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, 96 insertions, 0 deletions

diff --git a/lib/crc/arm/crc32.h b/lib/crc/arm/crc32.h
new file mode 100644
index 000000000..f33de6b22
--- /dev/null
+++ b/lib/crc/arm/crc32.h
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/cpufeature.h>
+
+#include <asm/hwcap.h>
+#include <asm/simd.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pmull);
+
+#define PMULL_MIN_LEN	64	/* min size of buffer for pmull functions */
+
+asmlinkage u32 crc32_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+asmlinkage u32 crc32c_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+static inline u32 crc32_le_scalar(u32 crc, const u8 *p, size_t len)
+{
+	if (static_branch_likely(&have_crc32))
+		return crc32_armv8_le(crc, p, len);
+	return crc32_le_base(crc, p, len);
+}
+
+static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (len >= PMULL_MIN_LEN + 15 &&
+	    static_branch_likely(&have_pmull) && likely(may_use_simd())) {
+		size_t n = -(uintptr_t)p & 15;
+
+		/* align p to 16-byte boundary */
+		if (n) {
+			crc = crc32_le_scalar(crc, p, n);
+			p += n;
+			len -= n;
+		}
+		n = round_down(len, 16);
+		scoped_ksimd()
+			crc = crc32_pmull_le(p, n, crc);
+		p += n;
+		len -= n;
+	}
+	return crc32_le_scalar(crc, p, len);
+}
+
+static inline u32 crc32c_scalar(u32 crc, const u8 *p, size_t len)
+{
+	if (static_branch_likely(&have_crc32))
+		return crc32c_armv8_le(crc, p, len);
+	return crc32c_base(crc, p, len);
+}
+
+static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (len >= PMULL_MIN_LEN + 15 &&
+	    static_branch_likely(&have_pmull) && likely(may_use_simd())) {
+		size_t n = -(uintptr_t)p & 15;
+
+		/* align p to 16-byte boundary */
+		if (n) {
+			crc = crc32c_scalar(crc, p, n);
+			p += n;
+			len -= n;
+		}
+		n = round_down(len, 16);
+		scoped_ksimd()
+			crc = crc32c_pmull_le(p, n, crc);
+		p += n;
+		len -= n;
+	}
+	return crc32c_scalar(crc, p, len);
+}
+
+#define crc32_be_arch crc32_be_base /* not implemented on this arch */
+
+#define crc32_mod_init_arch crc32_mod_init_arch
+static void crc32_mod_init_arch(void)
+{
+	if (elf_hwcap2 & HWCAP2_CRC32)
+		static_branch_enable(&have_crc32);
+	if (elf_hwcap2 & HWCAP2_PMULL)
+		static_branch_enable(&have_pmull);
+}
+
+static inline u32 crc32_optimizations_arch(void)
+{
+	if (elf_hwcap2 & (HWCAP2_CRC32 | HWCAP2_PMULL))
+		return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION;
+	return 0;
+}