Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few random little subsystems

 - almost all of the MM patches which are staged ahead of linux-next
   material. I'll trickle to post-linux-next work in as the dependents
   get merged up.

Subsystems affected by this patch series: kthread, kbuild, ide, ntfs,
ocfs2, arch, and mm (slab-generic, slab, slub, dax, debug, pagecache,
gup, swap, shmem, memcg, pagemap, mremap, hmm, vmalloc, documentation,
kasan, pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction,
oom-kill, migration, cma, page-poison, userfaultfd, zswap, zsmalloc,
uaccess, zram, and cleanups).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (200 commits)
  mm: cleanup kstrto*() usage
  mm: fix fall-through warnings for Clang
  mm: slub: convert sysfs sprintf family to sysfs_emit/sysfs_emit_at
  mm: shmem: convert shmem_enabled_show to use sysfs_emit_at
  mm:backing-dev: use sysfs_emit in macro defining functions
  mm: huge_memory: convert remaining use of sprintf to sysfs_emit and neatening
  mm: use sysfs_emit for struct kobject * uses
  mm: fix kernel-doc markups
  zram: break the strict dependency from lzo
  zram: add stat to gather incompressible pages since zram set up
  zram: support page writeback
  mm/process_vm_access: remove redundant initialization of iov_r
  mm/zsmalloc.c: rework the list_add code in insert_zspage()
  mm/zswap: move to use crypto_acomp API for hardware acceleration
  mm/zswap: fix passing zero to 'PTR_ERR' warning
  mm/zswap: make struct kernel_param_ops definitions const
  userfaultfd/selftests: hint the test runner on required privilege
  userfaultfd/selftests: fix retval check for userfaultfd_open()
  userfaultfd/selftests: always dump something in modes
  userfaultfd: selftests: make __{s,u}64 format specifiers portable
  ...

10 files changed, 688 insertions, 216 deletions

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 849e8226395a..9a35c3f6a557 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -8,6 +8,7 @@ thuge-gen
 compaction_test
 mlock2-tests
 mremap_dontunmap
+mremap_test
 on-fault-limit
 transhuge-stress
 protection_keys
@@ -15,8 +16,9 @@ userfaultfd
 mlock-intersect-test
 mlock-random-test
 virtual_address_range
-gup_benchmark
+gup_test
 va_128TBswitch
 map_fixed_noreplace
 write_to_hugetlbfs
 hmm-tests
+local_config.*
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 691893afc15d..9a25307f6115 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for vm selftests
+
+include local_config.mk
+
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
 
@@ -21,23 +24,24 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
 MAKEFLAGS += --no-builtin-rules
 
 CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
-LDLIBS = -lrt
+LDLIBS = -lrt -lpthread
 TEST_GEN_FILES = compaction_test
-TEST_GEN_FILES += gup_benchmark
+TEST_GEN_FILES += gup_test
 TEST_GEN_FILES += hmm-tests
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-shm
-TEST_GEN_FILES += map_hugetlb
+TEST_GEN_FILES += khugepaged
 TEST_GEN_FILES += map_fixed_noreplace
+TEST_GEN_FILES += map_hugetlb
 TEST_GEN_FILES += map_populate
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += mlock2-tests
 TEST_GEN_FILES += mremap_dontunmap
+TEST_GEN_FILES += mremap_test
 TEST_GEN_FILES += on-fault-limit
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
-TEST_GEN_FILES += khugepaged
 
 ifeq ($(ARCH),x86_64)
 CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
@@ -73,15 +77,13 @@ TEST_GEN_FILES += virtual_address_range
 TEST_GEN_FILES += write_to_hugetlbfs
 endif
 
-TEST_PROGS := run_vmtests
+TEST_PROGS := run_vmtests.sh
 
 TEST_FILES := test_vmalloc.sh
 
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
-$(OUTPUT)/hmm-tests: LDLIBS += -lhugetlbfs -lpthread
-
 ifeq ($(ARCH),x86_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
@@ -131,6 +133,25 @@ warn_32bit_failure:
 endif
 endif
 
