Merge tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:
 "Almost all of MM here. A few things are still getting finished off,
  reviewed, etc.

   - Yang Shi has improved the behaviour of khugepaged collapsing of
     readonly file-backed transparent hugepages.

   - Johannes Weiner has arranged for zswap memory use to be tracked and
     managed on a per-cgroup basis.

   - Munchun Song adds a /proc knob ("hugetlb_optimize_vmemmap") for
     runtime enablement of the recent huge page vmemmap optimization
     feature.

   - Baolin Wang contributes a series to fix some issues around hugetlb
     pagetable invalidation.

   - Zhenwei Pi has fixed some interactions between hwpoisoned pages and
     virtualization.

   - Tong Tiangen has enabled the use of the presently x86-only
     page_table_check debugging feature on arm64 and riscv.

   - David Vernet has done some fixup work on the memcg selftests.

   - Peter Xu has taught userfaultfd to handle write protection faults
     against shmem- and hugetlbfs-backed files.

   - More DAMON development from SeongJae Park - adding online tuning of
     the feature and support for monitoring of fixed virtual address
     ranges. Also easier discovery of which monitoring operations are
     available.

   - Nadav Amit has done some optimization of TLB flushing during
     mprotect().

   - Neil Brown continues to labor away at improving our swap-over-NFS
     support.

   - David Hildenbrand has some fixes to anon page COWing versus
     get_user_pages().

   - Peng Liu fixed some errors in the core hugetlb code.

   - Joao Martins has reduced the amount of memory consumed by
     device-dax's compound devmaps.

   - Some cleanups of the arch-specific pagemap code from Anshuman
     Khandual.

   - Muchun Song has found and fixed some errors in the TLB flushing of
     transparent hugepages.

   - Roman Gushchin has done more work on the memcg selftests.

  ... and, of course, many smaller fixes and cleanups. Notably, the
  customary million cleanup serieses from Miaohe Lin"

* tag 'mm-stable-2022-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (381 commits)
  mm: kfence: use PAGE_ALIGNED helper
  selftests: vm: add the "settings" file with timeout variable
  selftests: vm: add "test_hmm.sh" to TEST_FILES
  selftests: vm: check numa_available() before operating "merge_across_nodes" in ksm_tests
  selftests: vm: add migration to the .gitignore
  selftests/vm/pkeys: fix typo in comment
  ksm: fix typo in comment
  selftests: vm: add process_mrelease tests
  Revert "mm/vmscan: never demote for memcg reclaim"
  mm/kfence: print disabling or re-enabling message
  include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace"
  include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion"
  mm: fix a potential infinite loop in start_isolate_page_range()
  MAINTAINERS: add Muchun as co-maintainer for HugeTLB
  zram: fix Kconfig dependency warning
  mm/shmem: fix shmem folio swapoff hang
  cgroup: fix an error handling path in alloc_pagecache_max_30M()
  mm: damon: use HPAGE_PMD_SIZE
  tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
  nodemask.h: fix compilation error with GCC12
  ...

3 files changed, 199 insertions, 57 deletions

diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 4297d580e3f8..4c52cc6f2f9c 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -19,6 +19,7 @@
 #include "cgroup_util.h"
 #include "../clone3/clone3_selftests.h"
 
+/* Returns read len on success, or -errno on failure. */
 static ssize_t read_text(const char *path, char *buf, size_t max_len)
 {
 	ssize_t len;
@@ -26,35 +27,29 @@ static ssize_t read_text(const char *path, char *buf, size_t max_len)
 
 	fd = open(path, O_RDONLY);
 	if (fd < 0)
-		return fd;
+		return -errno;
 
 	len = read(fd, buf, max_len - 1);
-	if (len < 0)
-		goto out;
 
-	buf[len] = 0;
-out:
+	if (len >= 0)
+		buf[len] = 0;
+
 	close(fd);
-	return len;
+	return len < 0 ? -errno : len;
 }
 
