20 files changed, 786 insertions, 48 deletions

diff --git a/tools/cgroup/memcg_shrinker.py b/tools/cgroup/memcg_shrinker.py
new file mode 100644
index 000000000000..706ab27666a4
--- /dev/null
+++ b/tools/cgroup/memcg_shrinker.py
@@ -0,0 +1,71 @@
+#!/usr/bin/env python3
+#
+# Copyright (C) 2022 Roman Gushchin <roman.gushchin@linux.dev>
+# Copyright (C) 2022 Meta
+
+import os
+import argparse
+import sys
+
+
+def scan_cgroups(cgroup_root):
+    cgroups = {}
+
+    for root, subdirs, _ in os.walk(cgroup_root):
+        for cgroup in subdirs:
+            path = os.path.join(root, cgroup)
+            ino = os.stat(path).st_ino
+            cgroups[ino] = path
+
+    # (memcg ino, path)
+    return cgroups
+
+
+def scan_shrinkers(shrinker_debugfs):
+    shrinkers = []
+
+    for root, subdirs, _ in os.walk(shrinker_debugfs):
+        for shrinker in subdirs:
+            count_path = os.path.join(root, shrinker, "count")
+            with open(count_path) as f:
+                for line in f.readlines():
+                    items = line.split(' ')
+                    ino = int(items[0])
+                    # (count, shrinker, memcg ino)
+                    shrinkers.append((int(items[1]), shrinker, ino))
+    return shrinkers
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Display biggest shrinkers')
+    parser.add_argument('-n', '--lines', type=int, help='Number of lines to print')
+
+    args = parser.parse_args()
+
+    cgroups = scan_cgroups("/sys/fs/cgroup/")
+    shrinkers = scan_shrinkers("/sys/kernel/debug/shrinker/")
+    shrinkers = sorted(shrinkers, reverse = True, key = lambda x: x[0])
+
+    n = 0
+    for s in shrinkers:
+        count, name, ino = (s[0], s[1], s[2])
+        if count == 0:
+            break
+
+        if ino == 0 or ino == 1:
+            cg = "/"
+        else:
+            try:
+                cg = cgroups[ino]
+            except KeyError:
+                cg = "unknown (%d)" % ino
+
+        print("%-8s %-20s %s" % (count, name, cg))
+
+        n += 1
+        if args.lines and n >= args.lines:
+            break
+
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h
index b238dbc9eb85..56eec4445bc9 100644
--- a/tools/include/linux/gfp.h
+++ b/tools/include/linux/gfp.h
@@ -12,7 +12,6 @@
 #define __GFP_FS		0x80u
 #define __GFP_NOWARN		0x200u
 #define __GFP_ZERO		0x8000u
-#define __GFP_ATOMIC		0x80000u
 #define __GFP_ACCOUNT		0x100000u
 #define __GFP_DIRECT_RECLAIM	0x400000u
 #define __GFP_KSWAPD_RECLAIM	0x2000000u
@@ -20,7 +19,7 @@
 #define __GFP_RECLAIM	(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM)
 
 #define GFP_ZONEMASK	0x0fu
-#define GFP_ATOMIC	(__GFP_HIGH | __GFP_ATOMIC | __GFP_KSWAPD_RECLAIM)
+#define GFP_ATOMIC	(__GFP_HIGH | __GFP_KSWAPD_RECLAIM)
 #define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
 #define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
 
diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h
index 0616409513eb..311759ea25e9 100644
--- a/tools/include/linux/slab.h
+++ b/tools/include/linux/slab.h
@@ -41,4 +41,8 @@ struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
 			unsigned int align, unsigned int flags,
 			void (*ctor)(void *));
 
+void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list);
+int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
+			  void **list);
+
 #endif		/* _TOOLS_SLAB_H */
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index ebfab2ca1702..4a06d83f2ac5 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -640,7 +640,6 @@ static const struct {
 	{ "__GFP_HIGHMEM",		"HM" },
 	{ "GFP_DMA32",			"D32" },
 	{ "__GFP_HIGH",			"H" },
-	{ "__GFP_ATOMIC",		"_A" },
 	{ "__GFP_IO",			"I" },
 	{ "__GFP_FS",			"F" },
 	{ "__GFP_NOWARN",		"NWR" },
diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore
index d971516401e6..c901d96dd013 100644
--- a/tools/testing/radix-tree/.gitignore
+++ b/tools/testing/radix-tree/.gitignore
@@ -6,3 +6,5 @@ main
 multiorder
 radix-tree.c
 xarray
+maple
+ma_xa_benchmark
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index c4ea4fbb0bfc..89d613e0505b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -4,9 +4,9 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 	  -fsanitize=undefined
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
-TARGETS = main idr-test multiorder xarray
+TARGETS = main idr-test multiorder xarray maple
 CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o \
-			 slab.o
+			 slab.o maple.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 regression4.o tag_check.o multiorder.o idr-test.o iteration_check.o \
 	 iteration_check_2.o benchmark.o
@@ -29,6 +29,8 @@ idr-test: idr-test.o $(CORE_OFILES)
 
 xarray: $(CORE_OFILES)
 
+maple: $(CORE_OFILES)
+
 multiorder: multiorder.o $(CORE_OFILES)
 
 clean:
@@ -40,6 +42,7 @@ $(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
 	../../../include/linux/xarray.h \
+	../../../include/linux/maple_tree.h \
 	../../../include/linux/radix-tree.h \
 	../../../include/linux/idr.h
 
