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, 72 insertions, 0 deletions

diff --git a/arch/powerpc/boot/ps3-head.S b/arch/powerpc/boot/ps3-head.S
new file mode 100644
index 000000000..0a4ebfcc3
--- /dev/null
+++ b/arch/powerpc/boot/ps3-head.S
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  PS3 bootwrapper entry.
+ *
+ *  Copyright (C) 2007 Sony Computer Entertainment Inc.
+ *  Copyright 2007 Sony Corp.
+ */
+
+#include "ppc_asm.h"
+
+	.machine "ppc64"
+
+	.text
+
+/*
+ * __system_reset_overlay - The PS3 first stage entry.
+ *
+ * The bootwraper build script copies the 512 bytes at symbol
+ * __system_reset_overlay to offset 0x100 of the rom image.  This symbol
+ * must occupy 512 or less bytes.
+ *
+ * The PS3 has a single processor with two threads.
+ */
+
+	.globl __system_reset_overlay
+__system_reset_overlay:
+
+	/* Switch to 32-bit mode. */
+
+	mfmsr	r9
+	clrldi	r9,r9,1
+	mtmsrd	r9
+	nop
+
+	/* Get thread number in r3 and branch. */
+
+	mfspr	r3, 0x88
+	cntlzw.	r3, r3
+	beq	1f
+
+	/* Secondary goes to __secondary_hold in kernel. */
+
+	li	r4, 0x60
+	mtctr	r4
+	bctr
+
+1:
+	/* Primary delays then goes to _zimage_start in wrapper. */
+
+	or	31, 31, 31 /* db16cyc */
+	or	31, 31, 31 /* db16cyc */
+
+	lis	r4, _zimage_start@ha
+	addi	r4, r4, _zimage_start@l
+	mtctr	r4
+	bctr
+
+	. = __system_reset_overlay + 512
+
+/*
+ * __system_reset_kernel - Place holder for the kernel reset vector.
+ *
+ * The bootwrapper build script copies 512 bytes from offset 0x100
+ * of the rom image to the symbol __system_reset_kernel.  At runtime
+ * the bootwrapper program copies the 512 bytes at __system_reset_kernel
+ * to ram address 0x100.  This symbol must occupy 512 bytes.
+ */
+
+	.globl __system_reset_kernel
+__system_reset_kernel:
+
+	. = __system_reset_kernel + 512