-$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
-
 $(OUTPUT)/mlock-random-test: LDLIBS += -lcap
+
+$(OUTPUT)/gup_test: ../../../../mm/gup_test.h
+
+$(OUTPUT)/hmm-tests: local_config.h
+
+# HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty.
+$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS)
+
+local_config.mk local_config.h: check_config.sh
+	/bin/sh ./check_config.sh $(CC)
+
+EXTRA_CLEAN += local_config.mk local_config.h
+
+ifeq ($(HMM_EXTRA_LIBS),)
+all: warn_missing_hugelibs
+
+warn_missing_hugelibs:
+	@echo ; \
+	echo "Warning: missing libhugetlbfs support. Some HMM tests will be skipped." ; \
+	echo
+endif
diff --git a/tools/testing/selftests/vm/check_config.sh b/tools/testing/selftests/vm/check_config.sh
new file mode 100644
index 000000000000..079c8a40b85d
--- /dev/null
+++ b/tools/testing/selftests/vm/check_config.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Probe for libraries and create header files to record the results. Both C
+# header files and Makefile include fragments are created.
+
+OUTPUT_H_FILE=local_config.h
+OUTPUT_MKFILE=local_config.mk
+
+# libhugetlbfs
+tmpname=$(mktemp)
+tmpfile_c=${tmpname}.c
+tmpfile_o=${tmpname}.o
+
+echo "#include <sys/types.h>"        > $tmpfile_c
+echo "#include <hugetlbfs.h>"       >> $tmpfile_c
+echo "int func(void) { return 0; }" >> $tmpfile_c
+
+CC=${1:?"Usage: $0 <compiler> # example compiler: gcc"}
+$CC -c $tmpfile_c -o $tmpfile_o >/dev/null 2>&1
+
+if [ -f $tmpfile_o ]; then
+    echo "#define LOCAL_CONFIG_HAVE_LIBHUGETLBFS 1" > $OUTPUT_H_FILE
+    echo "HMM_EXTRA_LIBS = -lhugetlbfs"             > $OUTPUT_MKFILE
+else
+    echo "// No libhugetlbfs support found"      > $OUTPUT_H_FILE
+    echo "# No libhugetlbfs support found, so:"  > $OUTPUT_MKFILE
+    echo "HMM_EXTRA_LIBS = "                    >> $OUTPUT_MKFILE
+fi
+
+rm ${tmpname}.*
diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config
index 69dd0d1aa30b..60e82da0de85 100644
--- a/tools/testing/selftests/vm/config
+++ b/tools/testing/selftests/vm/config
@@ -3,4 +3,4 @@ CONFIG_USERFAULTFD=y
 CONFIG_TEST_VMALLOC=m
 CONFIG_DEVICE_PRIVATE=y
 CONFIG_TEST_HMM=m
-CONFIG_GUP_BENCHMARK=y
+CONFIG_GUP_TEST=y
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
deleted file mode 100644
index 1d4359341e44..000000000000
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ /dev/null
@@ -1,143 +0,0 @@
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include <sys/prctl.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-
-#include <linux/types.h>
-
-#define MB (1UL << 20)
-#define PAGE_SIZE sysconf(_SC_PAGESIZE)
-
-#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
-#define GUP_BENCHMARK		_IOWR('g', 2, struct gup_benchmark)
-
-/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
-#define PIN_FAST_BENCHMARK	_IOWR('g', 3, struct gup_benchmark)
-#define PIN_BENCHMARK		_IOWR('g', 4, struct gup_benchmark)
-#define PIN_LONGTERM_BENCHMARK	_IOWR('g', 5, struct gup_benchmark)
-
-/* Just the flags we need, copied from mm.h: */
-#define FOLL_WRITE	0x01	/* check pte is writable */
-
-struct gup_benchmark {
-	__u64 get_delta_usec;
-	__u64 put_delta_usec;
-	__u64 addr;
-	__u64 size;
-	__u32 nr_pages_per_call;
-	__u32 flags;
-	__u64 expansion[10];	/* For future use */
-};
-
-int main(int argc, char **argv)
-{
-	struct gup_benchmark gup;
-	unsigned long size = 128 * MB;
-	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
-	int cmd = GUP_FAST_BENCHMARK, flags = MAP_PRIVATE;
-	char *file = "/dev/zero";
-	char *p;
-
-	while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
-		switch (opt) {
-		case 'a':
-			cmd = PIN_FAST_BENCHMARK;
-			break;
-		case 'b':
-			cmd = PIN_BENCHMARK;
-			break;
-		case 'L':
-			cmd = PIN_LONGTERM_BENCHMARK;
-			break;
-		case 'm':
-			size = atoi(optarg) * MB;
-			break;
-		case 'r':
-			repeats = atoi(optarg);
-			break;
-		case 'n':
-			nr_pages = atoi(optarg);
-			break;
-		case 't':
-			thp = 1;
-			break;
-		case 'T':
-			thp = 0;
-			break;
-		case 'U':
-			cmd = GUP_BENCHMARK;
-			break;
-		case 'u':
-			cmd = GUP_FAST_BENCHMARK;
-			break;
-		case 'w':
-			write = 1;
-			break;
-		case 'f':
-			file = optarg;
-			break;
-		case 'S':
-			flags &= ~MAP_PRIVATE;
-			flags |= MAP_SHARED;
-			break;
-		case 'H':
-			flags |= (MAP_HUGETLB | MAP_ANONYMOUS);
-			break;
-		default:
-			return -1;
-		}
-	}
-
-	filed = open(file, O_RDWR|O_CREAT);
-	if (filed < 0) {
-		perror("open");
-		exit(filed);
-	}
-
-	gup.nr_pages_per_call = nr_pages;
-	if (write)
-		gup.flags |= FOLL_WRITE;
-
-	fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
-	if (fd == -1) {
-		perror("open");
-		exit(1);
-	}
-
-	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
-	if (p == MAP_FAILED) {
-		perror("mmap");
-		exit(1);
-	}
-	gup.addr = (unsigned long)p;
-
-	if (thp == 1)
-		madvise(p, size, MADV_HUGEPAGE);
-	else if (thp == 0)
-		madvise(p, size, MADV_NOHUGEPAGE);
-