+/* Returns written len on success, or -errno on failure. */
 static ssize_t write_text(const char *path, char *buf, ssize_t len)
 {
 	int fd;
 
 	fd = open(path, O_WRONLY | O_APPEND);
 	if (fd < 0)
-		return fd;
+		return -errno;
 
 	len = write(fd, buf, len);
-	if (len < 0) {
-		close(fd);
-		return len;
-	}
-
 	close(fd);
-
-	return len;
+	return len < 0 ? -errno : len;
 }
 
 char *cg_name(const char *root, const char *name)
@@ -87,16 +82,16 @@ char *cg_control(const char *cgroup, const char *control)
 	return ret;
 }
 
+/* Returns 0 on success, or -errno on failure. */
 int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
 {
 	char path[PATH_MAX];
+	ssize_t ret;
 
 	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
 
-	if (read_text(path, buf, len) >= 0)
-		return 0;
-
-	return -1;
+	ret = read_text(path, buf, len);
+	return ret >= 0 ? 0 : ret;
 }
 
 int cg_read_strcmp(const char *cgroup, const char *control,
@@ -177,17 +172,15 @@ long cg_read_lc(const char *cgroup, const char *control)
 	return cnt;
 }
 
+/* Returns 0 on success, or -errno on failure. */
 int cg_write(const char *cgroup, const char *control, char *buf)
 {
 	char path[PATH_MAX];
-	ssize_t len = strlen(buf);
+	ssize_t len = strlen(buf), ret;
 
 	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
-
-	if (write_text(path, buf, len) == len)
-		return 0;
-
-	return -1;
+	ret = write_text(path, buf, len);
+	return ret == len ? 0 : ret;
 }
 
 int cg_write_numeric(const char *cgroup, const char *control, long value)
@@ -547,6 +540,18 @@ int set_oom_adj_score(int pid, int score)
 	return 0;
 }
 
+int proc_mount_contains(const char *option)
+{
+	char buf[4 * PAGE_SIZE];
+	ssize_t read;
+
+	read = read_text("/proc/mounts", buf, sizeof(buf));
+	if (read < 0)
+		return read;
+
+	return strstr(buf, option) != NULL;
+}
+
 ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
 {
 	char path[PATH_MAX];
@@ -557,7 +562,8 @@ ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t
 	else
 		snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
 
-	return read_text(path, buf, size);
+	size = read_text(path, buf, size);
+	return size < 0 ? -1 : size;
 }
 
 int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 2ee2119281d7..c92df4e5d395 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -52,6 +52,7 @@ extern int is_swap_enabled(void);
 extern int set_oom_adj_score(int pid, int score);
 extern int cg_wait_for_proc_count(const char *cgroup, int count);
 extern int cg_killall(const char *cgroup);
+int proc_mount_contains(const char *option);
 extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
 extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
 extern pid_t clone_into_cgroup(int cgroup_fd);
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 36ccf2322e21..44a974ec472c 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -21,6 +21,9 @@
 #include "../kselftest.h"
 #include "cgroup_util.h"
 
+static bool has_localevents;
+static bool has_recursiveprot;
+
 /*
  * This test creates two nested cgroups with and without enabling
  * the memory controller.
@@ -211,13 +214,17 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg)
 static int alloc_anon_noexit(const char *cgroup, void *arg)
 {
 	int ppid = getppid();
+	size_t size = (unsigned long)arg;
+	char *buf, *ptr;
 
-	if (alloc_anon(cgroup, arg))
-		return -1;
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
 
 	while (getppid() == ppid)
 		sleep(1);
 
