[PATCH v5 20/23] mm/ksw: add multi-thread corruption test cases

[Jinchao Wang <wangjinchao600@gmail.com>]

These tests share a common structure and are grouped together.

- buggy():
  exposes the stack address to corrupting(); may omit waiting
- corrupting():
  reads the exposed pointer and modifies memory;
  if buggy() omits waiting, victim()'s buffer is corrupted
- victim():
  initializes a local buffer and later verifies it;
  reports an error if the buffer was unexpectedly modified

buggy() and victim() run in worker() thread, with similar stack frame sizes
to simplify testing. By adjusting fence_size in corrupting(), the test can
trigger either silent corruption or overflow across threads.

- Test 3: one worker, 20 loops, silent corruption
- Test 4: 20 workers, one loop each, silent corruption
- Test 5: one worker, one loop, overflow corruption

Test 4 also exercises multiple watchpoint instances.

Signed-off-by: Jinchao Wang <wangjinchao600@gmail.com>
---
 mm/kstackwatch/test.c | 178 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 176 insertions(+), 2 deletions(-)

diff --git a/mm/kstackwatch/test.c b/mm/kstackwatch/test.c
index 08e3d37c4c04..859122bbbdeb 100644
--- a/mm/kstackwatch/test.c
+++ b/mm/kstackwatch/test.c
@@ -17,11 +17,12 @@
 
 static struct proc_dir_entry *test_proc;
 
-#define BUFFER_SIZE 16
+#define BUFFER_SIZE 32
 #define MAX_DEPTH 6
 
 struct work_node {
 	ulong *ptr;
+	u64 start_ns;
 	struct completion done;
 	struct list_head list;
 };
@@ -30,6 +31,9 @@ static DECLARE_COMPLETION(work_res);
 static DEFINE_MUTEX(work_mutex);
 static LIST_HEAD(work_list);
 
+static int global_fence_size;
+static int global_loop_count;
+
 static void test_watch_fire(void)
 {
 	u64 buffer[BUFFER_SIZE] = { 0 };
@@ -72,6 +76,164 @@ static void test_recursive_depth(int depth)
 	pr_info("exit of %s depth:%d\n", __func__, depth);
 }
 