-	for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
-		p[0] = 0;
-
-	for (i = 0; i < repeats; i++) {
-		gup.size = size;
-		if (ioctl(fd, cmd, &gup)) {
-			perror("ioctl");
-			exit(1);
-		}
-
-		printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
-			gup.put_delta_usec);
-		if (gup.size != size)
-			printf(", truncated (size: %lld)", gup.size);
-		printf("\n");
-	}
-
-	return 0;
-}
diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c
new file mode 100644
index 000000000000..6c6336dd3b7f
--- /dev/null
+++ b/tools/testing/selftests/vm/gup_test.c
@@ -0,0 +1,194 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include "../../../../mm/gup_test.h"
+
+#define MB (1UL << 20)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE	0x01	/* check pte is writable */
+
+static char *cmd_to_str(unsigned long cmd)
+{
+	switch (cmd) {
+	case GUP_FAST_BENCHMARK:
+		return "GUP_FAST_BENCHMARK";
+	case PIN_FAST_BENCHMARK:
+		return "PIN_FAST_BENCHMARK";
+	case PIN_LONGTERM_BENCHMARK:
+		return "PIN_LONGTERM_BENCHMARK";
+	case GUP_BASIC_TEST:
+		return "GUP_BASIC_TEST";
+	case PIN_BASIC_TEST:
+		return "PIN_BASIC_TEST";
+	case DUMP_USER_PAGES_TEST:
+		return "DUMP_USER_PAGES_TEST";
+	}
+	return "Unknown command";
+}
+
+int main(int argc, char **argv)
+{
+	struct gup_test gup = { 0 };
+	unsigned long size = 128 * MB;
+	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	unsigned long cmd = GUP_FAST_BENCHMARK;
+	int flags = MAP_PRIVATE;
+	char *file = "/dev/zero";
+	char *p;
+
+	while ((opt = getopt(argc, argv, "m:r:n:F:f:abctTLUuwSH")) != -1) {
+		switch (opt) {
+		case 'a':
+			cmd = PIN_FAST_BENCHMARK;
+			break;
+		case 'b':
+			cmd = PIN_BASIC_TEST;
+			break;
+		case 'L':
+			cmd = PIN_LONGTERM_BENCHMARK;
+			break;
+		case 'c':
+			cmd = DUMP_USER_PAGES_TEST;
+			/*
+			 * Dump page 0 (index 1). May be overridden later, by
+			 * user's non-option arguments.
+			 *
+			 * .which_pages is zero-based, so that zero can mean "do
+			 * nothing".
+			 */
+			gup.which_pages[0] = 1;
+			break;
+		case 'F':
+			/* strtol, so you can pass flags in hex form */
+			gup.flags = strtol(optarg, 0, 0);
+			break;
+		case 'm':
+			size = atoi(optarg) * MB;
+			break;
+		case 'r':
+			repeats = atoi(optarg);
+			break;
+		case 'n':
+			nr_pages = atoi(optarg);
+			break;
+		case 't':
+			thp = 1;
+			break;
+		case 'T':
+			thp = 0;
+			break;
+		case 'U':
+			cmd = GUP_BASIC_TEST;
+			break;
+		case 'u':
+			cmd = GUP_FAST_BENCHMARK;
+			break;
+		case 'w':
+			write = 1;
+			break;
+		case 'f':
+			file = optarg;
+			break;
+		case 'S':
+			flags &= ~MAP_PRIVATE;
+			flags |= MAP_SHARED;
+			break;
+		case 'H':
+			flags |= (MAP_HUGETLB | MAP_ANONYMOUS);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	if (optind < argc) {
+		int extra_arg_count = 0;
+		/*
+		 * For example:
+		 *
+		 *   ./gup_test -c 0 1 0x1001
+		 *
+		 * ...to dump pages 0, 1, and 4097
+		 */
+
+		while ((optind < argc) &&
+		       (extra_arg_count < GUP_TEST_MAX_PAGES_TO_DUMP)) {
+			/*
+			 * Do the 1-based indexing here, so that the user can
+			 * use normal 0-based indexing on the command line.
+			 */
+			long page_index = strtol(argv[optind], 0, 0) + 1;
+
+			gup.which_pages[extra_arg_count] = page_index;
+			extra_arg_count++;
+			optind++;
+		}
+	}
+
+	filed = open(file, O_RDWR|O_CREAT);
+	if (filed < 0) {
+		perror("open");
+		exit(filed);
+	}
+
+	gup.nr_pages_per_call = nr_pages;
+	if (write)
+		gup.flags |= FOLL_WRITE;
+
+	fd = open("/sys/kernel/debug/gup_test", O_RDWR);
+	if (fd == -1) {
+		perror("open");
+		exit(1);
+	}
+
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
+	if (p == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+	gup.addr = (unsigned long)p;
+
+	if (thp == 1)
+		madvise(p, size, MADV_HUGEPAGE);
+	else if (thp == 0)
+		madvise(p, size, MADV_NOHUGEPAGE);
+
+	for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
+		p[0] = 0;
+
+	/* Only report timing information on the *_BENCHMARK commands: */
+	if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) ||
+	     (cmd == PIN_LONGTERM_BENCHMARK)) {
+		for (i = 0; i < repeats; i++) {
+			gup.size = size;
+			if (ioctl(fd, cmd, &gup))
+				perror("ioctl"), exit(1);
+
+			printf("%s: Time: get:%lld put:%lld us",
+			       cmd_to_str(cmd), gup.get_delta_usec,
+			       gup.put_delta_usec);
+			if (gup.size != size)
+				printf(", truncated (size: %lld)", gup.size);
+			printf("\n");
+		}
+	} else {
+		gup.size = size;
+		if (ioctl(fd, cmd, &gup)) {
+			perror("ioctl");
+			exit(1);
+		}
+
+		printf("%s: done\n", cmd_to_str(cmd));
+		if (gup.size != size)
+			printf("Truncated (size: %lld)\n", gup.size);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index c9404ef9698e..5d1ac691b9f4 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -21,12 +21,16 @@
 #include <strings.h>
 #include <time.h>
 #include <pthread.h>
-#include <hugetlbfs.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <sys/ioctl.h>
 
