Merge feature/memory-reclaim/5.15 into v5.15.153

* commit 'fed46d1f99d22a5a9efd06da0bf5baf6a04045d8':
  selftests: cgroup: add a selftest for memory.reclaim
  selftests: cgroup: fix unsigned comparison with less than zero
  selftests: cgroup: fix alloc_anon_noexit() instantly freeing memory
  selftests: cgroup: return -errno from cg_read()/cg_write() on failure
  memcg: introduce per-memcg reclaim interface

Author: kelsey-steele

Documentation/admin-guide/cgroup-v2.rst

@@ -1200,6 +1200,27 @@ PAGE_SIZE multiple when read back.
 	high limit is used and monitored properly, this limit's
 	utility is limited to providing the final safety net.
 
+  memory.reclaim
+	A write-only nested-keyed file which exists for all cgroups.
+
+	This is a simple interface to trigger memory reclaim in the
+	target cgroup.
+
+	This file accepts a single key, the number of bytes to reclaim.
+	No nested keys are currently supported.
+
+	Example::
+
+	  echo "1G" > memory.reclaim
+
+	The interface can be later extended with nested keys to
+	configure the reclaim behavior. For example, specify the
+	type of memory to reclaim from (anon, file, ..).
+
+	Please note that the kernel can over or under reclaim from
+	the target cgroup. If less bytes are reclaimed than the
+	specified amount, -EAGAIN is returned.
+
   memory.oom.group
 	A read-write single value file which exists on non-root
 	cgroups.  The default value is "0".

mm/memcontrol.c

@@ -6483,6 +6483,46 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
+	unsigned long nr_to_reclaim, nr_reclaimed = 0;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "", &nr_to_reclaim);
+	if (err)
+		return err;
+
+	while (nr_reclaimed < nr_to_reclaim) {
+		unsigned long reclaimed;
+
+		if (signal_pending(current))
+			return -EINTR;
+
+		/*
+		 * This is the final attempt, drain percpu lru caches in the
+		 * hope of introducing more evictable pages for
+		 * try_to_free_mem_cgroup_pages().
+		 */
+		if (!nr_retries)
+			lru_add_drain_all();
+
+		reclaimed = try_to_free_mem_cgroup_pages(memcg,
+						nr_to_reclaim - nr_reclaimed,
+						GFP_KERNEL, true);
+
+		if (!reclaimed && !nr_retries--)
+			return -EAGAIN;
+
+		nr_reclaimed += reclaimed;
+	}
+
+	return nbytes;
+}
+
 static struct cftype memory_files[] = {
 	{
 		.name = "current",
@@ -6541,6 +6581,11 @@ static struct cftype memory_files[] = {
 		.seq_show = memory_oom_group_show,
 		.write = memory_oom_group_write,
 	},
+	{
+		.name = "reclaim",
+		.flags = CFTYPE_NS_DELEGATABLE,
+		.write = memory_reclaim,
+	},
 	{ }	/* terminate */
 };
 

tools/testing/selftests/cgroup/cgroup_util.c

@@ -19,42 +19,37 @@
 #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;
 	int fd;
 
 	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_find_unified_root(char *root, size_t len)
@@ -538,14 +531,16 @@ int set_oom_adj_score(int pid, int score)
 ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
 {
 	char path[PATH_MAX];
+	ssize_t ret;
 
 	if (!pid)
 		snprintf(path, sizeof(path), "/proc/%s/%s",
 			 thread ? "thread-self" : "self", item);
 	else
 		snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
 
-	return read_text(path, buf, size);
+	ret = read_text(path, buf, size);
+	return ret < 0 ? -1 : ret;
 }
 
 int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)

tools/testing/selftests/cgroup/test_memcontrol.c

@@ -210,13 +210,17 @@ 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;
 }
 
@@ -679,6 +683,111 @@ static int test_memcg_max(const char *root)
 	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;
@@ -1181,6 +1290,7 @@ struct memcg_test {
 	T(test_memcg_low),
 	T(test_memcg_high),
 	T(test_memcg_max),
+	T(test_memcg_reclaim),
 	T(test_memcg_oom_events),
 	T(test_memcg_swap_max),
 	T(test_memcg_sock),