@@ -51,6 +54,8 @@ idr.c: ../../../lib/idr.c
 
 xarray.o: ../../../lib/xarray.c ../../../lib/test_xarray.c
 
+maple.o: ../../../lib/maple_tree.c ../../../lib/test_maple_tree.c
+
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index 2218b3cc184e..e7da80350236 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1 +1,2 @@
 #define CONFIG_XARRAY_MULTI 1
+#define CONFIG_64BIT 1
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index d5c1bcba86fe..2048d12c31df 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -23,15 +23,47 @@ struct kmem_cache {
 	int nr_objs;
 	void *objs;
 	void (*ctor)(void *);
+	unsigned int non_kernel;
+	unsigned long nr_allocated;
+	unsigned long nr_tallocated;
 };
 
+void kmem_cache_set_non_kernel(struct kmem_cache *cachep, unsigned int val)
+{
+	cachep->non_kernel = val;
+}
+
+unsigned long kmem_cache_get_alloc(struct kmem_cache *cachep)
+{
+	return cachep->size * cachep->nr_allocated;
+}
+
+unsigned long kmem_cache_nr_allocated(struct kmem_cache *cachep)
+{
+	return cachep->nr_allocated;
+}
+
+unsigned long kmem_cache_nr_tallocated(struct kmem_cache *cachep)
+{
+	return cachep->nr_tallocated;
+}
+
+void kmem_cache_zero_nr_tallocated(struct kmem_cache *cachep)
+{
+	cachep->nr_tallocated = 0;
+}
+
 void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 		int gfp)
 {
 	void *p;
 
-	if (!(gfp & __GFP_DIRECT_RECLAIM))
-		return NULL;
+	if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+		if (!cachep->non_kernel)
+			return NULL;
+
+		cachep->non_kernel--;
+	}
 
 	pthread_mutex_lock(&cachep->lock);
 	if (cachep->nr_objs) {
@@ -53,19 +85,21 @@ void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 			memset(p, 0, cachep->size);
 	}
 
+	uatomic_inc(&cachep->nr_allocated);
 	uatomic_inc(&nr_allocated);
+	uatomic_inc(&cachep->nr_tallocated);
 	if (kmalloc_verbose)
 		printf("Allocating %p from slab\n", p);
 	return p;
 }
 
-void kmem_cache_free(struct kmem_cache *cachep, void *objp)
+void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
 {
 	assert(objp);
 	uatomic_dec(&nr_allocated);
+	uatomic_dec(&cachep->nr_allocated);
 	if (kmalloc_verbose)
 		printf("Freeing %p to slab\n", objp);
-	pthread_mutex_lock(&cachep->lock);
 	if (cachep->nr_objs > 10 || cachep->align) {
 		memset(objp, POISON_FREE, cachep->size);
 		free(objp);
@@ -75,9 +109,80 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 		node->parent = cachep->objs;
 		cachep->objs = node;
 	}
+}
+
+void kmem_cache_free(struct kmem_cache *cachep, void *objp)
+{
+	pthread_mutex_lock(&cachep->lock);
+	kmem_cache_free_locked(cachep, objp);
 	pthread_mutex_unlock(&cachep->lock);
 }
 
+void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
+{
+	if (kmalloc_verbose)
+		pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
+
+	pthread_mutex_lock(&cachep->lock);
+	for (int i = 0; i < size; i++)
+		kmem_cache_free_locked(cachep, list[i]);
+	pthread_mutex_unlock(&cachep->lock);
+}
+
+int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
+			  void **p)
+{
+	size_t i;
+
+	if (kmalloc_verbose)
+		pr_debug("Bulk alloc %lu\n", size);
+
+	if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+		if (cachep->non_kernel < size)
+			return 0;
+
+		cachep->non_kernel -= size;
+	}
+
+	pthread_mutex_lock(&cachep->lock);
+	if (cachep->nr_objs >= size) {
+		struct radix_tree_node *node;
+
+		for (i = 0; i < size; i++) {
+			node = cachep->objs;
+			cachep->nr_objs--;
+			cachep->objs = node->parent;
+			p[i] = node;
+			node->parent = NULL;
+		}
+		pthread_mutex_unlock(&cachep->lock);
+	} else {
+		pthread_mutex_unlock(&cachep->lock);
+		for (i = 0; i < size; i++) {
+			if (cachep->align) {
+				posix_memalign(&p[i], cachep->align,
+					       cachep->size * size);
+			} else {
+				p[i] = malloc(cachep->size * size);
+			}
+			if (cachep->ctor)
+				cachep->ctor(p[i]);
+			else if (gfp & __GFP_ZERO)
+				memset(p[i], 0, cachep->size);
+		}
+	}
+
+	for (i = 0; i < size; i++) {
+		uatomic_inc(&nr_allocated);
+		uatomic_inc(&cachep->nr_allocated);
+		uatomic_inc(&cachep->nr_tallocated);
+		if (kmalloc_verbose)
+			printf("Allocating %p from slab\n", p[i]);
+	}
+
+	return size;
+}
+
 struct kmem_cache *
 kmem_cache_create(const char *name, unsigned int size, unsigned int align,
 		unsigned int flags, void (*ctor)(void *))
@@ -88,7 +193,54 @@ kmem_cache_create(const char *name, unsigned int size, unsigned int align,
 	ret->size = size;
 	ret->align = align;
 	ret->nr_objs = 0;
+	ret->nr_allocated = 0;
+	ret->nr_tallocated = 0;
 	ret->objs = NULL;
 	ret->ctor = ctor;
+	ret->non_kernel = 0;
 	return ret;
 }
+
+/*
+ * Test the test infrastructure for kem_cache_alloc/free and bulk counterparts.
+ */
+void test_kmem_cache_bulk(void)
+{
+	int i;
+	void *list[12];
+	static struct kmem_cache *test_cache, *test_cache2;
+
+	/*
+	 * Testing the bulk allocators without aligned kmem_cache to force the
+	 * bulk alloc/free to reuse
+	 */
+	test_cache = kmem_cache_create("test_cache", 256, 0, SLAB_PANIC, NULL);
+
+	for (i = 0; i < 5; i++)
+		list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
+
+	for (i = 0; i < 5; i++)
+		kmem_cache_free(test_cache, list[i]);
+	assert(test_cache->nr_objs == 5);
+
+	kmem_cache_alloc_bulk(test_cache, __GFP_DIRECT_RECLAIM, 5, list);
+	kmem_cache_free_bulk(test_cache, 5, list);
+
+	for (i = 0; i < 12 ; i++)
+		list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
+
+	for (i = 0; i < 12; i++)
+		kmem_cache_free(test_cache, list[i]);
+
+	/* The last free will not be kept around */
+	assert(test_cache->nr_objs == 11);
+
+	/* Aligned caches will immediately free */
+	test_cache2 = kmem_cache_create("test_cache2", 128, 128, SLAB_PANIC, NULL);
+
+	kmem_cache_alloc_bulk(test_cache2, __GFP_DIRECT_RECLAIM, 10, list);
+	kmem_cache_free_bulk(test_cache2, 10, list);
+	assert(!test_cache2->nr_objs);
+
+
+}
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 39867fd80c8f..c5c9d05f29da 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -14,6 +14,7 @@
 #include "../../../include/linux/kconfig.h"
 
