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, 127 insertions, 0 deletions

diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h
new file mode 100644
index 000000000..c4f7a1b97
--- /dev/null
+++ b/include/soc/tegra/fuse.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2012-2023, NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#ifndef __SOC_TEGRA_FUSE_H__
+#define __SOC_TEGRA_FUSE_H__
+
+#include <linux/types.h>
+
+#define TEGRA20		0x20
+#define TEGRA30		0x30
+#define TEGRA114	0x35
+#define TEGRA124	0x40
+#define TEGRA132	0x13
+#define TEGRA210	0x21
+#define TEGRA186	0x18
+#define TEGRA194	0x19
+#define TEGRA234	0x23
+#define TEGRA241	0x24
+#define TEGRA264	0x26
+
+#define TEGRA_FUSE_SKU_CALIB_0	0xf0
+#define TEGRA30_FUSE_SATA_CALIB	0x124
+#define TEGRA_FUSE_USB_CALIB_EXT_0 0x250
+
+#ifndef __ASSEMBLER__
+
+enum tegra_revision {
+	TEGRA_REVISION_UNKNOWN = 0,
+	TEGRA_REVISION_A01,
+	TEGRA_REVISION_A02,
+	TEGRA_REVISION_A03,
+	TEGRA_REVISION_A03p,
+	TEGRA_REVISION_A04,
+	TEGRA_REVISION_MAX,
+};
+
+enum tegra_platform {
+	TEGRA_PLATFORM_SILICON = 0,
+	TEGRA_PLATFORM_QT,
+	TEGRA_PLATFORM_SYSTEM_FPGA,
+	TEGRA_PLATFORM_UNIT_FPGA,
+	TEGRA_PLATFORM_ASIM_QT,
+	TEGRA_PLATFORM_ASIM_LINSIM,
+	TEGRA_PLATFORM_DSIM_ASIM_LINSIM,
+	TEGRA_PLATFORM_VERIFICATION_SIMULATION,
+	TEGRA_PLATFORM_VDK,
+	TEGRA_PLATFORM_VSP,
+	TEGRA_PLATFORM_MAX,
+};
+
+struct tegra_sku_info {
+	int sku_id;
+	int cpu_process_id;
+	int cpu_speedo_id;
+	int cpu_speedo_value;
+	int cpu_iddq_value;
+	int soc_process_id;
+	int soc_speedo_id;
+	int soc_speedo_value;
+	int gpu_process_id;
+	int gpu_speedo_id;
+	int gpu_speedo_value;
+	enum tegra_revision revision;
+	enum tegra_platform platform;
+};
+
+#ifdef CONFIG_ARCH_TEGRA
+extern struct tegra_sku_info tegra_sku_info;
+u32 tegra_read_straps(void);
+u32 tegra_read_ram_code(void);
+int tegra_fuse_readl(unsigned long offset, u32 *value);
+u32 tegra_read_chipid(void);
+u8 tegra_get_chip_id(void);
+u8 tegra_get_platform(void);
+bool tegra_is_silicon(void);
+int tegra194_miscreg_mask_serror(void);
+#else
+static struct tegra_sku_info tegra_sku_info __maybe_unused;
+
+static inline u32 tegra_read_straps(void)
+{
+	return 0;
+}
+
+static inline u32 tegra_read_ram_code(void)
+{
+	return 0;
+}
+
+static inline int tegra_fuse_readl(unsigned long offset, u32 *value)
+{
+	return -ENODEV;
+}
+
+static inline u32 tegra_read_chipid(void)
+{
+	return 0;
+}
+
+static inline u8 tegra_get_chip_id(void)
+{
+	return 0;
+}
+
+static inline u8 tegra_get_platform(void)
+{
+	return 0;
+}
+
+static inline bool tegra_is_silicon(void)
+{
+	return false;
+}
+
+static inline int tegra194_miscreg_mask_serror(void)
+{
+	return false;
+}
+#endif
+
+struct device *tegra_soc_device_register(void);
+
+#endif /* __ASSEMBLER__ */
+
+#endif /* __SOC_TEGRA_FUSE_H__ */