Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few MM hotfixes

 - kthread, tools, scripts, ntfs and ocfs2

 - some of MM

Subsystems affected by this patch series: kthread, tools, scripts, ntfs,
ocfs2 and mm (hofixes, pagealloc, slab-generic, slab, slub, kcsan,
debug, pagecache, gup, swap, shmem, memcg, pagemap, mremap, mincore,
sparsemem, vmalloc, kasan, pagealloc, hugetlb and vmscan).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  mm: vmscan: consistent update to pgrefill
  mm/vmscan.c: fix typo
  khugepaged: khugepaged_test_exit() check mmget_still_valid()
  khugepaged: retract_page_tables() remember to test exit
  khugepaged: collapse_pte_mapped_thp() protect the pmd lock
  khugepaged: collapse_pte_mapped_thp() flush the right range
  mm/hugetlb: fix calculation of adjust_range_if_pmd_sharing_possible
  mm: thp: replace HTTP links with HTTPS ones
  mm/page_alloc: fix memalloc_nocma_{save/restore} APIs
  mm/page_alloc.c: skip setting nodemask when we are in interrupt
  mm/page_alloc: fallbacks at most has 3 elements
  mm/page_alloc: silence a KASAN false positive
  mm/page_alloc.c: remove unnecessary end_bitidx for [set|get]_pfnblock_flags_mask()
  mm/page_alloc.c: simplify pageblock bitmap access
  mm/page_alloc.c: extract the common part in pfn_to_bitidx()
  mm/page_alloc.c: replace the definition of NR_MIGRATETYPE_BITS with PB_migratetype_bits
  mm/shuffle: remove dynamic reconfiguration
  mm/memory_hotplug: document why shuffle_zone() is relevant
  mm/page_alloc: remove nr_free_pagecache_pages()
  mm: remove vm_total_pages
  ...

14 files changed, 987 insertions, 6 deletions

diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py
new file mode 100644
index 000000000000..c4225ed63565
--- /dev/null
+++ b/tools/cgroup/memcg_slabinfo.py
@@ -0,0 +1,226 @@
+#!/usr/bin/env drgn
+#
+# Copyright (C) 2020 Roman Gushchin <guro@fb.com>
+# Copyright (C) 2020 Facebook
+
+from os import stat
+import argparse
+import sys
+
+from drgn.helpers.linux import list_for_each_entry, list_empty
+from drgn.helpers.linux import for_each_page
+from drgn.helpers.linux.cpumask import for_each_online_cpu
+from drgn.helpers.linux.percpu import per_cpu_ptr
+from drgn import container_of, FaultError, Object
+
+
+DESC = """
+This is a drgn script to provide slab statistics for memory cgroups.
+It supports cgroup v2 and v1 and can emulate memory.kmem.slabinfo
+interface of cgroup v1.
+For drgn, visit https://github.com/osandov/drgn.
+"""
+
+
+MEMCGS = {}
+
+OO_SHIFT = 16
+OO_MASK = ((1 << OO_SHIFT) - 1)
+
+
+def err(s):
+    print('slabinfo.py: error: %s' % s, file=sys.stderr, flush=True)
+    sys.exit(1)
+
+
+def find_memcg_ids(css=prog['root_mem_cgroup'].css, prefix=''):
+    if not list_empty(css.children.address_of_()):
+        for css in list_for_each_entry('struct cgroup_subsys_state',
+                                       css.children.address_of_(),
+                                       'sibling'):
+            name = prefix + '/' + css.cgroup.kn.name.string_().decode('utf-8')
+            memcg = container_of(css, 'struct mem_cgroup', 'css')
+            MEMCGS[css.cgroup.kn.id.value_()] = memcg
+            find_memcg_ids(css, name)
+
+
+def is_root_cache(s):
+    try:
+        return False if s.memcg_params.root_cache else True
+    except AttributeError:
+        return True
+
+
+def cache_name(s):
+    if is_root_cache(s):
+        return s.name.string_().decode('utf-8')
+    else:
+        return s.memcg_params.root_cache.name.string_().decode('utf-8')
+
+
+# SLUB
+
+def oo_order(s):
+    return s.oo.x >> OO_SHIFT
+
+
+def oo_objects(s):
+    return s.oo.x & OO_MASK
+
+
+def count_partial(n, fn):
+    nr_pages = 0
+    for page in list_for_each_entry('struct page', n.partial.address_of_(),
+                                    'lru'):
+         nr_pages += fn(page)
+    return nr_pages
+
+
+def count_free(page):
+    return page.objects - page.inuse
+
+
+def slub_get_slabinfo(s, cfg):
+    nr_slabs = 0
+    nr_objs = 0
+    nr_free = 0
+
+    for node in range(cfg['nr_nodes']):
+        n = s.node[node]
+        nr_slabs += n.nr_slabs.counter.value_()
+        nr_objs += n.total_objects.counter.value_()
+        nr_free += count_partial(n, count_free)
+
+    return {'active_objs': nr_objs - nr_free,
+            'num_objs': nr_objs,
+            'active_slabs': nr_slabs,