 #define printk printf
+#define pr_err printk
 #define pr_info printk
 #define pr_debug printk
 #define pr_cont printk
diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h
index 016cff473cfc..62473ab57f99 100644
--- a/tools/testing/radix-tree/linux/lockdep.h
+++ b/tools/testing/radix-tree/linux/lockdep.h
@@ -11,4 +11,6 @@ static inline void lockdep_set_class(spinlock_t *lock,
 					struct lock_class_key *key)
 {
 }
+
+extern int lockdep_is_held(const void *);
 #endif /* _LINUX_LOCKDEP_H */
diff --git a/tools/testing/radix-tree/linux/maple_tree.h b/tools/testing/radix-tree/linux/maple_tree.h
new file mode 100644
index 000000000000..7d8d1f445b89
--- /dev/null
+++ b/tools/testing/radix-tree/linux/maple_tree.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#define atomic_t int32_t
+#include "../../../../include/linux/maple_tree.h"
+#define atomic_inc(x) uatomic_inc(x)
+#define atomic_read(x) uatomic_read(x)
+#define atomic_set(x, y) do {} while (0)
+#define U8_MAX UCHAR_MAX
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
new file mode 100644
index 000000000000..35082671928a
--- /dev/null
+++ b/tools/testing/radix-tree/maple.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * maple_tree.c: Userspace shim for maple tree test-suite
+ * Copyright (c) 2018 Liam R. Howlett <Liam.Howlett@Oracle.com>
+ */
+
+#define CONFIG_DEBUG_MAPLE_TREE
+#define CONFIG_MAPLE_SEARCH
+#include "test.h"
+
+#define module_init(x)
+#define module_exit(x)
+#define MODULE_AUTHOR(x)
+#define MODULE_LICENSE(x)
+#define dump_stack()	assert(0)
+
+#include "../../../lib/maple_tree.c"
+#undef CONFIG_DEBUG_MAPLE_TREE
+#include "../../../lib/test_maple_tree.c"
+
+void farmer_tests(void)
+{
+	struct maple_node *node;
+	DEFINE_MTREE(tree);
+
+	mt_dump(&tree);
+
+	tree.ma_root = xa_mk_value(0);
+	mt_dump(&tree);
+
+	node = mt_alloc_one(GFP_KERNEL);
+	node->parent = (void *)((unsigned long)(&tree) | 1);
+	node->slot[0] = xa_mk_value(0);
+	node->slot[1] = xa_mk_value(1);
+	node->mr64.pivot[0] = 0;
+	node->mr64.pivot[1] = 1;
+	node->mr64.pivot[2] = 0;
+	tree.ma_root = mt_mk_node(node, maple_leaf_64);
+	mt_dump(&tree);
+
+	ma_free_rcu(node);
+}
+
+void maple_tree_tests(void)
+{
+	farmer_tests();
+	maple_tree_seed();
+	maple_tree_harvest();
+}
+
+int __weak main(void)
+{
+	maple_tree_init();
+	maple_tree_tests();
+	rcu_barrier();
+	if (nr_allocated)
+		printf("nr_allocated = %d\n", nr_allocated);
+	return 0;
+}
diff --git a/tools/testing/radix-tree/trace/events/maple_tree.h b/tools/testing/radix-tree/trace/events/maple_tree.h
new file mode 100644
index 000000000000..97d0e1ddcf08
--- /dev/null
+++ b/tools/testing/radix-tree/trace/events/maple_tree.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#define trace_ma_op(a, b) do {} while (0)
+#define trace_ma_read(a, b) do {} while (0)
+#define trace_ma_write(a, b, c, d) do {} while (0)
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 44f25acfbeca..6a34209379a4 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -93,6 +93,7 @@ TEST_PROGS := run_vmtests.sh
 
