selftests/bpf: Test timer field on recycled rhtab element

Exercise the rhtab special-field lifecycle with the sequence from the
original report. A bpf_for_each_map_elem() callback deletes the sole
element, then initializes and arms a timer through the callback value
pointer while it remains valid.

Use a one-element map and pin userspace and BPF execution to one CPU.
Repeated delete-and-replace cycles drain the per-CPU allocator cache, and
periodic RCU synchronization makes the deleted units available for
recycling.

After each replacement, a second BPF program calls bpf_timer_cancel()
on its value. A successful cancellation proves both that a timer-bearing
unit was recycled and that insertion preserved the timer field. Without
the fix, insertion clears that field and cancellation keeps returning
-EINVAL. A long expiration keeps the timer callback out of the test, so
the regression is detected without accessing freed memory.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260904104203.345917-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 239 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/rhash_timer.c b/tools/testing/selftests/bpf/prog_tests/rhash_timer.c
new file mode 100644
index 000000000000..3aad9fc02e06
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/rhash_timer.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <sched.h>
+
+#include <test_progs.h>
+#include "rhash_timer.skel.h"
+
+#define MAX_ATTEMPTS 256
+#define RCU_SYNC_INTERVAL 64
+
+static int pin_to_first_cpu(cpu_set_t *old_mask)
+{
+	cpu_set_t new_mask;
+	int cpu;
+
+	if (sched_getaffinity(0, sizeof(*old_mask), old_mask))
+		return -errno;
+
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++)
+		if (CPU_ISSET(cpu, old_mask))
+			break;
+	if (cpu == CPU_SETSIZE)
+		return -EINVAL;
+
+	CPU_ZERO(&new_mask);
+	CPU_SET(cpu, &new_mask);
+	if (sched_setaffinity(0, sizeof(new_mask), &new_mask))
+		return -errno;
+	return 0;
+}
+
+static int update_timer_map(int map_fd, __u64 key)
+{
+	__u64 value[3] = {};
+
+	return bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+}
+
+static int run_prog(int prog_fd, struct bpf_test_run_opts *opts)
+{
+	int err;
+
+	err = bpf_prog_test_run_opts(prog_fd, opts);
+	if (err)
+		return err;
+	return opts->retval;
+}
+
+void test_rhash_timer(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct rhash_timer *skel = NULL;
+	cpu_set_t old_mask;
+	int map_fd = -1, arm_fd, cancel_fd;
+	bool affinity_set = false;
+	__u64 key = 1;
+	int attempt, err;
+
+	err = pin_to_first_cpu(&old_mask);
+	if (!ASSERT_OK(err, "pin_to_first_cpu"))
+		return;
+	affinity_set = true;
+
+	skel = rhash_timer__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto out;
+
+	map_fd = bpf_map__fd(skel->maps.timer_map);
+	if (!ASSERT_GE(map_fd, 0, "timer_map fd"))
+		goto out;
+	arm_fd = bpf_program__fd(skel->progs.arm_deleted_timer);
+	if (!ASSERT_GE(arm_fd, 0, "arm_deleted_timer fd"))
+		goto out;
+	cancel_fd = bpf_program__fd(skel->progs.cancel_recycled_timer);
+	if (!ASSERT_GE(cancel_fd, 0, "cancel_recycled_timer fd"))
+		goto out;
+
+	err = update_timer_map(map_fd, key);
+	if (!ASSERT_OK(err, "seed_timer_map"))
+		goto out;
+
+	for (attempt = 0; attempt < MAX_ATTEMPTS; attempt++) {
+		err = run_prog(arm_fd, &opts);
+		if (err) {
+			ASSERT_OK(err, "arm_deleted_timer");
+			goto out;
+		}
