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, 88 insertions, 0 deletions

diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c
new file mode 100644
index 000000000..fdb5fc21f
--- /dev/null
+++ b/drivers/clocksource/numachip.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2015 Numascale AS. All rights reserved.
+ */
+
+#include <linux/clockchips.h>
+
+#include <asm/irq.h>
+#include <asm/numachip/numachip.h>
+#include <asm/numachip/numachip_csr.h>
+
+static DEFINE_PER_CPU(struct clock_event_device, numachip2_ced);
+
+static cycles_t numachip2_timer_read(struct clocksource *cs)
+{
+	return numachip2_read64_lcsr(NUMACHIP2_TIMER_NOW);
+}
+
+static struct clocksource numachip2_clocksource = {
+	.name            = "numachip2",
+	.rating          = 295,
+	.read            = numachip2_timer_read,
+	.mask            = CLOCKSOURCE_MASK(64),
+	.flags           = CLOCK_SOURCE_IS_CONTINUOUS,
+	.mult            = 1,
+	.shift           = 0,
+};
+
+static int numachip2_set_next_event(unsigned long delta, struct clock_event_device *ced)
+{
+	numachip2_write64_lcsr(NUMACHIP2_TIMER_DEADLINE + numachip2_timer(),
+		delta);
+	return 0;
+}
+
+static const struct clock_event_device numachip2_clockevent __initconst = {
+	.name            = "numachip2",
+	.rating          = 400,
+	.set_next_event  = numachip2_set_next_event,
+	.features        = CLOCK_EVT_FEAT_ONESHOT,
+	.mult            = 1,
+	.shift           = 0,
+	.min_delta_ns    = 1250,
+	.min_delta_ticks = 1250,
+	.max_delta_ns    = LONG_MAX,
+	.max_delta_ticks = LONG_MAX,
+};
+
+static void numachip_timer_interrupt(void)
+{
+	struct clock_event_device *ced = this_cpu_ptr(&numachip2_ced);
+
+	ced->event_handler(ced);
+}
+
+static __init void numachip_timer_each(struct work_struct *work)
+{
+	unsigned local_apicid = __this_cpu_read(x86_cpu_to_apicid) & 0xff;
+	struct clock_event_device *ced = this_cpu_ptr(&numachip2_ced);
+
+	/* Setup IPI vector to local core and relative timing mode */
+	numachip2_write64_lcsr(NUMACHIP2_TIMER_INT + numachip2_timer(),
+		(3 << 22) | (X86_PLATFORM_IPI_VECTOR << 14) |
+		(local_apicid << 6));
+
+	*ced = numachip2_clockevent;
+	ced->cpumask = cpumask_of(smp_processor_id());
+	clockevents_register_device(ced);
+}
+
+static int __init numachip_timer_init(void)
+{
+	if (numachip_system != 2)
+		return -ENODEV;
+
+	/* Reset timer */
+	numachip2_write64_lcsr(NUMACHIP2_TIMER_RESET, 0);
+	clocksource_register_hz(&numachip2_clocksource, NSEC_PER_SEC);
+
+	/* Setup per-cpu clockevents */
+	x86_platform_ipi_callback = numachip_timer_interrupt;
+	schedule_on_each_cpu(&numachip_timer_each);
+
+	return 0;
+}
+
+arch_initcall(numachip_timer_init);