 TEST_FILES := test_vmalloc.sh
 TEST_FILES += test_hmm.sh
+TEST_FILES += va_128TBswitch.sh
 
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 203323967b50..2da9d5baf339 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -36,6 +36,7 @@
  * in the usual include/uapi/... directory.
  */
 #include "../../../../lib/test_hmm_uapi.h"
+#include "../../../../mm/gup_test.h"
 
 struct hmm_buffer {
 	void		*ptr;
@@ -46,12 +47,21 @@ struct hmm_buffer {
 	uint64_t	faults;
 };
 
+enum {
+	HMM_PRIVATE_DEVICE_ONE,
+	HMM_PRIVATE_DEVICE_TWO,
+	HMM_COHERENCE_DEVICE_ONE,
+	HMM_COHERENCE_DEVICE_TWO,
+};
+
 #define TWOMEG		(1 << 21)
 #define HMM_BUFFER_SIZE (1024 << 12)
 #define HMM_PATH_MAX    64
 #define NTIMES		10
 
 #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1)))
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE	0x01	/* check pte is writable */
 
 FIXTURE(hmm)
 {
@@ -60,6 +70,21 @@ FIXTURE(hmm)
 	unsigned int	page_shift;
 };
 
+FIXTURE_VARIANT(hmm)
+{
+	int     device_number;
+};
+
+FIXTURE_VARIANT_ADD(hmm, hmm_device_private)
+{
+	.device_number = HMM_PRIVATE_DEVICE_ONE,
+};
+
+FIXTURE_VARIANT_ADD(hmm, hmm_device_coherent)
+{
+	.device_number = HMM_COHERENCE_DEVICE_ONE,
+};
+
 FIXTURE(hmm2)
 {
 	int		fd0;
@@ -68,6 +93,24 @@ FIXTURE(hmm2)
 	unsigned int	page_shift;
 };
 
+FIXTURE_VARIANT(hmm2)
+{
+	int     device_number0;
+	int     device_number1;
+};
+
+FIXTURE_VARIANT_ADD(hmm2, hmm2_device_private)
+{
+	.device_number0 = HMM_PRIVATE_DEVICE_ONE,
+	.device_number1 = HMM_PRIVATE_DEVICE_TWO,
+};
+
+FIXTURE_VARIANT_ADD(hmm2, hmm2_device_coherent)
+{
+	.device_number0 = HMM_COHERENCE_DEVICE_ONE,
+	.device_number1 = HMM_COHERENCE_DEVICE_TWO,
+};
+
 static int hmm_open(int unit)
 {
 	char pathname[HMM_PATH_MAX];
@@ -81,12 +124,19 @@ static int hmm_open(int unit)
 	return fd;
 }
 
+static bool hmm_is_coherent_type(int dev_num)
+{
+	return (dev_num >= HMM_COHERENCE_DEVICE_ONE);
+}
+
 FIXTURE_SETUP(hmm)
 {
 	self->page_size = sysconf(_SC_PAGE_SIZE);
 	self->page_shift = ffs(self->page_size) - 1;
 
-	self->fd = hmm_open(0);
+	self->fd = hmm_open(variant->device_number);
+	if (self->fd < 0 && hmm_is_coherent_type(variant->device_number))
+		SKIP(exit(0), "DEVICE_COHERENT not available");
 	ASSERT_GE(self->fd, 0);
 }
 
@@ -95,9 +145,11 @@ FIXTURE_SETUP(hmm2)
 	self->page_size = sysconf(_SC_PAGE_SIZE);
 	self->page_shift = ffs(self->page_size) - 1;
 
-	self->fd0 = hmm_open(0);
+	self->fd0 = hmm_open(variant->device_number0);
+	if (self->fd0 < 0 && hmm_is_coherent_type(variant->device_number0))
+		SKIP(exit(0), "DEVICE_COHERENT not available");
 	ASSERT_GE(self->fd0, 0);
-	self->fd1 = hmm_open(1);
+	self->fd1 = hmm_open(variant->device_number1);
 	ASSERT_GE(self->fd1, 0);
 }
 
@@ -211,6 +263,20 @@ static void hmm_nanosleep(unsigned int n)
 	nanosleep(&t, NULL);
 }
 
+static int hmm_migrate_sys_to_dev(int fd,
+				   struct hmm_buffer *buffer,
+				   unsigned long npages)
+{
+	return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_DEV, buffer, npages);
+}
+
+static int hmm_migrate_dev_to_sys(int fd,
+				   struct hmm_buffer *buffer,
+				   unsigned long npages)
+{
+	return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_SYS, buffer, npages);
+}
+
 /*
  * Simple NULL test of device open/close.
  */
@@ -875,7 +941,7 @@ TEST_F(hmm, migrate)
 		ptr[i] = i;
 
 	/* Migrate memory to device. */
-	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
 	ASSERT_EQ(ret, 0);
 	ASSERT_EQ(buffer->cpages, npages);
 
@@ -923,7 +989,7 @@ TEST_F(hmm, migrate_fault)
 		ptr[i] = i;
 
 	/* Migrate memory to device. */
-	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
 	ASSERT_EQ(ret, 0);
 	ASSERT_EQ(buffer->cpages, npages);
 
@@ -936,7 +1002,7 @@ TEST_F(hmm, migrate_fault)
 		ASSERT_EQ(ptr[i], i);
 
