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, 72 insertions, 0 deletions

diff --git a/drivers/clk/mediatek/reset.h b/drivers/clk/mediatek/reset.h
new file mode 100644
index 000000000..562ffd290
--- /dev/null
+++ b/drivers/clk/mediatek/reset.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 MediaTek Inc.
+ */
+
+#ifndef __DRV_CLK_MTK_RESET_H
+#define __DRV_CLK_MTK_RESET_H
+
+#include <linux/reset-controller.h>
+#include <linux/types.h>
+
+#define RST_NR_PER_BANK 32
+
+/* Infra global controller reset set register */
+#define INFRA_RST0_SET_OFFSET 0x120
+#define INFRA_RST1_SET_OFFSET 0x130
+#define INFRA_RST2_SET_OFFSET 0x140
+#define INFRA_RST3_SET_OFFSET 0x150
+#define INFRA_RST4_SET_OFFSET 0x730
+
+/**
+ * enum mtk_reset_version - Version of MediaTek clock reset controller.
+ * @MTK_RST_SIMPLE: Use the same registers for bit set and clear.
+ * @MTK_RST_SET_CLR: Use separate registers for bit set and clear.
+ * @MTK_RST_MAX: Total quantity of version for MediaTek clock reset controller.
+ */
+enum mtk_reset_version {
+	MTK_RST_SIMPLE = 0,
+	MTK_RST_SET_CLR,
+	MTK_RST_MAX,
+};
+
+/**
+ * struct mtk_clk_rst_desc - Description of MediaTek clock reset.
+ * @version: Reset version which is defined in enum mtk_reset_version.
+ * @rst_bank_ofs: Pointer to an array containing base offsets of the reset register.
+ * @rst_bank_nr: Quantity of reset bank.
+ * @rst_idx_map:Pointer to an array containing ids if input argument is index.
+ *		This array is not necessary if our input argument does not mean index.
+ * @rst_idx_map_nr: Quantity of reset index map.
+ */
+struct mtk_clk_rst_desc {
+	enum mtk_reset_version version;
+	u16 *rst_bank_ofs;
+	u32 rst_bank_nr;
+	u16 *rst_idx_map;
+	u32 rst_idx_map_nr;
+};
+
+/**
+ * struct mtk_clk_rst_data - Data of MediaTek clock reset controller.
+ * @regmap: Pointer to base address of reset register address.
+ * @rcdev: Reset controller device.
+ * @desc: Pointer to description of the reset controller.
+ */
+struct mtk_clk_rst_data {
+	struct regmap *regmap;
+	struct reset_controller_dev rcdev;
+	const struct mtk_clk_rst_desc *desc;
+};
+
+/**
+ * mtk_register_reset_controller - Register mediatek clock reset controller with device
+ * @np: Pointer to device.
+ * @desc: Constant pointer to description of clock reset.
+ *
+ * Return: 0 on success and errorno otherwise.
+ */
+int mtk_register_reset_controller_with_dev(struct device *dev,
+					   const struct mtk_clk_rst_desc *desc);
+
+#endif /* __DRV_CLK_MTK_RESET_H */