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, 228 insertions, 0 deletions

diff --git a/drivers/reset/reset-ti-syscon.c b/drivers/reset/reset-ti-syscon.c
new file mode 100644
index 000000000..23f86ddb8
--- /dev/null
+++ b/drivers/reset/reset-ti-syscon.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * TI SYSCON regmap reset driver
+ *
+ * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/
+ *	Andrew F. Davis <afd@ti.com>
+ *	Suman Anna <afd@ti.com>
+ */
+
+#include <linux/mfd/syscon.h>
+#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/ti-syscon.h>
+
+/**
+ * struct ti_syscon_reset_control - reset control structure
+ * @assert_offset: reset assert control register offset from syscon base
+ * @assert_bit: reset assert bit in the reset assert control register
+ * @deassert_offset: reset deassert control register offset from syscon base
+ * @deassert_bit: reset deassert bit in the reset deassert control register
+ * @status_offset: reset status register offset from syscon base
+ * @status_bit: reset status bit in the reset status register
+ * @flags: reset flag indicating how the (de)assert and status are handled
+ */
+struct ti_syscon_reset_control {
+	unsigned int assert_offset;
+	unsigned int assert_bit;
+	unsigned int deassert_offset;
+	unsigned int deassert_bit;
+	unsigned int status_offset;
+	unsigned int status_bit;
+	u32 flags;
+};
+
+/**
+ * struct ti_syscon_reset_data - reset controller information structure
+ * @rcdev: reset controller entity
+ * @regmap: regmap handle containing the memory-mapped reset registers
+ * @controls: array of reset controls
+ * @nr_controls: number of controls in control array
+ */
+struct ti_syscon_reset_data {
+	struct reset_controller_dev rcdev;
+	struct regmap *regmap;
+	struct ti_syscon_reset_control *controls;
+	unsigned int nr_controls;
+};
+
+#define to_ti_syscon_reset_data(_rcdev)	\
+	container_of(_rcdev, struct ti_syscon_reset_data, rcdev)
+
+/**
+ * ti_syscon_reset_assert() - assert device reset
+ * @rcdev: reset controller entity
+ * @id: ID of the reset to be asserted
+ *
+ * This function implements the reset driver op to assert a device's reset.
+ * This asserts the reset in a manner prescribed by the reset flags.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int ti_syscon_reset_assert(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	struct ti_syscon_reset_data *data = to_ti_syscon_reset_data(rcdev);
+	struct ti_syscon_reset_control *control;
+	unsigned int mask, value;
+
+	if (id >= data->nr_controls)
+		return -EINVAL;
+
+	control = &data->controls[id];
+
+	if (control->flags & ASSERT_NONE)
+		return -ENOTSUPP; /* assert not supported for this reset */
+
+	mask = BIT(control->assert_bit);
+	value = (control->flags & ASSERT_SET) ? mask : 0x0;
+
+	return regmap_write_bits(data->regmap, control->assert_offset, mask, value);
+}
+
+/**
+ * ti_syscon_reset_deassert() - deassert device reset
+ * @rcdev: reset controller entity
+ * @id: ID of reset to be deasserted
+ *
+ * This function implements the reset driver op to deassert a device's reset.
+ * This deasserts the reset in a manner prescribed by the reset flags.
+ *
+ * Return: 0 for successful request, else a corresponding error value
+ */
+static int ti_syscon_reset_deassert(struct reset_controller_dev *rcdev,
+				    unsigned long id)
+{
+	struct ti_syscon_reset_data *data = to_ti_syscon_reset_data(rcdev);
+	struct ti_syscon_reset_control *control;
+	unsigned int mask, value;
+
+	if (id >= data->nr_controls)
+		return -EINVAL;
+
+	control = &data->controls[id];
+
+	if (control->flags & DEASSERT_NONE)
+		return -ENOTSUPP; /* deassert not supported for this reset */
+
+	mask = BIT(control->deassert_bit);
+	value = (control->flags & DEASSERT_SET) ? mask : 0x0;
+
+	return regmap_write_bits(data->regmap, control->deassert_offset, mask, value);
+}
+
+/**
+ * ti_syscon_reset_status() - check device reset status
+ * @rcdev: reset controller entity
+ * @id: ID of the reset for which the status is being requested
+ *
+ * This function implements the reset driver op to return the status of a
+ * device's reset.
+ *
+ * Return: 0 if reset is deasserted, true if reset is asserted, else a
+ * corresponding error value
+ */
+static int ti_syscon_reset_status(struct reset_controller_dev *rcdev,
+				  unsigned long id)
+{
+	struct ti_syscon_reset_data *data = to_ti_syscon_reset_data(rcdev);
+	struct ti_syscon_reset_control *control;
+	unsigned int reset_state;
+	int ret;
+
+	if (id >= data->nr_controls)
+		return -EINVAL;
+
+	control = &data->controls[id];
+
+	if (control->flags & STATUS_NONE)
+		return -ENOTSUPP; /* status not supported for this reset */
+
+	ret = regmap_read(data->regmap, control->status_offset, &reset_state);
+	if (ret)
+		return ret;
+
+	return !(reset_state & BIT(control->status_bit)) ==
+		!(control->flags & STATUS_SET);
+}
+
+static const struct reset_control_ops ti_syscon_reset_ops = {
+	.assert		= ti_syscon_reset_assert,
+	.deassert	= ti_syscon_reset_deassert,
+	.status		= ti_syscon_reset_status,
+};
+
+static int ti_syscon_reset_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct ti_syscon_reset_data *data;
+	struct regmap *regmap;
+	const __be32 *list;
+	struct ti_syscon_reset_control *controls;
+	int size, nr_controls, i;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	regmap = syscon_node_to_regmap(np->parent);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	list = of_get_property(np, "ti,reset-bits", &size);
+	if (!list || (size / sizeof(*list)) % 7 != 0) {
+		dev_err(dev, "invalid DT reset description\n");
+		return -EINVAL;
+	}
+
+	nr_controls = (size / sizeof(*list)) / 7;
+	controls = devm_kcalloc(dev, nr_controls, sizeof(*controls),
+				GFP_KERNEL);
+	if (!controls)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_controls; i++) {
+		controls[i].assert_offset = be32_to_cpup(list++);
+		controls[i].assert_bit = be32_to_cpup(list++);
+		controls[i].deassert_offset = be32_to_cpup(list++);
+		controls[i].deassert_bit = be32_to_cpup(list++);
+		controls[i].status_offset = be32_to_cpup(list++);
+		controls[i].status_bit = be32_to_cpup(list++);
+		controls[i].flags = be32_to_cpup(list++);
+	}
+
+	data->rcdev.ops = &ti_syscon_reset_ops;
+	data->rcdev.owner = THIS_MODULE;
+	data->rcdev.of_node = np;
+	data->rcdev.nr_resets = nr_controls;
+	data->regmap = regmap;
+	data->controls = controls;
+	data->nr_controls = nr_controls;
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+
+static const struct of_device_id ti_syscon_reset_of_match[] = {
+	{ .compatible = "ti,syscon-reset", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ti_syscon_reset_of_match);
+
+static struct platform_driver ti_syscon_reset_driver = {
+	.probe = ti_syscon_reset_probe,
+	.driver = {
+		.name = "ti-syscon-reset",
+		.of_match_table = ti_syscon_reset_of_match,
+	},
+};
+module_platform_driver(ti_syscon_reset_driver);
+
+MODULE_AUTHOR("Andrew F. Davis <afd@ti.com>");
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
+MODULE_DESCRIPTION("TI SYSCON Regmap Reset Driver");
+MODULE_LICENSE("GPL v2");