 	/* Migrate memory to the device again. */
-	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
 	ASSERT_EQ(ret, 0);
 	ASSERT_EQ(buffer->cpages, npages);
 
@@ -976,7 +1042,7 @@ TEST_F(hmm, migrate_shared)
 	ASSERT_NE(buffer->ptr, MAP_FAILED);
 
 	/* Migrate memory to device. */
-	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
 	ASSERT_EQ(ret, -ENOENT);
 
 	hmm_buffer_free(buffer);
@@ -1015,7 +1081,7 @@ TEST_F(hmm2, migrate_mixed)
 	p = buffer->ptr;
 
 	/* Migrating a protected area should be an error. */
-	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages);
 	ASSERT_EQ(ret, -EINVAL);
 
 	/* Punch a hole after the first page address. */
@@ -1023,7 +1089,7 @@ TEST_F(hmm2, migrate_mixed)
 	ASSERT_EQ(ret, 0);
 
 	/* We expect an error if the vma doesn't cover the range. */
-	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 3);
+	ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 3);
 	ASSERT_EQ(ret, -EINVAL);
 
 	/* Page 2 will be a read-only zero page. */
@@ -1055,13 +1121,13 @@ TEST_F(hmm2, migrate_mixed)
 
 	/* Now try to migrate pages 2-5 to device 1. */
 	buffer->ptr = p + 2 * self->page_size;
-	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 4);
+	ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 4);
 	ASSERT_EQ(ret, 0);
 	ASSERT_EQ(buffer->cpages, 4);
 
 	/* Page 5 won't be migrated to device 0 because it's on device 1. */
 	buffer->ptr = p + 5 * self->page_size;
-	ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1);
+	ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1);
 	ASSERT_EQ(ret, -ENOENT);
 	buffer->ptr = p;
 
@@ -1070,8 +1136,12 @@ TEST_F(hmm2, migrate_mixed)
 }
 
 /*
- * Migrate anonymous memory to device private memory and fault it back to system
- * memory multiple times.
+ * Migrate anonymous memory to device memory and back to system memory
+ * multiple times. In case of private zone configuration, this is done
+ * through fault pages accessed by CPU. In case of coherent zone configuration,
+ * the pages from the device should be explicitly migrated back to system memory.
+ * The reason is Coherent device zone has coherent access by CPU, therefore
+ * it will not generate any page fault.
  */
 TEST_F(hmm, migrate_multiple)
 {
@@ -1107,8 +1177,7 @@ TEST_F(hmm, migrate_multiple)
 			ptr[i] = i;
 
 		/* Migrate memory to device. */
-		ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer,
-				      npages);
+		ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
 		ASSERT_EQ(ret, 0);
 		ASSERT_EQ(buffer->cpages, npages);
 
@@ -1116,7 +1185,13 @@ TEST_F(hmm, migrate_multiple)
 		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. */
+		/* Migrate back to system memory and check them. */
+		if (hmm_is_coherent_type(variant->device_number)) {
+			ret = hmm_migrate_dev_to_sys(self->fd, buffer, npages);
+			ASSERT_EQ(ret, 0);
+			ASSERT_EQ(buffer->cpages, npages);
+		}
+
 		for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
 			ASSERT_EQ(ptr[i], i);
 
@@ -1354,13 +1429,13 @@ TEST_F(hmm2, snapshot)
 
 	/* Page 5 will be migrated to device 0. */
 	buffer->ptr = p + 5 * self->page_size;
-	ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1);
+	ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1);
 	ASSERT_EQ(ret, 0);
 	ASSERT_EQ(buffer->cpages, 1);
 
 	/* Page 6 will be migrated to device 1. */
 	buffer->ptr = p + 6 * self->page_size;
-	ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 1);
+	ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 1);
 	ASSERT_EQ(ret, 0);
 	ASSERT_EQ(buffer->cpages, 1);
 
@@ -1377,9 +1452,16 @@ TEST_F(hmm2, snapshot)
 	ASSERT_EQ(m[2], HMM_DMIRROR_PROT_ZERO | HMM_DMIRROR_PROT_READ);
 	ASSERT_EQ(m[3], HMM_DMIRROR_PROT_READ);
 	ASSERT_EQ(m[4], HMM_DMIRROR_PROT_WRITE);
-	ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL |
-			HMM_DMIRROR_PROT_WRITE);
-	ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE);
+	if (!hmm_is_coherent_type(variant->device_number0)) {
+		ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL |
+				HMM_DMIRROR_PROT_WRITE);
+		ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE);
+	} else {
+		ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL |
+				HMM_DMIRROR_PROT_WRITE);
+		ASSERT_EQ(m[6], HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE |
+				HMM_DMIRROR_PROT_WRITE);
+	}
 
 	hmm_buffer_free(buffer);
 }
@@ -1685,4 +1767,186 @@ TEST_F(hmm, exclusive_cow)
 	hmm_buffer_free(buffer);
 }
 