+            'num_slabs': nr_slabs,
+            'objects_per_slab': oo_objects(s),
+            'cache_order': oo_order(s),
+            'limit': 0,
+            'batchcount': 0,
+            'shared': 0,
+            'shared_avail': 0}
+
+
+def cache_show(s, cfg, objs):
+    if cfg['allocator'] == 'SLUB':
+        sinfo = slub_get_slabinfo(s, cfg)
+    else:
+        err('SLAB isn\'t supported yet')
+
+    if cfg['shared_slab_pages']:
+        sinfo['active_objs'] = objs
+        sinfo['num_objs'] = objs
+
+    print('%-17s %6lu %6lu %6u %4u %4d'
+          ' : tunables %4u %4u %4u'
+          ' : slabdata %6lu %6lu %6lu' % (
+              cache_name(s), sinfo['active_objs'], sinfo['num_objs'],
+              s.size, sinfo['objects_per_slab'], 1 << sinfo['cache_order'],
+              sinfo['limit'], sinfo['batchcount'], sinfo['shared'],
+              sinfo['active_slabs'], sinfo['num_slabs'],
+              sinfo['shared_avail']))
+
+
+def detect_kernel_config():
+    cfg = {}
+
+    cfg['nr_nodes'] = prog['nr_online_nodes'].value_()
+
+    if prog.type('struct kmem_cache').members[1][1] == 'flags':
+        cfg['allocator'] = 'SLUB'
+    elif prog.type('struct kmem_cache').members[1][1] == 'batchcount':
+        cfg['allocator'] = 'SLAB'
+    else:
+        err('Can\'t determine the slab allocator')
+
+    cfg['shared_slab_pages'] = False
+    try:
+        if prog.type('struct obj_cgroup'):
+            cfg['shared_slab_pages'] = True
+    except:
+        pass
+
+    return cfg
+
+
+def for_each_slab_page(prog):
+    PGSlab = 1 << prog.constant('PG_slab')
+    PGHead = 1 << prog.constant('PG_head')
+
+    for page in for_each_page(prog):
+        try:
+            if page.flags.value_() & PGSlab:
+                yield page
+        except FaultError:
+            pass
+
+
+def main():
+    parser = argparse.ArgumentParser(description=DESC,
+                                     formatter_class=
+                                     argparse.RawTextHelpFormatter)
+    parser.add_argument('cgroup', metavar='CGROUP',
+                        help='Target memory cgroup')
+    args = parser.parse_args()
+
+    try:
+        cgroup_id = stat(args.cgroup).st_ino
+        find_memcg_ids()
+        memcg = MEMCGS[cgroup_id]
+    except KeyError:
+        err('Can\'t find the memory cgroup')
+
+    cfg = detect_kernel_config()
+
+    print('# name            <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>'
+          ' : tunables <limit> <batchcount> <sharedfactor>'
+          ' : slabdata <active_slabs> <num_slabs> <sharedavail>')
+
+    if cfg['shared_slab_pages']:
+        obj_cgroups = set()
+        stats = {}
+        caches = {}
+
+        # find memcg pointers belonging to the specified cgroup
+        obj_cgroups.add(memcg.objcg.value_())
+        for ptr in list_for_each_entry('struct obj_cgroup',
+                                       memcg.objcg_list.address_of_(),
+                                       'list'):
+            obj_cgroups.add(ptr.value_())
+
+        # look over all slab pages, belonging to non-root memcgs
+        # and look for objects belonging to the given memory cgroup
+        for page in for_each_slab_page(prog):
+            objcg_vec_raw = page.obj_cgroups.value_()
+            if objcg_vec_raw == 0:
+                continue
+            cache = page.slab_cache
+            if not cache:
+                continue
+            addr = cache.value_()
+            caches[addr] = cache
+            # clear the lowest bit to get the true obj_cgroups
+            objcg_vec = Object(prog, page.obj_cgroups.type_,
+                               value=objcg_vec_raw & ~1)
+
+            if addr not in stats:
+                stats[addr] = 0
+
+            for i in range(oo_objects(cache)):
+                if objcg_vec[i].value_() in obj_cgroups:
+                    stats[addr] += 1
+
+        for addr in caches:
+            if stats[addr] > 0:
+                cache_show(caches[addr], cfg, stats[addr])
+
+    else:
+        for s in list_for_each_entry('struct kmem_cache',
+                                     memcg.kmem_caches.address_of_(),
+                                     'memcg_params.kmem_caches_node'):
+            cache_show(s, cfg, None)
+
+
+main()
diff --git a/tools/include/linux/jhash.h b/tools/include/linux/jhash.h
index 348c6f47e4cc..af8d0fe1c6ce 100644
