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, 167 insertions, 0 deletions

diff --git a/drivers/clk/qcom/hfpll.c b/drivers/clk/qcom/hfpll.c
new file mode 100644
index 000000000..385964196
--- /dev/null
+++ b/drivers/clk/qcom/hfpll.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+
+#include "clk-regmap.h"
+#include "clk-hfpll.h"
+
+static const struct hfpll_data qcs404 = {
+	.mode_reg = 0x00,
+	.l_reg = 0x04,
+	.m_reg = 0x08,
+	.n_reg = 0x0c,
+	.user_reg = 0x10,
+	.config_reg = 0x14,
+	.config_val = 0x430405d,
+	.status_reg = 0x1c,
+	.lock_bit = 16,
+
+	.user_val = 0x8,
+	.user_vco_mask = 0x100000,
+	.low_vco_max_rate = 1248000000,
+	.min_rate = 537600000UL,
+	.max_rate = 2900000000UL,
+};
+
+static const struct hfpll_data msm8976_a53 = {
+	.mode_reg = 0x00,
+	.l_reg = 0x04,
+	.m_reg = 0x08,
+	.n_reg = 0x0c,
+	.user_reg = 0x10,
+	.config_reg = 0x14,
+	.config_val = 0x341600,
+	.status_reg = 0x1c,
+	.lock_bit = 16,
+
+	.l_val = 0x35,
+	.user_val = 0x109,
+	.min_rate = 902400000UL,
+	.max_rate = 1478400000UL,
+};
+
+static const struct hfpll_data msm8976_a72 = {
+	.mode_reg = 0x00,
+	.l_reg = 0x04,
+	.m_reg = 0x08,
+	.n_reg = 0x0c,
+	.user_reg = 0x10,
+	.config_reg = 0x14,
+	.config_val = 0x4e0405d,
+	.status_reg = 0x1c,
+	.lock_bit = 16,
+
+	.l_val = 0x3e,
+	.user_val = 0x100109,
+	.min_rate = 940800000UL,
+	.max_rate = 2016000000UL,
+};
+
+static const struct hfpll_data msm8976_cci = {
+	.mode_reg = 0x00,
+	.l_reg = 0x04,
+	.m_reg = 0x08,
+	.n_reg = 0x0c,
+	.user_reg = 0x10,
+	.config_reg = 0x14,
+	.config_val = 0x141400,
+	.status_reg = 0x1c,
+	.lock_bit = 16,
+
+	.l_val = 0x20,
+	.user_val = 0x100109,
+	.min_rate = 556800000UL,
+	.max_rate = 902400000UL,
+};
+
+static const struct of_device_id qcom_hfpll_match_table[] = {
+	{ .compatible = "qcom,msm8976-hfpll-a53", .data = &msm8976_a53 },
+	{ .compatible = "qcom,msm8976-hfpll-a72", .data = &msm8976_a72 },
+	{ .compatible = "qcom,msm8976-hfpll-cci", .data = &msm8976_cci },
+	{ .compatible = "qcom,qcs404-hfpll", .data = &qcs404 },
+	/* Deprecated in bindings */
+	{ .compatible = "qcom,hfpll", .data = &qcs404 },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qcom_hfpll_match_table);
+
+static const struct regmap_config hfpll_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x30,
+};
+
+static int qcom_hfpll_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	void __iomem *base;
+	struct regmap *regmap;
+	struct clk_hfpll *h;
+	struct clk_init_data init = {
+		.num_parents = 1,
+		.ops = &clk_ops_hfpll,
+		/*
+		 * rather than marking the clock critical and forcing the clock
+		 * to be always enabled, we make sure that the clock is not
+		 * disabled: the firmware remains responsible of enabling this
+		 * clock (for more info check the commit log)
+		 */
+		.flags = CLK_IGNORE_UNUSED,
+	};
+	int ret;
+	struct clk_parent_data pdata = { .index = 0 };
+
+	h = devm_kzalloc(dev, sizeof(*h), GFP_KERNEL);
+	if (!h)
+		return -ENOMEM;
+
+	base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	regmap = devm_regmap_init_mmio(&pdev->dev, base, &hfpll_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	if (of_property_read_string_index(dev->of_node, "clock-output-names",
+					  0, &init.name))
+		return -ENODEV;
+
+	init.parent_data = &pdata;
+
+	h->d = of_device_get_match_data(&pdev->dev);
+	h->clkr.hw.init = &init;
+	spin_lock_init(&h->lock);
+
+	ret = devm_clk_register_regmap(dev, &h->clkr);
+	if (ret) {
+		dev_err(dev, "failed to register regmap clock: %d\n", ret);
+		return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					   &h->clkr.hw);
+}
+
+static struct platform_driver qcom_hfpll_driver = {
+	.probe		= qcom_hfpll_probe,
+	.driver		= {
+		.name	= "qcom-hfpll",
+		.of_match_table = qcom_hfpll_match_table,
+	},
+};
+module_platform_driver(qcom_hfpll_driver);
+
+MODULE_DESCRIPTION("QCOM HFPLL Clock Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:qcom-hfpll");