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>

1 files changed, 108 insertions, 0 deletions

diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
new file mode 100644
index 000000000..65d6dcafd
--- /dev/null
+++ b/samples/kprobes/kretprobe_example.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kretprobe_example.c
+ *
+ * Here's a sample kernel module showing the use of return probes to
+ * report the return value and total time taken for probed function
+ * to run.
+ *
+ * usage: insmod kretprobe_example.ko func=<func_name>
+ *
+ * If no func_name is specified, kernel_clone is instrumented
+ *
+ * For more information on theory of operation of kretprobes, see
+ * Documentation/trace/kprobes.rst
+ *
+ * Build and insert the kernel module as done in the kprobe example.
+ * You will see the trace data in /var/log/messages and on the console
+ * whenever the probed function returns. (Some messages may be suppressed
+ * if syslogd is configured to eliminate duplicate messages.)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
+
+static char func_name[KSYM_NAME_LEN] = "kernel_clone";
+module_param_string(func, func_name, KSYM_NAME_LEN, 0644);
+MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the"
+			" function's execution time");
+
+/* per-instance private data */
+struct my_data {
+	ktime_t entry_stamp;
+};
+
+/* Here we use the entry_handler to timestamp function entry */
+static int entry_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	struct my_data *data;
+
+	if (!current->mm)
+		return 1;	/* Skip kernel threads */
+
+	data = (struct my_data *)ri->data;
+	data->entry_stamp = ktime_get();
+	return 0;
+}
+NOKPROBE_SYMBOL(entry_handler);
+
+/*
+ * Return-probe handler: Log the return value and duration. Duration may turn
+ * out to be zero consistently, depending upon the granularity of time
+ * accounting on the platform.
+ */
+static int ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	unsigned long retval = regs_return_value(regs);
+	struct my_data *data = (struct my_data *)ri->data;
+	s64 delta;
+	ktime_t now;
+
+	now = ktime_get();
+	delta = ktime_to_ns(ktime_sub(now, data->entry_stamp));
+	pr_info("%s returned %lu and took %lld ns to execute\n",
+			func_name, retval, (long long)delta);
+	return 0;
+}
+NOKPROBE_SYMBOL(ret_handler);
+
+static struct kretprobe my_kretprobe = {
+	.handler		= ret_handler,
+	.entry_handler		= entry_handler,
+	.data_size		= sizeof(struct my_data),
+	/* Probe up to 20 instances concurrently. */
+	.maxactive		= 20,
+};
+
+static int __init kretprobe_init(void)
+{
+	int ret;
+
+	my_kretprobe.kp.symbol_name = func_name;
+	ret = register_kretprobe(&my_kretprobe);
+	if (ret < 0) {
+		pr_err("register_kretprobe failed, returned %d\n", ret);
+		return ret;
+	}
+	pr_info("Planted return probe at %s: %p\n",
+			my_kretprobe.kp.symbol_name, my_kretprobe.kp.addr);
+	return 0;
+}
+
+static void __exit kretprobe_exit(void)
+{
+	unregister_kretprobe(&my_kretprobe);
+	pr_info("kretprobe at %p unregistered\n", my_kretprobe.kp.addr);
+
+	/* nmissed > 0 suggests that maxactive was set too low. */
+	pr_info("Missed probing %d instances of %s\n",
+		my_kretprobe.nmissed, my_kretprobe.kp.symbol_name);
+}
+
+module_init(kretprobe_init)
+module_exit(kretprobe_exit)
+MODULE_DESCRIPTION("sample kernel module showing the use of return probes");
+MODULE_LICENSE("GPL");