--- a/tools/include/linux/jhash.h
+++ b/tools/include/linux/jhash.h
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net)
  *
- * http://burtleburtle.net/bob/hash/
+ * https://burtleburtle.net/bob/hash/
  *
  * These are the credits from Bob's sources:
  *
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
index 06ac7bd2144b..727396de6be5 100644
--- a/tools/lib/rbtree.c
+++ b/tools/lib/rbtree.c
@@ -13,7 +13,7 @@
 #include <linux/export.h>
 
 /*
- * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ * red-black trees properties:  https://en.wikipedia.org/wiki/Rbtree
  *
  *  1) A node is either red or black
  *  2) The root is black
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index b77837f75a0d..ad7799c85429 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -379,7 +379,7 @@ enum tep_errno {
 	 * errno since SUS requires the errno has distinct positive values.
 	 * See 'Issue 6' in the link below.
 	 *
-	 * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
+	 * https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
 	 */
 	__TEP_ERRNO__START			= -100000,
 
diff --git a/tools/testing/ktest/examples/README b/tools/testing/ktest/examples/README
index a12d295a09d8..4f048789b260 100644
--- a/tools/testing/ktest/examples/README
+++ b/tools/testing/ktest/examples/README
@@ -11,7 +11,7 @@ crosstests.conf - this config shows an example of testing a git repo against
     lots of different architectures. It only does build tests, but makes
     it easy to compile test different archs. You can download the arch
     cross compilers from:
-  http://kernel.org/pub/tools/crosstool/files/bin/x86_64/
+  https://kernel.org/pub/tools/crosstool/files/bin/x86_64/
 
 test.conf - A generic example of a config. This is based on an actual config
      used to perform real testing.
diff --git a/tools/testing/ktest/examples/crosstests.conf b/tools/testing/ktest/examples/crosstests.conf
index 6907f32590b2..3b15e85f26bd 100644
--- a/tools/testing/ktest/examples/crosstests.conf
+++ b/tools/testing/ktest/examples/crosstests.conf
@@ -3,7 +3,7 @@
 #
 # In this config, it is expected that the tool chains from:
 #
-#   http://kernel.org/pub/tools/crosstool/files/bin/x86_64/
+#   https://kernel.org/pub/tools/crosstool/files/bin/x86_64/
 #
 # running on a x86_64 system have been downloaded and installed into:
 #
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index e03bc15ce731..9018f45d631d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -32,6 +32,7 @@ TARGETS += lkdtm
 TARGETS += membarrier
 TARGETS += memfd
 TARGETS += memory-hotplug
+TARGETS += mincore
 TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index aa6de65b0838..84cfcabea838 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -2,3 +2,4 @@
 test_memcontrol
 test_core
 test_freezer
+test_kmem
\ No newline at end of file
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 967f268fde74..f027d933595b 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -6,11 +6,13 @@ all:
 TEST_FILES     := with_stress.sh
 TEST_PROGS     := test_stress.sh
 TEST_GEN_PROGS = test_memcontrol
+TEST_GEN_PROGS += test_kmem
 TEST_GEN_PROGS += test_core
 TEST_GEN_PROGS += test_freezer
 
 include ../lib.mk
 
 $(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_kmem: cgroup_util.c ../clone3/clone3_selftests.h
 $(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h
 $(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 8a637ca7d73a..05853b0b8831 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -106,7 +106,7 @@ int cg_read_strcmp(const char *cgroup, const char *control,
 
 	/* Handle the case of comparing against empty string */
 	if (!expected)
-		size = 32;
+		return -1;
 	else
 		size = strlen(expected) + 1;
 
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
new file mode 100644
index 000000000000..5224dae216e5
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <sys/sysinfo.h>
+#include <pthread.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+
+static int alloc_dcache(const char *cgroup, void *arg)
+{
+	unsigned long i;
+	struct stat st;
+	char buf[128];
+
+	for (i = 0; i < (unsigned long)arg; i++) {
+		snprintf(buf, sizeof(buf),
+			"/something-non-existent-with-a-long-name-%64lu-%d",
+			 i, getpid());
+		stat(buf, &st);
+	}
+
+	return 0;
+}
+
+/*
+ * This test allocates 100000 of negative dentries with long names.
