1 files changed, 271 insertions, 37 deletions

diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 16f5d74ae762..0ebf796f3cff 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -10,6 +10,7 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <unistd.h>
+#include <sys/inotify.h>
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include <arpa/inet.h>
@@ -18,11 +19,108 @@
 #include <errno.h>
 #include <sys/mman.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "cgroup_util.h"
 
+#define MEMCG_SOCKSTAT_WAIT_RETRIES        30
+
 static bool has_localevents;
 static bool has_recursiveprot;
+static int page_size;
+
+int get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[BUF_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;
+}
+
+static char *alloc_and_populate_anon(size_t size)
+{
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	if (buf == NULL) {
+		fprintf(stderr, "malloc() failed\n");
+		return NULL;
+	}
+
+	for (ptr = buf; ptr < buf + size; ptr += page_size)
+		*ptr = 0;
+
+	return buf;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf;
+
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
+		return -1;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[BUF_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
@@ -32,7 +130,7 @@ static int test_memcg_subtree_control(const char *root)
 {
 	char *parent, *child, *parent2 = NULL, *child2 = NULL;
 	int ret = KSFT_FAIL;
-	char buf[PAGE_SIZE];
+	char buf[BUF_SIZE];
 
 	/* Create two nested cgroups with the memory controller enabled */
 	parent = cg_name(root, "memcg_test_0");
@@ -93,18 +191,13 @@ cleanup_free:
 static int alloc_anon_50M_check(const char *cgroup, void *arg)
 {
 	size_t size = MB(50);
-	char *buf, *ptr;
+	char *buf;
 	long anon, current;
 	int ret = -1;
 
-	buf = malloc(size);
-	if (buf == NULL) {
-		fprintf(stderr, "malloc() failed\n");
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
 		return -1;
-	}
-
-	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
-		*ptr = 0;
 
 	current = cg_read_long(cgroup, "memory.current");
 	if (current < size)
@@ -325,16 +418,11 @@ static int alloc_anon_noexit(const char *cgroup, void *arg)
 {
 	int ppid = getppid();
 	size_t size = (unsigned long)arg;
-	char *buf, *ptr;
+	char *buf;
 
-	buf = malloc(size);
-	if (buf == NULL) {
-		fprintf(stderr, "malloc() failed\n");
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
 		return -1;
-	}
-
-	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
-		*ptr = 0;
 
 	while (getppid() == ppid)
 		sleep(1);
@@ -380,10 +468,11 @@ 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
@@ -495,10 +584,10 @@ 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)
@@ -525,7 +614,14 @@ 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;
 
@@ -534,6 +630,8 @@ 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)
@@ -899,18 +997,13 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
 {
 	long mem_max = (long)arg;
 	size_t size = MB(50);
-	char *buf, *ptr;
+	char *buf;
 	long mem_current, swap_current;
 	int ret = -1;
 
-	buf = malloc(size);
-	if (buf == NULL) {
-		fprintf(stderr, "malloc() failed\n");
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
 		return -1;
-	}
-
-	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
-		*ptr = 0;
 
 	mem_current = cg_read_long(cgroup, "memory.current");
 	if (!mem_current || !values_close(mem_current, mem_max, 3))
@@ -1190,8 +1283,11 @@ static int tcp_server(const char *cgroup, void *arg)
 	saddr.sin6_port = htons(srv_args->port);
 
 	sk = socket(AF_INET6, SOCK_STREAM, 0);
-	if (sk < 0)
+	if (sk < 0) {
+		/* Pass back errno to the ctl_fd */
+		write(ctl_fd, &errno, sizeof(errno));
 		return ret;
+	}
 
 	if (setsockopt(sk, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0)
 		goto cleanup;
@@ -1296,6 +1392,7 @@ static int test_memcg_sock(const char *root)
 	int bind_retries = 5, ret = KSFT_FAIL, pid, err;
 	unsigned short port;
 	char *memcg;
+	long sock_post = -1;
 
 	memcg = cg_name(root, "memcg_test");
 	if (!memcg)
@@ -1321,6 +1418,12 @@ static int test_memcg_sock(const char *root)
 			goto cleanup;
 		close(args.ctl[0]);
 
