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, 123 insertions, 0 deletions

diff --git a/drivers/mfd/atmel-flexcom.c b/drivers/mfd/atmel-flexcom.c
new file mode 100644
index 000000000..d5df5466e
--- /dev/null
+++ b/drivers/mfd/atmel-flexcom.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Driver for Atmel Flexcom
+ *
+ * Copyright (C) 2015 Atmel Corporation
+ *
+ * Author: Cyrille Pitchen <cyrille.pitchen@atmel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <dt-bindings/mfd/atmel-flexcom.h>
+
+/* I/O register offsets */
+#define FLEX_MR		0x0	/* Mode Register */
+#define FLEX_VERSION	0xfc	/* Version Register */
+
+/* Mode Register bit fields */
+#define FLEX_MR_OPMODE_OFFSET	(0)  /* Operating Mode */
+#define FLEX_MR_OPMODE_MASK	(0x3 << FLEX_MR_OPMODE_OFFSET)
+#define FLEX_MR_OPMODE(opmode)	(((opmode) << FLEX_MR_OPMODE_OFFSET) &	\
+				 FLEX_MR_OPMODE_MASK)
+
+struct atmel_flexcom {
+	void __iomem *base;
+	u32 opmode;
+	struct clk *clk;
+};
+
+static int atmel_flexcom_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct atmel_flexcom *ddata;
+	int err;
+
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, ddata);
+
+	err = of_property_read_u32(np, "atmel,flexcom-mode", &ddata->opmode);
+	if (err)
+		return err;
+
+	if (ddata->opmode < ATMEL_FLEXCOM_MODE_USART ||
+	    ddata->opmode > ATMEL_FLEXCOM_MODE_TWI)
+		return -EINVAL;
+
+	ddata->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(ddata->base))
+		return PTR_ERR(ddata->base);
+
+	ddata->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(ddata->clk))
+		return PTR_ERR(ddata->clk);
+
+	err = clk_prepare_enable(ddata->clk);
+	if (err)
+		return err;
+
+	/*
+	 * Set the Operating Mode in the Mode Register: only the selected device
+	 * is clocked. Hence, registers of the other serial devices remain
+	 * inaccessible and are read as zero. Also the external I/O lines of the
+	 * Flexcom are muxed to reach the selected device.
+	 */
+	writel(FLEX_MR_OPMODE(ddata->opmode), ddata->base + FLEX_MR);
+
+	clk_disable_unprepare(ddata->clk);
+
+	return devm_of_platform_populate(&pdev->dev);
+}
+
+static const struct of_device_id atmel_flexcom_of_match[] = {
+	{ .compatible = "atmel,sama5d2-flexcom" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, atmel_flexcom_of_match);
+
+static int __maybe_unused atmel_flexcom_resume_noirq(struct device *dev)
+{
+	struct atmel_flexcom *ddata = dev_get_drvdata(dev);
+	int err;
+	u32 val;
+
+	err = clk_prepare_enable(ddata->clk);
+	if (err)
+		return err;
+
+	val = FLEX_MR_OPMODE(ddata->opmode);
+	writel(val, ddata->base + FLEX_MR);
+
+	clk_disable_unprepare(ddata->clk);
+
+	return 0;
+}
+
+static const struct dev_pm_ops __maybe_unused atmel_flexcom_pm_ops = {
+	.resume_noirq = atmel_flexcom_resume_noirq,
+};
+
+static struct platform_driver atmel_flexcom_driver = {
+	.probe	= atmel_flexcom_probe,
+	.driver	= {
+		.name		= "atmel_flexcom",
+		.pm		= pm_ptr(&atmel_flexcom_pm_ops),
+		.of_match_table	= atmel_flexcom_of_match,
+	},
+};
+
+module_platform_driver(atmel_flexcom_driver);
+
+MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@atmel.com>");
+MODULE_DESCRIPTION("Atmel Flexcom MFD driver");
+MODULE_LICENSE("GPL v2");