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, 93 insertions, 0 deletions

diff --git a/lib/crc/crc64-main.c b/lib/crc/crc64-main.c
new file mode 100644
index 000000000..133703601
--- /dev/null
+++ b/lib/crc/crc64-main.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Normal 64-bit CRC calculation.
+ *
+ * This is a basic crc64 implementation following ECMA-182 specification,
+ * which can be found from,
+ * https://www.ecma-international.org/publications/standards/Ecma-182.htm
+ *
+ * Dr. Ross N. Williams has a great document to introduce the idea of CRC
+ * algorithm, here the CRC64 code is also inspired by the table-driven
+ * algorithm and detail example from this paper. This paper can be found
+ * from,
+ * http://www.ross.net/crc/download/crc_v3.txt
+ *
+ * crc64table[256] is the lookup table of a table-driven 64-bit CRC
+ * calculation, which is generated by gen_crc64table.c in kernel build
+ * time. The polynomial of crc64 arithmetic is from ECMA-182 specification
+ * as well, which is defined as,
+ *
+ * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
+ * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
+ * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
+ * x^7 + x^4 + x + 1
+ *
+ * crc64nvmetable[256] uses the CRC64 polynomial from the NVME NVM Command Set
+ * Specification and uses least-significant-bit first bit order:
+ *
+ * x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + x^47 +
+ * x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + x^26 + x^23 +
+ * x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + x^4 + x^3 + 1
+ *
+ * Copyright 2018 SUSE Linux.
+ *   Author: Coly Li <colyli@suse.de>
+ */
+
+#include <linux/crc64.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+#include "crc64table.h"
+
+static inline u64 __maybe_unused
+crc64_be_generic(u64 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc << 8) ^ crc64table[(crc >> 56) ^ *p++];
+	return crc;
+}
+
+static inline u64 __maybe_unused
+crc64_nvme_generic(u64 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc64nvmetable[(crc & 0xff) ^ *p++];
+	return crc;
+}
+
+#ifdef CONFIG_CRC64_ARCH
+#include "crc64.h" /* $(SRCARCH)/crc64.h */
+#else
+#define crc64_be_arch crc64_be_generic
+#define crc64_nvme_arch crc64_nvme_generic
+#endif
+
+u64 crc64_be(u64 crc, const void *p, size_t len)
+{
+	return crc64_be_arch(crc, p, len);
+}
+EXPORT_SYMBOL_GPL(crc64_be);
+
+u64 crc64_nvme(u64 crc, const void *p, size_t len)
+{
+	return ~crc64_nvme_arch(~crc, p, len);
+}
+EXPORT_SYMBOL_GPL(crc64_nvme);
+
+#ifdef crc64_mod_init_arch
+static int __init crc64_mod_init(void)
+{
+	crc64_mod_init_arch();
+	return 0;
+}
+subsys_initcall(crc64_mod_init);
+
+static void __exit crc64_mod_exit(void)
+{
+}
+module_exit(crc64_mod_exit);
+#endif
+
+MODULE_DESCRIPTION("CRC64 library functions");
+MODULE_LICENSE("GPL");