mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Hui Zhu <hui.zhu@linux.dev>
To: Roman Gushchin <roman.gushchin@linux.dev>,
	JP Kobryn <inwardvessel@gmail.com>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andrii Nakryiko <andrii@kernel.org>,
	Eduard Zingerman <eddyz87@gmail.com>,
	Ihor Solodrai <ihor.solodrai@linux.dev>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Kumar Kartikeya Dwivedi <memxor@gmail.com>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	Song Liu <song@kernel.org>,
	Yonghong Song <yonghong.song@linux.dev>,
	Jiri Olsa <jolsa@kernel.org>,
	Emil Tsalapatis <emil@etsalapatis.com>,
	Shuah Khan <shuah@kernel.org>,
	David Hildenbrand <david@kernel.org>,
	Barry Song <baohua@kernel.org>, Geliang Tang <geliang@kernel.org>,
	linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
	linux-mm@kvack.org, linux-kselftest@vger.kernel.org
Cc: Hui Zhu <zhuhui@kylinos.cn>
Subject: [PATCH bpf-next v12 2/2] selftests/bpf: Add memcg async reclaim test
Date: Fri, 18 Sep 2026 14:58:54 +0800	[thread overview]
Message-ID: <44f7fcfafd5f33072dd2b9abc31aa9bf5eacd9bb.1789714023.git.zhuhui@kylinos.cn> (raw)
In-Reply-To: <cover.1789714023.git.zhuhui@kylinos.cn>

From: Hui Zhu <zhuhui@kylinos.cn>

Exercise BPF-driven async proactive reclaim. A BPF program watches the
refault stats of a memory-pressured cgroup and, once they grow, reclaims
a second cgroup from a bpf_wq callback through bpf_proactive_reclaim().
Pass/fail rests on the reclaim counters. The workload timings are a
benchmark, not a criterion, so they are logged only under
TEST_MEMCG_ASYNC_RECLAIM_BENCH=1, which also runs a baseline without the
BPF program, recreating the cgroups in between so both runs start cold.

A second test removes the reclaim target while the program keeps running
and verifies that reclaim stops. The program skips a target whose css has
lost CSS_ONLINE, but that window sits inside rmdir() and is too narrow to
hit reliably, so the test asserts the post-rmdir outcome and only counts
the in-window one.

Add CONFIG_MEMCG to the selftests config fragment because
bpf_proactive_reclaim() is built only under it and the program fails to
load without it.

Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---
 tools/testing/selftests/bpf/config            |   1 +
 .../bpf/prog_tests/memcg_async_reclaim.c      | 890 ++++++++++++++++++
 .../selftests/bpf/progs/memcg_async_reclaim.c | 327 +++++++
 3 files changed, 1218 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c
 create mode 100644 tools/testing/selftests/bpf/progs/memcg_async_reclaim.c

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 2f79688dcf7c..1edaa752facb 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -57,6 +57,7 @@ CONFIG_LIRC=y
 CONFIG_LIVEPATCH=y
 CONFIG_LWTUNNEL=y
 CONFIG_LWTUNNEL_BPF=y
+CONFIG_MEMCG=y
 CONFIG_MODULE_SIG=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 CONFIG_MODULE_UNLOAD=y
diff --git a/tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c b/tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c
new file mode 100644
index 000000000000..179b64fb6de8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/memcg_async_reclaim.c
@@ -0,0 +1,890 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Memory controller eBPF async reclaim test
+ *
+ * Setting TEST_MEMCG_ASYNC_RECLAIM_BENCH=1 adds a baseline run of the
+ * workload without the BPF program to memcg_async_reclaim, and prints
+ * the baseline and reclaim timings, plus the speedup of the pressured
+ * cgroup, to stdout. The cgroups are recreated between the two runs so
+ * that both start from the same cold state.
+ */
+
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/vfs.h>
+#include <sys/wait.h>
+#include <signal.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <limits.h>
+#include <linux/magic.h>
+
+#include "cgroup_helpers.h"
+
+struct bpf_args {
+	u64 high_cgroup_id;
+	u64 low_cgroup_id;
+	u64 event_delta_threshold;
+	u64 check_ns;
+};
+
+/* Reclaim outcomes reported by the BPF program through the ringbuf. */
+enum reclaim_outcome {
+	RECLAIM_OUTCOME_CALLED,
+	RECLAIM_OUTCOME_SKIPPED_DYING,
+	RECLAIM_OUTCOME_TARGET_GONE,
+};
+
+struct reclaim_event {
+	u64 outcome;
+};
+
+#include "memcg_async_reclaim.skel.h"
+
+#define FILE_SIZE (32 * 1024 * 1024ul)
+#define BUFFER_SIZE (4096)
+#define CG_LIMIT (32 * 1024 * 1024ul)
+#define READ_TIMES 50
+
+#define CG_DIR "/memcg_async_reclaim"
+#define CG_HIGH_DIR CG_DIR "/high"
+#define CG_LOW_DIR CG_DIR "/low"
+
+#define CG_DYING_DIR "/memcg_async_reclaim_dying"
+#define CG_DYING_TRIGGER_DIR CG_DYING_DIR "/trigger"
+#define CG_DYING_TARGET_DIR CG_DYING_DIR "/target"
+
+#define CHECK_PERIOD_NS (2 * 1000 * 1000ull)
+#define EVENT_DELTA_THRESHOLD 1
+
+/*
+ * Timing for the dying test: after the target cgroup is removed, give
+ * in-flight reclaim passes time to drain, then wait for a reclaim round
+ * to hit the removed target. The keepalive reader keeps the trigger
+ * cgroup refaulting, and the timer fires every CHECK_PERIOD_NS, so
+ * such a round must show up within a few timer periods. The BPF
+ * program reports every reclaim outcome through the ringbuf, so the
+ * waits just poll it with a timeout.
+ */
+#define DYING_SETTLE_US (200 * 1000)
+#define EVENT_POLL_TIMEOUT_MS (100)
+#define EVENT_POLL_ROUNDS (50)
+
+static bool usable_for_workload_files(const char *dir)
+{
+	struct statfs st;
+
+	if (statfs(dir, &st))
+		return false;
+
+	return st.f_type != TMPFS_MAGIC && st.f_type != RAMFS_MAGIC;
+}
+
+/*
+ * The workload files must sit on a regular filesystem: with swap
+ * disabled for the cgroup, tmpfs/ramfs pages are unevictable and would
+ * OOM the cgroup instead of exercising reclaim; they are also charged
+ * as anonymous memory, so they never raise the WORKINGSET_REFAULT_FILE
+ * events the BPF program monitors.
