x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 175 insertions, 0 deletions

diff --git a/arch/m68k/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c
new file mode 100644
index 000000000..e2f7af1fa
--- /dev/null
+++ b/arch/m68k/coldfire/gpio.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Coldfire generic GPIO support.
+ *
+ * (C) Copyright 2009, Steven King <sfking@fdwdc.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/gpio/driver.h>
+
+#include <linux/io.h>
+#include <asm/coldfire.h>
+#include <asm/mcfsim.h>
+#include <asm/mcfgpio.h>
+
+int __mcfgpio_get_value(unsigned gpio)
+{
+	return mcfgpio_read(__mcfgpio_ppdr(gpio)) & mcfgpio_bit(gpio);
+}
+EXPORT_SYMBOL(__mcfgpio_get_value);
+
+void __mcfgpio_set_value(unsigned gpio, int value)
+{
+	if (gpio < MCFGPIO_SCR_START) {
+		unsigned long flags;
+		MCFGPIO_PORTTYPE data;
+
+		local_irq_save(flags);
+		data = mcfgpio_read(__mcfgpio_podr(gpio));
+		if (value)
+			data |= mcfgpio_bit(gpio);
+		else
+			data &= ~mcfgpio_bit(gpio);
+		mcfgpio_write(data, __mcfgpio_podr(gpio));
+		local_irq_restore(flags);
+	} else {
+		if (value)
+			mcfgpio_write(mcfgpio_bit(gpio),
+					MCFGPIO_SETR_PORT(gpio));
+		else
+			mcfgpio_write(~mcfgpio_bit(gpio),
+					MCFGPIO_CLRR_PORT(gpio));
+	}
+}
+EXPORT_SYMBOL(__mcfgpio_set_value);
+
+int __mcfgpio_direction_input(unsigned gpio)
+{
+	unsigned long flags;
+	MCFGPIO_PORTTYPE dir;
+
+	local_irq_save(flags);
+	dir = mcfgpio_read(__mcfgpio_pddr(gpio));
+	dir &= ~mcfgpio_bit(gpio);
+	mcfgpio_write(dir, __mcfgpio_pddr(gpio));
+	local_irq_restore(flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(__mcfgpio_direction_input);
+
+int __mcfgpio_direction_output(unsigned gpio, int value)
+{
+	unsigned long flags;
+	MCFGPIO_PORTTYPE data;
+
+	local_irq_save(flags);
+	data = mcfgpio_read(__mcfgpio_pddr(gpio));
+	data |= mcfgpio_bit(gpio);
+	mcfgpio_write(data, __mcfgpio_pddr(gpio));
+
+	/* now set the data to output */
+	if (gpio < MCFGPIO_SCR_START) {
+		data = mcfgpio_read(__mcfgpio_podr(gpio));
+		if (value)
+			data |= mcfgpio_bit(gpio);
+		else
+			data &= ~mcfgpio_bit(gpio);
+		mcfgpio_write(data, __mcfgpio_podr(gpio));
+	} else {
+		 if (value)
+			mcfgpio_write(mcfgpio_bit(gpio),
+					MCFGPIO_SETR_PORT(gpio));
+		 else
+			 mcfgpio_write(~mcfgpio_bit(gpio),
+					 MCFGPIO_CLRR_PORT(gpio));
+	}
+	local_irq_restore(flags);
+	return 0;
+}
+EXPORT_SYMBOL(__mcfgpio_direction_output);
+
+int __mcfgpio_request(unsigned gpio)
+{
+	return 0;
+}
+EXPORT_SYMBOL(__mcfgpio_request);
+
+void __mcfgpio_free(unsigned gpio)
+{
+	__mcfgpio_direction_input(gpio);
+}
+EXPORT_SYMBOL(__mcfgpio_free);
+
+#ifdef CONFIG_GPIOLIB
+
+static int mcfgpio_direction_input(struct gpio_chip *chip, unsigned offset)
+{
+	return __mcfgpio_direction_input(offset);
+}
+
+static int mcfgpio_get_value(struct gpio_chip *chip, unsigned offset)
+{
+	return !!__mcfgpio_get_value(offset);
+}
+
+static int mcfgpio_direction_output(struct gpio_chip *chip, unsigned offset,
+				    int value)
+{
+	return __mcfgpio_direction_output(offset, value);
+}
+
+static int mcfgpio_set_value(struct gpio_chip *chip, unsigned int offset,
+			     int value)
+{
+	__mcfgpio_set_value(offset, value);
+
+	return 0;
+}
+
+static int mcfgpio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return __mcfgpio_request(offset);
+}
+
+static void mcfgpio_free(struct gpio_chip *chip, unsigned offset)
+{
+	__mcfgpio_free(offset);
+}
+
+static int mcfgpio_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+#if defined(MCFGPIO_IRQ_MIN)
+	if ((offset >= MCFGPIO_IRQ_MIN) && (offset < MCFGPIO_IRQ_MAX))
+#else
+	if (offset < MCFGPIO_IRQ_MAX)
+#endif
+		return MCFGPIO_IRQ_VECBASE + offset;
+	else
+		return -EINVAL;
+}
+
+static struct gpio_chip mcfgpio_chip = {
+	.label			= "mcfgpio",
+	.request		= mcfgpio_request,
+	.free			= mcfgpio_free,
+	.direction_input	= mcfgpio_direction_input,
+	.direction_output	= mcfgpio_direction_output,
+	.get			= mcfgpio_get_value,
+	.set			= mcfgpio_set_value,
+	.to_irq			= mcfgpio_to_irq,
+	.base			= 0,
+	.ngpio			= MCFGPIO_PIN_MAX,
+};
+
+static int __init mcfgpio_sysinit(void)
+{
+	return gpiochip_add_data(&mcfgpio_chip, NULL);
+}
+
+core_initcall(mcfgpio_sysinit);
+#endif