+#include "./local_config.h"
+#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
+#include <hugetlbfs.h>
+#endif
+
 /*
  * This is a private UAPI to the kernel test module so it isn't exported
  * in the usual include/uapi/... directory.
@@ -662,6 +666,7 @@ TEST_F(hmm, anon_write_huge)
 	hmm_buffer_free(buffer);
 }
 
+#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
 /*
  * Write huge TLBFS page.
  */
@@ -720,6 +725,7 @@ TEST_F(hmm, anon_write_hugetlbfs)
 	buffer->ptr = NULL;
 	hmm_buffer_free(buffer);
 }
+#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */
 
 /*
  * Read mmap'ed file memory.
@@ -1336,6 +1342,7 @@ TEST_F(hmm2, snapshot)
 	hmm_buffer_free(buffer);
 }
 
+#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
 /*
  * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that
  * should be mapped by a large page table entry.
@@ -1411,6 +1418,7 @@ TEST_F(hmm, compound)
 	buffer->ptr = NULL;
 	hmm_buffer_free(buffer);
 }
+#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */
 
 /*
  * Test two devices reading the same memory (double mapped).
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
new file mode 100644
index 000000000000..9c391d016922
--- /dev/null
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020 Google LLC
+ */
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <time.h>
+
+#include "../kselftest.h"
+
+#define EXPECT_SUCCESS 0
+#define EXPECT_FAILURE 1
+#define NON_OVERLAPPING 0
+#define OVERLAPPING 1
+#define NS_PER_SEC 1000000000ULL
+#define VALIDATION_DEFAULT_THRESHOLD 4	/* 4MB */
+#define VALIDATION_NO_THRESHOLD 0	/* Verify the entire region */
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+
+struct config {
+	unsigned long long src_alignment;
+	unsigned long long dest_alignment;
+	unsigned long long region_size;
+	int overlapping;
+};
+
+struct test {
+	const char *name;
+	struct config config;
+	int expect_failure;
+};
+
+enum {
+	_1KB = 1ULL << 10,	/* 1KB -> not page aligned */
+	_4KB = 4ULL << 10,
+	_8KB = 8ULL << 10,
+	_1MB = 1ULL << 20,
+	_2MB = 2ULL << 20,
+	_4MB = 4ULL << 20,
+	_1GB = 1ULL << 30,
+	_2GB = 2ULL << 30,
+	PTE = _4KB,
+	PMD = _2MB,
+	PUD = _1GB,
+};
+
+#define MAKE_TEST(source_align, destination_align, size,	\
+		  overlaps, should_fail, test_name)		\
+{								\
+	.name = test_name,					\
+	.config = {						\
+		.src_alignment = source_align,			\
+		.dest_alignment = destination_align,		\
+		.region_size = size,				\
+		.overlapping = overlaps,			\
+	},							\
+	.expect_failure = should_fail				\
+}
+
+/*
+ * Returns the start address of the mapping on success, else returns
+ * NULL on failure.
+ */
+static void *get_source_mapping(struct config c)
+{
+	unsigned long long addr = 0ULL;
+	void *src_addr = NULL;
+retry:
+	addr += c.src_alignment;
+	src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE,
+			MAP_FIXED | MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+	if (src_addr == MAP_FAILED) {
+		if (errno == EPERM)
+			goto retry;
+		goto error;
+	}
+	/*
+	 * Check that the address is aligned to the specified alignment.
+	 * Addresses which have alignments that are multiples of that
+	 * specified are not considered valid. For instance, 1GB address is
+	 * 2MB-aligned, however it will not be considered valid for a
+	 * requested alignment of 2MB. This is done to reduce coincidental
+	 * alignment in the tests.
+	 */
+	if (((unsigned long long) src_addr & (c.src_alignment - 1)) ||
+			!((unsigned long long) src_addr & c.src_alignment))
+		goto retry;
+
+	if (!src_addr)
+		goto error;
+
+	return src_addr;
+error:
+	ksft_print_msg("Failed to map source region: %s\n",
+			strerror(errno));
+	return NULL;
+}
+
+/* Returns the time taken for the remap on success else returns -1. */
+static long long remap_region(struct config c, unsigned int threshold_mb,
+			      char pattern_seed)
+{
+	void *addr, *src_addr, *dest_addr;
+	unsigned long long i;
+	struct timespec t_start = {0, 0}, t_end = {0, 0};