+	free(buf);
 	return 0;
 }
 
@@ -244,8 +251,8 @@ static int cg_test_proc_killed(const char *cgroup)
  * A/B     memory.min = 50M,  memory.current = 50M
  * A/B/C   memory.min = 75M,  memory.current = 50M
  * A/B/D   memory.min = 25M,  memory.current = 50M
- * A/B/E   memory.min = 500M, memory.current = 0
- * A/B/F   memory.min = 0,    memory.current = 50M
+ * A/B/E   memory.min = 0,    memory.current = 50M
+ * A/B/F   memory.min = 500M, memory.current = 0
  *
  * Usages are pagecache, but the test keeps a running
  * process in every leaf cgroup.
@@ -255,7 +262,7 @@ static int cg_test_proc_killed(const char *cgroup)
  * A/B    memory.current ~= 50M
  * A/B/C  memory.current ~= 33M
  * A/B/D  memory.current ~= 17M
- * A/B/E  memory.current ~= 0
+ * A/B/F  memory.current ~= 0
  *
  * After that it tries to allocate more than there is
  * unprotected memory in A available, and checks
@@ -321,7 +328,7 @@ static int test_memcg_min(const char *root)
 		if (cg_create(children[i]))
 			goto cleanup;
 
-		if (i == 2)
+		if (i > 2)
 			continue;
 
 		cg_run_nowait(children[i], alloc_pagecache_50M_noexit,
@@ -336,9 +343,9 @@ static int test_memcg_min(const char *root)
 		goto cleanup;
 	if (cg_write(children[1], "memory.min", "25M"))
 		goto cleanup;
-	if (cg_write(children[2], "memory.min", "500M"))
+	if (cg_write(children[2], "memory.min", "0"))
 		goto cleanup;
-	if (cg_write(children[3], "memory.min", "0"))
+	if (cg_write(children[3], "memory.min", "500M"))
 		goto cleanup;
 
 	attempts = 0;
@@ -364,7 +371,7 @@ static int test_memcg_min(const char *root)
 	if (!values_close(c[1], MB(17), 10))
 		goto cleanup;
 
-	if (!values_close(c[2], 0, 1))
+	if (c[3] != 0)
 		goto cleanup;
 
 	if (!cg_run(parent[2], alloc_anon, (void *)MB(170)))
@@ -401,8 +408,8 @@ cleanup:
  * A/B     memory.low = 50M,  memory.current = 50M
  * A/B/C   memory.low = 75M,  memory.current = 50M
  * A/B/D   memory.low = 25M,  memory.current = 50M
- * A/B/E   memory.low = 500M, memory.current = 0
- * A/B/F   memory.low = 0,    memory.current = 50M
+ * A/B/E   memory.low = 0,    memory.current = 50M
+ * A/B/F   memory.low = 500M, memory.current = 0
  *
  * Usages are pagecache.
  * Then it creates A/G an creates a significant
@@ -412,7 +419,7 @@ cleanup:
  * A/B    memory.current ~= 50M
  * A/B/   memory.current ~= 33M
  * A/B/D  memory.current ~= 17M
- * A/B/E  memory.current ~= 0
+ * A/B/F  memory.current ~= 0
  *
  * After that it tries to allocate more than there is
  * unprotected memory in A available,
@@ -476,7 +483,7 @@ static int test_memcg_low(const char *root)
 		if (cg_create(children[i]))
 			goto cleanup;
 
-		if (i == 2)
+		if (i > 2)
 			continue;
 
 		if (cg_run(children[i], alloc_pagecache_50M, (void *)(long)fd))
@@ -491,9 +498,9 @@ static int test_memcg_low(const char *root)
 		goto cleanup;
 	if (cg_write(children[1], "memory.low", "25M"))
 		goto cleanup;
-	if (cg_write(children[2], "memory.low", "500M"))
+	if (cg_write(children[2], "memory.low", "0"))
 		goto cleanup;
-	if (cg_write(children[3], "memory.low", "0"))
+	if (cg_write(children[3], "memory.low", "500M"))
 		goto cleanup;
 
 	if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
@@ -511,7 +518,7 @@ static int test_memcg_low(const char *root)
 	if (!values_close(c[1], MB(17), 10))
 		goto cleanup;
 
