap_test(page_size);
+		/*
+		 * Hard-code for x86_64 for now for 2M THP, as x86_64 is
+		 * currently the only one that supports uffd-wp
+		 */
+		userfaultfd_pagemap_test(page_size * 512);
+	}
 
-	close(uffd);
 	return userfaultfd_zeropage_test() || userfaultfd_sig_test()
 		|| userfaultfd_events_test() || userfaultfd_minor_test();
 }
@@ -1610,8 +1595,9 @@ static void set_test_type(const char *type)
 		map_shared = true;
 		test_type = TEST_SHMEM;
 		uffd_test_ops = &shmem_uffd_test_ops;
+		test_uffdio_minor = true;
 	} else {
-		fprintf(stderr, "Unknown test type: %s\n", type); exit(1);
+		err("Unknown test type: %s", type);
 	}
 
 	if (test_type == TEST_HUGETLB)
@@ -1619,15 +1605,11 @@ static void set_test_type(const char *type)
 	else
 		page_size = sysconf(_SC_PAGE_SIZE);
 
-	if (!page_size) {
-		fprintf(stderr, "Unable to determine page size\n");
-		exit(2);
-	}
+	if (!page_size)
+		err("Unable to determine page size");
 	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
-	    > page_size) {
-		fprintf(stderr, "Impossible to run this test\n");
-		exit(2);
-	}
+	    > page_size)
+		err("Impossible to run this test");
 }
 
 static void sigalrm(int sig)
@@ -1644,10 +1626,8 @@ int main(int argc, char **argv)
 	if (argc < 4)
 		usage();
 
-	if (signal(SIGALRM, sigalrm) == SIG_ERR) {
-		fprintf(stderr, "failed to arm SIGALRM");
-		exit(1);
-	}
+	if (signal(SIGALRM, sigalrm) == SIG_ERR)
+		err("failed to arm SIGALRM");
 	alarm(ALARM_INTERVAL_SECS);
 
 	set_test_type(argv[1]);
@@ -1656,13 +1636,13 @@ int main(int argc, char **argv)
 	nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size /
 		nr_cpus;
 	if (!nr_pages_per_cpu) {
-		fprintf(stderr, "invalid MiB\n");
+		_err("invalid MiB");
 		usage();
 	}
 
 	bounces = atoi(argv[3]);
 	if (bounces <= 0) {
-		fprintf(stderr, "invalid bounces\n");
+		_err("invalid bounces");
 		usage();
 	}
 	nr_pages = nr_pages_per_cpu * nr_cpus;
@@ -1671,16 +1651,20 @@ int main(int argc, char **argv)
 		if (argc < 5)
 			usage();
 		huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755);
-		if (huge_fd < 0) {
-			fprintf(stderr, "Open of %s failed", argv[3]);
-			perror("open");
-			exit(1);
-		}
-		if (ftruncate(huge_fd, 0)) {
-			fprintf(stderr, "ftruncate %s to size 0 failed", argv[3]);
-			perror("ftruncate");
-			exit(1);
-		}
+		if (huge_fd < 0)
+			err("Open of %s failed", argv[4]);
+		if (ftruncate(huge_fd, 0))
+			err("ftruncate %s to size 0 failed", argv[4]);
+	} else if (test_type == TEST_SHMEM) {
+		shm_fd = memfd_create(argv[0], 0);
+		if (shm_fd < 0)
+			err("memfd_create");
+		if (ftruncate(shm_fd, nr_pages * page_size * 2))
+			err("ftruncate");
+		if (fallocate(shm_fd,
+			      FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0,
+			      nr_pages * page_size * 2))
+			err("fallocate");
 	}
 	printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
 	       nr_pages, nr_pages_per_cpu);