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, 121 insertions, 0 deletions

diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
new file mode 100644
index 000000000..f794dac98
--- /dev/null
+++ b/arch/arm/xen/hypercall.S
@@ -0,0 +1,121 @@
+/******************************************************************************
+ * hypercall.S
+ *
+ * Xen hypercall wrappers
+ *
+ * Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Citrix, 2012
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+/*
+ * The Xen hypercall calling convention is very similar to the ARM
+ * procedure calling convention: the first paramter is passed in r0, the
+ * second in r1, the third in r2 and the fourth in r3. Considering that
+ * Xen hypercalls have 5 arguments at most, the fifth paramter is passed
+ * in r4, differently from the procedure calling convention of using the
+ * stack for that case.
+ *
+ * The hypercall number is passed in r12.
+ *
+ * The return value is in r0.
+ *
+ * The hvc ISS is required to be 0xEA1, that is the Xen specific ARM
+ * hypercall tag.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/opcodes-virt.h>
+#include <xen/interface/xen.h>
+
+
+#define XEN_IMM 0xEA1
+
+#define HYPERCALL_SIMPLE(hypercall)		\
+ENTRY(HYPERVISOR_##hypercall)			\
+	mov r12, #__HYPERVISOR_##hypercall;	\
+	__HVC(XEN_IMM);						\
+	ret lr;					\
+ENDPROC(HYPERVISOR_##hypercall)
+
+#define HYPERCALL0 HYPERCALL_SIMPLE
+#define HYPERCALL1 HYPERCALL_SIMPLE
+#define HYPERCALL2 HYPERCALL_SIMPLE
+#define HYPERCALL3 HYPERCALL_SIMPLE
+#define HYPERCALL4 HYPERCALL_SIMPLE
+
+#define HYPERCALL5(hypercall)			\
+ENTRY(HYPERVISOR_##hypercall)			\
+	stmdb sp!, {r4}						\
+	ldr r4, [sp, #4]					\
+	mov r12, #__HYPERVISOR_##hypercall;	\
+	__HVC(XEN_IMM);						\
+	ldm sp!, {r4}						\
+	ret lr					\
+ENDPROC(HYPERVISOR_##hypercall)
+
+                .text
+
+HYPERCALL2(xen_version);
+HYPERCALL3(console_io);
+HYPERCALL3(grant_table_op);
+HYPERCALL2(sched_op);
+HYPERCALL2(event_channel_op);
+HYPERCALL2(hvm_op);
+HYPERCALL2(memory_op);
+HYPERCALL2(physdev_op);
+HYPERCALL3(vcpu_op);
+HYPERCALL1(platform_op_raw);
+HYPERCALL2(multicall);
+HYPERCALL2(vm_assist);
+HYPERCALL3(dm_op);
+
+ENTRY(privcmd_call)
+	stmdb sp!, {r4}
+	mov r12, r0
+	mov r0, r1
+	mov r1, r2
+	mov r2, r3
+	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
+	ldr r4, [sp, #4]
+	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS) is called before.
+	 */
+	uaccess_disable r4
+
+	ldm sp!, {r4}
+	ret lr
+ENDPROC(privcmd_call);