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, 131 insertions, 0 deletions

diff --git a/drivers/reset/reset-k210.c b/drivers/reset/reset-k210.c
new file mode 100644
index 000000000..e77e4cca3
--- /dev/null
+++ b/drivers/reset/reset-k210.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2020 Western Digital Corporation or its affiliates.
+ */
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset-controller.h>
+#include <linux/delay.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <soc/canaan/k210-sysctl.h>
+
+#include <dt-bindings/reset/k210-rst.h>
+
+#define K210_RST_MASK	0x27FFFFFF
+
+struct k210_rst {
+	struct regmap *map;
+	struct reset_controller_dev rcdev;
+};
+
+static inline struct k210_rst *
+to_k210_rst(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct k210_rst, rcdev);
+}
+
+static inline int k210_rst_assert(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	struct k210_rst *ksr = to_k210_rst(rcdev);
+
+	return regmap_update_bits(ksr->map, K210_SYSCTL_PERI_RESET, BIT(id), 1);
+}
+
+static inline int k210_rst_deassert(struct reset_controller_dev *rcdev,
+				    unsigned long id)
+{
+	struct k210_rst *ksr = to_k210_rst(rcdev);
+
+	return regmap_update_bits(ksr->map, K210_SYSCTL_PERI_RESET, BIT(id), 0);
+}
+
+static int k210_rst_reset(struct reset_controller_dev *rcdev,
+			  unsigned long id)
+{
+	int ret;
+
+	ret = k210_rst_assert(rcdev, id);
+	if (ret == 0) {
+		udelay(10);
+		ret = k210_rst_deassert(rcdev, id);
+	}
+
+	return ret;
+}
+
+static int k210_rst_status(struct reset_controller_dev *rcdev,
+			   unsigned long id)
+{
+	struct k210_rst *ksr = to_k210_rst(rcdev);
+	u32 reg, bit = BIT(id);
+	int ret;
+
+	ret = regmap_read(ksr->map, K210_SYSCTL_PERI_RESET, &reg);
+	if (ret)
+		return ret;
+
+	return reg & bit;
+}
+
+static int k210_rst_xlate(struct reset_controller_dev *rcdev,
+			  const struct of_phandle_args *reset_spec)
+{
+	unsigned long id = reset_spec->args[0];
+
+	if (!(BIT(id) & K210_RST_MASK))
+		return -EINVAL;
+
+	return id;
+}
+
+static const struct reset_control_ops k210_rst_ops = {
+	.assert		= k210_rst_assert,
+	.deassert	= k210_rst_deassert,
+	.reset		= k210_rst_reset,
+	.status		= k210_rst_status,
+};
+
+static int k210_rst_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *parent_np;
+	struct k210_rst *ksr;
+
+	dev_info(dev, "K210 reset controller\n");
+
+	ksr = devm_kzalloc(dev, sizeof(*ksr), GFP_KERNEL);
+	if (!ksr)
+		return -ENOMEM;
+
+	parent_np = of_get_parent(dev->of_node);
+	ksr->map = syscon_node_to_regmap(parent_np);
+	of_node_put(parent_np);
+	if (IS_ERR(ksr->map))
+		return PTR_ERR(ksr->map);
+
+	ksr->rcdev.owner = THIS_MODULE;
+	ksr->rcdev.dev = dev;
+	ksr->rcdev.of_node = dev->of_node;
+	ksr->rcdev.ops = &k210_rst_ops;
+	ksr->rcdev.nr_resets = fls(K210_RST_MASK);
+	ksr->rcdev.of_reset_n_cells = 1;
+	ksr->rcdev.of_xlate = k210_rst_xlate;
+
+	return devm_reset_controller_register(dev, &ksr->rcdev);
+}
+
+static const struct of_device_id k210_rst_dt_ids[] = {
+	{ .compatible = "canaan,k210-rst" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver k210_rst_driver = {
+	.probe	= k210_rst_probe,
+	.driver = {
+		.name		= "k210-rst",
+		.of_match_table	= k210_rst_dt_ids,
+	},
+};
+builtin_platform_driver(k210_rst_driver);