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, 95 insertions, 0 deletions

diff --git a/arch/mips/dec/tc.c b/arch/mips/dec/tc.c
new file mode 100644
index 000000000..dba583976
--- /dev/null
+++ b/arch/mips/dec/tc.c
@@ -0,0 +1,95 @@
+/*
+ *	TURBOchannel architecture calls.
+ *
+ *	Copyright (c) Harald Koerfgen, 1998
+ *	Copyright (c) 2001, 2003, 2005, 2006  Maciej W. Rozycki
+ *	Copyright (c) 2005  James Simmons
+ *
+ *	This file is subject to the terms and conditions of the GNU
+ *	General Public License.  See the file "COPYING" in the main
+ *	directory of this archive for more details.
+ */
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/tc.h>
+#include <linux/types.h>
+
+#include <asm/addrspace.h>
+#include <asm/bootinfo.h>
+#include <asm/paccess.h>
+
+#include <asm/dec/interrupts.h>
+#include <asm/dec/prom.h>
+#include <asm/dec/system.h>
+
+/*
+ * Protected read byte from TURBOchannel slot space.
+ */
+int tc_preadb(u8 *valp, void __iomem *addr)
+{
+	return get_dbe(*valp, (u8 *)addr);
+}
+
+/*
+ * Get TURBOchannel bus information as specified by the spec, plus
+ * the slot space base address and the number of slots.
+ */
+int __init tc_bus_get_info(struct tc_bus *tbus)
+{
+	if (!dec_tc_bus)
+		return -ENXIO;
+
+	memcpy(&tbus->info, rex_gettcinfo(), sizeof(tbus->info));
+	tbus->slot_base = CPHYSADDR((long)rex_slot_address(0));
+
+	switch (mips_machtype) {
+	case MACH_DS5000_200:
+		tbus->num_tcslots = 7;
+		break;
+	case MACH_DS5000_2X0:
+	case MACH_DS5900:
+		tbus->ext_slot_base = 0x20000000;
+		tbus->ext_slot_size = 0x20000000;
+		fallthrough;
+	case MACH_DS5000_1XX:
+		tbus->num_tcslots = 3;
+		break;
+	case MACH_DS5000_XX:
+		tbus->num_tcslots = 2;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Get the IRQ for the specified slot.
+ */
+void __init tc_device_get_irq(struct tc_dev *tdev)
+{
+	switch (tdev->slot) {
+	case 0:
+		tdev->interrupt = dec_interrupt[DEC_IRQ_TC0];
+		break;
+	case 1:
+		tdev->interrupt = dec_interrupt[DEC_IRQ_TC1];
+		break;
+	case 2:
+		tdev->interrupt = dec_interrupt[DEC_IRQ_TC2];
+		break;
+	/*
+	 * Yuck! DS5000/200 onboard devices
+	 */
+	case 5:
+		tdev->interrupt = dec_interrupt[DEC_IRQ_TC5];
+		break;
+	case 6:
+		tdev->interrupt = dec_interrupt[DEC_IRQ_TC6];
+		break;
+	default:
+		tdev->interrupt = -1;
+		break;
+	}
+}