+static struct work_node *test_mthread_buggy(int thread_id, int seq_id)
+{
+	ulong buf[BUFFER_SIZE];
+	struct work_node *node;
+	bool trigger;
+
+	node = kmalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return NULL;
+
+	init_completion(&node->done);
+	node->ptr = buf;
+	node->start_ns = ktime_get_ns();
+	mutex_lock(&work_mutex);
+	list_add(&node->list, &work_list);
+	mutex_unlock(&work_mutex);
+	complete(&work_res);
+
+	trigger = (get_random_u32() % 100) < 10;
+	if (trigger)
+		return node; /* let the caller handle cleanup */
+
+	wait_for_completion(&node->done);
+	kfree(node);
+	return NULL;
+}
+
+#define CORRUPTING_MINIOR_WAIT_NS (100000)
+#define VICTIM_MINIOR_WAIT_NS (300000)
+
+static inline void silent_wait_us(u64 start_ns, u64 min_wait_us)
+{
+	u64 diff_ns, remain_us;
+
+	diff_ns = ktime_get_ns() - start_ns;
+	if (diff_ns < min_wait_us * 1000ULL) {
+		remain_us = min_wait_us - (diff_ns >> 10);
+		usleep_range(remain_us, remain_us + 200);
+	}
+}
+
+static void test_mthread_victim(int thread_id, int seq_id, u64 start_ns)
+{
+	ulong buf[BUFFER_SIZE];
+
+	for (int j = 0; j < BUFFER_SIZE; j++)
+		buf[j] = 0xdeadbeef + seq_id;
+	if (start_ns)
+		silent_wait_us(start_ns, VICTIM_MINIOR_WAIT_NS);
+
+	for (int j = 0; j < BUFFER_SIZE; j++) {
+		if (buf[j] != (0xdeadbeef + seq_id)) {
+			pr_warn("victim[%d][%d]: unhappy buf[%d]=0x%lx\n",
+				thread_id, seq_id, j, buf[j]);
+			return;
+		}
+	}
+
+	pr_info("victim[%d][%d]: happy\n", thread_id, seq_id);
+}
+
+static int test_mthread_corrupting(void *data)
+{
+	struct work_node *node;
+	int fence_size;
+
+	while (!kthread_should_stop()) {
+		if (!wait_for_completion_timeout(&work_res, HZ))
+			continue;
+		while (true) {
+			mutex_lock(&work_mutex);
+			node = list_first_entry_or_null(&work_list,
+							struct work_node, list);
+			if (node)
+				list_del(&node->list);
+			mutex_unlock(&work_mutex);
+
+			if (!node)
+				break; /* no more nodes, exit inner loop */
+			silent_wait_us(node->start_ns,
+				       CORRUPTING_MINIOR_WAIT_NS);
+
+			fence_size = READ_ONCE(global_fence_size);
+			for (int i = fence_size; i < BUFFER_SIZE - fence_size;
+			     i++)
+				node->ptr[i] = 0xabcdabcd;
+
+			complete(&node->done);
+		}
+	}
+
+	return 0;
+}
+
+static int test_mthread_worker(void *data)
+{
+	int thread_id = (long)data;
+	int loop_count;
+	struct work_node *node;
+
+	loop_count = READ_ONCE(global_loop_count);
+
+	for (int i = 0; i < loop_count; i++) {
+		node = test_mthread_buggy(thread_id, i);
+
+		if (node)
+			test_mthread_victim(thread_id, i, node->start_ns);
+		else
+			test_mthread_victim(thread_id, i, 0);
+		if (node) {
+			wait_for_completion(&node->done);
+			kfree(node);
+		}
+	}
+	return 0;
+}
+
+static void test_mthread_case(int num_workers, int loop_count, int fence_size)
+{
+	static struct task_struct *corrupting;
+	static struct task_struct **workers;
+
+	WRITE_ONCE(global_loop_count, loop_count);
+	WRITE_ONCE(global_fence_size, fence_size);
+
+	init_completion(&work_res);
+	workers = kmalloc_array(num_workers, sizeof(void *), GFP_KERNEL);
+	memset(workers, 0, sizeof(struct task_struct *) * num_workers);
+
+	corrupting = kthread_run(test_mthread_corrupting, NULL, "corrupting");
+	if (IS_ERR(corrupting)) {
+		pr_err("failed to create corrupting thread\n");
+		return;
+	}
+
+	for (ulong i = 0; i < num_workers; i++) {
+		workers[i] = kthread_run(test_mthread_worker, (void *)i,
+					 "worker_%ld", i);
+		if (IS_ERR(workers[i])) {
+			pr_err("failto create worker thread %ld", i);
+			workers[i] = NULL;
+		}
+	}
+
+	for (ulong i = 0; i < num_workers; i++) {
+		if (workers[i] && workers[i]->__state != TASK_DEAD) {
+			usleep_range(1000, 2000);
+			i--;
+		}
+	}
+	kfree(workers);
+
+	if (corrupting && !IS_ERR(corrupting)) {
+		kthread_stop(corrupting);
+		corrupting = NULL;
+	}
+}
+
 static ssize_t test_proc_write(struct file *file, const char __user *buffer,
 			       size_t count, loff_t *pos)
 {
@@ -100,6 +262,15 @@ static ssize_t test_proc_write(struct file *file, const char __user *buffer,
 		case 2:
 			test_recursive_depth(0);
 			break;
+		case 3:
+			test_mthread_case(1, 20, BUFFER_SIZE / 4);
+			break;
+		case 4:
+			test_mthread_case(20, 1, BUFFER_SIZE / 4);
+			break;
+		case 5:
+			test_mthread_case(1, 1, -3);
+			break;
 		default:
 			pr_err("Unknown test number %d\n", test_num);
 			return -EINVAL;
@@ -121,7 +292,10 @@ static ssize_t test_proc_read(struct file *file, char __user *buffer,
 				    "echo test{i} > /proc/kstackwatch_test\n"
 				    " test0 - test watch fire\n"
 				    " test1 - test canary overflow\n"
-				    " test2 - test recursive func\n";
+				    " test2 - test recursive func\n"
+				    " test3 - test silent corruption\n"
+				    " test4 - test multiple silent corruption\n"
+				    " test5 - test prologue corruption\n";
 
 	return simple_read_from_buffer(buffer, count, pos, usage,
 				       strlen(usage));
-- 
2.43.0