1 files changed, 354 insertions, 16 deletions

diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index c7c9572003a8..a680f773f2d5 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -24,6 +24,84 @@
 static bool has_localevents;
 static bool has_recursiveprot;
 
+int get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[PAGE_SIZE];
+	struct stat st;
+	int i;
+
+	if (fstat(fd, &st))
+		goto cleanup;
+
+	size += st.st_size;
+
+	if (ftruncate(fd, size))
+		goto cleanup;
+
+	for (i = 0; i < size; i += sizeof(buf))
+		read(fd, buf, sizeof(buf));
+
+	return 0;
+
+cleanup:
+	return -1;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[PAGE_SIZE];
+	const char delim[] = "\n";
+	int cnt = 0;
+	char *line;
+
+	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt > 1;
+}
+
+int set_oom_adj_score(int pid, int score)
+{
+	char path[PATH_MAX];
+	int fd, len;
+
+	sprintf(path, "/proc/%d/oom_score_adj", pid);
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return fd;
+
+	len = dprintf(fd, "%d", score);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+	return 0;
+}
+
 /*
  * This test creates two nested cgroups with and without enabling
  * the memory controller.
@@ -161,13 +239,16 @@ cleanup:
 /*
  * This test create a memory cgroup, allocates
  * some anonymous memory and some pagecache
- * and check memory.current and some memory.stat values.
+ * and checks memory.current, memory.peak, and some memory.stat values.
  */
-static int test_memcg_current(const char *root)
+static int test_memcg_current_peak(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long current;
+	long current, peak, peak_reset;
 	char *memcg;
+	bool fd2_closed = false, fd3_closed = false, fd4_closed = false;
+	int peak_fd = -1, peak_fd2 = -1, peak_fd3 = -1, peak_fd4 = -1;
+	struct stat ss;
 
 	memcg = cg_name(root, "memcg_test");
 	if (!memcg)
@@ -180,15 +261,124 @@ static int test_memcg_current(const char *root)
 	if (current != 0)
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak != 0)
+		goto cleanup;
+
 	if (cg_run(memcg, alloc_anon_50M_check, NULL))
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	/*
+	 * We'll open a few FDs for the same memory.peak file to exercise the free-path
+	 * We need at least three to be closed in a different order than writes occurred to test
+	 * the linked-list handling.
+	 */
+	peak_fd = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd == -1) {
+		if (errno == ENOENT)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	/*
+	 * Before we try to use memory.peak's fd, try to figure out whether
+	 * this kernel supports writing to that file in the first place. (by
+	 * checking the writable bit on the file's st_mode)
+	 */
+	if (fstat(peak_fd, &ss))
+		goto cleanup;
+
+	if ((ss.st_mode & S_IWUSR) == 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	peak_fd2 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd2 == -1)
+		goto cleanup;
+
+	peak_fd3 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd3 == -1)
+		goto cleanup;
+
+	/* any non-empty string resets, but make it clear */
+	static const char reset_string[] = "reset\n";
+
+	peak_reset = write(peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(peak_fd2, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(peak_fd3, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	/* Make sure a completely independent read isn't affected by our  FD-local reset above*/
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	fd2_closed = true;
+	if (close(peak_fd2))
+		goto cleanup;
+
+	peak_fd4 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd4 == -1)
+		goto cleanup;
+
+	peak_reset = write(peak_fd4, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak = cg_read_long_fd(peak_fd);
+	if (peak > MB(30) || peak < 0)
+		goto cleanup;
+
 	if (cg_run(memcg, alloc_pagecache_50M_check, NULL))
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	/* Make sure everything is back to normal */
+	peak = cg_read_long_fd(peak_fd);
+	if (peak < MB(50))
+		goto cleanup;
+
+	peak = cg_read_long_fd(peak_fd4);
+	if (peak < MB(50))
+		goto cleanup;
+
+	fd3_closed = true;
+	if (close(peak_fd3))
+		goto cleanup;
+
+	fd4_closed = true;
+	if (close(peak_fd4))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
+	close(peak_fd);
+	if (!fd2_closed)
+		close(peak_fd2);
+	if (!fd3_closed)
+		close(peak_fd3);
+	if (!fd4_closed)
+		close(peak_fd4);
 	cg_destroy(memcg);
 	free(memcg);
 
@@ -268,10 +458,11 @@ static bool reclaim_until(const char *memcg, long goal);
  *
  * Then it checks actual memory usages and expects that:
  * A/B    memory.current ~= 50M
- * A/B/C  memory.current ~= 29M
- * A/B/D  memory.current ~= 21M
- * A/B/E  memory.current ~= 0
- * A/B/F  memory.current  = 0
+ * A/B/C  memory.current ~= 29M [memory.events:low > 0]
+ * A/B/D  memory.current ~= 21M [memory.events:low > 0]
+ * A/B/E  memory.current ~= 0   [memory.events:low == 0 if !memory_recursiveprot,
+ *				 undefined otherwise]
+ * A/B/F  memory.current  = 0   [memory.events:low == 0]
  * (for origin of the numbers, see model in memcg_protection.m.)
  *
  * After that it tries to allocate more than there is
@@ -383,10 +574,10 @@ static int test_memcg_protection(const char *root, bool min)
 	for (i = 0; i < ARRAY_SIZE(children); i++)
 		c[i] = cg_read_long(children[i], "memory.current");
 
-	if (!values_close(c[0], MB(29), 10))
+	if (!values_close(c[0], MB(29), 15))
 		goto cleanup;
 
-	if (!values_close(c[1], MB(21), 10))
+	if (!values_close(c[1], MB(21), 20))
 		goto cleanup;
 
 	if (c[3] != 0)
@@ -413,7 +604,14 @@ static int test_memcg_protection(const char *root, bool min)
 		goto cleanup;
 	}
 