+		if (skel->bss->armed != attempt + 1) {
+			ASSERT_EQ(skel->bss->armed, attempt + 1, "armed");
+			goto out;
+		}
+		if (skel->bss->timer_init_err) {
+			ASSERT_OK(skel->bss->timer_init_err, "timer_init_err");
+			goto out;
+		}
+		if (skel->bss->timer_set_callback_err) {
+			ASSERT_OK(skel->bss->timer_set_callback_err,
+				  "timer_set_callback_err");
+			goto out;
+		}
+		if (skel->bss->timer_start_err) {
+			ASSERT_OK(skel->bss->timer_start_err, "timer_start_err");
+			goto out;
+		}
+
+		if ((attempt + 1) % RCU_SYNC_INTERVAL == 0) {
+			err = kern_sync_rcu();
+			if (err) {
+				ASSERT_OK(err, "kern_sync_rcu");
+				goto out;
+			}
+		}
+
+		err = update_timer_map(map_fd, ++key);
+		if (err) {
+			ASSERT_OK(err, "replace_timer_map");
+			goto out;
+		}
+
+		err = run_prog(cancel_fd, &opts);
+		if (err) {
+			ASSERT_OK(err, "cancel_recycled_timer");
+			goto out;
+		}
+		if (skel->bss->timer_cancel_err) {
+			ASSERT_OK(skel->bss->timer_cancel_err, "timer_cancel_err");
+			goto out;
+		}
+		if (skel->bss->cancelled)
+			break;
+	}
+
+	ASSERT_GT(skel->bss->cancelled, 0, "preserved timer");
+out:
+	if (map_fd >= 0)
+		bpf_map_delete_elem(map_fd, &key);
+	rhash_timer__destroy(skel);
+	if (affinity_set)
+		sched_setaffinity(0, sizeof(old_mask), &old_mask);
+}
diff --git a/tools/testing/selftests/bpf/progs/rhash_timer.c b/tools/testing/selftests/bpf/progs/rhash_timer.c
new file mode 100644
index 000000000000..2e06a463c605
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rhash_timer.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+#define CLOCK_MONOTONIC 1
+#define TIMER_NSEC (60ULL * 1000 * 1000 * 1000)
+
+struct timer_value {
+	struct bpf_timer timer;
+	u64 data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RHASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, 1);
+	__type(key, u64);
+	__type(value, struct timer_value);
+} timer_map SEC(".maps");
+
+u64 armed;
+u64 cancelled;
+long timer_init_err;
+long timer_set_callback_err;
+long timer_start_err;
+long timer_cancel_err;
+
+static int timer_cb(void *map, u64 *key, struct timer_value *value)
+{
+	return 0;
+}
+
+static long arm_timer_cb(struct bpf_map *map, u64 *key,
+			 struct timer_value *value, void *ctx)
+{
+	u64 key_copy = *key;
+	long err;
+
+	err = bpf_map_delete_elem(map, &key_copy);
+	if (err)
+		return 1;
+
+	err = bpf_timer_init(&value->timer, map, CLOCK_MONOTONIC);
+	if (err) {
+		timer_init_err = err;
+		return 1;
+	}
+
+	err = bpf_timer_set_callback(&value->timer, timer_cb);
+	if (err) {
+		timer_set_callback_err = err;
+		return 1;
+	}
+
+	err = bpf_timer_start(&value->timer, TIMER_NSEC, BPF_F_TIMER_CPU_PIN);
+	if (err) {
+		timer_start_err = err;
+		return 1;
+	}
+
+	__sync_fetch_and_add(&armed, 1);
+	return 1;
+}
+
+static long cancel_timer_cb(struct bpf_map *map, u64 *key,
+			    struct timer_value *value, void *ctx)
+{
+	long err;
+
+	err = bpf_timer_cancel(&value->timer);
+	if (err == -EINVAL)
+		return 1;
+	if (err < 0) {
+		timer_cancel_err = err;
+		return 1;
+	}
+
+	__sync_fetch_and_add(&cancelled, 1);
+	return 1;
+}
+
+SEC("syscall")
+int arm_deleted_timer(void *ctx)
+{
+	bpf_for_each_map_elem(&timer_map, arm_timer_cb, NULL, 0);
+	return 0;
+}
+
+SEC("syscall")
+int cancel_recycled_timer(void *ctx)
+{
+	bpf_for_each_map_elem(&timer_map, cancel_timer_cb, NULL, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";