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, 174 insertions, 0 deletions

diff --git a/drivers/clk/mediatek/reset.c b/drivers/clk/mediatek/reset.c
new file mode 100644
index 000000000..2e3303975
--- /dev/null
+++ b/drivers/clk/mediatek/reset.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include "reset.h"
+
+static inline struct mtk_clk_rst_data *to_mtk_clk_rst_data(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct mtk_clk_rst_data, rcdev);
+}
+
+static int mtk_reset_update(struct reset_controller_dev *rcdev,
+			    unsigned long id, bool deassert)
+{
+	struct mtk_clk_rst_data *data = to_mtk_clk_rst_data(rcdev);
+	unsigned int val = deassert ? 0 : ~0;
+
+	return regmap_update_bits(data->regmap,
+				  data->desc->rst_bank_ofs[id / RST_NR_PER_BANK],
+				  BIT(id % RST_NR_PER_BANK), val);
+}
+
+static int mtk_reset_assert(struct reset_controller_dev *rcdev,
+			    unsigned long id)
+{
+	return mtk_reset_update(rcdev, id, false);
+}
+
+static int mtk_reset_deassert(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	return mtk_reset_update(rcdev, id, true);
+}
+
+static int mtk_reset(struct reset_controller_dev *rcdev, unsigned long id)
+{
+	int ret;
+
+	ret = mtk_reset_assert(rcdev, id);
+	if (ret)
+		return ret;
+
+	return mtk_reset_deassert(rcdev, id);
+}
+
+static int mtk_reset_update_set_clr(struct reset_controller_dev *rcdev,
+				    unsigned long id, bool deassert)
+{
+	struct mtk_clk_rst_data *data = to_mtk_clk_rst_data(rcdev);
+	unsigned int deassert_ofs = deassert ? 0x4 : 0;
+
+	return regmap_write(data->regmap,
+			    data->desc->rst_bank_ofs[id / RST_NR_PER_BANK] +
+			    deassert_ofs,
+			    BIT(id % RST_NR_PER_BANK));
+}
+
+static int mtk_reset_assert_set_clr(struct reset_controller_dev *rcdev,
+				    unsigned long id)
+{
+	return mtk_reset_update_set_clr(rcdev, id, false);
+}
+
+static int mtk_reset_deassert_set_clr(struct reset_controller_dev *rcdev,
+				      unsigned long id)
+{
+	return mtk_reset_update_set_clr(rcdev, id, true);
+}
+
+static int mtk_reset_set_clr(struct reset_controller_dev *rcdev,
+			     unsigned long id)
+{
+	int ret;
+
+	ret = mtk_reset_assert_set_clr(rcdev, id);
+	if (ret)
+		return ret;
+	return mtk_reset_deassert_set_clr(rcdev, id);
+}
+
+static const struct reset_control_ops mtk_reset_ops = {
+	.assert = mtk_reset_assert,
+	.deassert = mtk_reset_deassert,
+	.reset = mtk_reset,
+};
+
+static const struct reset_control_ops mtk_reset_ops_set_clr = {
+	.assert = mtk_reset_assert_set_clr,
+	.deassert = mtk_reset_deassert_set_clr,
+	.reset = mtk_reset_set_clr,
+};
+
+static int reset_xlate(struct reset_controller_dev *rcdev,
+		       const struct of_phandle_args *reset_spec)
+{
+	struct mtk_clk_rst_data *data = to_mtk_clk_rst_data(rcdev);
+
+	if (reset_spec->args[0] >= rcdev->nr_resets ||
+	    reset_spec->args[0] >= data->desc->rst_idx_map_nr)
+		return -EINVAL;
+
+	return data->desc->rst_idx_map[reset_spec->args[0]];
+}
+
+int mtk_register_reset_controller_with_dev(struct device *dev,
+					   const struct mtk_clk_rst_desc *desc)
+{
+	struct device_node *np = dev->of_node;
+	struct regmap *regmap;
+	const struct reset_control_ops *rcops = NULL;
+	struct mtk_clk_rst_data *data;
+	int ret;
+
+	if (!desc) {
+		dev_err(dev, "mtk clock reset desc is NULL\n");
+		return -EINVAL;
+	}
+
+	switch (desc->version) {
+	case MTK_RST_SIMPLE:
+		rcops = &mtk_reset_ops;
+		break;
+	case MTK_RST_SET_CLR:
+		rcops = &mtk_reset_ops_set_clr;
+		break;
+	default:
+		dev_err(dev, "Unknown reset version %d\n", desc->version);
+		return -EINVAL;
+	}
+
+	regmap = device_node_to_regmap(np);
+	if (IS_ERR(regmap)) {
+		dev_err(dev, "Cannot find regmap %pe\n", regmap);
+		return PTR_ERR(regmap);
+	}
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->desc = desc;
+	data->regmap = regmap;
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.ops = rcops;
+	data->rcdev.of_node = np;
+	data->rcdev.dev = dev;
+
+	if (data->desc->rst_idx_map_nr > 0) {
+		data->rcdev.of_reset_n_cells = 1;
+		data->rcdev.nr_resets = desc->rst_idx_map_nr;
+		data->rcdev.of_xlate = reset_xlate;
+	} else {
+		data->rcdev.nr_resets = desc->rst_bank_nr * RST_NR_PER_BANK;
+	}
+
+	ret = devm_reset_controller_register(dev, &data->rcdev);
+	if (ret) {
+		dev_err(dev, "could not register reset controller: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mtk_register_reset_controller_with_dev);
+
+MODULE_LICENSE("GPL");