+ *
+ * /tmp is tmpfs on many systems, so fall back to the current directory.
+ * That fallback needs the very same check: test_progs is routinely run
+ * from a tmpfs working directory, and silently landing there produces an
+ * OOM that looks like a reclaim failure. Returns NULL when neither
+ * directory is usable, in which case the workload cannot run at all.
+ */
+static const char *workload_files_dir(void)
+{
+	if (usable_for_workload_files("/tmp"))
+		return "/tmp";
+	if (usable_for_workload_files("."))
+		return ".";
+
+	return NULL;
+}
+
+/*
+ * Keep the workload from swapping out, so that reclaim has to evict page
+ * cache instead. memory.swap.max only exists when the kernel is built with
+ * CONFIG_SWAP, and /proc/swaps is registered by the same CONFIG_SWAP-gated
+ * code (mm/swapfile.c), so it stands in for the file here. With CONFIG_SWAP=n
+ * no swap can happen anyway, so skipping the write is the correct behaviour.
+ */
+static int disable_swap(const char *cgroup_dir)
+{
+	if (access("/proc/swaps", F_OK))
+		return 0;
+
+	return write_cgroup_file(cgroup_dir, "memory.swap.max", "0");
+}
+
+/*
+ * The forked children run after test_progs hijacked stdio, so anything
+ * they print is lost with their private copy of the hijacked buffer
+ * unless the test runs under -v. The exit status is the one diagnostics
+ * channel that always reaches the parent, so each failing step gets its
+ * own code.
+ */
+enum child_exit_code {
+	CHILD_EXIT_OK = 0,
+	CHILD_EXIT_JOIN_CGROUP,
+	CHILD_EXIT_WRITE_FILE,
+	CHILD_EXIT_READ_FILE,
+	CHILD_EXIT_TIME_FILE,
+};
+
+static const char *child_exit_str(int code)
+{
+	switch (code) {
+	case CHILD_EXIT_OK:
+		return "success";
+	case CHILD_EXIT_JOIN_CGROUP:
+		return "join cgroup";
+	case CHILD_EXIT_WRITE_FILE:
+		return "write data file";
+	case CHILD_EXIT_READ_FILE:
+		return "read data file";
+	case CHILD_EXIT_TIME_FILE:
+		return "write time file";
+	default:
+		return "unknown";
+	}
+}
+
+static int setup_high_low_cgroups(u64 *high_cgroup_id, u64 *low_cgroup_id)
+{
+	int ret;
+	char limit_buf[20];
+
+	ret = setup_cgroup_environment();
+	if (!ASSERT_OK(ret, "setup_cgroup_environment"))
+		goto cleanup;
+
+	ret = create_and_get_cgroup(CG_DIR);
+	if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_DIR))
+		goto cleanup;
+	close(ret);
+
+	ret = enable_controllers(CG_DIR, "memory");
+	if (!ASSERT_OK(ret, "enable_controllers"))
+		goto cleanup;
+
+	snprintf(limit_buf, sizeof(limit_buf), "%lu", CG_LIMIT);
+	ret = write_cgroup_file(CG_DIR, "memory.max", limit_buf);
+	if (!ASSERT_OK(ret, "write_cgroup_file memory.max"))
+		goto cleanup;
+
+	ret = disable_swap(CG_DIR);
+	if (!ASSERT_OK(ret, "disable_swap"))
+		goto cleanup;
+
+	ret = create_and_get_cgroup(CG_HIGH_DIR);
+	if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_HIGH_DIR))
+		goto cleanup;
+	close(ret);
+
+	*high_cgroup_id = get_cgroup_id(CG_HIGH_DIR);
+	if (!ASSERT_GT(*high_cgroup_id, 0, "get_cgroup_id"))
+		goto cleanup;
+
+	ret = create_and_get_cgroup(CG_LOW_DIR);
+	if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_LOW_DIR))
+		goto cleanup;
+	close(ret);
+
+	*low_cgroup_id = get_cgroup_id(CG_LOW_DIR);
+	if (!ASSERT_GT(*low_cgroup_id, 0, "get_cgroup_id"))
+		goto cleanup;
+
+	return 0;
+
+cleanup:
+	cleanup_cgroup_environment();
+	return -1;
+}
+
+/*
+ * The dying test needs an empty reclaim target plus a cgroup that keeps
+ * refaulting while the target is removed, so reclaim rounds keep
+ * starting and run into the removed target. The two have to be separate
+ * cgroups: the target must hold no processes to be removed, and v2's
+ * no-internal-process constraint keeps the refaulting workload out of
+ * any parent that has domain children.
+ */
+static int setup_dying_cgroups(u64 *trigger_cgroup_id, u64 *target_cgroup_id)
+{
+	int ret;
+	char limit_buf[20];
+
+	ret = setup_cgroup_environment();
+	if (!ASSERT_OK(ret, "setup_cgroup_environment"))
+		goto cleanup;
+
+	ret = create_and_get_cgroup(CG_DYING_DIR);
+	if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_DYING_DIR))
+		goto cleanup;
+	close(ret);
+
+	ret = enable_controllers(CG_DYING_DIR, "memory");
+	if (!ASSERT_OK(ret, "enable_controllers"))
+		goto cleanup;
+
+	snprintf(limit_buf, sizeof(limit_buf), "%lu", CG_LIMIT);
+	ret = write_cgroup_file(CG_DYING_DIR, "memory.max", limit_buf);
+	if (!ASSERT_OK(ret, "write_cgroup_file memory.max"))
+		goto cleanup;
+
+	ret = disable_swap(CG_DYING_DIR);
+	if (!ASSERT_OK(ret, "disable_swap"))
+		goto cleanup;
+
+	ret = create_and_get_cgroup(CG_DYING_TRIGGER_DIR);
+	if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_DYING_TRIGGER_DIR))
+		goto cleanup;
+	close(ret);
+
+	*trigger_cgroup_id = get_cgroup_id(CG_DYING_TRIGGER_DIR);
+	if (!ASSERT_GT(*trigger_cgroup_id, 0, "get_cgroup_id"))
+		goto cleanup;
+
+	ret = create_and_get_cgroup(CG_DYING_TARGET_DIR);
+	if (!ASSERT_GE(ret, 0, "create_and_get_cgroup " CG_DYING_TARGET_DIR))
+		goto cleanup;
+	close(ret);
+
+	*target_cgroup_id = get_cgroup_id(CG_DYING_TARGET_DIR);
+	if (!ASSERT_GT(*target_cgroup_id, 0, "get_cgroup_id"))
+		goto cleanup;
+
+	return 0;
+
+cleanup:
+	cleanup_cgroup_environment();
+	return -1;
+}
+
+static int write_file(int fd)
+{
+	int ret = -1;
+	size_t written = 0;
+	char *buffer;
+
+	buffer = malloc(BUFFER_SIZE);
+	if (!buffer)
+		goto out;
+
+	memset(buffer, 'A', BUFFER_SIZE);
+
+	while (written < FILE_SIZE) {
+		size_t to_write = FILE_SIZE - written < BUFFER_SIZE ?
