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

6 files changed, 350 insertions, 0 deletions

diff --git a/drivers/reset/starfive/Kconfig b/drivers/reset/starfive/Kconfig
new file mode 100644
index 000000000..d832339f6
--- /dev/null
+++ b/drivers/reset/starfive/Kconfig
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config RESET_STARFIVE_JH71X0
+	bool
+
+config RESET_STARFIVE_JH7100
+	bool "StarFive JH7100 Reset Driver"
+	depends on ARCH_STARFIVE || COMPILE_TEST
+	select RESET_STARFIVE_JH71X0
+	default ARCH_STARFIVE
+	help
+	  This enables the reset controller driver for the StarFive JH7100 SoC.
+
+config RESET_STARFIVE_JH7110
+	bool "StarFive JH7110 Reset Driver"
+	depends on CLK_STARFIVE_JH7110_SYS
+	select AUXILIARY_BUS
+	select RESET_STARFIVE_JH71X0
+	default ARCH_STARFIVE
+	help
+	  This enables the reset controller driver for the StarFive JH7110 SoC.
diff --git a/drivers/reset/starfive/Makefile b/drivers/reset/starfive/Makefile
new file mode 100644
index 000000000..7a44b66fb
--- /dev/null
+++ b/drivers/reset/starfive/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_RESET_STARFIVE_JH71X0)		+= reset-starfive-jh71x0.o
+
+obj-$(CONFIG_RESET_STARFIVE_JH7100)		+= reset-starfive-jh7100.o
+obj-$(CONFIG_RESET_STARFIVE_JH7110)		+= reset-starfive-jh7110.o
diff --git a/drivers/reset/starfive/reset-starfive-jh7100.c b/drivers/reset/starfive/reset-starfive-jh7100.c
new file mode 100644
index 000000000..b178dc7d9
--- /dev/null
+++ b/drivers/reset/starfive/reset-starfive-jh7100.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Reset driver for the StarFive JH7100 SoC
+ *
+ * Copyright (C) 2021 Emil Renner Berthing <kernel@esmil.dk>
+ */
+
+#include <linux/platform_device.h>
+
+#include "reset-starfive-jh71x0.h"
+
+#include <dt-bindings/reset/starfive-jh7100.h>
+
+/* register offsets */
+#define JH7100_RESET_ASSERT0	0x00
+#define JH7100_RESET_ASSERT1	0x04
+#define JH7100_RESET_ASSERT2	0x08
+#define JH7100_RESET_ASSERT3	0x0c
+#define JH7100_RESET_STATUS0	0x10
+#define JH7100_RESET_STATUS1	0x14
+#define JH7100_RESET_STATUS2	0x18
+#define JH7100_RESET_STATUS3	0x1c
+
+/*
+ * Writing a 1 to the n'th bit of the m'th ASSERT register asserts
+ * line 32m + n, and writing a 0 deasserts the same line.
+ * Most reset lines have their status inverted so a 0 bit in the STATUS
+ * register means the line is asserted and a 1 means it's deasserted. A few
+ * lines don't though, so store the expected value of the status registers when
+ * all lines are asserted.
+ */
+static const u32 jh7100_reset_asserted[4] = {
+	/* STATUS0 */
+	BIT(JH7100_RST_U74 % 32) |
+	BIT(JH7100_RST_VP6_DRESET % 32) |
+	BIT(JH7100_RST_VP6_BRESET % 32),
+	/* STATUS1 */
+	BIT(JH7100_RST_HIFI4_DRESET % 32) |
+	BIT(JH7100_RST_HIFI4_BRESET % 32),
+	/* STATUS2 */
+	BIT(JH7100_RST_E24 % 32),
+	/* STATUS3 */
+	0,
+};
+
+static int __init jh7100_reset_probe(struct platform_device *pdev)
+{
+	void __iomem *base = devm_platform_ioremap_resource(pdev, 0);
+
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	return reset_starfive_jh71x0_register(&pdev->dev, pdev->dev.of_node,
+					      base + JH7100_RESET_ASSERT0,
+					      base + JH7100_RESET_STATUS0,
+					      jh7100_reset_asserted,
+					      JH7100_RSTN_END,
+					      THIS_MODULE);
+}
+
+static const struct of_device_id jh7100_reset_dt_ids[] = {
+	{ .compatible = "starfive,jh7100-reset" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver jh7100_reset_driver = {
+	.driver = {
+		.name = "jh7100-reset",
+		.of_match_table = jh7100_reset_dt_ids,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver_probe(jh7100_reset_driver, jh7100_reset_probe);
diff --git a/drivers/reset/starfive/reset-starfive-jh7110.c b/drivers/reset/starfive/reset-starfive-jh7110.c
new file mode 100644
index 000000000..29a43f0f2
--- /dev/null
+++ b/drivers/reset/starfive/reset-starfive-jh7110.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Reset driver for the StarFive JH7110 SoC
+ *
+ * Copyright (C) 2022 StarFive Technology Co., Ltd.
+ */
+
+#include <linux/auxiliary_bus.h>
+
+#include <soc/starfive/reset-starfive-jh71x0.h>
+
+#include "reset-starfive-jh71x0.h"
+
+#include <dt-bindings/reset/starfive,jh7110-crg.h>
+
+struct jh7110_reset_info {
+	unsigned int nr_resets;
+	unsigned int assert_offset;
+	unsigned int status_offset;
+};
+
+static const struct jh7110_reset_info jh7110_sys_info = {
+	.nr_resets = JH7110_SYSRST_END,
+	.assert_offset = 0x2F8,
+	.status_offset = 0x308,
+};
+
+static const struct jh7110_reset_info jh7110_aon_info = {
+	.nr_resets = JH7110_AONRST_END,
+	.assert_offset = 0x38,
+	.status_offset = 0x3C,
+};
+
+static const struct jh7110_reset_info jh7110_stg_info = {
+	.nr_resets = JH7110_STGRST_END,
+	.assert_offset = 0x74,
+	.status_offset = 0x78,
+};
+
+static const struct jh7110_reset_info jh7110_isp_info = {
+	.nr_resets = JH7110_ISPRST_END,
+	.assert_offset = 0x38,
+	.status_offset = 0x3C,
+};
+
+static const struct jh7110_reset_info jh7110_vout_info = {
+	.nr_resets = JH7110_VOUTRST_END,
+	.assert_offset = 0x48,
+	.status_offset = 0x4C,
+};
+
+static int jh7110_reset_probe(struct auxiliary_device *adev,
+			      const struct auxiliary_device_id *id)
+{
+	struct jh7110_reset_info *info = (struct jh7110_reset_info *)(id->driver_data);
+	struct jh71x0_reset_adev *rdev = to_jh71x0_reset_adev(adev);
+	void __iomem *base = rdev->base;
+
+	if (!info || !base)
+		return -ENODEV;
+
+	return reset_starfive_jh71x0_register(&adev->dev, adev->dev.parent->of_node,
+					      base + info->assert_offset,
+					      base + info->status_offset,
+					      NULL,
+					      info->nr_resets,
+					      NULL);
+}
+
+static const struct auxiliary_device_id jh7110_reset_ids[] = {
+	{
+		.name = "clk_starfive_jh7110_sys.rst-sys",
+		.driver_data = (kernel_ulong_t)&jh7110_sys_info,
+	},
+	{
+		.name = "clk_starfive_jh7110_sys.rst-aon",
+		.driver_data = (kernel_ulong_t)&jh7110_aon_info,
+	},
+	{
+		.name = "clk_starfive_jh7110_sys.rst-stg",
+		.driver_data = (kernel_ulong_t)&jh7110_stg_info,
+	},
+	{
+		.name = "clk_starfive_jh7110_sys.rst-isp",
+		.driver_data = (kernel_ulong_t)&jh7110_isp_info,
+	},
+	{
+		.name = "clk_starfive_jh7110_sys.rst-vo",
+		.driver_data = (kernel_ulong_t)&jh7110_vout_info,
+	},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(auxiliary, jh7110_reset_ids);
+
+static struct auxiliary_driver jh7110_reset_driver = {
+	.probe		= jh7110_reset_probe,
+	.id_table	= jh7110_reset_ids,
+};
+module_auxiliary_driver(jh7110_reset_driver);
+
+MODULE_AUTHOR("Hal Feng <hal.feng@starfivetech.com>");
+MODULE_DESCRIPTION("StarFive JH7110 reset driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.c b/drivers/reset/starfive/reset-starfive-jh71x0.c
new file mode 100644
index 000000000..29ce34867
--- /dev/null
+++ b/drivers/reset/starfive/reset-starfive-jh71x0.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Reset driver for the StarFive JH71X0 SoCs
+ *
+ * Copyright (C) 2021 Emil Renner Berthing <kernel@esmil.dk>
+ */
+
+#include <linux/bitmap.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/reset-controller.h>
+#include <linux/spinlock.h>
+
+#include "reset-starfive-jh71x0.h"
+
+struct jh71x0_reset {
+	struct reset_controller_dev rcdev;
+	/* protect registers against concurrent read-modify-write */
+	spinlock_t lock;
+	void __iomem *assert;
+	void __iomem *status;
+	const u32 *asserted;
+};
+
+static inline struct jh71x0_reset *
+jh71x0_reset_from(struct reset_controller_dev *rcdev)
+{
+	return container_of(rcdev, struct jh71x0_reset, rcdev);
+}
+
+static int jh71x0_reset_update(struct reset_controller_dev *rcdev,
+			       unsigned long id, bool assert)
+{
+	struct jh71x0_reset *data = jh71x0_reset_from(rcdev);
+	unsigned long offset = id / 32;
+	u32 mask = BIT(id % 32);
+	void __iomem *reg_assert = data->assert + offset * sizeof(u32);
+	void __iomem *reg_status = data->status + offset * sizeof(u32);
+	u32 done = data->asserted ? data->asserted[offset] & mask : 0;
+	u32 value;
+	unsigned long flags;
+	int ret;
+
+	if (!assert)
+		done ^= mask;
+
+	spin_lock_irqsave(&data->lock, flags);
+
+	value = readl(reg_assert);
+	if (assert)
+		value |= mask;
+	else
+		value &= ~mask;
+	writel(value, reg_assert);
+
+	/* if the associated clock is gated, deasserting might otherwise hang forever */
+	ret = readl_poll_timeout_atomic(reg_status, value, (value & mask) == done, 0, 1000);
+
+	spin_unlock_irqrestore(&data->lock, flags);
+	return ret;
+}
+
+static int jh71x0_reset_assert(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	return jh71x0_reset_update(rcdev, id, true);
+}
+
+static int jh71x0_reset_deassert(struct reset_controller_dev *rcdev,
+				 unsigned long id)
+{
+	return jh71x0_reset_update(rcdev, id, false);
+}
+
+static int jh71x0_reset_reset(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	int ret;
+
+	ret = jh71x0_reset_assert(rcdev, id);
+	if (ret)
+		return ret;
+
+	return jh71x0_reset_deassert(rcdev, id);
+}
+
+static int jh71x0_reset_status(struct reset_controller_dev *rcdev,
+			       unsigned long id)
+{
+	struct jh71x0_reset *data = jh71x0_reset_from(rcdev);
+	unsigned long offset = id / 32;
+	u32 mask = BIT(id % 32);
+	void __iomem *reg_status = data->status + offset * sizeof(u32);
+	u32 value = readl(reg_status);
+
+	if (!data->asserted)
+		return !(value & mask);
+
+	return !((value ^ data->asserted[offset]) & mask);
+}
+
+static const struct reset_control_ops jh71x0_reset_ops = {
+	.assert		= jh71x0_reset_assert,
+	.deassert	= jh71x0_reset_deassert,
+	.reset		= jh71x0_reset_reset,
+	.status		= jh71x0_reset_status,
+};
+
+int reset_starfive_jh71x0_register(struct device *dev, struct device_node *of_node,
+				   void __iomem *assert, void __iomem *status,
+				   const u32 *asserted, unsigned int nr_resets,
+				   struct module *owner)
+{
+	struct jh71x0_reset *data;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->rcdev.ops = &jh71x0_reset_ops;
+	data->rcdev.owner = owner;
+	data->rcdev.nr_resets = nr_resets;
+	data->rcdev.dev = dev;
+	data->rcdev.of_node = of_node;
+
+	spin_lock_init(&data->lock);
+	data->assert = assert;
+	data->status = status;
+	data->asserted = asserted;
+
+	return devm_reset_controller_register(dev, &data->rcdev);
+}
+EXPORT_SYMBOL_GPL(reset_starfive_jh71x0_register);
diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.h b/drivers/reset/starfive/reset-starfive-jh71x0.h
new file mode 100644
index 000000000..db7d39a87
--- /dev/null
+++ b/drivers/reset/starfive/reset-starfive-jh71x0.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2021 Emil Renner Berthing <kernel@esmil.dk>
+ */
+
+#ifndef __RESET_STARFIVE_JH71X0_H
+#define __RESET_STARFIVE_JH71X0_H
+
+int reset_starfive_jh71x0_register(struct device *dev, struct device_node *of_node,
+				   void __iomem *assert, void __iomem *status,
+				   const u32 *asserted, unsigned int nr_resets,
+				   struct module *owner);
+
+#endif /* __RESET_STARFIVE_JH71X0_H */