Merge tag 'mm-nonmm-stable-2024-03-14-09-36' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:

 - Kuan-Wei Chiu has developed the well-named series "lib min_heap: Min
   heap optimizations".

 - Kuan-Wei Chiu has also sped up the library sorting code in the series
   "lib/sort: Optimize the number of swaps and comparisons".

 - Alexey Gladkov has added the ability for code running within an IPC
   namespace to alter its IPC and MQ limits. The series is "Allow to
   change ipc/mq sysctls inside ipc namespace".

 - Geert Uytterhoeven has contributed some dhrystone maintenance work in
   the series "lib: dhry: miscellaneous cleanups".

 - Ryusuke Konishi continues nilfs2 maintenance work in the series

	"nilfs2: eliminate kmap and kmap_atomic calls"
	"nilfs2: fix kernel bug at submit_bh_wbc()"

 - Nathan Chancellor has updated our build tools requirements in the
   series "Bump the minimum supported version of LLVM to 13.0.1".

 - Muhammad Usama Anjum continues with the selftests maintenance work in
   the series "selftests/mm: Improve run_vmtests.sh".

 - Oleg Nesterov has done some maintenance work against the signal code
   in the series "get_signal: minor cleanups and fix".

Plus the usual shower of singleton patches in various parts of the tree.
Please see the individual changelogs for details.

* tag 'mm-nonmm-stable-2024-03-14-09-36' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (77 commits)
  nilfs2: prevent kernel bug at submit_bh_wbc()
  nilfs2: fix failure to detect DAT corruption in btree and direct mappings
  ocfs2: enable ocfs2_listxattr for special files
  ocfs2: remove SLAB_MEM_SPREAD flag usage
  assoc_array: fix the return value in assoc_array_insert_mid_shortcut()
  buildid: use kmap_local_page()
  watchdog/core: remove sysctl handlers from public header
  nilfs2: use div64_ul() instead of do_div()
  mul_u64_u64_div_u64: increase precision by conditionally swapping a and b
  kexec: copy only happens before uchunk goes to zero
  get_signal: don't initialize ksig->info if SIGNAL_GROUP_EXIT/group_exec_task
  get_signal: hide_si_addr_tag_bits: fix the usage of uninitialized ksig
  get_signal: don't abuse ksig->info.si_signo and ksig->sig
  const_structs.checkpatch: add device_type
  Normalise "name (ad@dr)" MODULE_AUTHORs to "name <ad@dr>"
  dyndbg: replace kstrdup() + strchr() with kstrdup_and_replace()
  list: leverage list_is_head() for list_entry_is_head()
  nilfs2: MAINTAINERS: drop unreachable project mirror site
  smp: make __smp_processor_id() 0-argument macro
  fat: fix uninitialized field in nostale filehandles
  ...