+				  FILE_SIZE - written : BUFFER_SIZE;
+		ssize_t n = write(fd, buffer, to_write);
+
+		if (n <= 0)
+			goto cleanup;
+		written += n;
+	}
+
+	ret = 0;
+cleanup:
+	free(buffer);
+out:
+	return ret;
+}
+
+static int read_file(int fd, int iterations)
+{
+	long page_size = sysconf(_SC_PAGESIZE);
+	struct stat sb;
+	char *map;
+	size_t i;
+
+	if (fstat(fd, &sb) == -1)
+		return -1;
+
+	if (sb.st_size != FILE_SIZE) {
+		fprintf(stderr, "File size mismatch: expected %lu, got %lu\n",
+			(unsigned long)FILE_SIZE, (unsigned long)sb.st_size);
+		return -1;
+	}
+
+	map = mmap(NULL, FILE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (map == MAP_FAILED)
+		return -1;
+
+	for (int iter = 0; iter < iterations; iter++) {
+		for (i = 0; i < FILE_SIZE; i += page_size) {
+			/* access a byte to trigger page fault */
+			volatile char v = map[i];
+			(void)v;
+		}
+	}
+
+	if (munmap(map, FILE_SIZE) == -1)
+		return -1;
+
+	return 0;
+}
+
+static int real_test_child_work(const char *cgroup_path, int data_fd,
+				int time_fd, int read_times)
+{
+	struct timespec start, end;
+	double elapsed;
+	char buf[32];
+	int len;
+
+	if (join_parent_cgroup(cgroup_path))
+		return CHILD_EXIT_JOIN_CGROUP;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	if (write_file(data_fd))
+		return CHILD_EXIT_WRITE_FILE;
+
+	if (read_file(data_fd, read_times))
+		return CHILD_EXIT_READ_FILE;
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+
+	elapsed = (end.tv_sec - start.tv_sec) +
+		  (end.tv_nsec - start.tv_nsec) / 1000000000.0;
+
+	len = snprintf(buf, sizeof(buf), "%.6f", elapsed);
+	/* snprintf() returns the untruncated length, so bound it before write() */
+	if (len < 0 || len >= (int)sizeof(buf) || write(time_fd, buf, len) != len)
+		return CHILD_EXIT_TIME_FILE;
+
+	return CHILD_EXIT_OK;
+}
+
+static int get_time(int fd, double *time)
+{
+	char buf[64] = {};
+	ssize_t n;
+
+	/* The child wrote through the fork-shared description, so rewind. */
+	if (lseek(fd, 0, SEEK_SET) == (off_t)-1) {
+		PRINT_FAIL("lseek time file");
+		return -1;
+	}
+
+	n = read(fd, buf, sizeof(buf) - 1);
+	if (!ASSERT_GT(n, 0, "read time file"))
+		return -1;
+
+	if (sscanf(buf, "%lf", time) != 1) {
+		PRINT_FAIL("sscanf %s", buf);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int
+run_high_low_workload(const char *dir, double *high_elapsed, double *low_elapsed,
+		      int read_times)
+{
+	char high_data_file[PATH_MAX];
+	char low_data_file[PATH_MAX];
+	char high_time_file[PATH_MAX];
+	char low_time_file[PATH_MAX];
+	int high_data_fd = -1, low_data_fd = -1;
+	int high_time_fd = -1, low_time_fd = -1;
+	pid_t high_pid = -1, low_pid = -1;
+	pid_t wait_ret;
+	int status;
+	int ret = -1;
+
+	snprintf(high_data_file, sizeof(high_data_file),
+		 "%s/memcg_async_high_data_XXXXXX", dir);
+	snprintf(low_data_file, sizeof(low_data_file),
+		 "%s/memcg_async_low_data_XXXXXX", dir);
+	snprintf(high_time_file, sizeof(high_time_file),
+		 "%s/memcg_async_high_time_XXXXXX", dir);
+	snprintf(low_time_file, sizeof(low_time_file),
+		 "%s/memcg_async_low_time_XXXXXX", dir);
+
+	/*
+	 * The mkstemp() fds are kept and inherited by the children rather
+	 * than reopened by name: reopening would resolve the path again and
+	 * follow whatever sits there by then.
+	 */
+	high_data_fd = mkstemp(high_data_file);
+	if (!ASSERT_GE(high_data_fd, 0, "mkstemp high data"))
+		goto cleanup;
+
+	low_data_fd = mkstemp(low_data_file);
+	if (!ASSERT_GE(low_data_fd, 0, "mkstemp low data"))
+		goto cleanup;
+
+	high_time_fd = mkstemp(high_time_file);
+	if (!ASSERT_GE(high_time_fd, 0, "mkstemp high time"))
+		goto cleanup;
+
+	low_time_fd = mkstemp(low_time_file);
+	if (!ASSERT_GE(low_time_fd, 0, "mkstemp low time"))
+		goto cleanup;
+
+	low_pid = fork();
+	if (!ASSERT_GE(low_pid, 0, "fork low"))
+		goto cleanup;
+	if (low_pid == 0)
+		_exit(real_test_child_work(CG_LOW_DIR, low_data_fd,
+					   low_time_fd, read_times));
+
+	high_pid = fork();
+	if (!ASSERT_GE(high_pid, 0, "fork high"))
+		goto cleanup;
+	if (high_pid == 0)
+		_exit(real_test_child_work(CG_HIGH_DIR, high_data_fd,
+					   high_time_fd, read_times));
+
+	wait_ret = waitpid(low_pid, &status, 0);
+	if (!ASSERT_GT(wait_ret, 0, "low waitpid"))
+		goto cleanup;
+	/*
+	 * The child has been reaped and its PID can already be reused,
+	 * so mark it to keep cleanup from signaling an unrelated process.