-	if (!values_close(c[2], 0, 1))
+	if (c[3] != 0)
 		goto cleanup;
 
 	if (cg_run(parent[2], alloc_anon, (void *)MB(166))) {
@@ -521,15 +528,18 @@ static int test_memcg_low(const char *root)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		int no_low_events_index = has_recursiveprot ? 2 : 1;
+
 		oom = cg_read_key_long(children[i], "memory.events", "oom ");
 		low = cg_read_key_long(children[i], "memory.events", "low ");
 
 		if (oom)
 			goto cleanup;
-		if (i < 2 && low <= 0)
+		if (i <= no_low_events_index && low <= 0)
 			goto cleanup;
-		if (i >= 2 && low)
+		if (i > no_low_events_index && low)
 			goto cleanup;
+
 	}
 
 	ret = KSFT_PASS;
@@ -558,9 +568,14 @@ static int alloc_pagecache_max_30M(const char *cgroup, void *arg)
 {
 	size_t size = MB(50);
 	int ret = -1;
-	long current;
+	long current, high, max;
 	int fd;
 
+	high = cg_read_long(cgroup, "memory.high");
+	max = cg_read_long(cgroup, "memory.max");
+	if (high != MB(30) && max != MB(30))
+		return -1;
+
 	fd = get_temp_fd();
 	if (fd < 0)
 		return -1;
@@ -569,7 +584,7 @@ static int alloc_pagecache_max_30M(const char *cgroup, void *arg)
 		goto cleanup;
 
 	current = cg_read_long(cgroup, "memory.current");
-	if (current <= MB(29) || current > MB(30))
+	if (!values_close(current, MB(30), 5))
 		goto cleanup;
 
 	ret = 0;
@@ -607,7 +622,7 @@ static int test_memcg_high(const char *root)
 	if (cg_write(memcg, "memory.high", "30M"))
 		goto cleanup;
 
-	if (cg_run(memcg, alloc_anon, (void *)MB(100)))
+	if (cg_run(memcg, alloc_anon, (void *)MB(31)))
 		goto cleanup;
 
 	if (!cg_run(memcg, alloc_pagecache_50M_check, NULL))
@@ -756,6 +771,111 @@ cleanup:
 	return ret;
 }
 
+/*
+ * This test checks that memory.reclaim reclaims the given
+ * amount of memory (from both anon and file, if possible).
+ */
+static int test_memcg_reclaim(const char *root)
+{
+	int ret = KSFT_FAIL, fd, retries;
+	char *memcg;
+	long current, expected_usage, to_reclaim;
+	char buf[64];
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	current = cg_read_long(memcg, "memory.current");
+	if (current != 0)
+		goto cleanup;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		goto cleanup;
+
+	cg_run_nowait(memcg, alloc_pagecache_50M_noexit, (void *)(long)fd);
+
+	/*
+	 * If swap is enabled, try to reclaim from both anon and file, else try
+	 * to reclaim from file only.
+	 */
+	if (is_swap_enabled()) {
+		cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(50));
+		expected_usage = MB(100);
+	} else
+		expected_usage = MB(50);
+
+	/*
+	 * Wait until current usage reaches the expected usage (or we run out of
+	 * retries).
+	 */
+	retries = 5;
+	while (!values_close(cg_read_long(memcg, "memory.current"),
+			    expected_usage, 10)) {
+		if (retries--) {
+			sleep(1);
+			continue;
+		} else {
+			fprintf(stderr,
+				"failed to allocate %ld for memcg reclaim test\n",
+				expected_usage);
+			goto cleanup;
+		}
+	}
+
+	/*
+	 * Reclaim until current reaches 30M, this makes sure we hit both anon
+	 * and file if swap is enabled.
+	 */
+	retries = 5;
+	while (true) {
+		int err;
+
+		current = cg_read_long(memcg, "memory.current");
+		to_reclaim = current - MB(30);
+
+		/*
+		 * We only keep looping if we get EAGAIN, which means we could
+		 * not reclaim the full amount.
+		 */
+		if (to_reclaim <= 0)
+			goto cleanup;
+
+
+		snprintf(buf, sizeof(buf), "%ld", to_reclaim);
+		err = cg_write(memcg, "memory.reclaim", buf);
+		if (!err) {
+			/*
+			 * If writing succeeds, then the written amount should have been
+			 * fully reclaimed (and maybe more).
+			 */
+			current = cg_read_long(memcg, "memory.current");
+			if (!values_close(current, MB(30), 3) && current > MB(30))
+				goto cleanup;
+			break;
+		}
+
+		/* The kernel could not reclaim the full amount, try again. */
+		if (err == -EAGAIN && retries--)
+			continue;
+
+		/* We got an unexpected error or ran out of retries. */
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+	close(fd);
+
+	return ret;
+}
+
 static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
 {
 	long mem_max = (long)arg;
@@ -987,9 +1107,6 @@ static int tcp_client(const char *cgroup, unsigned short port)
 		if (current < 0 || sock < 0)
 			goto close_sk;
 