+	long long  start_ns, end_ns, align_mask, ret, offset;
+	unsigned long long threshold;
+
+	if (threshold_mb == VALIDATION_NO_THRESHOLD)
+		threshold = c.region_size;
+	else
+		threshold = MIN(threshold_mb * _1MB, c.region_size);
+
+	src_addr = get_source_mapping(c);
+	if (!src_addr) {
+		ret = -1;
+		goto out;
+	}
+
+	/* Set byte pattern */
+	srand(pattern_seed);
+	for (i = 0; i < threshold; i++)
+		memset((char *) src_addr + i, (char) rand(), 1);
+
+	/* Mask to zero out lower bits of address for alignment */
+	align_mask = ~(c.dest_alignment - 1);
+	/* Offset of destination address from the end of the source region */
+	offset = (c.overlapping) ? -c.dest_alignment : c.dest_alignment;
+	addr = (void *) (((unsigned long long) src_addr + c.region_size
+			  + offset) & align_mask);
+
+	/* See comment in get_source_mapping() */
+	if (!((unsigned long long) addr & c.dest_alignment))
+		addr = (void *) ((unsigned long long) addr | c.dest_alignment);
+
+	clock_gettime(CLOCK_MONOTONIC, &t_start);
+	dest_addr = mremap(src_addr, c.region_size, c.region_size,
+			MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr);
+	clock_gettime(CLOCK_MONOTONIC, &t_end);
+
+	if (dest_addr == MAP_FAILED) {
+		ksft_print_msg("mremap failed: %s\n", strerror(errno));
+		ret = -1;
+		goto clean_up_src;
+	}
+
+	/* Verify byte pattern after remapping */
+	srand(pattern_seed);
+	for (i = 0; i < threshold; i++) {
+		char c = (char) rand();
+
+		if (((char *) dest_addr)[i] != c) {
+			ksft_print_msg("Data after remap doesn't match at offset %d\n",
+				       i);
+			ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
+					((char *) dest_addr)[i] & 0xff);
+			ret = -1;
+			goto clean_up_dest;
+		}
+	}
+
+	start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec;
+	end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec;
+	ret = end_ns - start_ns;
+
+/*
+ * Since the destination address is specified using MREMAP_FIXED, subsequent
+ * mremap will unmap any previous mapping at the address range specified by
+ * dest_addr and region_size. This significantly affects the remap time of
+ * subsequent tests. So we clean up mappings after each test.
+ */
+clean_up_dest:
+	munmap(dest_addr, c.region_size);
+clean_up_src:
+	munmap(src_addr, c.region_size);
+out:
+	return ret;
+}
+
+static void run_mremap_test_case(struct test test_case, int *failures,
+				 unsigned int threshold_mb,
+				 unsigned int pattern_seed)
+{
+	long long remap_time = remap_region(test_case.config, threshold_mb,
+					    pattern_seed);
+
+	if (remap_time < 0) {
+		if (test_case.expect_failure)
+			ksft_test_result_pass("%s\n\tExpected mremap failure\n",
+					      test_case.name);
+		else {
+			ksft_test_result_fail("%s\n", test_case.name);
+			*failures += 1;
+		}
+	} else {
+		/*
+		 * Comparing mremap time is only applicable if entire region
+		 * was faulted in.
+		 */
+		if (threshold_mb == VALIDATION_NO_THRESHOLD ||
+		    test_case.config.region_size <= threshold_mb * _1MB)
+			ksft_test_result_pass("%s\n\tmremap time: %12lldns\n",
+					      test_case.name, remap_time);
+		else
+			ksft_test_result_pass("%s\n", test_case.name);
+	}
+}
+
+static void usage(const char *cmd)
+{
+	fprintf(stderr,
+		"Usage: %s [[-t <threshold_mb>] [-p <pattern_seed>]]\n"
+		"-t\t only validate threshold_mb of the remapped region\n"
+		"  \t if 0 is supplied no threshold is used; all tests\n"
+		"  \t are run and remapped regions validated fully.\n"
+		"  \t The default threshold used is 4MB.\n"
+		"-p\t provide a seed to generate the random pattern for\n"
+		"  \t validating the remapped region.\n", cmd);
+}
+
+static int parse_args(int argc, char **argv, unsigned int *threshold_mb,
+		      unsigned int *pattern_seed)
+{
+	const char *optstr = "t:p:";
+	int opt;
+
+	while ((opt = getopt(argc, argv, optstr)) != -1) {
+		switch (opt) {
+		case 't':
+			*threshold_mb = atoi(optarg);
+			break;
+		case 'p':
+			*pattern_seed = atoi(optarg);
