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, 65 insertions, 0 deletions

diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
new file mode 100644
index 000000000..4e610deea
--- /dev/null
+++ b/drivers/nvmem/internals.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_NVMEM_INTERNALS_H
+#define _LINUX_NVMEM_INTERNALS_H
+
+#include <linux/device.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+
+/* Hold pointers to callbacks owned by the nvmem provider module. */
+struct nvmem_operations {
+	nvmem_reg_read_t	reg_read;
+	nvmem_reg_write_t	reg_write;
+};
+
+struct nvmem_device {
+	struct module		*owner;
+	struct device		dev;
+	int			stride;
+	int			word_size;
+	int			id;
+	struct kref		refcnt;
+	size_t			size;
+	bool			read_only;
+	bool			root_only;
+	int			flags;
+	enum nvmem_type		type;
+	struct bin_attribute	eeprom;
+	struct device		*base_dev;
+	struct list_head	cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
+	const struct nvmem_keepout *keepout;
+	unsigned int		nkeepout;
+	struct gpio_desc	*wp_gpio;
+	struct nvmem_layout	*layout;
+	struct nvmem_operations	*ops;
+	void *priv;
+	bool			sysfs_cells_populated;
+};
+
+int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np);
+
+#if IS_ENABLED(CONFIG_OF)
+int nvmem_layout_bus_register(void);
+void nvmem_layout_bus_unregister(void);
+int nvmem_populate_layout(struct nvmem_device *nvmem);
+void nvmem_destroy_layout(struct nvmem_device *nvmem);
+#else /* CONFIG_OF */
+static inline int nvmem_layout_bus_register(void)
+{
+	return 0;
+}
+
+static inline void nvmem_layout_bus_unregister(void) {}
+
+static inline int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	return 0;
+}
+
+static inline void nvmem_destroy_layout(struct nvmem_device *nvmem) { }
+#endif /* CONFIG_OF */
+
+#endif  /* ifndef _LINUX_NVMEM_INTERNALS_H */