+	/*
+	 * Child 2 has memory.low=0, but some low protection may still be
+	 * distributed down from its parent with memory.low=50M if cgroup2
+	 * memory_recursiveprot mount option is enabled. Ignore the low
+	 * event count in this case.
+	 */
 	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		int ignore_low_events_index = has_recursiveprot ? 2 : -1;
 		int no_low_events_index = 1;
 		long low, oom;
 
@@ -422,6 +620,8 @@ static int test_memcg_protection(const char *root, bool min)
 
 		if (oom)
 			goto cleanup;
+		if (i == ignore_low_events_index)
+			continue;
 		if (i <= no_low_events_index && low <= 0)
 			goto cleanup;
 		if (i > no_low_events_index && low)
@@ -716,7 +916,9 @@ static bool reclaim_until(const char *memcg, long goal)
  */
 static int test_memcg_reclaim(const char *root)
 {
-	int ret = KSFT_FAIL, fd, retries;
+	int ret = KSFT_FAIL;
+	int fd = -1;
+	int retries;
 	char *memcg;
 	long current, expected_usage;
 
@@ -815,13 +1017,19 @@ cleanup:
 
 /*
  * This test checks that memory.swap.max limits the amount of
- * anonymous memory which can be swapped out.
+ * anonymous memory which can be swapped out. Additionally, it verifies that
+ * memory.swap.peak reflects the high watermark and can be reset.
  */
-static int test_memcg_swap_max(const char *root)
+static int test_memcg_swap_max_peak(const char *root)
 {
 	int ret = KSFT_FAIL;
 	char *memcg;
-	long max;
+	long max, peak;
+	struct stat ss;
+	int swap_peak_fd = -1, mem_peak_fd = -1;
+
+	/* any non-empty string resets */
+	static const char reset_string[] = "foobarbaz";
 
 	if (!is_swap_enabled())
 		return KSFT_SKIP;
@@ -838,6 +1046,61 @@ static int test_memcg_swap_max(const char *root)
 		goto cleanup;
 	}
 
+	swap_peak_fd = cg_open(memcg, "memory.swap.peak",
+			       O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (swap_peak_fd == -1) {
+		if (errno == ENOENT)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	/*
+	 * Before we try to use memory.swap.peak's fd, try to figure out
+	 * whether this kernel supports writing to that file in the first
+	 * place. (by checking the writable bit on the file's st_mode)
+	 */
+	if (fstat(swap_peak_fd, &ss))
+		goto cleanup;
+
+	if ((ss.st_mode & S_IWUSR) == 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	mem_peak_fd = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (mem_peak_fd == -1)
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.peak"))
+		goto cleanup;
+
+	if (cg_read_long_fd(swap_peak_fd))
+		goto cleanup;
+
+	/* switch the swap and mem fds into local-peak tracking mode*/
+	int peak_reset = write(swap_peak_fd, reset_string, sizeof(reset_string));
+
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	if (cg_read_long_fd(swap_peak_fd))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.peak"))
+		goto cleanup;
+
+	if (cg_read_long_fd(mem_peak_fd))
+		goto cleanup;
+
+	peak_reset = write(mem_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	if (cg_read_long_fd(mem_peak_fd))
+		goto cleanup;
+
 	if (cg_read_strcmp(memcg, "memory.max", "max\n"))
 		goto cleanup;
 
@@ -860,6 +1123,61 @@ static int test_memcg_swap_max(const char *root)
 	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.swap.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	/*
+	 * open, reset and close the peak swap on another FD to make sure
+	 * multiple extant fds don't corrupt the linked-list
+	 */
+	peak_reset = cg_write(memcg, "memory.swap.peak", (char *)reset_string);
+	if (peak_reset)
+		goto cleanup;
+
+	peak_reset = cg_write(memcg, "memory.peak", (char *)reset_string);
+	if (peak_reset)
+		goto cleanup;
+
+	/* actually reset on the fds */
+	peak_reset = write(swap_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(mem_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak > MB(10))
+		goto cleanup;
+
+	/*
+	 * The cgroup is now empty, but there may be a page or two associated
+	 * with the open FD accounted to it.
+	 */
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak > MB(1))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.peak") < MB(29))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.peak") < MB(29))
+		goto cleanup;
+
 	if (cg_run(memcg, alloc_anon_50M_check_swap, (void *)MB(30)))
 		goto cleanup;
 
@@ -867,9 +1185,29 @@ static int test_memcg_swap_max(const char *root)
 	if (max <= 0)
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.swap.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak < MB(19))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
+	if (mem_peak_fd != -1 && close(mem_peak_fd))
+		ret = KSFT_FAIL;
+	if (swap_peak_fd != -1 && close(swap_peak_fd))
+		ret = KSFT_FAIL;
 	cg_destroy(memcg);
 	free(memcg);
 
@@ -1293,7 +1631,7 @@ struct memcg_test {
 	const char *name;
 } tests[] = {
 	T(test_memcg_subtree_control),
-	T(test_memcg_current),
+	T(test_memcg_current_peak),
 	T(test_memcg_min),
 	T(test_memcg_low),
 	T(test_memcg_high),
@@ -1301,7 +1639,7 @@ struct memcg_test {
 	T(test_memcg_max),
 	T(test_memcg_reclaim),
 	T(test_memcg_oom_events),
-	T(test_memcg_swap_max),
+	T(test_memcg_swap_max_peak),
 	T(test_memcg_sock),
 	T(test_memcg_oom_group_leaf_events),
 	T(test_memcg_oom_group_parent_events),
@@ -1314,7 +1652,7 @@ int main(int argc, char **argv)
 	char root[PATH_MAX];
 	int i, proc_status, ret = EXIT_SUCCESS;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*