+		/* Skip if address family not supported by protocol */
+		if (err == EAFNOSUPPORT) {
+			ret = KSFT_SKIP;
+			goto cleanup;
+		}
+
 		if (!err)
 			break;
 		if (err != EADDRINUSE)
@@ -1344,7 +1447,22 @@ static int test_memcg_sock(const char *root)
 	if (cg_read_long(memcg, "memory.current") < 0)
 		goto cleanup;
 
-	if (cg_read_key_long(memcg, "memory.stat", "sock "))
+	/*
+	 * memory.stat is updated asynchronously via the memcg rstat
+	 * flushing worker, which runs periodically (every 2 seconds,
+	 * see FLUSH_TIME). On a busy system, the "sock " counter may
+	 * stay non-zero for a short period of time after the TCP
+	 * connection is closed and all socket memory has been
+	 * uncharged.
+	 *
+	 * Poll memory.stat for up to 3 seconds (~FLUSH_TIME plus some
+	 * scheduling slack) and require that the "sock " counter
+	 * eventually drops to zero.
+	 */
+	sock_post = cg_read_key_long_poll(memcg, "memory.stat", "sock ", 0,
+					 MEMCG_SOCKSTAT_WAIT_RETRIES,
+					 DEFAULT_WAIT_INTERVAL_US);
+	if (sock_post)
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -1537,6 +1655,115 @@ cleanup:
 	return ret;
 }
 
+static int read_event(int inotify_fd, int expected_event, int expected_wd)
+{
+	struct inotify_event event;
+	ssize_t len = 0;
+
+	len = read(inotify_fd, &event, sizeof(event));
+	if (len < (ssize_t)sizeof(event))
+		return -1;
+
+	if (event.mask != expected_event || event.wd != expected_wd) {
+		fprintf(stderr,
+			"event does not match expected values: mask %d (expected %d) wd %d (expected %d)\n",
+			event.mask, expected_event, event.wd, expected_wd);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int test_memcg_inotify_delete_file(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg = NULL;
+	int fd, wd;
+
+	memcg = cg_name(root, "memcg_test_0");
+
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	fd = inotify_init1(0);
+	if (fd == -1)
+		goto cleanup;
+
+	wd = inotify_add_watch(fd, cg_control(memcg, "memory.events"), IN_DELETE_SELF);
+	if (wd == -1)
+		goto cleanup;
+
+	if (cg_destroy(memcg))
+		goto cleanup;
+	free(memcg);
+	memcg = NULL;
+
+	if (read_event(fd, IN_DELETE_SELF, wd))
+		goto cleanup;
+
+	if (read_event(fd, IN_IGNORED, wd))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (fd >= 0)
+		close(fd);
+	if (memcg)
+		cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+static int test_memcg_inotify_delete_dir(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg = NULL;
+	int fd, wd;
+
+	memcg = cg_name(root, "memcg_test_0");
+
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	fd = inotify_init1(0);
+	if (fd == -1)
+		goto cleanup;
+
+	wd = inotify_add_watch(fd, memcg, IN_DELETE_SELF);
+	if (wd == -1)
+		goto cleanup;
+
+	if (cg_destroy(memcg))
+		goto cleanup;
+	free(memcg);
+	memcg = NULL;
+
+	if (read_event(fd, IN_DELETE_SELF, wd))
+		goto cleanup;
+
+	if (read_event(fd, IN_IGNORED, wd))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (fd >= 0)
+		close(fd);
+	if (memcg)
+		cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
 #define T(x) { x, #x }
 struct memcg_test {
 	int (*fn)(const char *root);
@@ -1556,14 +1783,22 @@ struct memcg_test {
 	T(test_memcg_oom_group_leaf_events),
 	T(test_memcg_oom_group_parent_events),
 	T(test_memcg_oom_group_score_events),
+	T(test_memcg_inotify_delete_file),
+	T(test_memcg_inotify_delete_dir),
 };
 #undef T
 
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, proc_status, ret = EXIT_SUCCESS;
+	int i, proc_status;
 
+	page_size = sysconf(_SC_PAGE_SIZE);
+	if (page_size <= 0)
+		page_size = BUF_SIZE;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
 	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
@@ -1597,11 +1832,10 @@ int main(int argc, char **argv)
 			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;
+	ksft_finished();
 }