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, 161 insertions, 0 deletions

diff --git a/drivers/reset/reset-qcom-pdc.c b/drivers/reset/reset-qcom-pdc.c
new file mode 100644
index 000000000..ae2b5aba7
--- /dev/null
+++ b/drivers/reset/reset-qcom-pdc.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/reset/qcom,sdm845-pdc.h>
+
+#define RPMH_SDM845_PDC_SYNC_RESET	0x100
+#define RPMH_SC7280_PDC_SYNC_RESET	0x1000
+
+struct qcom_pdc_reset_map {
+	u8 bit;
+};
+
+struct qcom_pdc_reset_desc {
+	const struct qcom_pdc_reset_map *resets;
+	size_t num_resets;
+	unsigned int offset;
+};
+
+struct qcom_pdc_reset_data {
+	struct reset_controller_dev rcdev;
+	struct regmap *regmap;
+	const struct qcom_pdc_reset_desc *desc;
+};
+
+static const struct regmap_config pdc_regmap_config = {
+	.name		= "pdc-reset",
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x20000,
+};
+
+static const struct qcom_pdc_reset_map sdm845_pdc_resets[] = {
+	[PDC_APPS_SYNC_RESET] = {0},
+	[PDC_SP_SYNC_RESET] = {1},
+	[PDC_AUDIO_SYNC_RESET] = {2},
+	[PDC_SENSORS_SYNC_RESET] = {3},
+	[PDC_AOP_SYNC_RESET] = {4},
+	[PDC_DEBUG_SYNC_RESET] = {5},
+	[PDC_GPU_SYNC_RESET] = {6},
+	[PDC_DISPLAY_SYNC_RESET] = {7},
+	[PDC_COMPUTE_SYNC_RESET] = {8},
+	[PDC_MODEM_SYNC_RESET] = {9},
+};
+
+static const struct qcom_pdc_reset_desc sdm845_pdc_reset_desc = {
+	.resets = sdm845_pdc_resets,
+	.num_resets = ARRAY_SIZE(sdm845_pdc_resets),
+	.offset = RPMH_SDM845_PDC_SYNC_RESET,
+};
+
+static const struct qcom_pdc_reset_map sc7280_pdc_resets[] = {
+	[PDC_APPS_SYNC_RESET] = {0},
+	[PDC_SP_SYNC_RESET] = {1},
+	[PDC_AUDIO_SYNC_RESET] = {2},
+	[PDC_SENSORS_SYNC_RESET] = {3},
+	[PDC_AOP_SYNC_RESET] = {4},
+	[PDC_DEBUG_SYNC_RESET] = {5},
+	[PDC_GPU_SYNC_RESET] = {6},
+	[PDC_DISPLAY_SYNC_RESET] = {7},
+	[PDC_COMPUTE_SYNC_RESET] = {8},
+	[PDC_MODEM_SYNC_RESET] = {9},
+	[PDC_WLAN_RF_SYNC_RESET] = {10},
+	[PDC_WPSS_SYNC_RESET] = {11},
+};
+
+static const struct qcom_pdc_reset_desc sc7280_pdc_reset_desc = {
+	.resets = sc7280_pdc_resets,
+	.num_resets = ARRAY_SIZE(sc7280_pdc_resets),
+	.offset = RPMH_SC7280_PDC_SYNC_RESET,
+};
+
+static inline struct qcom_pdc_reset_data *to_qcom_pdc_reset_data(
+				struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct qcom_pdc_reset_data, rcdev);
+}
+
+static int qcom_pdc_control_assert(struct reset_controller_dev *rcdev,
+					unsigned long idx)
+{
+	struct qcom_pdc_reset_data *data = to_qcom_pdc_reset_data(rcdev);
+	u32 mask = BIT(data->desc->resets[idx].bit);
+
+	return regmap_update_bits(data->regmap, data->desc->offset, mask, mask);
+}
+
+static int qcom_pdc_control_deassert(struct reset_controller_dev *rcdev,
+					unsigned long idx)
+{
+	struct qcom_pdc_reset_data *data = to_qcom_pdc_reset_data(rcdev);
+	u32 mask = BIT(data->desc->resets[idx].bit);
+
+	return regmap_update_bits(data->regmap, data->desc->offset, mask, 0);
+}
+
+static const struct reset_control_ops qcom_pdc_reset_ops = {
+	.assert = qcom_pdc_control_assert,
+	.deassert = qcom_pdc_control_deassert,
+};
+
+static int qcom_pdc_reset_probe(struct platform_device *pdev)
+{
+	const struct qcom_pdc_reset_desc *desc;
+	struct qcom_pdc_reset_data *data;
+	struct device *dev = &pdev->dev;
+	void __iomem *base;
+
+	desc = device_get_match_data(&pdev->dev);
+	if (!desc)
+		return -EINVAL;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->desc = desc;
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	data->regmap = devm_regmap_init_mmio(dev, base, &pdc_regmap_config);
+	if (IS_ERR(data->regmap)) {
+		dev_err(dev, "Unable to initialize regmap\n");
+		return PTR_ERR(data->regmap);
+	}
+
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.ops = &qcom_pdc_reset_ops;
+	data->rcdev.nr_resets = desc->num_resets;
+	data->rcdev.of_node = dev->of_node;
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static const struct of_device_id qcom_pdc_reset_of_match[] = {
+	{ .compatible = "qcom,sc7280-pdc-global", .data = &sc7280_pdc_reset_desc },
+	{ .compatible = "qcom,sdm845-pdc-global", .data = &sdm845_pdc_reset_desc },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qcom_pdc_reset_of_match);
+
+static struct platform_driver qcom_pdc_reset_driver = {
+	.probe = qcom_pdc_reset_probe,
+	.driver = {
+		.name = "qcom_pdc_reset",
+		.of_match_table = qcom_pdc_reset_of_match,
+	},
+};
+module_platform_driver(qcom_pdc_reset_driver);
+
+MODULE_DESCRIPTION("Qualcomm PDC Reset Driver");
+MODULE_LICENSE("GPL v2");