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, 160 insertions, 0 deletions

diff --git a/drivers/power/reset/arm-versatile-reboot.c b/drivers/power/reset/arm-versatile-reboot.c
new file mode 100644
index 000000000..c7624d761
--- /dev/null
+++ b/drivers/power/reset/arm-versatile-reboot.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2014 Linaro Ltd.
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ */
+#include <linux/init.h>
+#include <linux/mfd/syscon.h>
+#include <linux/reboot.h>
+#include <linux/regmap.h>
+#include <linux/of.h>
+
+#define INTEGRATOR_HDR_CTRL_OFFSET	0x0C
+#define INTEGRATOR_HDR_LOCK_OFFSET	0x14
+#define INTEGRATOR_CM_CTRL_RESET	(1 << 3)
+
+#define VERSATILE_SYS_LOCK_OFFSET	0x20
+#define VERSATILE_SYS_RESETCTL_OFFSET	0x40
+
+/* Magic unlocking token used on all Versatile boards */
+#define VERSATILE_LOCK_VAL		0xA05F
+
+/*
+ * We detect the different syscon types from the compatible strings.
+ */
+enum versatile_reboot {
+	INTEGRATOR_REBOOT_CM,
+	VERSATILE_REBOOT_CM,
+	REALVIEW_REBOOT_EB,
+	REALVIEW_REBOOT_PB1176,
+	REALVIEW_REBOOT_PB11MP,
+	REALVIEW_REBOOT_PBA8,
+	REALVIEW_REBOOT_PBX,
+};
+
+/* Pointer to the system controller */
+static struct regmap *syscon_regmap;
+static enum versatile_reboot versatile_reboot_type;
+
+static const struct of_device_id versatile_reboot_of_match[] = {
+	{
+		.compatible = "arm,core-module-integrator",
+		.data = (void *)INTEGRATOR_REBOOT_CM
+	},
+	{
+		.compatible = "arm,core-module-versatile",
+		.data = (void *)VERSATILE_REBOOT_CM,
+	},
+	{
+		.compatible = "arm,realview-eb-syscon",
+		.data = (void *)REALVIEW_REBOOT_EB,
+	},
+	{
+		.compatible = "arm,realview-pb1176-syscon",
+		.data = (void *)REALVIEW_REBOOT_PB1176,
+	},
+	{
+		.compatible = "arm,realview-pb11mp-syscon",
+		.data = (void *)REALVIEW_REBOOT_PB11MP,
+	},
+	{
+		.compatible = "arm,realview-pba8-syscon",
+		.data = (void *)REALVIEW_REBOOT_PBA8,
+	},
+	{
+		.compatible = "arm,realview-pbx-syscon",
+		.data = (void *)REALVIEW_REBOOT_PBX,
+	},
+	{},
+};
+
+static int versatile_reboot(struct notifier_block *this, unsigned long mode,
+			    void *cmd)
+{
+	/* Unlock the reset register */
+	/* Then hit reset on the different machines */
+	switch (versatile_reboot_type) {
+	case INTEGRATOR_REBOOT_CM:
+		regmap_write(syscon_regmap, INTEGRATOR_HDR_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_update_bits(syscon_regmap,
+				   INTEGRATOR_HDR_CTRL_OFFSET,
+				   INTEGRATOR_CM_CTRL_RESET,
+				   INTEGRATOR_CM_CTRL_RESET);
+		break;
+	case VERSATILE_REBOOT_CM:
+		regmap_write(syscon_regmap, VERSATILE_SYS_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_update_bits(syscon_regmap,
+				   VERSATILE_SYS_RESETCTL_OFFSET,
+				   0x0107,
+				   0x0105);
+		regmap_write(syscon_regmap, VERSATILE_SYS_LOCK_OFFSET,
+			     0);
+		break;
+	case REALVIEW_REBOOT_EB:
+		regmap_write(syscon_regmap, VERSATILE_SYS_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_write(syscon_regmap,
+			     VERSATILE_SYS_RESETCTL_OFFSET, 0x0008);
+		break;
+	case REALVIEW_REBOOT_PB1176:
+		regmap_write(syscon_regmap, VERSATILE_SYS_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_write(syscon_regmap,
+			     VERSATILE_SYS_RESETCTL_OFFSET, 0x0100);
+		break;
+	case REALVIEW_REBOOT_PB11MP:
+	case REALVIEW_REBOOT_PBA8:
+		regmap_write(syscon_regmap, VERSATILE_SYS_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_write(syscon_regmap, VERSATILE_SYS_RESETCTL_OFFSET,
+			     0x0000);
+		regmap_write(syscon_regmap, VERSATILE_SYS_RESETCTL_OFFSET,
+			     0x0004);
+		break;
+	case REALVIEW_REBOOT_PBX:
+		regmap_write(syscon_regmap, VERSATILE_SYS_LOCK_OFFSET,
+			     VERSATILE_LOCK_VAL);
+		regmap_write(syscon_regmap, VERSATILE_SYS_RESETCTL_OFFSET,
+			     0x00f0);
+		regmap_write(syscon_regmap, VERSATILE_SYS_RESETCTL_OFFSET,
+			     0x00f4);
+		break;
+	}
+	dsb();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block versatile_reboot_nb = {
+	.notifier_call = versatile_reboot,
+	.priority = 192,
+};
+
+static int __init versatile_reboot_probe(void)
+{
+	const struct of_device_id *reboot_id;
+	struct device_node *np;
+	int err;
+
+	np = of_find_matching_node_and_match(NULL, versatile_reboot_of_match,
+						 &reboot_id);
+	if (!np)
+		return -ENODEV;
+	versatile_reboot_type = (enum versatile_reboot)reboot_id->data;
+
+	syscon_regmap = syscon_node_to_regmap(np);
+	of_node_put(np);
+	if (IS_ERR(syscon_regmap))
+		return PTR_ERR(syscon_regmap);
+
+	err = register_restart_handler(&versatile_reboot_nb);
+	if (err)
+		return err;
+
+	pr_info("versatile reboot driver registered\n");
+	return 0;
+}
+device_initcall(versatile_reboot_probe);