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, 81 insertions, 0 deletions

diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
new file mode 100644
index 000000000..bfc31923f
--- /dev/null
+++ b/drivers/dax/bus.h
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
+#ifndef __DAX_BUS_H__
+#define __DAX_BUS_H__
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/range.h>
+#include <linux/workqueue.h>
+
+struct dev_dax;
+struct resource;
+struct dax_device;
+struct dax_region;
+
+/* dax bus specific ioresource flags */
+#define IORESOURCE_DAX_STATIC BIT(0)
+#define IORESOURCE_DAX_KMEM BIT(1)
+
+#define DAX_KMEM_UNPLUGGED	(-1) /* Do not create memory blocks */
+
+struct dax_region *alloc_dax_region(struct device *parent, int region_id,
+		struct range *range, int target_node, unsigned int align,
+		unsigned long flags);
+
+struct dev_dax_data {
+	struct dax_region *dax_region;
+	struct dev_pagemap *pgmap;
+	resource_size_t size;
+	int id;
+	bool memmap_on_memory;
+};
+
+struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
+
+enum dax_driver_type {
+	DAXDRV_KMEM_TYPE,
+	DAXDRV_DEVICE_TYPE,
+	DAXDRV_FSDEV_TYPE,
+};
+
+struct dax_device_driver {
+	struct device_driver drv;
+	struct list_head ids;
+	enum dax_driver_type type;
+	int (*probe)(struct dev_dax *dev);
+	void (*remove)(struct dev_dax *dev);
+};
+
+#define to_dax_drv(__drv) container_of_const(__drv, struct dax_device_driver, drv)
+
+int __dax_driver_register(struct dax_device_driver *dax_drv,
+		struct module *module, const char *mod_name);
+#define dax_driver_register(driver) \
+	__dax_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
+void dax_driver_unregister(struct dax_device_driver *dax_drv);
+void kill_dev_dax(struct dev_dax *dev_dax);
+bool static_dev_dax(struct dev_dax *dev_dax);
+
+struct hmem_platform_device {
+	struct platform_device pdev;
+	struct work_struct work;
+	bool did_probe;
+};
+
+static inline struct hmem_platform_device *
+to_hmem_platform_device(struct platform_device *pdev)
+{
+	return container_of(pdev, struct hmem_platform_device, pdev);
+}
+
+#if IS_ENABLED(CONFIG_DEV_DAX_HMEM)
+void dax_hmem_flush_work(void);
+#else
+static inline void dax_hmem_flush_work(void) { }
+#endif
+
+#define MODULE_ALIAS_DAX_DEVICE(type) \
+	MODULE_ALIAS("dax:t" __stringify(type) "*")
+#define DAX_DEVICE_MODALIAS_FMT "dax:t%d"
+
+#endif /* __DAX_BUS_H__ */