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, 148 insertions, 0 deletions

diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
new file mode 100644
index 000000000..de75ae4d5
--- /dev/null
+++ b/arch/arm/lib/memset.S
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/lib/memset.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/unwind.h>
+
+	.text
+	.align	5
+
+ENTRY(__memset)
+ENTRY(mmioset)
+WEAK(memset)
+UNWIND( .fnstart         )
+	and	r1, r1, #255		@ cast to unsigned char
+	ands	r3, r0, #3		@ 1 unaligned?
+	mov	ip, r0			@ preserve r0 as return value
+	bne	6f			@ 1
+/*
+ * we know that the pointer in ip is aligned to a word boundary.
+ */
+1:	orr	r1, r1, r1, lsl #8
+	orr	r1, r1, r1, lsl #16
+	mov	r3, r1
+7:	cmp	r2, #16
+	blt	4f
+UNWIND( .fnend              )
+
+#if ! CALGN(1)+0
+
+/*
+ * We need 2 extra registers for this loop - use r8 and the LR
+ */
+UNWIND( .fnstart            )
+UNWIND( .save {r8, lr}      )
+	stmfd	sp!, {r8, lr}
+	mov	r8, r1
+	mov	lr, r3
+
+2:	subs	r2, r2, #64
+	stmiage	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	bgt	2b
+	ldmfdeq	sp!, {r8, pc}		@ Now <64 bytes to go.
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+	tst	r2, #32
+	stmiane	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
+	tst	r2, #16
+	stmiane	ip!, {r1, r3, r8, lr}
+	ldmfd	sp!, {r8, lr}
+UNWIND( .fnend              )
+
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+UNWIND( .fnstart               )
+UNWIND( .save {r4-r8, lr}      )
+	stmfd	sp!, {r4-r8, lr}
+	mov	r4, r1
+	mov	r5, r3
+	mov	r6, r1
+	mov	r7, r3
+	mov	r8, r1
+	mov	lr, r3
+
+	cmp	r2, #96
+	tstgt	ip, #31
+	ble	3f
+
+	and	r8, ip, #31
+	rsb	r8, r8, #32
+	sub	r2, r2, r8
+	movs	r8, r8, lsl #(32 - 4)
+	stmiacs	ip!, {r4, r5, r6, r7}
+	stmiami	ip!, {r4, r5}
+	tst	r8, #(1 << 30)
+	mov	r8, r1
+	strne	r1, [ip], #4
+
+3:	subs	r2, r2, #64
+	stmiage	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
+	bgt	3b
+	ldmfdeq	sp!, {r4-r8, pc}
+
+	tst	r2, #32
+	stmiane	ip!, {r1, r3-r8, lr}
+	tst	r2, #16
+	stmiane	ip!, {r4-r7}
+	ldmfd	sp!, {r4-r8, lr}
+UNWIND( .fnend                 )
+
+#endif
+
+UNWIND( .fnstart            )
+4:	tst	r2, #8
+	stmiane	ip!, {r1, r3}
+	tst	r2, #4
+	strne	r1, [ip], #4
+/*
+ * When we get here, we've got less than 4 bytes to set.  We
+ * may have an unaligned pointer as well.
+ */
+5:	tst	r2, #2
+	strbne	r1, [ip], #1
+	strbne	r1, [ip], #1
+	tst	r2, #1
+	strbne	r1, [ip], #1
+	ret	lr
+
+6:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5b			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strblt	r1, [ip], #1		@ 1
+	strble	r1, [ip], #1		@ 1
+	strb	r1, [ip], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+	b	1b
+UNWIND( .fnend   )
+ENDPROC(memset)
+ENDPROC(mmioset)
+ENDPROC(__memset)
+
+ENTRY(__memset32)
+UNWIND( .fnstart         )
+	mov	r3, r1			@ copy r1 to r3 and fall into memset64
+UNWIND( .fnend   )
+ENDPROC(__memset32)
+ENTRY(__memset64)
+UNWIND( .fnstart         )
+	mov	ip, r0			@ preserve r0 as return value
+	b	7b			@ jump into the middle of memset
+UNWIND( .fnend   )
+ENDPROC(__memset64)