+	 */
+	low_pid = -1;
+	if (!ASSERT_TRUE(WIFEXITED(status), "low exited"))
+		goto cleanup;
+	if (WEXITSTATUS(status) != CHILD_EXIT_OK) {
+		PRINT_FAIL("low child failed at: %s (exit status %d)",
+			   child_exit_str(WEXITSTATUS(status)),
+			   WEXITSTATUS(status));
+		goto cleanup;
+	}
+
+	wait_ret = waitpid(high_pid, &status, 0);
+	if (!ASSERT_GT(wait_ret, 0, "high waitpid"))
+		goto cleanup;
+	/* Same as above: the reaped PID must not be signaled again. */
+	high_pid = -1;
+	if (!ASSERT_TRUE(WIFEXITED(status), "high exited"))
+		goto cleanup;
+	if (WEXITSTATUS(status) != CHILD_EXIT_OK) {
+		PRINT_FAIL("high child failed at: %s (exit status %d)",
+			   child_exit_str(WEXITSTATUS(status)),
+			   WEXITSTATUS(status));
+		goto cleanup;
+	}
+
+	if (get_time(high_time_fd, high_elapsed))
+		goto cleanup;
+	if (get_time(low_time_fd, low_elapsed))
+		goto cleanup;
+
+	ret = 0;
+
+cleanup:
+	/* On failure, make sure no child process is left behind */
+	if (ret) {
+		if (high_pid > 0) {
+			kill(high_pid, SIGKILL);
+			(void)waitpid(high_pid, NULL, 0);
+		}
+		if (low_pid > 0) {
+			kill(low_pid, SIGKILL);
+			(void)waitpid(low_pid, NULL, 0);
+		}
+	}
+	if (high_data_fd >= 0)
+		close(high_data_fd);
+	if (low_data_fd >= 0)
+		close(low_data_fd);
+	if (high_time_fd >= 0)
+		close(high_time_fd);
+	if (low_time_fd >= 0)
+		close(low_time_fd);
+	unlink(low_time_file);
+	unlink(high_time_file);
+	unlink(low_data_file);
+	unlink(high_data_file);
+	return ret;
+}
+
+static int
+setup_bpf(u64 high_cgroup_id, u64 low_cgroup_id,
+	  struct memcg_async_reclaim **skel_ptr)
+{
+	struct memcg_async_reclaim *skel;
+	struct bpf_args args = {
+		.high_cgroup_id = high_cgroup_id,
+		.low_cgroup_id = low_cgroup_id,
+		.event_delta_threshold = EVENT_DELTA_THRESHOLD,
+		.check_ns = CHECK_PERIOD_NS,
+	};
+	LIBBPF_OPTS(bpf_test_run_opts, run_opts,
+		.ctx_in = &args,
+		.ctx_size_in = sizeof(args));
+	int prog_init_fd, err;
+
+	skel = memcg_async_reclaim__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "memcg_async_reclaim__open_and_load"))
+		return -1;
+
+	prog_init_fd = bpf_program__fd(skel->progs.wq_prog_init);
+
+	err = bpf_prog_test_run_opts(prog_init_fd, &run_opts);
+	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+		goto error_out;
+	if (!ASSERT_EQ(run_opts.retval, 0, "prog_init retval"))
+		goto error_out;
+
+	*skel_ptr = skel;
+	return 0;
+
+error_out:
+	memcg_async_reclaim__destroy(skel);
+	return -1;
+}
+
+/*
+ * A timer that stopped rearming produces no further reclaim rounds, which
+ * the "no events" failures below would otherwise report as a kernel bug.
+ * Only call this on a path that is already failing.
+ */
+static void report_timer_failures(struct memcg_async_reclaim *skel)
+{
+	u64 failures = skel->bss->timer_failures;
+
+	if (failures)
+		PRINT_FAIL("bpf_timer failed to rearm %llu time(s), so the reclaim loop stopped",
+			   (unsigned long long)failures);
+}
+
+/*
+ * A kfunc that fails on every call is indistinguishable from a cgroup with
+ * nothing left to reclaim, which the reclaim_calls and reclaimed_bytes
+ * assertions below cannot tell apart. Only call this on a path that is
+ * already failing.
+ */
+static void report_reclaim_errors(struct memcg_async_reclaim *skel)
+{
+	u64 last_err = skel->bss->last_reclaim_err;
+
+	if (last_err)
+		PRINT_FAIL("bpf_proactive_reclaim() last failed with -%llu, nothing was reclaimed",
+			   (unsigned long long)last_err);
+}
+
+/*
+ * The benchmark numbers are only interesting when the test passes, but
+ * dump_test_log() drops the captured log unless the test failed or -v was
+ * given, so they have to bypass the hijack. The ?: stdout fallback is
+ * required, not defensive: stdio_hijack() returns early in verbose mode and
+ * never sets env.stdout_saved.
+ *
+ * This also bypasses the worker-to-dispatcher log protocol, so under -j the
+ * line can interleave with the per-test records. It carries no '#' prefix:
+ * test_progs uses that only for its own result records, and print_test_log()
+ * dumps free-form test output verbatim.
