mm, memcg: cg2 memory{.swap,}.peak write tests

Extend two existing tests to cover extracting memory usage through the
newly mutable memory.peak and memory.swap.peak handlers.

In particular, make sure to exercise adding and removing watchers with
overlapping lifetimes so the less-trivial logic gets tested.

The new/updated tests attempt to detect a lack of the write handler by
fstat'ing the memory.peak and memory.swap.peak files and skip the tests if
that's the case.  Additionally, skip if the file doesn't exist at all.

[davidf@vimeo.com: update tests]
  Link: https://lkml.kernel.org/r/20240730231304.761942-3-davidf@vimeo.com
Link: https://lkml.kernel.org/r/20240729143743.34236-3-davidf@vimeo.com
Signed-off-by: David Finkel <davidf@vimeo.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 280 insertions, 8 deletions

diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 432db923bced..1e2d46636a0c 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -141,6 +141,16 @@ long cg_read_long(const char *cgroup, const char *control)
 	return atol(buf);
 }
 
+long cg_read_long_fd(int fd)
+{
+	char buf[128];
+
+	if (pread(fd, buf, sizeof(buf), 0) <= 0)
+		return -1;
+
+	return atol(buf);
+}
+
 long cg_read_key_long(const char *cgroup, const char *control, const char *key)
 {
 	char buf[PAGE_SIZE];
@@ -183,6 +193,18 @@ int cg_write(const char *cgroup, const char *control, char *buf)
 	return ret == len ? 0 : ret;
 }
 
+/*
+ * Returns fd on success, or -1 on failure.
+ * (fd should be closed with close() as usual)
+ */
+int cg_open(const char *cgroup, const char *control, int flags)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+	return open(path, flags);
+}
+
 int cg_write_numeric(const char *cgroup, const char *control, long value)
 {
 	char buf[64];
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index e8d04ac9e3d2..19b131ee7707 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -34,9 +34,11 @@ extern int cg_read_strcmp(const char *cgroup, const char *control,
 extern int cg_read_strstr(const char *cgroup, const char *control,
 			  const char *needle);
 extern long cg_read_long(const char *cgroup, const char *control);
+extern long cg_read_long_fd(int fd);
 long cg_read_key_long(const char *cgroup, const char *control, const char *key);
 extern long cg_read_lc(const char *cgroup, const char *control);
 extern int cg_write(const char *cgroup, const char *control, char *buf);
+extern int cg_open(const char *cgroup, const char *control, int flags);
 int cg_write_numeric(const char *cgroup, const char *control, long value);
 extern int cg_run(const char *cgroup,
 		  int (*fn)(const char *cgroup, void *arg),
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 41ae8047b889..16f5d74ae762 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -161,13 +161,16 @@ 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 +183,124 @@ 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);
 
@@ -817,13 +929,19 @@ 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;
@@ -840,6 +958,61 @@ 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;
 
@@ -862,6 +1035,61 @@ 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;
 
@@ -869,9 +1097,29 @@ 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);
 
@@ -1295,7 +1543,7 @@ 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),
@@ -1303,7 +1551,7 @@ 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),