+ * Then it checks that "slab" in memory.stat is larger than 1M.
+ * Then it sets memory.high to 1M and checks that at least 1/2
+ * of slab memory has been reclaimed.
+ */
+static int test_kmem_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+	long slab0, slab1, current;
+
+	cg = cg_name(root, "kmem_basic_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, alloc_dcache, (void *)100000))
+		goto cleanup;
+
+	slab0 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab0 < (1 << 20))
+		goto cleanup;
+
+	cg_write(cg, "memory.high", "1M");
+	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab1 <= 0)
+		goto cleanup;
+
+	current = cg_read_long(cg, "memory.current");
+	if (current <= 0)
+		goto cleanup;
+
+	if (slab1 < slab0 / 2 && current < slab0 / 2)
+		ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+static void *alloc_kmem_fn(void *arg)
+{
+	alloc_dcache(NULL, (void *)100);
+	return NULL;
+}
+
+static int alloc_kmem_smp(const char *cgroup, void *arg)
+{
+	int nr_threads = 2 * get_nprocs();
+	pthread_t *tinfo;
+	unsigned long i;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &alloc_kmem_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return -1;
+		}
+	}
+
+	for (i = 0; i < nr_threads; i++) {
+		ret = pthread_join(tinfo[i], NULL);
+		if (ret)
+			break;
+	}
+
+	free(tinfo);
+	return ret;
+}
+
+static int cg_run_in_subcgroups(const char *parent,
+				int (*fn)(const char *cgroup, void *arg),
+				void *arg, int times)
+{
+	char *child;
+	int i;
+
+	for (i = 0; i < times; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child)
+			return -1;
+
+		if (cg_create(child)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		if (cg_run(child, fn, NULL)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		cg_destroy(child);
+		free(child);
+	}
+
+	return 0;
+}
+
+/*
+ * The test creates and destroys a large number of cgroups. In each cgroup it
+ * allocates some slab memory (mostly negative dentries) using 2 * NR_CPUS
+ * threads. Then it checks the sanity of numbers on the parent level:
+ * the total size of the cgroups should be roughly equal to
+ * anon + file + slab + kernel_stack.
+ */
+static int test_kmem_memcg_deletion(const char *root)
+{
+	long current, slab, anon, file, kernel_stack, sum;
+	int ret = KSFT_FAIL;
+	char *parent;
+
+	parent = cg_name(root, "kmem_memcg_deletion_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_kmem_smp, NULL, 100))
+		goto cleanup;
+
+	current = cg_read_long(parent, "memory.current");
+	slab = cg_read_key_long(parent, "memory.stat", "slab ");
+	anon = cg_read_key_long(parent, "memory.stat", "anon ");
+	file = cg_read_key_long(parent, "memory.stat", "file ");
+	kernel_stack = cg_read_key_long(parent, "memory.stat", "kernel_stack ");
+	if (current < 0 || slab < 0 || anon < 0 || file < 0 ||
+	    kernel_stack < 0)
+		goto cleanup;
+
+	sum = slab + anon + file + kernel_stack;
+	if (abs(sum - current) < 4096 * 32 * 2 * get_nprocs()) {
+		ret = KSFT_PASS;
+	} else {
+		printf("memory.current = %ld\n", current);
+		printf("slab + anon + file + kernel_stack = %ld\n", sum);
+		printf("slab = %ld\n", slab);
+		printf("anon = %ld\n", anon);
+		printf("file = %ld\n", file);
+		printf("kernel_stack = %ld\n", kernel_stack);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * The test reads the entire /proc/kpagecgroup. If the operation went
+ * successfully (and the kernel didn't panic), the test is treated as passed.