+ */
+static void bench_printf(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(env.stdout_saved ?: stdout, fmt, ap);
+	va_end(ap);
+}
+
+void test_memcg_async_reclaim(void)
+{
+	u64 high_cgroup_id, low_cgroup_id;
+	double high_time = 0.0, low_time = 0.0;
+	double base_high_time = 0.0, base_low_time = 0.0;
+	struct memcg_async_reclaim *skel = NULL;
+	const char *dir;
+	int err, bench;
+
+	dir = workload_files_dir();
+	if (!ASSERT_TRUE(dir != NULL, "workload_files_dir"))
+		return;
+
+	bench = !!getenv("TEST_MEMCG_ASYNC_RECLAIM_BENCH");
+
+	err = setup_high_low_cgroups(&high_cgroup_id, &low_cgroup_id);
+	if (!ASSERT_OK(err, "setup_high_low_cgroups reclaim"))
+		return;
+
+	/*
+	 * Optional baseline for the benchmark numbers below: run the
+	 * same workload once without the BPF program, so the log can
+	 * report how much async reclaim improved the pressured cgroup.
+	 */
+	if (bench) {
+		err = run_high_low_workload(dir, &base_high_time,
+					    &base_low_time, READ_TIMES);
+		if (!ASSERT_OK(err, "run_high_low_workload baseline"))
+			goto out;
+
+		/*
+		 * The baseline left up to CG_LIMIT of page cache charged to the
+		 * high and low cgroups, and memcg charges outlive the workload
+		 * processes. Recreate the cgroups so that the instrumented run
+		 * below starts from the same cold state the baseline did;
+		 * otherwise the reported speedup compares a cold run against a
+		 * warm one.
+		 */
+		cleanup_cgroup_environment();
+		err = setup_high_low_cgroups(&high_cgroup_id, &low_cgroup_id);
+		if (!ASSERT_OK(err, "setup_high_low_cgroups after baseline"))
+			goto out;
+	}
+
+	err = setup_bpf(high_cgroup_id, low_cgroup_id, &skel);
+	if (!ASSERT_OK(err, "setup_bpf"))
+		goto out;
+
+	err = run_high_low_workload(dir, &high_time, &low_time, READ_TIMES);
+	if (!ASSERT_OK(err, "run_high_low_workload reclaim"))
+		goto out;
+
+	/*
+	 * Timing alone cannot distinguish a working reclaim from a no-op
+	 * one, so require that the BPF program actually reclaimed memory
+	 * from the low cgroup.
+	 */
+	if (!ASSERT_GT(skel->bss->reclaim_calls, 0, "reclaim_calls")) {
+		report_timer_failures(skel);
+		report_reclaim_errors(skel);
+		goto out;
+	}
+	if (!ASSERT_GT(skel->bss->reclaimed_bytes, 0, "reclaimed_bytes")) {
+		report_reclaim_errors(skel);
+		goto out;
+	}
+
+	/*
+	 * The timing comparison is a benchmark and too flaky to fail CI
+	 * runs, so it only logs the numbers; the counters above already
+	 * proved that the BPF program reclaimed memory.
+	 */
+	if (bench && base_high_time > 0.0)
+		bench_printf("memcg_async_reclaim: baseline high=%f low=%f, "
+			     "reclaim high=%f low=%f, high speedup=%.1f%%\n",
+			     base_high_time, base_low_time, high_time, low_time,
+			     100.0 * (base_high_time - high_time) / base_high_time);
+
+out:
+	if (skel)
+		memcg_async_reclaim__destroy(skel);
+	cleanup_cgroup_environment();
+}
+
+/*
+ * Keep refaults flowing through the trigger cgroup so reclaim rounds
+ * keep being triggered while the target cgroup is being removed. The
+ * child joins the trigger cgroup and writes the data file there, so
+ * that the file pages are charged to the trigger cgroup and actually
+ * come under its memory limit; then it re-reads the file in a loop
+ * until it is killed.
+ */
+static pid_t spawn_keepalive_reader(int data_fd)
+{
+	pid_t pid = fork();
+
+	if (pid != 0)
+		return pid;
+
+	if (join_parent_cgroup(CG_DYING_TRIGGER_DIR))
+		_exit(CHILD_EXIT_JOIN_CGROUP);
+	if (write_file(data_fd))
+		_exit(CHILD_EXIT_WRITE_FILE);
+	for (;;) {
+		if (read_file(data_fd, READ_TIMES))
+			_exit(CHILD_EXIT_READ_FILE);
+	}
+}
+
+/* Reclaim outcomes observed so far, tallied from ringbuf events. */
+struct reclaim_events_seen {
+	int called;
+	int skipped_dying;
+	int target_gone;
+};
+
+static int on_reclaim_event(void *ctx, void *data, size_t sz)
+{
+	struct reclaim_events_seen *seen = ctx;
+	const struct reclaim_event *ev = data;
+
+	if (sz < sizeof(*ev))
+		return 0;
+
+	switch (ev->outcome) {
+	case RECLAIM_OUTCOME_CALLED:
+		seen->called++;
+		break;
+	case RECLAIM_OUTCOME_SKIPPED_DYING:
+		seen->skipped_dying++;
+		break;
+	case RECLAIM_OUTCOME_TARGET_GONE:
+		seen->target_gone++;
+		break;
+	}
+
+	return 0;
+}
+
+/*
+ * Remove the reclaim target while the BPF program keeps running and verify
+ * that reclaim stops instead of reclaiming from the removed cgroup.
+ *
+ * The target stays empty; the workload lives in the trigger cgroup and only
+ * keeps refaults flowing so that reclaim rounds keep starting, both before
+ * and after the target is removed. A CALLED event while the target is alive
+ * proves that rounds really run (the kfunc returns 0 on the empty target, but
+ * the call is still counted).
+ *
+ * Once rmdir has returned, bpf_cgroup_from_id() has already stopped resolving
+ * the target: kernfs deactivates the directory node inside the rmdir syscall,
+ * see cgroup_is_dying() in the BPF program. TARGET_GONE is therefore the
+ * outcome this test can rely on, and the one it asserts. SKIPPED_DYING needs
+ * an attempt to land in the short window between cgroup_destroy_locked()
+ * clearing CSS_ONLINE and kernfs_remove() deactivating the node, so it is
+ * counted and reported on failure but never required.
