ARM: 9485/1: mm: acquire mmap write lock around show_pte() for user faultsgrafted

When CONFIG_DEBUG_USER=y, and cmdline "user_debug=31" is set,
a user fault may trigger show_pte() without any lock.
If another thread in the same process concurrently calls munmap(),
the page table pages may be freed while show_pte() is still traversing
them, causing a use-after-free in show_pte().

If CONFIG_ARM_LPAE=y, this may cause a kernel panic if the pages table
of PMD are freed when show_pte() is running.

Acquire mmap_write_lock() around show_pte() for user faults to fix the
contention.

For user faults, additionally restrict that show_pte() is called only
when the addr is a user-space address (addr < TASK_SIZE). This is because
the lock of tsk->mm only protects the virtual memory of user address space,
furthermore, dumping the page tables of a kernel-space address for user
faults is unnecessary and may have security implications.

Keep everything unchanged for kernel faults, because the kernel is
already in the "oops" state, acquiring a lock may risk a deadlock.

Co-developed-by: Qi Xi <xiqi2@huawei.com>

Fixes: 6d021b724481 ("ARM: dump pgd, pmd and pte states on unhandled data abort faults")
Link: https://lore.kernel.org/20260716014022.2823-1-xieyuanbin1@huawei.com
Acked-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Qi Xi <xiqi2@huawei.com>
Signed-off-by: Xie Yuanbin <xieyuanbin1@huawei.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

2 files changed, 99 insertions, 0 deletions

diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile
new file mode 100644
index 000000000..8849e85e9
--- /dev/null
+++ b/samples/workqueue/stall_detector/Makefile
@@ -0,0 +1 @@
+obj-m += wq_stall.o
diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c
new file mode 100644
index 000000000..6f4a497b1
--- /dev/null
+++ b/samples/workqueue/stall_detector/wq_stall.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * wq_stall - Test module for the workqueue stall detector.
+ *
+ * Deliberately creates a workqueue stall so the watchdog fires and
+ * prints diagnostic output.  Useful for verifying that the stall
+ * detector correctly identifies stuck workers and produces useful
+ * backtraces.
+ *
+ * The stall is triggered by clearing PF_WQ_WORKER before sleeping,
+ * which hides the worker from the concurrency manager.  A second
+ * work item queued on the same pool then sits in the worklist with
+ * no worker available to process it.
+ *
+ * After ~30s the workqueue watchdog fires:
+ *   BUG: workqueue lockup - pool cpus=N ...
+ *
+ * Build:
+ *	make -C <kernel tree> M=samples/workqueue/stall_detector modules
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Breno Leitao <leitao@debian.org>
+ */
+
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/atomic.h>
+#include <linux/sched.h>
+
+static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head);
+static atomic_t wake_condition = ATOMIC_INIT(0);
+static struct work_struct stall_work1;
+static struct work_struct stall_work2;
+
+static void stall_work2_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: second work item finally ran\n");
+}
+
+static void stall_work1_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: first work item running on cpu %d\n",
+		raw_smp_processor_id());
+
+	/*
+	 * Queue second item while we're still counted as running
+	 * (pool->nr_running > 0).  Since schedule_work() on a per-CPU
+	 * workqueue targets raw_smp_processor_id(), item 2 lands on the
+	 * same pool.  __queue_work -> kick_pool -> need_more_worker()
+	 * sees nr_running > 0 and does NOT wake a new worker.
+	 */
+	schedule_work(&stall_work2);
+
+	/*
+	 * Hide from the workqueue concurrency manager.  Without
+	 * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(),
+	 * so nr_running is never decremented and no replacement
+	 * worker is created.  Item 2 stays stuck in pool->worklist.
+	 */
+	current->flags &= ~PF_WQ_WORKER;
+
+	pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n");
+	pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n");
+	wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0);
+
+	/* Restore so process_one_work() cleanup works correctly */
+	current->flags |= PF_WQ_WORKER;
+	pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n");
+}
+
+static int __init wq_stall_init(void)
+{
+	pr_info("wq_stall: loading\n");
+
+	INIT_WORK(&stall_work1, stall_work1_fn);
+	INIT_WORK(&stall_work2, stall_work2_fn);
+	schedule_work(&stall_work1);
+
+	return 0;
+}
+
+static void __exit wq_stall_exit(void)
+{
+	pr_info("wq_stall: unloading\n");
+	atomic_set(&wake_condition, 1);
+	wake_up(&stall_wq_head);
+	flush_work(&stall_work1);
+	flush_work(&stall_work2);
+	pr_info("wq_stall: all work flushed, module unloaded\n");
+}
+
+module_init(wq_stall_init);
+module_exit(wq_stall_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse");
+MODULE_AUTHOR("Breno Leitao <leitao@debian.org>");