+ */
+static int test_kmem_proc_kpagecgroup(const char *root)
+{
+	unsigned long buf[128];
+	int ret = KSFT_FAIL;
+	ssize_t len;
+	int fd;
+
+	fd = open("/proc/kpagecgroup", O_RDONLY);
+	if (fd < 0)
+		return ret;
+
+	do {
+		len = read(fd, buf, sizeof(buf));
+	} while (len > 0);
+
+	if (len == 0)
+		ret = KSFT_PASS;
+
+	close(fd);
+	return ret;
+}
+
+static void *pthread_wait_fn(void *arg)
+{
+	sleep(100);
+	return NULL;
+}
+
+static int spawn_1000_threads(const char *cgroup, void *arg)
+{
+	int nr_threads = 1000;
+	pthread_t *tinfo;
+	unsigned long i;
+	long stack;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &pthread_wait_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return(-1);
+		}
+	}
+
+	stack = cg_read_key_long(cgroup, "memory.stat", "kernel_stack ");
+	if (stack >= 4096 * 1000)
+		ret = 0;
+
+	free(tinfo);
+	return ret;
+}
+
+/*
+ * The test spawns a process, which spawns 1000 threads. Then it checks
+ * that memory.stat's kernel_stack is at least 1000 pages large.
+ */
+static int test_kmem_kernel_stacks(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+
+	cg = cg_name(root, "kmem_kernel_stacks_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, spawn_1000_threads, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+/*
+ * This test sequentionally creates 30 child cgroups, allocates some
+ * kernel memory in each of them, and deletes them. Then it checks
+ * that the number of dying cgroups on the parent level is 0.
+ */
+static int test_kmem_dead_cgroups(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent;
+	long dead;
+	int i;
+
+	parent = cg_name(root, "kmem_dead_cgroups_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
+		goto cleanup;
+
+	for (i = 0; i < 5; i++) {
+		dead = cg_read_key_long(parent, "cgroup.stat",
+					"nr_dying_descendants ");
+		if (dead == 0) {
+			ret = KSFT_PASS;
+			break;
+		}
+		/*
+		 * Reclaiming cgroups might take some time,
+		 * let's wait a bit and repeat.
+		 */
+		sleep(1);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct kmem_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_kmem_basic),
+	T(test_kmem_memcg_deletion),
+	T(test_kmem_proc_kpagecgroup),
+	T(test_kmem_kernel_stacks),
+	T(test_kmem_dead_cgroups),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i, ret = EXIT_SUCCESS;
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ret = EXIT_FAILURE;
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/mincore/.gitignore b/tools/testing/selftests/mincore/.gitignore
new file mode 100644
index 000000000000..15c4dfc2df00
--- /dev/null
+++ b/tools/testing/selftests/mincore/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+mincore_selftest
diff --git a/tools/testing/selftests/mincore/Makefile b/tools/testing/selftests/mincore/Makefile
new file mode 100644
index 000000000000..38c7db1e8926
--- /dev/null
+++ b/tools/testing/selftests/mincore/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0+
+
+CFLAGS += -Wall
+
+TEST_GEN_PROGS := mincore_selftest
+include ../lib.mk
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
new file mode 100644
index 000000000000..5a1e85ff5d32
--- /dev/null
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * kselftest suite for mincore().
+ *
+ * Copyright (C) 2020 Collabora, Ltd.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <string.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+/* Default test file size: 4MB */
+#define MB (1UL << 20)
+#define FILE_SIZE (4 * MB)
+
+
+/*
+ * Tests the user interface. This test triggers most of the documented
+ * error conditions in mincore().