+ */
+void test_memcg_async_reclaim_dying(void)
+{
+	u64 trigger_cgroup_id, target_cgroup_id;
+	char data_file[PATH_MAX] = "";
+	struct reclaim_events_seen seen = {};
+	struct memcg_async_reclaim *skel = NULL;
+	struct ring_buffer *rb = NULL;
+	u64 calls_before;
+	const char *dir;
+	pid_t reader_pid = -1;
+	int data_fd = -1;
+	int err, status, i, n;
+
+	dir = workload_files_dir();
+	if (!ASSERT_TRUE(dir != NULL, "workload_files_dir"))
+		return;
+
+	err = setup_dying_cgroups(&trigger_cgroup_id, &target_cgroup_id);
+	if (!ASSERT_OK(err, "setup_dying_cgroups"))
+		return;
+
+	err = setup_bpf(trigger_cgroup_id, target_cgroup_id, &skel);
+	if (!ASSERT_OK(err, "setup_bpf"))
+		goto out;
+
+	rb = ring_buffer__new(bpf_map__fd(skel->maps.reclaim_events),
+			      on_reclaim_event, &seen, NULL);
+	if (!ASSERT_OK_PTR(rb, "ring_buffer__new"))
+		goto out;
+
+	snprintf(data_file, sizeof(data_file),
+		 "%s/memcg_async_dying_XXXXXX", dir);
+	/* Kept open and inherited, see run_high_low_workload(). */
+	data_fd = mkstemp(data_file);
+	if (!ASSERT_GE(data_fd, 0, "mkstemp"))
+		goto out;
+
+	reader_pid = spawn_keepalive_reader(data_fd);
+	if (!ASSERT_GT(reader_pid, 0, "fork keepalive reader"))
+		goto out;
+
+	/* Wait for reclaim rounds to reach the live target cgroup. */
+	for (i = 0; i < EVENT_POLL_ROUNDS && !seen.called; i++) {
+		n = ring_buffer__poll(rb, EVENT_POLL_TIMEOUT_MS);
+		if (!ASSERT_GE(n, 0, "ring_buffer__poll"))
+			goto out;
+
+		/*
+		 * The reader loops until killed, so finding it already gone
+		 * means the refaults the BPF program waits for never started.
+		 * Report its exit code rather than letting the assert below
+		 * blame the kernel for the full poll window.
+		 */
+		if (waitpid(reader_pid, &status, WNOHANG) == reader_pid) {
+			/* Reaped, so cleanup must not signal a reused PID. */
+			reader_pid = -1;
+			if (WIFEXITED(status))
+				PRINT_FAIL("keepalive reader exited early: %s",
+					   child_exit_str(WEXITSTATUS(status)));
+			else
+				PRINT_FAIL("keepalive reader died, status 0x%x",
+					   status);
+			goto out;
+		}
+	}
+	if (!ASSERT_GT(seen.called, 0, "reclaim events")) {
+		report_timer_failures(skel);
+		goto out;
+	}
+
+	remove_cgroup(CG_DYING_TARGET_DIR);
+
+	/* Let reclaim passes that were already in flight drain. */
+	usleep(DYING_SETTLE_US);
+
+	calls_before = skel->bss->reclaim_calls;
+
+	/*
+	 * Wait for a reclaim round to hit the removed cgroup. Only TARGET_GONE
+	 * ends the wait: an attempt that lands inside the rmdir window reports
+	 * SKIPPED_DYING first, and stopping there would miss the events that
+	 * follow it.
+	 */
+	for (i = 0; i < EVENT_POLL_ROUNDS && !seen.target_gone; i++) {
+		n = ring_buffer__poll(rb, EVENT_POLL_TIMEOUT_MS);
+		if (!ASSERT_GE(n, 0, "ring_buffer__poll"))
+			goto out;
+	}
+
+	/*
+	 * TARGET_GONE is what the test can rely on: by the time rmdir has
+	 * returned, bpf_cgroup_from_id() has stopped resolving the target.
+	 * SKIPPED_DYING only happens if an attempt lands inside the rmdir
+	 * window, so it is reported here rather than asserted.
+	 */
+	if (!seen.target_gone) {
+		report_timer_failures(skel);
+		PRINT_FAIL("no reclaim round hit the removed cgroup (gone=%d, dying=%d)",
+			   seen.target_gone, seen.skipped_dying);
+		goto out;
+	}
+
+	/*
+	 * Reclaim must have stopped with the target. Both counters stay put for
+	 * the same reason: once rmdir has returned, bpf_cgroup_from_id() fails,
+	 * so every attempt takes the TARGET_GONE path before it can reach
+	 * reclaim_calls++. This therefore checks that reclaim really stops, not
+	 * that cgroup_is_dying() works -- see that function in the BPF program
+	 * for why the dying window cannot be hit reliably from userspace.
+	 *
+	 * reclaimed_bytes is compared against 0 rather than against its
+	 * pre-removal value: the target is empty for the whole test, so
+	 * bpf_proactive_reclaim() has nothing to reclaim and must have returned
+	 * 0 on every call, before and after the removal alike. An "unchanged"
+	 * comparison would be 0 == 0 and could never fail.
+	 */
+	if (!ASSERT_EQ(skel->bss->reclaim_calls, calls_before, "reclaim_calls"))
+		goto out;
+	if (!ASSERT_EQ(skel->bss->reclaimed_bytes, 0ULL, "reclaimed_bytes"))
+		goto out;
+
+out:
+	if (reader_pid > 0) {
+		kill(reader_pid, SIGKILL);
+		(void)waitpid(reader_pid, NULL, 0);
+	}
+	if (data_fd >= 0)
+		close(data_fd);
+	if (data_file[0])
+		unlink(data_file);
+	if (rb)
+		ring_buffer__free(rb);
+	if (skel)
+		memcg_async_reclaim__destroy(skel);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/progs/memcg_async_reclaim.c b/tools/testing/selftests/bpf/progs/memcg_async_reclaim.c
new file mode 100644
index 000000000000..d78d547af7bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/memcg_async_reclaim.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include "bpf_experimental.h"
+
+#define CLOCK_MONOTONIC		1
+/*
+ * One reclaim round targets RECLAIM_MAX_ITER batches of RECLAIM_SIZE
+ * each, i.e. 4 MiB in total. Each bpf_wq callback reclaims a single
+ * batch and requeues the same work item for the next one, so no callback
+ * runs longer than one bounded reclaim pass.
+ *
+ * RECLAIM_SIZE is a byte count, not a page count: bpf_proactive_reclaim()
+ * converts it against the running kernel's PAGE_SIZE and returns bytes, so
+ * this holds on any page size. The kfunc also clamps a batch to the
+ * kernel's MEMCG_CHARGE_BATCH, which is not visible to BPF; a clamped
+ * batch only means a round needs more callbacks, because remaining is
+ * decremented by the bytes actually reclaimed.