+			break;
+		default:
+			usage(argv[0]);
+			return -1;
+		}
+	}
+
+	if (optind < argc) {
+		usage(argv[0]);
+		return -1;
+	}
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	int failures = 0;
+	int i, run_perf_tests;
+	unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD;
+	unsigned int pattern_seed;
+	time_t t;
+
+	pattern_seed = (unsigned int) time(&t);
+
+	if (parse_args(argc, argv, &threshold_mb, &pattern_seed) < 0)
+		exit(EXIT_FAILURE);
+
+	ksft_print_msg("Test configs:\n\tthreshold_mb=%u\n\tpattern_seed=%u\n\n",
+		       threshold_mb, pattern_seed);
+
+	struct test test_cases[] = {
+		/* Expected mremap failures */
+		MAKE_TEST(_4KB, _4KB, _4KB, OVERLAPPING, EXPECT_FAILURE,
+		  "mremap - Source and Destination Regions Overlapping"),
+		MAKE_TEST(_4KB, _1KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE,
+		  "mremap - Destination Address Misaligned (1KB-aligned)"),
+		MAKE_TEST(_1KB, _4KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE,
+		  "mremap - Source Address Misaligned (1KB-aligned)"),
+
+		/* Src addr PTE aligned */
+		MAKE_TEST(PTE, PTE, _8KB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "8KB mremap - Source PTE-aligned, Destination PTE-aligned"),
+
+		/* Src addr 1MB aligned */
+		MAKE_TEST(_1MB, PTE, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "2MB mremap - Source 1MB-aligned, Destination PTE-aligned"),
+		MAKE_TEST(_1MB, _1MB, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "2MB mremap - Source 1MB-aligned, Destination 1MB-aligned"),
+
+		/* Src addr PMD aligned */
+		MAKE_TEST(PMD, PTE, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "4MB mremap - Source PMD-aligned, Destination PTE-aligned"),
+		MAKE_TEST(PMD, _1MB, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "4MB mremap - Source PMD-aligned, Destination 1MB-aligned"),
+		MAKE_TEST(PMD, PMD, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "4MB mremap - Source PMD-aligned, Destination PMD-aligned"),
+
+		/* Src addr PUD aligned */
+		MAKE_TEST(PUD, PTE, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "2GB mremap - Source PUD-aligned, Destination PTE-aligned"),
+		MAKE_TEST(PUD, _1MB, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "2GB mremap - Source PUD-aligned, Destination 1MB-aligned"),
+		MAKE_TEST(PUD, PMD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "2GB mremap - Source PUD-aligned, Destination PMD-aligned"),
+		MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "2GB mremap - Source PUD-aligned, Destination PUD-aligned"),
+	};
+
+	struct test perf_test_cases[] = {
+		/*
+		 * mremap 1GB region - Page table level aligned time
+		 * comparison.
+		 */
+		MAKE_TEST(PTE, PTE, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "1GB mremap - Source PTE-aligned, Destination PTE-aligned"),
+		MAKE_TEST(PMD, PMD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "1GB mremap - Source PMD-aligned, Destination PMD-aligned"),
+		MAKE_TEST(PUD, PUD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+		  "1GB mremap - Source PUD-aligned, Destination PUD-aligned"),
+	};
+
+	run_perf_tests =  (threshold_mb == VALIDATION_NO_THRESHOLD) ||
+				(threshold_mb * _1MB >= _1GB);
+
+	ksft_set_plan(ARRAY_SIZE(test_cases) + (run_perf_tests ?
+		      ARRAY_SIZE(perf_test_cases) : 0));
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++)
+		run_mremap_test_case(test_cases[i], &failures, threshold_mb,
+				     pattern_seed);
+
+	if (run_perf_tests) {
+		ksft_print_msg("\n%s\n",
+		 "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:");
+		for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++)
+			run_mremap_test_case(perf_test_cases[i], &failures,
+					     threshold_mb, pattern_seed);
+	}
+
+	if (failures > 0)
+		ksft_exit_fail();
+	else
+		ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index a3f4f30f0a2e..e953f3cd9664 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -123,10 +123,10 @@ else
 	echo "[PASS]"
 fi
 