+static int gup_test_exec(int gup_fd, unsigned long addr,
+			 int cmd, int npages, int size)
+{
+	struct gup_test gup = {
+		.nr_pages_per_call	= npages,
+		.addr			= addr,
+		.gup_flags		= FOLL_WRITE,
+		.size			= size,
+	};
+
+	if (ioctl(gup_fd, cmd, &gup)) {
+		perror("ioctl on error\n");
+		return errno;
+	}
+
+	return 0;
+}
+
+/*
+ * Test get user device pages through gup_test. Setting PIN_LONGTERM flag.
+ * This should trigger a migration back to system memory for both, private
+ * and coherent type pages.
+ * This test makes use of gup_test module. Make sure GUP_TEST_CONFIG is added
+ * to your configuration before you run it.
+ */
+TEST_F(hmm, hmm_gup_test)
+{
+	struct hmm_buffer *buffer;
+	int gup_fd;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+	unsigned char *m;
+
+	gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR);
+	if (gup_fd == -1)
+		SKIP(return, "Skipping test, could not find gup_test driver");
+
+	npages = 3;
+	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;
+
+	/* Migrate memory to device. */
+	ret = hmm_migrate_sys_to_dev(self->fd, 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);
+
+	ASSERT_EQ(gup_test_exec(gup_fd,
+				(unsigned long)buffer->ptr,
+				GUP_BASIC_TEST, 1, self->page_size), 0);
+	ASSERT_EQ(gup_test_exec(gup_fd,
+				(unsigned long)buffer->ptr + 1 * self->page_size,
+				GUP_FAST_BENCHMARK, 1, self->page_size), 0);
+	ASSERT_EQ(gup_test_exec(gup_fd,
+				(unsigned long)buffer->ptr + 2 * self->page_size,
+				PIN_LONGTERM_BENCHMARK, 1, self->page_size), 0);
+
+	/* Take snapshot to CPU pagetables */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	m = buffer->mirror;
+	if (hmm_is_coherent_type(variant->device_number)) {
+		ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[0]);
+		ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[1]);
+	} else {
+		ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[0]);
+		ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[1]);
+	}
+	ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[2]);
+	/*
+	 * Check again the content on the pages. Make sure there's no
+	 * corrupted data.
+	 */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	close(gup_fd);
+	hmm_buffer_free(buffer);
+}
+
+/*
+ * Test copy-on-write in device pages.
+ * In case of writing to COW private page(s), a page fault will migrate pages
+ * back to system memory first. Then, these pages will be duplicated. In case
+ * of COW device coherent type, pages are duplicated directly from device
+ * memory.
+ */
+TEST_F(hmm, hmm_cow_in_device)
+{
+	struct hmm_buffer *buffer;
+	unsigned long npages;
+	unsigned long size;
+	unsigned long i;
+	int *ptr;
+	int ret;
+	unsigned char *m;
+	pid_t pid;
+	int status;
+
+	npages = 4;
+	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;
+
+	/* Migrate memory to device. */
+
+	ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	pid = fork();
+	if (pid == -1)
+		ASSERT_EQ(pid, 0);
+	if (!pid) {
+		/* Child process waitd for SIGTERM from the parent. */
+		while (1) {
+		}
+		perror("Should not reach this\n");
+		exit(0);
+	}
+	/* Parent process writes to COW pages(s) and gets a
+	 * new copy in system. In case of device private pages,
+	 * this write causes a migration to system mem first.
+	 */
+	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+		ptr[i] = i;
+
+	/* Terminate child and wait */
+	EXPECT_EQ(0, kill(pid, SIGTERM));
+	EXPECT_EQ(pid, waitpid(pid, &status, 0));
+	EXPECT_NE(0, WIFSIGNALED(status));
+	EXPECT_EQ(SIGTERM, WTERMSIG(status));
+
+	/* Take snapshot to CPU pagetables */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+	m = buffer->mirror;
+	for (i = 0; i < npages; i++)
+		ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[i]);
+
+	hmm_buffer_free(buffer);
+}
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
index db0270127aeb..9496346973d4 100644
--- a/tools/testing/selftests/vm/mremap_test.c
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -119,6 +119,50 @@ static unsigned long long get_mmap_min_addr(void)
 }
 
 /*
+ * This test validates that merge is called when expanding a mapping.
+ * Mapping containing three pages is created, middle page is unmapped
+ * and then the mapping containing the first page is expanded so that
+ * it fills the created hole. The two parts should merge creating
+ * single mapping with three pages.
+ */
+static void mremap_expand_merge(unsigned long page_size)
+{
+	char *test_name = "mremap expand merge";
+	FILE *fp;
+	char *line = NULL;
+	size_t len = 0;
+	bool success = false;
+	char *start = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+
+	munmap(start + page_size, page_size);
+	mremap(start, page_size, 2 * page_size, 0);
+
+	fp = fopen("/proc/self/maps", "r");
+	if (fp == NULL) {
+		ksft_test_result_fail("%s\n", test_name);
+		return;
+	}
+
+	while (getline(&line, &len, fp) != -1) {
+		char *first = strtok(line, "- ");
+		void *first_val = (void *)strtol(first, NULL, 16);
+		char *second = strtok(NULL, "- ");
+		void *second_val = (void *) strtol(second, NULL, 16);
+
+		if (first_val == start && second_val == start + 3 * page_size) {
+			success = true;
+			break;
+		}
+	}
+	if (success)
+		ksft_test_result_pass("%s\n", test_name);
+	else
+		ksft_test_result_fail("%s\n", test_name);
+	fclose(fp);
+}
+
+/*
  * Returns the start address of the mapping on success, else returns
  * NULL on failure.
  */
@@ -336,6 +380,7 @@ int main(int argc, char **argv)
 	int i, run_perf_tests;
 	unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD;
 	unsigned int pattern_seed;
+	int num_expand_tests = 1;
 	struct test test_cases[MAX_TEST];
 	struct test perf_test_cases[MAX_PERF_TEST];
 	int page_size;
@@ -407,12 +452,14 @@ int main(int argc, char **argv)
 				(threshold_mb * _1MB >= _1GB);
 
 	ksft_set_plan(ARRAY_SIZE(test_cases) + (run_perf_tests ?
-		      ARRAY_SIZE(perf_test_cases) : 0));
+		      ARRAY_SIZE(perf_test_cases) : 0) + num_expand_tests);
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++)
 		run_mremap_test_case(test_cases[i], &failures, threshold_mb,
 				     pattern_seed);
 