+ */
+#define RECLAIM_SIZE		(128 * 1024UL)
+#define RECLAIM_MAX_ITER	32
+
+struct bpf_args {
+	u64 high_cgroup_id;
+	u64 low_cgroup_id;
+	u64 event_delta_threshold;
+	u64 check_ns;
+};
+
+struct cgroup_memcg {
+	struct cgroup *cgrp;
+	struct mem_cgroup *memcg;
+};
+
+static u64 wq_high_cgroup_id;
+static u64 wq_low_cgroup_id;
+
+/*
+ * Statistics exposed to userspace through .bss, so the test can verify
+ * that reclaim actually happened instead of relying on timing alone.
+ */
+u64 reclaim_calls;
+u64 reclaimed_bytes;
+
+/*
+ * A timer that fails to rearm stops the whole chain, which from userspace
+ * looks exactly like "the kernel never reclaimed". Count it so the test can
+ * tell the two apart instead of blaming the kernel.
+ */
+u64 timer_failures;
+
+/*
+ * bpf_proactive_reclaim() reports failure as a negative return, which is
+ * otherwise indistinguishable from "this cgroup has nothing left to
+ * reclaim". Keep the last one so a failing kfunc is not mistaken for an
+ * idle cgroup. Stored as a positive errno.
+ */
+u64 last_reclaim_err;
+
+/*
+ * Outcome of a single reclaim attempt, reported to userspace through
+ * the reclaim_events ringbuf so tests can wait for reclaim events with
+ * a timeout instead of polling the counters above.
+ */
+enum reclaim_outcome {
+	RECLAIM_OUTCOME_CALLED,
+	RECLAIM_OUTCOME_SKIPPED_DYING,
+	RECLAIM_OUTCOME_TARGET_GONE,
+};
+
+struct reclaim_event {
+	__u64 outcome;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1 << 16);
+} reclaim_events SEC(".maps");
+
+/*
+ * Reports are best effort: when the ringbuf is full, for example when
+ * userspace does not consume the events, the report is dropped.
+ */
+static void emit_reclaim_event(enum reclaim_outcome outcome)
+{
+	struct reclaim_event *ev;
+
+	ev = bpf_ringbuf_reserve(&reclaim_events, sizeof(*ev), 0);
+	if (!ev)
+		return;
+
+	ev->outcome = outcome;
+	bpf_ringbuf_submit(ev, 0);
+}
+
+static int get_cgroup_memcg_from_id(u64 cgroup_id, struct cgroup_memcg *cm)
+{
+	cm->cgrp = bpf_cgroup_from_id(cgroup_id);
+	if (!cm->cgrp)
+		return -1;
+
+	cm->memcg = bpf_get_mem_cgroup(&cm->cgrp->self);
+	if (!cm->memcg) {
+		bpf_cgroup_release(cm->cgrp);
+		return -1;
+	}
+
+	return 0;
+}
+
+static void put_cgroup_memcg(struct cgroup_memcg *cm)
+{
+	bpf_put_mem_cgroup(cm->memcg);
+	bpf_cgroup_release(cm->cgrp);
+}
+
+static int get_cgroup_event(u64 cgroup_id, u64 *val)
+{
+	struct cgroup_memcg cm;
+
+	if (get_cgroup_memcg_from_id(cgroup_id, &cm))
+		return -1;
+	bpf_mem_cgroup_flush_stats(cm.memcg);
+	*val = bpf_mem_cgroup_page_state(cm.memcg,
+		bpf_core_enum_value(enum node_stat_item,
+				    WORKINGSET_REFAULT_FILE));
+	put_cgroup_memcg(&cm);
+
+	return 0;
+}
+
+static bool
+should_reclaim_cgroup(u64 cgroup_id, u64 *prev_event, u64 event_delta_threshold)
+{
+	u64 cur, delta;
+
+	if (get_cgroup_event(cgroup_id, &cur))
+		return false;
+
+	delta = cur - *prev_event;
+	*prev_event = cur;
+
+	return delta >= event_delta_threshold;
+}
+
+/*
+ * rmdir clears CSS_ONLINE on cgrp->self in cgroup_destroy_locked() and only
+ * then deactivates the cgroup's kernfs node with kernfs_remove().
+ * bpf_cgroup_from_id() resolves an id through
+ * kernfs_find_and_get_node_by_id(), which refuses deactivated nodes, so the
+ * lookup starts failing inside the rmdir syscall -- not, as one might expect,
+ * once the cgroup's last reference has been dropped.
+ *
+ * The window in which the lookup still succeeds while the cgroup is already
+ * dying is therefore just the few statements between those two. An attempt
+ * that lands in it reports RECLAIM_OUTCOME_SKIPPED_DYING; after rmdir has
+ * returned, every attempt reports TARGET_GONE instead. The check is kept
+ * because it is the only thing standing between reclaim and a cgroup that is
+ * mid-teardown, but it cannot be hit reliably from userspace, so the test
+ * does not require SKIPPED_DYING.
+ *
+ * Only CSS_ONLINE is worth testing. CSS_DYING is raised by kill_css_sync(),
+ * which dereferences css->ss and so is never called with cgrp->self; the
+ * cgroup's own css only ever loses CSS_ONLINE. This is therefore
+ * cgroup_is_dead() from include/linux/cgroup.h, not css_is_dying().
+ *
+ * CSS_ONLINE comes from vmlinux.h: the kernel defines it in an anonymous
+ * enum, so bpf_core_enum_value() has no enum type to bind to, and
+ * redeclaring it locally would clash with the vmlinux.h enumerators.
+ * vmlinux.h is generated from the running kernel's BTF, so the value
+ * already matches the target kernel.
+ */
+static bool cgroup_is_dying(struct cgroup *cgrp)
+{
+	return !(cgrp->self.flags & CSS_ONLINE);
+}
+
+/*
+ * Reclaim one batch from the target cgroup. Returns the number of
+ * bytes reclaimed, or 0 if the cgroup is dying or gone, the kfunc
+ * failed, or nothing was reclaimed. Each attempt reports its outcome
+ * through the reclaim_events ringbuf, and a failing kfunc additionally
+ * records its errno in last_reclaim_err.