-		if (current < sock)
-			goto close_sk;
-
 		if (values_close(current, sock, 10)) {
 			ret = KSFT_PASS;
 			break;
@@ -1079,12 +1196,14 @@ cleanup:
 /*
  * This test disables swapping and tries to allocate anonymous memory
  * up to OOM with memory.group.oom set. Then it checks that all
- * processes in the leaf (but not the parent) were killed.
+ * processes in the leaf were killed. It also checks that oom_events
+ * were propagated to the parent level.
  */
 static int test_memcg_oom_group_leaf_events(const char *root)
 {
 	int ret = KSFT_FAIL;
 	char *parent, *child;
+	long parent_oom_events;
 
 	parent = cg_name(root, "memcg_test_0");
 	child = cg_name(root, "memcg_test_0/memcg_test_1");
@@ -1122,7 +1241,7 @@ static int test_memcg_oom_group_leaf_events(const char *root)
 	if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0)
 		goto cleanup;
 
-	if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0)
+	if (cg_read_key_long(parent, "memory.events", "oom_kill ") <= 0)
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -1230,14 +1349,20 @@ static int test_memcg_oom_group_score_events(const char *root)
 	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
 		goto cleanup;
 
-	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3)
-		goto cleanup;
+	parent_oom_events = cg_read_key_long(
+			parent, "memory.events", "oom_kill ");
+	/*
+	 * If memory_localevents is not enabled (the default), the parent should
+	 * count OOM events in its children groups. Otherwise, it should not
+	 * have observed any events.
+	 */
+	if ((has_localevents && parent_oom_events == 0) ||
+	     parent_oom_events > 0)
+		ret = KSFT_PASS;
 
 	if (kill(safe_pid, SIGKILL))
 		goto cleanup;
 
-	ret = KSFT_PASS;
-
 cleanup:
 	if (memcg)
 		cg_destroy(memcg);
@@ -1246,7 +1371,6 @@ cleanup:
 	return ret;
 }
 
-
 #define T(x) { x, #x }
 struct memcg_test {
 	int (*fn)(const char *root);
@@ -1259,6 +1383,7 @@ struct memcg_test {
 	T(test_memcg_high),
 	T(test_memcg_high_sync),
 	T(test_memcg_max),
+	T(test_memcg_reclaim),
 	T(test_memcg_oom_events),
 	T(test_memcg_swap_max),
 	T(test_memcg_sock),
@@ -1271,7 +1396,7 @@ struct memcg_test {
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i, proc_status, ret = EXIT_SUCCESS;
 
 	if (cg_find_unified_root(root, sizeof(root)))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -1287,6 +1412,16 @@ int main(int argc, char **argv)
 		if (cg_write(root, "cgroup.subtree_control", "+memory"))
 			ksft_exit_skip("Failed to set memory controller\n");
 
+	proc_status = proc_mount_contains("memory_recursiveprot");
+	if (proc_status < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	has_recursiveprot = proc_status;
+
+	proc_status = proc_mount_contains("memory_localevents");
+	if (proc_status < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	has_localevents = proc_status;
+
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS: