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, 133 insertions, 0 deletions

diff --git a/drivers/mfd/stm32-lptimer.c b/drivers/mfd/stm32-lptimer.c
new file mode 100644
index 000000000..123659178
--- /dev/null
+++ b/drivers/mfd/stm32-lptimer.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * STM32 Low-Power Timer parent driver.
+ * Copyright (C) STMicroelectronics 2017
+ * Author: Fabrice Gasnier <fabrice.gasnier@st.com>
+ * Inspired by Benjamin Gaignard's stm32-timers driver
+ */
+
+#include <linux/bitfield.h>
+#include <linux/mfd/stm32-lptimer.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+
+#define STM32_LPTIM_MAX_REGISTER	0x3fc
+
+static const struct regmap_config stm32_lptimer_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = sizeof(u32),
+	.max_register = STM32_LPTIM_MAX_REGISTER,
+};
+
+static int stm32_lptimer_detect_encoder(struct stm32_lptimer *ddata)
+{
+	u32 val;
+	int ret;
+
+	/*
+	 * Quadrature encoder mode bit can only be written and read back when
+	 * Low-Power Timer supports it.
+	 */
+	ret = regmap_update_bits(ddata->regmap, STM32_LPTIM_CFGR,
+				 STM32_LPTIM_ENC, STM32_LPTIM_ENC);
+	if (ret)
+		return ret;
+
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_CFGR, &val);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(ddata->regmap, STM32_LPTIM_CFGR,
+				 STM32_LPTIM_ENC, 0);
+	if (ret)
+		return ret;
+
+	ddata->has_encoder = !!(val & STM32_LPTIM_ENC);
+
+	return 0;
+}
+
+static int stm32_lptimer_detect_hwcfgr(struct stm32_lptimer *ddata)
+{
+	u32 val;
+	int ret;
+
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_VERR, &ddata->version);
+	if (ret)
+		return ret;
+
+	/* Try to guess parameters from HWCFGR: e.g. encoder mode (STM32MP15) */
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_HWCFGR1, &val);
+	if (ret)
+		return ret;
+
+	/* Fallback to legacy init if HWCFGR isn't present */
+	if (!val)
+		return stm32_lptimer_detect_encoder(ddata);
+
+	ddata->has_encoder = FIELD_GET(STM32_LPTIM_HWCFGR1_ENCODER, val);
+
+	ret = regmap_read(ddata->regmap, STM32_LPTIM_HWCFGR2, &val);
+	if (ret)
+		return ret;
+
+	/* Number of capture/compare channels */
+	ddata->num_cc_chans = FIELD_GET(STM32_LPTIM_HWCFGR2_CHAN_NUM, val);
+
+	return 0;
+}
+
+static int stm32_lptimer_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct stm32_lptimer *ddata;
+	void __iomem *mmio;
+	int ret;
+
+	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	mmio = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(mmio))
+		return PTR_ERR(mmio);
+
+	ddata->regmap = devm_regmap_init_mmio_clk(dev, "mux", mmio,
+						  &stm32_lptimer_regmap_cfg);
+	if (IS_ERR(ddata->regmap))
+		return PTR_ERR(ddata->regmap);
+
+	ddata->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(ddata->clk))
+		return PTR_ERR(ddata->clk);
+
+	ret = stm32_lptimer_detect_hwcfgr(ddata);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, ddata);
+
+	return devm_of_platform_populate(&pdev->dev);
+}
+
+static const struct of_device_id stm32_lptimer_of_match[] = {
+	{ .compatible = "st,stm32-lptimer", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, stm32_lptimer_of_match);
+
+static struct platform_driver stm32_lptimer_driver = {
+	.probe = stm32_lptimer_probe,
+	.driver = {
+		.name = "stm32-lptimer",
+		.of_match_table = stm32_lptimer_of_match,
+	},
+};
+module_platform_driver(stm32_lptimer_driver);
+
+MODULE_AUTHOR("Fabrice Gasnier <fabrice.gasnier@st.com>");
+MODULE_DESCRIPTION("STMicroelectronics STM32 Low-Power Timer");
+MODULE_ALIAS("platform:stm32-lptimer");
+MODULE_LICENSE("GPL v2");