9 files changed, 277 insertions, 23 deletions

diff --git a/tools/testing/selftests/filesystems/eventfd/.gitignore b/tools/testing/selftests/filesystems/eventfd/.gitignore
new file mode 100644
index 000000000000..483faf59fe4a
--- /dev/null
+++ b/tools/testing/selftests/filesystems/eventfd/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+eventfd_test
diff --git a/tools/testing/selftests/filesystems/eventfd/Makefile b/tools/testing/selftests/filesystems/eventfd/Makefile
new file mode 100644
index 000000000000..0a8e3910df15
--- /dev/null
+++ b/tools/testing/selftests/filesystems/eventfd/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += $(KHDR_INCLUDES)
+LDLIBS += -lpthread
+TEST_GEN_PROGS := eventfd_test
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/eventfd/eventfd_test.c b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c
new file mode 100644
index 000000000000..f142a137526c
--- /dev/null
+++ b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <asm/unistd.h>
+#include <linux/time_types.h>
+#include <unistd.h>
+#include <assert.h>
+#include <signal.h>
+#include <pthread.h>
+#include <sys/epoll.h>
+#include <sys/eventfd.h>
+#include "../../kselftest_harness.h"
+
+struct error {
+	int  code;
+	char msg[512];
+};
+
+static int error_set(struct error *err, int code, const char *fmt, ...)
+{
+	va_list args;
+	int r;
+
+	if (code == 0 || !err || err->code != 0)
+		return code;
+
+	err->code = code;
+	va_start(args, fmt);
+	r = vsnprintf(err->msg, sizeof(err->msg), fmt, args);
+	assert((size_t)r < sizeof(err->msg));
+	va_end(args);
+
+	return code;
+}
+
+static inline int sys_eventfd2(unsigned int count, int flags)
+{
+	return syscall(__NR_eventfd2, count, flags);
+}
+
+TEST(eventfd01)
+{
+	int fd, flags;
+
+	fd = sys_eventfd2(0, 0);
+	ASSERT_GE(fd, 0);
+
+	flags = fcntl(fd, F_GETFL);
+	// since the kernel automatically added O_RDWR.
+	EXPECT_EQ(flags, O_RDWR);
+
+	close(fd);
+}
+
+TEST(eventfd02)
+{
+	int fd, flags;
+
+	fd = sys_eventfd2(0, EFD_CLOEXEC);
+	ASSERT_GE(fd, 0);
+
+	flags = fcntl(fd, F_GETFD);
+	ASSERT_GT(flags, -1);
+	EXPECT_EQ(flags, FD_CLOEXEC);
+
+	close(fd);
+}
+
+TEST(eventfd03)
+{
+	int fd, flags;
+
+	fd = sys_eventfd2(0, EFD_NONBLOCK);
+	ASSERT_GE(fd, 0);
+
+	flags = fcntl(fd, F_GETFL);
+	ASSERT_GT(flags, -1);
+	EXPECT_EQ(flags & EFD_NONBLOCK, EFD_NONBLOCK);
+	EXPECT_EQ(flags & O_RDWR, O_RDWR);
+
+	close(fd);
+}
+
+TEST(eventfd04)
+{
+	int fd, flags;
+
+	fd = sys_eventfd2(0, EFD_CLOEXEC|EFD_NONBLOCK);
+	ASSERT_GE(fd, 0);
+
+	flags = fcntl(fd, F_GETFL);
+	ASSERT_GT(flags, -1);
+	EXPECT_EQ(flags & EFD_NONBLOCK, EFD_NONBLOCK);
+	EXPECT_EQ(flags & O_RDWR, O_RDWR);
+
+	flags = fcntl(fd, F_GETFD);
+	ASSERT_GT(flags, -1);
+	EXPECT_EQ(flags, FD_CLOEXEC);
+
+	close(fd);
+}
+
+static inline void trim_newline(char *str)
+{
+	char *pos = strrchr(str, '\n');
+
+	if (pos)
+		*pos = '\0';
+}
+
+static int verify_fdinfo(int fd, struct error *err, const char *prefix,
+		size_t prefix_len, const char *expect, ...)
+{
+	char buffer[512] = {0, };
+	char path[512] = {0, };
+	va_list args;
+	FILE *f;
+	char *line = NULL;
+	size_t n = 0;
+	int found = 0;
+	int r;
+
+	va_start(args, expect);
+	r = vsnprintf(buffer, sizeof(buffer), expect, args);
+	assert((size_t)r < sizeof(buffer));
+	va_end(args);
+
+	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd);
+	f = fopen(path, "re");
+	if (!f)
+		return error_set(err, -1, "fdinfo open failed for %d", fd);
+
+	while (getline(&line, &n, f) != -1) {
+		char *val;
+
+		if (strncmp(line, prefix, prefix_len))
+			continue;
+
+		found = 1;
+
+		val = line + prefix_len;
+		r = strcmp(val, buffer);
+		if (r != 0) {
+			trim_newline(line);
+			trim_newline(buffer);
+			error_set(err, -1, "%s '%s' != '%s'",
+				  prefix, val, buffer);
+		}
+		break;
+	}
+
+	free(line);
+	fclose(f);
+
+	if (found == 0)
+		return error_set(err, -1, "%s not found for fd %d",
+				 prefix, fd);
+
+	return 0;
+}
+
+TEST(eventfd05)
+{
+	struct error err = {0};
+	int fd, ret;
+
+	fd = sys_eventfd2(0, EFD_SEMAPHORE);
+	ASSERT_GE(fd, 0);
+
+	ret = fcntl(fd, F_GETFL);
+	ASSERT_GT(ret, -1);
+	EXPECT_EQ(ret & O_RDWR, O_RDWR);
+
+	// The semaphore could only be obtained from fdinfo.
+	ret = verify_fdinfo(fd, &err, "eventfd-semaphore: ", 19, "1\n");
+	if (ret != 0)
+		ksft_print_msg("eventfd-semaphore check failed, msg: %s\n",
+				err.msg);
+	EXPECT_EQ(ret, 0);
+
+	close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 990e9bb112c5..eb5f39a2668b 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -115,6 +115,11 @@ TEST_PROGS := run_vmtests.sh
 TEST_FILES := test_vmalloc.sh
 TEST_FILES += test_hmm.sh
 TEST_FILES += va_high_addr_switch.sh
+TEST_FILES += charge_reserved_hugetlb.sh
+TEST_FILES += hugetlb_reparenting_test.sh
+
+# required by charge_reserved_hugetlb.sh
+TEST_FILES += write_hugetlb_memory.sh
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index e14bdd4455f2..d680c00d2853 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -11,6 +11,8 @@ if [[ $(id -u) -ne 0 ]]; then
   exit $ksft_skip
 fi
 
+nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
+
 fault_limit_file=limit_in_bytes
 reservation_limit_file=rsvd.limit_in_bytes
 fault_usage_file=usage_in_bytes
@@ -582,3 +584,5 @@ if [[ $do_umount ]]; then
   umount $cgroup_path
   rmdir $cgroup_path
 fi
+
+echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
index 14d26075c863..11f9bbe7dc22 100755
--- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
@@ -11,6 +11,7 @@ if [[ $(id -u) -ne 0 ]]; then
   exit $ksft_skip
 fi
 
+nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
 usage_file=usage_in_bytes
 
 if [[ "$1" == "-cgroup-v2" ]]; then
@@ -248,5 +249,9 @@ cleanup
 
 echo ALL PASS
 
-umount $CGROUP_ROOT
-rm -rf $CGROUP_ROOT
+if [[ $do_umount ]]; then
+  umount $CGROUP_ROOT
+  rm -rf $CGROUP_ROOT
+fi
+
+echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c
index b5888d613f34..431c1277d83a 100644
--- a/tools/testing/selftests/mm/on-fault-limit.c
+++ b/tools/testing/selftests/mm/on-fault-limit.c
@@ -5,40 +5,38 @@
 #include <string.h>
 #include <sys/time.h>
 #include <sys/resource.h>
+#include "../kselftest.h"
 
-static int test_limit(void)
+static void test_limit(void)
 {
-	int ret = 1;
 	struct rlimit lims;
 	void *map;
 
-	if (getrlimit(RLIMIT_MEMLOCK, &lims)) {
-		perror("getrlimit");
-		return ret;
-	}
+	if (getrlimit(RLIMIT_MEMLOCK, &lims))
+		ksft_exit_fail_msg("getrlimit: %s\n", strerror(errno));
 
-	if (mlockall(MCL_ONFAULT | MCL_FUTURE)) {
-		perror("mlockall");
-		return ret;
-	}
+	if (mlockall(MCL_ONFAULT | MCL_FUTURE))
+		ksft_exit_fail_msg("mlockall: %s\n", strerror(errno));
 
 	map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE,
 		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, -1, 0);
+
+	ksft_test_result(map == MAP_FAILED, "The map failed respecting mlock limits\n");
+
 	if (map != MAP_FAILED)
-		printf("mmap should have failed, but didn't\n");
-	else {
-		ret = 0;
 		munmap(map, 2 * lims.rlim_max);
-	}
-
 	munlockall();
-	return ret;
 }
 
 int main(int argc, char **argv)
 {
-	int ret = 0;
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	if (!getuid())
+		ksft_test_result_skip("The test must be run from a normal user\n");
+	else
+		test_limit();
 
-	ret += test_limit();
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index 48dc151f8fca..f822ae31af22 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -54,6 +54,7 @@ int test_nr;
 u64 shadow_pkey_reg;
 int dprint_in_signal;
 char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
+char buf[256];
 
 void cat_into_file(char *str, char *file)
 {
@@ -1744,6 +1745,38 @@ void pkey_setup_shadow(void)
 	shadow_pkey_reg = __read_pkey_reg();
 }
 
+void restore_settings_atexit(void)
+{
+	cat_into_file(buf, "/proc/sys/vm/nr_hugepages");
+}
+
+void save_settings(void)
+{
+	int fd;
+	int err;
+
+	if (geteuid())
+		return;
+
+	fd = open("/proc/sys/vm/nr_hugepages", O_RDONLY);
+	if (fd < 0) {
+		fprintf(stderr, "error opening\n");
+		perror("error: ");
+		exit(__LINE__);
+	}
+
+	/* -1 to guarantee leaving the trailing \0 */
+	err = read(fd, buf, sizeof(buf)-1);
+	if (err < 0) {
+		fprintf(stderr, "error reading\n");
+		perror("error: ");
+		exit(__LINE__);
+	}
+
+	atexit(restore_settings_atexit);
+	close(fd);
+}
+
 int main(void)
 {
 	int nr_iterations = 22;
@@ -1751,6 +1784,7 @@ int main(void)
 
 	srand((unsigned int)time(NULL));
 
+	save_settings();
 	setup_handlers();
 
 	printf("has pkeys: %d\n", pkeys_supported);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index a4f2e4d1da10..c2c542fe7b17 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -15,10 +15,11 @@ usage() {
 	cat <<EOF
 usage: ${BASH_SOURCE[0]:-$0} [ options ]
 
-  -a: run all tests, including extra ones
+  -a: run all tests, including extra ones (other than destructive ones)
   -t: specify specific categories to tests to run
   -h: display this message
   -n: disable TAP output
+  -d: run destructive tests
 
 The default behavior is to run required tests only.  If -a is specified,
 will run all tests.
@@ -81,6 +82,7 @@ EOF
 }
 
 RUN_ALL=false
+RUN_DESTRUCTIVE=false
 TAP_PREFIX="# "
 
 while getopts "aht:n" OPT; do
@@ -89,6 +91,7 @@ while getopts "aht:n" OPT; do
 		"h") usage ;;
 		"t") VM_SELFTEST_ITEMS=${OPTARG} ;;
 		"n") TAP_PREFIX= ;;
+		"d") RUN_DESTRUCTIVE=true ;;
 	esac
 done
 shift $((OPTIND -1))
@@ -302,7 +305,12 @@ echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
 
 CATEGORY="compaction" run_test ./compaction_test
 
-CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit
+if command -v sudo &> /dev/null;
+then
+	CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit
+else
+	echo "# SKIP ./on-fault-limit"
+fi
 
 CATEGORY="mmap" run_test ./map_populate
 
@@ -315,6 +323,11 @@ CATEGORY="process_mrelease" run_test ./mrelease_test
 CATEGORY="mremap" run_test ./mremap_test
 
 CATEGORY="hugetlb" run_test ./thuge-gen
+CATEGORY="hugetlb" run_test ./charge_reserved_hugetlb.sh -cgroup-v2
+CATEGORY="hugetlb" run_test ./hugetlb_reparenting_test.sh -cgroup-v2
+if $RUN_DESTRUCTIVE; then
+CATEGORY="hugetlb" run_test ./hugetlb-read-hwpoison
+fi
 
 if [ $VADDR64 -ne 0 ]; then