-echo "--------------------------------------------"
-echo "running 'gup_benchmark -U' (normal/slow gup)"
-echo "--------------------------------------------"
-./gup_benchmark -U
+echo "------------------------------------------------------"
+echo "running: gup_test -u # get_user_pages_fast() benchmark"
+echo "------------------------------------------------------"
+./gup_test -u
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1
@@ -134,10 +134,22 @@ else
 	echo "[PASS]"
 fi
 
-echo "------------------------------------------"
-echo "running gup_benchmark -b (pin_user_pages)"
-echo "------------------------------------------"
-./gup_benchmark -b
+echo "------------------------------------------------------"
+echo "running: gup_test -a # pin_user_pages_fast() benchmark"
+echo "------------------------------------------------------"
+./gup_test -a
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "------------------------------------------------------------"
+echo "# Dump pages 0, 19, and 4096, using pin_user_pages:"
+echo "running: gup_test -ct -F 0x1 0 19 0x1000 # dump_page() test"
+echo "------------------------------------------------------------"
+./gup_test -ct -F 0x1 0 19 0x1000
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1
@@ -148,7 +160,7 @@ fi
 echo "-------------------"
 echo "running userfaultfd"
 echo "-------------------"
-./userfaultfd anon 128 32
+./userfaultfd anon 20 16
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1
@@ -173,7 +185,7 @@ rm -f $mnt/ufd_test_file
 echo "-------------------------"
 echo "running userfaultfd_shmem"
 echo "-------------------------"
-./userfaultfd shmem 128 32
+./userfaultfd shmem 20 16
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1
@@ -241,6 +253,17 @@ else
 	echo "[PASS]"
 fi
 
+echo "-------------------"
+echo "running mremap_test"
+echo "-------------------"
+./mremap_test
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 echo "-----------------"
 echo "running thuge-gen"
 echo "-----------------"
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index c4425597769a..9d8650d4ba5a 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -55,6 +55,8 @@
 #include <setjmp.h>
 #include <stdbool.h>
 #include <assert.h>
+#include <inttypes.h>
+#include <stdint.h>
 
 #include "../kselftest.h"
 
@@ -135,6 +137,13 @@ 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);                                                       \
+	} while (0)
+
 static void uffd_stats_reset(struct uffd_stats *uffd_stats,
 			     unsigned long n_cpus)
 {
@@ -338,7 +347,7 @@ static int my_bcmp(char *str1, char *str2, size_t n)
 
 static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
 {
-	struct uffdio_writeprotect prms = { 0 };
+	struct uffdio_writeprotect prms;
 
 	/* Write protection page faults */
 	prms.range.start = start;
@@ -347,7 +356,8 @@ static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
 	prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0;
 
 	if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) {
-		fprintf(stderr, "clear WP failed for address 0x%Lx\n", start);
+		fprintf(stderr, "clear WP failed for address 0x%" PRIx64 "\n",
+			(uint64_t)start);
 		exit(1);
 	}
 }
@@ -481,14 +491,11 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
 	if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) {
 		/* real retval in ufdio_copy.copy */
 		if (uffdio_copy->copy != -EEXIST) {
-			fprintf(stderr, "UFFDIO_COPY retry error %Ld\n",
-				uffdio_copy->copy);
-			exit(1);
+			uffd_error(uffdio_copy->copy,
+				   "UFFDIO_COPY retry error");
 		}
-	} else {
-		fprintf(stderr,	"UFFDIO_COPY retry unexpected %Ld\n",
-			uffdio_copy->copy); exit(1);
-	}
+	} else
+		uffd_error(uffdio_copy->copy, "UFFDIO_COPY retry unexpected");
 }
 
 static int __copy_page(int ufd, unsigned long offset, bool retry)
@@ -509,14 +516,10 @@ static int __copy_page(int ufd, unsigned long offset, bool retry)
 	uffdio_copy.copy = 0;
 	if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
 		/* real retval in ufdio_copy.copy */
-		if (uffdio_copy.copy != -EEXIST) {
-			fprintf(stderr, "UFFDIO_COPY error %Ld\n",
-				uffdio_copy.copy);
-			exit(1);
-		}
+		if (uffdio_copy.copy != -EEXIST)
+			uffd_error(uffdio_copy.copy, "UFFDIO_COPY error");
 	} else if (uffdio_copy.copy != page_size) {
-		fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
-			uffdio_copy.copy); exit(1);
+		uffd_error(uffdio_copy.copy, "UFFDIO_COPY unexpected copy");
 	} else {
 		if (test_uffdio_copy_eexist && retry) {
 			test_uffdio_copy_eexist = false;
@@ -791,11 +794,13 @@ static int userfaultfd_open(int features)
 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = features;
 	if (ioctl(uffd, UFFDIO_API, &uffdio_api)) {
-		fprintf(stderr, "UFFDIO_API\n");
+		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 %Lu\n", uffdio_api.api);
+		fprintf(stderr, "UFFDIO_API error: %" PRIu64 "\n",
+			(uint64_t)uffdio_api.api);
 		return 1;
 	}
 
@@ -957,13 +962,12 @@ static void retry_uffdio_zeropage(int ufd,
 				     offset);
 	if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
 		if (uffdio_zeropage->zeropage != -EEXIST) {
-			fprintf(stderr, "UFFDIO_ZEROPAGE retry error %Ld\n",
-				uffdio_zeropage->zeropage);
-			exit(1);
+			uffd_error(uffdio_zeropage->zeropage,
+				   "UFFDIO_ZEROPAGE retry error");
 		}
 	} else {
-		fprintf(stderr, "UFFDIO_ZEROPAGE retry unexpected %Ld\n",
-			uffdio_zeropage->zeropage); exit(1);
+		uffd_error(uffdio_zeropage->zeropage,
+			   "UFFDIO_ZEROPAGE retry unexpected");
 	}
 }
 
@@ -972,6 +976,7 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 	struct uffdio_zeropage uffdio_zeropage;
 	int ret;
 	unsigned long has_zeropage;
+	__s64 res;
 
 	has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE);
 
@@ -983,29 +988,17 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 	uffdio_zeropage.range.len = page_size;
 	uffdio_zeropage.mode = 0;
 	ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
+	res = uffdio_zeropage.zeropage;
 	if (ret) {
 		/* real retval in ufdio_zeropage.zeropage */
 		if (has_zeropage) {
-			if (uffdio_zeropage.zeropage == -EEXIST) {
-				fprintf(stderr, "UFFDIO_ZEROPAGE -EEXIST\n");
-				exit(1);
-			} else {
-				fprintf(stderr, "UFFDIO_ZEROPAGE error %Ld\n",
-					uffdio_zeropage.zeropage);
-				exit(1);
-			}
-		} else {
-			if (uffdio_zeropage.zeropage != -EINVAL) {
-				fprintf(stderr,
-					"UFFDIO_ZEROPAGE not -EINVAL %Ld\n",
-					uffdio_zeropage.zeropage);
-				exit(1);
-			}
-		}
+			uffd_error(res, "UFFDIO_ZEROPAGE %s",
+				   res == -EEXIST ? "-EEXIST" : "error");
+		} else if (res != -EINVAL)
+			uffd_error(res, "UFFDIO_ZEROPAGE not -EINVAL");
 	} else if (has_zeropage) {
-		if (uffdio_zeropage.zeropage != page_size) {
-			fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
-				uffdio_zeropage.zeropage); exit(1);
+		if (res != page_size) {
+			uffd_error(res, "UFFDIO_ZEROPAGE unexpected");
 		} else {
 			if (test_uffdio_zeropage_eexist && retry) {
 				test_uffdio_zeropage_eexist = false;
@@ -1014,11 +1007,8 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 			}
 			return 1;
 		}
-	} else {
-		fprintf(stderr,
-			"UFFDIO_ZEROPAGE succeeded %Ld\n",
-			uffdio_zeropage.zeropage); exit(1);
-	}
+	} else
+		uffd_error(res, "UFFDIO_ZEROPAGE succeeded");
 
 	return 0;
 }
@@ -1040,7 +1030,7 @@ static int userfaultfd_zeropage_test(void)
 	if (uffd_test_ops->release_pages(area_dst))
 		return 1;
 
-	if (userfaultfd_open(0) < 0)
+	if (userfaultfd_open(0))
 		return 1;
 	uffdio_register.range.start = (unsigned long) area_dst;
 	uffdio_register.range.len = nr_pages * page_size;
@@ -1090,7 +1080,7 @@ static int userfaultfd_events_test(void)
 
 	features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
 		UFFD_FEATURE_EVENT_REMOVE;
-	if (userfaultfd_open(features) < 0)
+	if (userfaultfd_open(features))
 		return 1;
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
@@ -1162,7 +1152,7 @@ static int userfaultfd_sig_test(void)
 		return 1;
 
 	features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS;
-	if (userfaultfd_open(features) < 0)
+	if (userfaultfd_open(features))
 		return 1;
 	fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
 
@@ -1242,7 +1232,7 @@ static int userfaultfd_stress(void)
 	if (!area_dst)
 		return 1;
 
-	if (userfaultfd_open(0) < 0)
+	if (userfaultfd_open(0))
 		return 1;
 
 	count_verify = malloc(nr_pages * sizeof(unsigned long long));
@@ -1302,6 +1292,8 @@ static int userfaultfd_stress(void)
 			printf(" ver");
 		if (bounces & BOUNCE_POLL)
 			printf(" poll");
+		else
+			printf(" read");
 		printf(", ");
 		fflush(stdout);