+	mremap_expand_merge(page_size);
+
 	if (run_perf_tests) {
 		ksft_print_msg("\n%s\n",
 		 "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:");
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 41fce8bea929..249295a10f56 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -121,10 +121,17 @@ run_test ./gup_test -a
 run_test ./gup_test -ct -F 0x1 0 19 0x1000
 
 run_test ./userfaultfd anon 20 16
-# Test requires source and destination huge pages.  Size of source
-# (half_ufd_size_MB) is passed as argument to test.
+run_test ./userfaultfd anon:dev 20 16
+# Hugetlb tests require source and destination huge pages. Pass in half the
+# size ($half_ufd_size_MB), which is used for *each*.
 run_test ./userfaultfd hugetlb "$half_ufd_size_MB" 32
+run_test ./userfaultfd hugetlb:dev "$half_ufd_size_MB" 32
+run_test ./userfaultfd hugetlb_shared "$half_ufd_size_MB" 32 "$mnt"/uffd-test
+rm -f "$mnt"/uffd-test
+run_test ./userfaultfd hugetlb_shared:dev "$half_ufd_size_MB" 32 "$mnt"/uffd-test
+rm -f "$mnt"/uffd-test
 run_test ./userfaultfd shmem 20 16
+run_test ./userfaultfd shmem:dev 20 16
 
 #cleanup
 umount "$mnt"
@@ -151,7 +158,7 @@ if [ $VADDR64 -ne 0 ]; then
 	run_test ./virtual_address_range
 
 	# virtual address 128TB switch test
-	run_test ./va_128TBswitch
+	run_test ./va_128TBswitch.sh
 fi # VADDR64
 
 # vmalloc stability smoke test
@@ -179,4 +186,11 @@ run_test ./ksm_tests -N -m 1
 # KSM test with 2 NUMA nodes and merge_across_nodes = 0
 run_test ./ksm_tests -N -m 0
 
+# protection_keys tests
+if [ $VADDR64 -eq 0 ]; then
+	run_test ./protection_keys_32
+else
+	run_test ./protection_keys_64
+fi
+
 exit $exitcode
diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/vm/test_hmm.sh
index 0647b525a625..539c9371e592 100755
--- a/tools/testing/selftests/vm/test_hmm.sh
+++ b/tools/testing/selftests/vm/test_hmm.sh
@@ -40,11 +40,26 @@ check_test_requirements()
 
 load_driver()
 {
-	modprobe $DRIVER > /dev/null 2>&1
+	if [ $# -eq 0 ]; then
+		modprobe $DRIVER > /dev/null 2>&1
+	else
+		if [ $# -eq 2 ]; then
+			modprobe $DRIVER spm_addr_dev0=$1 spm_addr_dev1=$2
+				> /dev/null 2>&1
+		else
+			echo "Missing module parameters. Make sure pass"\
+			"spm_addr_dev0 and spm_addr_dev1"
+			usage
+		fi
+	fi
 	if [ $? == 0 ]; then
 		major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices)
 		mknod /dev/hmm_dmirror0 c $major 0
 		mknod /dev/hmm_dmirror1 c $major 1
+		if [ $# -eq 2 ]; then
+			mknod /dev/hmm_dmirror2 c $major 2
+			mknod /dev/hmm_dmirror3 c $major 3
+		fi
 	fi
 }
 
@@ -58,7 +73,7 @@ run_smoke()
 {
 	echo "Running smoke test. Note, this test provides basic coverage."
 
-	load_driver
+	load_driver $1 $2
 	$(dirname "${BASH_SOURCE[0]}")/hmm-tests
 	unload_driver
 }
@@ -75,6 +90,9 @@ usage()
 	echo "# Smoke testing"
 	echo "./${TEST_NAME}.sh smoke"
 	echo
+	echo "# Smoke testing with SPM enabled"
+	echo "./${TEST_NAME}.sh smoke <spm_addr_dev0> <spm_addr_dev1>"
+	echo
 	exit 0
 }
 
@@ -84,7 +102,7 @@ function run_test()
 		usage
 	else
 		if [ "$1" = "smoke" ]; then
-			run_smoke
+			run_smoke $2 $3
 		else
 			usage
 		fi
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 4bc24581760d..28b881523d15 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -77,6 +77,9 @@ static int bounces;
 #define TEST_SHMEM	3
 static int test_type;
 