+ */
+TEST(basic_interface)
+{
+	int retval;
+	int page_size;
+	unsigned char vec[1];
+	char *addr;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/* Query a 0 byte sized range */
+	retval = mincore(0, 0, vec);
+	EXPECT_EQ(0, retval);
+
+	/* Addresses in the specified range are invalid or unmapped */
+	errno = 0;
+	retval = mincore(NULL, page_size, vec);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(ENOMEM, errno);
+
+	errno = 0;
+	addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+		MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+
+	/* <addr> argument is not page-aligned */
+	errno = 0;
+	retval = mincore(addr + 1, page_size, vec);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(EINVAL, errno);
+
+	/* <length> argument is too large */
+	errno = 0;
+	retval = mincore(addr, -1, vec);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(ENOMEM, errno);
+
+	/* <vec> argument points to an illegal address */
+	errno = 0;
+	retval = mincore(addr, page_size, NULL);
+	EXPECT_EQ(-1, retval);
+	EXPECT_EQ(EFAULT, errno);
+	munmap(addr, page_size);
+}
+
+
+/*
+ * Test mincore() behavior on a private anonymous page mapping.
+ * Check that the page is not loaded into memory right after the mapping
+ * but after accessing it (on-demand allocation).
+ * Then free the page and check that it's not memory-resident.
+ */
+TEST(check_anonymous_locked_pages)
+{
+	unsigned char vec[1];
+	char *addr;
+	int retval;
+	int page_size;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/* Map one page and check it's not memory-resident */
+	errno = 0;
+	addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(0, vec[0]) {
+		TH_LOG("Page found in memory before use");
+	}
+
+	/* Touch the page and check again. It should now be in memory */
+	addr[0] = 1;
+	mlock(addr, page_size);
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[0]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	/*
+	 * It shouldn't be memory-resident after unlocking it and
+	 * marking it as unneeded.
+	 */
+	munlock(addr, page_size);
+	madvise(addr, page_size, MADV_DONTNEED);
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(0, vec[0]) {
+		TH_LOG("Page in memory after being zapped");
+	}
+	munmap(addr, page_size);
+}
+
+
+/*
+ * Check mincore() behavior on huge pages.
+ * This test will be skipped if the mapping fails (ie. if there are no
+ * huge pages available).
+ *
+ * Make sure the system has at least one free huge page, check
+ * "HugePages_Free" in /proc/meminfo.
+ * Increment /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages if
+ * needed.
+ */
+TEST(check_huge_pages)
+{
+	unsigned char vec[1];
+	char *addr;
+	int retval;
+	int page_size;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	errno = 0;
+	addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE,
+		MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+		-1, 0);
+	if (addr == MAP_FAILED) {
+		if (errno == ENOMEM)
+			SKIP(return, "No huge pages available.");
+		else
+			TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(0, vec[0]) {
+		TH_LOG("Page found in memory before use");
+	}
+
+	addr[0] = 1;
+	mlock(addr, page_size);
+	retval = mincore(addr, page_size, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[0]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	munlock(addr, page_size);
+	munmap(addr, page_size);
+}
+
+
+/*
+ * Test mincore() behavior on a file-backed page.
+ * No pages should be loaded into memory right after the mapping. Then,
+ * accessing any address in the mapping range should load the page
+ * containing the address and a number of subsequent pages (readahead).
+ *
+ * The actual readahead settings depend on the test environment, so we
+ * can't make a lot of assumptions about that. This test covers the most
+ * general cases.
+ */
+TEST(check_file_mmap)
+{
+	unsigned char *vec;
+	int vec_size;
+	char *addr;
+	int retval;
+	int page_size;
+	int fd;
+	int i;
+	int ra_pages = 0;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	vec_size = FILE_SIZE / page_size;
+	if (FILE_SIZE % page_size)
+		vec_size++;
+
+	vec = calloc(vec_size, sizeof(unsigned char));
+	ASSERT_NE(NULL, vec) {
+		TH_LOG("Can't allocate array");
+	}
+
+	errno = 0;
+	fd = open(".", O_TMPFILE | O_RDWR, 0600);
+	ASSERT_NE(-1, fd) {
+		TH_LOG("Can't create temporary file: %s",
+			strerror(errno));
+	}
+	errno = 0;
+	retval = fallocate(fd, 0, 0, FILE_SIZE);
+	ASSERT_EQ(0, retval) {
+		TH_LOG("Error allocating space for the temporary file: %s",
+			strerror(errno));
+	}
+
+	/*
+	 * Map the whole file, the pages shouldn't be fetched yet.