+ */
+static u64 reclaim_cgroup(u64 cgroup_id, u64 size)
+{
+	struct cgroup_memcg cm;
+	long nr;
+
+	if (get_cgroup_memcg_from_id(cgroup_id, &cm)) {
+		emit_reclaim_event(RECLAIM_OUTCOME_TARGET_GONE);
+		return 0;
+	}
+
+	if (cgroup_is_dying(cm.cgrp)) {
+		emit_reclaim_event(RECLAIM_OUTCOME_SKIPPED_DYING);
+		put_cgroup_memcg(&cm);
+		return 0;
+	}
+
+	reclaim_calls++;
+	nr = bpf_proactive_reclaim(cm.memcg, size, -1);
+	if (nr < 0)
+		last_reclaim_err = -nr;
+	else if (nr > 0)
+		reclaimed_bytes += nr;
+	emit_reclaim_event(RECLAIM_OUTCOME_CALLED);
+
+	put_cgroup_memcg(&cm);
+
+	return nr > 0 ? nr : 0;
+}
+
+struct wq_elem {
+	struct bpf_timer timer;
+	struct bpf_wq work;
+	u64 prev_event;
+	u64 event_delta_threshold;
+	u64 check_ns;
+	/*
+	 * Bytes still to reclaim in the current round, carried across
+	 * requeues. 0 means no round is in progress; the timer path
+	 * starts a new round by resetting it, requeued work only looks
+	 * at it.
+	 */
+	u64 remaining;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct wq_elem);
+} wq_map SEC(".maps");
+
+static int reclaim_work_fn(void *map, int *key, void *value)
+{
+	struct wq_elem *elem = value;
+	u64 nr, size;
+
+	if (!elem->remaining) {
+		/*
+		 * Timer-triggered entry: start a new round only when the
+		 * high cgroup refaults enough. Requeued entries skip this
+		 * check and only look at remaining, so a round consumes the
+		 * refault delta only on the tick that starts it; ticks that
+		 * find no round in progress consume and discard it.
+		 */
+		if (!should_reclaim_cgroup(wq_high_cgroup_id, &elem->prev_event,
+			elem->event_delta_threshold))
+			return 0;
+		elem->remaining = RECLAIM_MAX_ITER * RECLAIM_SIZE;
+	}
+
+	/* One bounded reclaim pass per callback */
+	size = elem->remaining < RECLAIM_SIZE ? elem->remaining : RECLAIM_SIZE;
+	nr = reclaim_cgroup(wq_low_cgroup_id, size);
+	if (!nr) {
+		elem->remaining = 0;
+		return 0;
+	}
+
+	/* try_to_free_mem_cgroup_pages() may reclaim more than requested */
+	if (nr >= elem->remaining)
+		elem->remaining = 0;
+	else
+		elem->remaining -= nr;
+
+	/* Requeue the same work item for the next batch */
+	if (elem->remaining)
+		bpf_wq_start(&elem->work, 0);
+
+	return 0;
+}
+
+static int wq_timer_cb(void *map, int *key, struct wq_elem *elem)
+{
+	/*
+	 * A failed bpf_wq_start() self-heals on the next tick; a failed
+	 * rearm does not, so only the latter is worth reporting.
+	 */
+	bpf_wq_start(&elem->work, 0);
+	if (bpf_timer_start(&elem->timer, elem->check_ns, 0))
+		timer_failures++;
+
+	return 0;
+}
+
+SEC("syscall")
+int wq_prog_init(struct bpf_args *ctx)
+{
+	struct wq_elem *elem;
+	__u32 key = 0;
+	int ret;
+
+	elem = bpf_map_lookup_elem(&wq_map, &key);
+	if (!elem)
+		return -1;
+
+	ret = bpf_wq_init(&elem->work, &wq_map, 0);
+	if (ret)
+		return ret;
+
+	ret = bpf_wq_set_callback(&elem->work, reclaim_work_fn, 0);
+	if (ret)
+		return ret;
+
+	ret = bpf_timer_init(&elem->timer, &wq_map, CLOCK_MONOTONIC);
+	if (ret)
+		return ret;
+
+	ret = bpf_timer_set_callback(&elem->timer, wq_timer_cb);
+	if (ret)
+		return ret;
+
+	elem->prev_event = 0;
+	elem->remaining = 0;
+	elem->event_delta_threshold = ctx->event_delta_threshold;
+	elem->check_ns = ctx->check_ns;
+
+	wq_high_cgroup_id = ctx->high_cgroup_id;
+	wq_low_cgroup_id = ctx->low_cgroup_id;
+
+	return bpf_timer_start(&elem->timer, elem->check_ns, 0);
+}
+
+char _license[] SEC("license") = "GPL";
-- 
2.43.0


  parent reply	other threads:[~2026-09-18  6:59 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-18  6:58 [PATCH bpf-next v12 0/2] bpf: BPF-driven proactive memcg reclaim Hui Zhu
2026-09-18  6:58 ` [PATCH bpf-next v12 1/2] mm/bpf: Add bpf_proactive_reclaim kfunc Hui Zhu
2026-09-18 19:45   ` JP Kobryn
2026-09-18 20:15     ` Shakeel Butt
2026-09-19 22:36       ` Barry Song
2026-09-19 23:21         ` Barry Song
2026-09-18  6:58 ` Hui Zhu [this message]
2026-09-18  8:07   ` [PATCH bpf-next v12 2/2] selftests/bpf: Add memcg async reclaim test bot+bpf-ci
2026-09-18 15:41   ` Alexei Starovoitov
2026-09-18 17:53     ` Shakeel Butt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=44f7fcfafd5f33072dd2b9abc31aa9bf5eacd9bb.1789714023.git.zhuhui@kylinos.cn \
    --to=hui.zhu@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=baohua@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=david@kernel.org \
    --cc=eddyz87@gmail.com \
    --cc=emil@etsalapatis.com \
    --cc=geliang@kernel.org \
    --cc=ihor.solodrai@linux.dev \
    --cc=inwardvessel@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=martin.lau@linux.dev \
    --cc=memxor@gmail.com \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=shuah@kernel.org \
    --cc=song@kernel.org \
    --cc=yonghong.song@linux.dev \
    --cc=zhuhui@kylinos.cn \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®