+/* test using /dev/userfaultfd, instead of userfaultfd(2) */
+static bool test_dev_userfaultfd;
+
 /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */
 #define ALARM_INTERVAL_SECS 10
 static volatile bool test_uffdio_copy_eexist = true;
@@ -125,6 +128,8 @@ struct uffd_stats {
 const char *examples =
     "# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
     "./userfaultfd anon 100 99999\n\n"
+    "# Run the same anonymous memory test, but using /dev/userfaultfd:\n"
+    "./userfaultfd anon:dev 100 99999\n\n"
     "# Run share memory test on 1GiB region with 99 bounces:\n"
     "./userfaultfd shmem 1000 99\n\n"
     "# Run hugetlb memory test on 256MiB region with 50 bounces:\n"
@@ -141,6 +146,13 @@ static void usage(void)
 		"[hugetlbfs_file]\n\n");
 	fprintf(stderr, "Supported <test type>: anon, hugetlb, "
 		"hugetlb_shared, shmem\n\n");
+	fprintf(stderr, "'Test mods' can be joined to the test type string with a ':'. "
+		"Supported mods:\n");
+	fprintf(stderr, "\tdev - Use /dev/userfaultfd instead of userfaultfd(2)\n");
+	fprintf(stderr, "\nExample test mod usage:\n");
+	fprintf(stderr, "# Run anonymous memory test with /dev/userfaultfd:\n");
+	fprintf(stderr, "./userfaultfd anon:dev 100 99999\n\n");
+
 	fprintf(stderr, "Examples:\n\n");
 	fprintf(stderr, "%s", examples);
 	exit(1);
@@ -154,12 +166,14 @@ static void usage(void)
 			ret, __LINE__);				\
 	} while (0)
 
-#define err(fmt, ...)				\
+#define errexit(exitcode, fmt, ...)		\
 	do {					\
 		_err(fmt, ##__VA_ARGS__);	\
-		exit(1);			\
+		exit(exitcode);			\
 	} while (0)
 
+#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__)
+
 static void uffd_stats_reset(struct uffd_stats *uffd_stats,
 			     unsigned long n_cpus)
 {
@@ -383,13 +397,31 @@ static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls)
 	}
 }
 
+static void __userfaultfd_open_dev(void)
+{
+	int fd;
+
+	uffd = -1;
+	fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		return;
+
+	uffd = ioctl(fd, USERFAULTFD_IOC_NEW,
+		     O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
+	close(fd);
+}
+
 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 (test_dev_userfaultfd)
+		__userfaultfd_open_dev();
+	else
+		uffd = syscall(__NR_userfaultfd,
+			       O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
 	if (uffd < 0)
-		err("userfaultfd syscall not available in this kernel");
+		errexit(KSFT_SKIP, "creating userfaultfd failed");
 	uffd_flags = fcntl(uffd, F_GETFD, NULL);
 
 	uffdio_api.api = UFFD_API;
@@ -931,7 +963,7 @@ static int faulting_process(int signal_test)
 	unsigned long split_nr_pages;
 	unsigned long lastnr;
 	struct sigaction act;
-	unsigned long signalled = 0;
+	volatile unsigned long signalled = 0;
 
 	split_nr_pages = (nr_pages + 1) / 2;
 
@@ -946,7 +978,7 @@ static int faulting_process(int signal_test)
 	}
 
 	for (nr = 0; nr < split_nr_pages; nr++) {
-		int steps = 1;
+		volatile int steps = 1;
 		unsigned long offset = nr * page_size;
 
 		if (signal_test) {
@@ -1584,8 +1616,6 @@ unsigned long default_huge_page_size(void)
 
 static void set_test_type(const char *type)
 {
-	uint64_t features = UFFD_API_FEATURES;
-
 	if (!strcmp(type, "anon")) {
 		test_type = TEST_ANON;
 		uffd_test_ops = &anon_uffd_test_ops;
@@ -1603,9 +1633,27 @@ static void set_test_type(const char *type)
 		test_type = TEST_SHMEM;
 		uffd_test_ops = &shmem_uffd_test_ops;
 		test_uffdio_minor = true;
-	} else {
-		err("Unknown test type: %s", type);
 	}
+}
+
+static void parse_test_type_arg(const char *raw_type)
+{
+	char *buf = strdup(raw_type);
+	uint64_t features = UFFD_API_FEATURES;
+
+	while (buf) {
+		const char *token = strsep(&buf, ":");
+
+		if (!test_type)
+			set_test_type(token);
+		else if (!strcmp(token, "dev"))
+			test_dev_userfaultfd = true;
+		else
+			err("unrecognized test mod '%s'", token);
+	}
+
+	if (!test_type)
+		err("failed to parse test type argument: '%s'", raw_type);
 
 	if (test_type == TEST_HUGETLB)
 		page_size = default_huge_page_size();
@@ -1653,7 +1701,7 @@ int main(int argc, char **argv)
 		err("failed to arm SIGALRM");
 	alarm(ALARM_INTERVAL_SECS);
 
-	set_test_type(argv[1]);
+	parse_test_type_arg(argv[1]);
 
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size /
diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/vm/va_128TBswitch.sh
new file mode 100644
index 000000000000..767a6465b5d2
--- /dev/null
+++ b/tools/testing/selftests/vm/va_128TBswitch.sh
@@ -0,0 +1,39 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2022 Adam Sindelar (Meta) <adam@wowsignal.io>
+#
+# This is a test for mmap behavior with 5-level paging. This script wraps the
+# real test to check that the kernel is configured to support at least 5
+# pagetable levels.
+
+# 1 means the test failed
+exitcode=1
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+die()
+{
+    echo "$1"
+    exit $exitcode
+}
+
+check_test_requirements()
+{
+    local config="/proc/config.gz"
+    [[ -f "${config}" ]] || config="/boot/config-$(uname -r)"
+    [[ -f "${config}" ]] || die "Cannot find kernel config in /proc or /boot"
+
+    # gzip -dcfq automatically handles both compressed and plaintext input.
+    # See man 1 gzip under '-f'.
+    local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
+
+    if [[ "${pg_table_levels}" -lt 5 ]]; then
+        echo "$0: PG_TABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
+        exit $ksft_skip
+    fi
+}
+
+check_test_requirements
+./va_128TBswitch