+	 */
+	errno = 0;
+	addr = mmap(NULL, FILE_SIZE, PROT_READ | PROT_WRITE,
+			MAP_SHARED, fd, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	for (i = 0; i < vec_size; i++) {
+		ASSERT_EQ(0, vec[i]) {
+			TH_LOG("Unexpected page in memory");
+		}
+	}
+
+	/*
+	 * Touch a page in the middle of the mapping. We expect the next
+	 * few pages (the readahead window) to be populated too.
+	 */
+	addr[FILE_SIZE / 2] = 1;
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[FILE_SIZE / 2 / page_size]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	i = FILE_SIZE / 2 / page_size + 1;
+	while (i < vec_size && vec[i]) {
+		ra_pages++;
+		i++;
+	}
+	EXPECT_GT(ra_pages, 0) {
+		TH_LOG("No read-ahead pages found in memory");
+	}
+
+	EXPECT_LT(i, vec_size) {
+		TH_LOG("Read-ahead pages reached the end of the file");
+	}
+	/*
+	 * End of the readahead window. The rest of the pages shouldn't
+	 * be in memory.
+	 */
+	if (i < vec_size) {
+		while (i < vec_size && !vec[i])
+			i++;
+		EXPECT_EQ(vec_size, i) {
+			TH_LOG("Unexpected page in memory beyond readahead window");
+		}
+	}
+
+	munmap(addr, FILE_SIZE);
+	close(fd);
+	free(vec);
+}
+
+
+/*
+ * Test mincore() behavior on a page backed by a tmpfs file.  This test
+ * performs the same steps as the previous one. However, we don't expect
+ * any readahead in this case.
+ */
+TEST(check_tmpfs_mmap)
+{
+	unsigned char *vec;
+	int vec_size;
+	char *addr;
+	int retval;
+	int page_size;
+	int fd;
+	int i;
+	int ra_pages = 0;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	vec_size = FILE_SIZE / page_size;
+	if (FILE_SIZE % page_size)
+		vec_size++;
+
+	vec = calloc(vec_size, sizeof(unsigned char));
+	ASSERT_NE(NULL, vec) {
+		TH_LOG("Can't allocate array");
+	}
+
+	errno = 0;
+	fd = open("/dev/shm", O_TMPFILE | O_RDWR, 0600);
+	ASSERT_NE(-1, fd) {
+		TH_LOG("Can't create temporary file: %s",
+			strerror(errno));
+	}
+	errno = 0;
+	retval = fallocate(fd, 0, 0, FILE_SIZE);
+	ASSERT_EQ(0, retval) {
+		TH_LOG("Error allocating space for the temporary file: %s",
+			strerror(errno));
+	}
+
+	/*
+	 * Map the whole file, the pages shouldn't be fetched yet.
+	 */
+	errno = 0;
+	addr = mmap(NULL, FILE_SIZE, PROT_READ | PROT_WRITE,
+			MAP_SHARED, fd, 0);
+	ASSERT_NE(MAP_FAILED, addr) {
+		TH_LOG("mmap error: %s", strerror(errno));
+	}
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	for (i = 0; i < vec_size; i++) {
+		ASSERT_EQ(0, vec[i]) {
+			TH_LOG("Unexpected page in memory");
+		}
+	}
+
+	/*
+	 * Touch a page in the middle of the mapping. We expect only
+	 * that page to be fetched into memory.
+	 */
+	addr[FILE_SIZE / 2] = 1;
+	retval = mincore(addr, FILE_SIZE, vec);
+	ASSERT_EQ(0, retval);
+	ASSERT_EQ(1, vec[FILE_SIZE / 2 / page_size]) {
+		TH_LOG("Page not found in memory after use");
+	}
+
+	i = FILE_SIZE / 2 / page_size + 1;
+	while (i < vec_size && vec[i]) {
+		ra_pages++;
+		i++;
+	}
+	ASSERT_EQ(ra_pages, 0) {
+		TH_LOG("Read-ahead pages found in memory");
+	}
+
+	munmap(addr, FILE_SIZE);
+	close(fd);
+	free(vec);
+}
+
+TEST_HARNESS_MAIN