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, 84 insertions, 0 deletions

diff --git a/arch/powerpc/boot/ns16550.c b/arch/powerpc/boot/ns16550.c
new file mode 100644
index 000000000..f16d2be1d
--- /dev/null
+++ b/arch/powerpc/boot/ns16550.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * 16550 serial console support.
+ *
+ * Original copied from <file:arch/ppc/boot/common/ns16550.c>
+ * (which had no copyright)
+ * Modifications: 2006 (c) MontaVista Software, Inc.
+ *
+ * Modified by: Mark A. Greer <mgreer@mvista.com>
+ */
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "string.h"
+#include "stdio.h"
+#include "io.h"
+#include "ops.h"
+#include "of.h"
+
+#define UART_DLL	0	/* Out: Divisor Latch Low */
+#define UART_DLM	1	/* Out: Divisor Latch High */
+#define UART_FCR	2	/* Out: FIFO Control Register */
+#define UART_LCR	3	/* Out: Line Control Register */
+#define UART_MCR	4	/* Out: Modem Control Register */
+#define UART_LSR	5	/* In:  Line Status Register */
+#define UART_LSR_THRE	0x20	/* Transmit-hold-register empty */
+#define UART_LSR_DR	0x01	/* Receiver data ready */
+#define UART_MSR	6	/* In:  Modem Status Register */
+#define UART_SCR	7	/* I/O: Scratch Register */
+
+static unsigned char *reg_base;
+static u32 reg_shift;
+
+static int ns16550_open(void)
+{
+	out_8(reg_base + (UART_FCR << reg_shift), 0x06);
+	return 0;
+}
+
+static void ns16550_putc(unsigned char c)
+{
+	while ((in_8(reg_base + (UART_LSR << reg_shift)) & UART_LSR_THRE) == 0);
+	out_8(reg_base, c);
+}
+
+static unsigned char ns16550_getc(void)
+{
+	while ((in_8(reg_base + (UART_LSR << reg_shift)) & UART_LSR_DR) == 0);
+	return in_8(reg_base);
+}
+
+static u8 ns16550_tstc(void)
+{
+	return ((in_8(reg_base + (UART_LSR << reg_shift)) & UART_LSR_DR) != 0);
+}
+
+int ns16550_console_init(void *devp, struct serial_console_data *scdp)
+{
+	int n;
+	u32 reg_offset;
+
+	if (dt_get_virtual_reg(devp, (void **)&reg_base, 1) < 1) {
+		printf("virt reg parse fail...\r\n");
+		return -1;
+	}
+
+	n = getprop(devp, "reg-offset", &reg_offset, sizeof(reg_offset));
+	if (n == sizeof(reg_offset))
+		reg_base += be32_to_cpu(reg_offset);
+
+	n = getprop(devp, "reg-shift", &reg_shift, sizeof(reg_shift));
+	if (n != sizeof(reg_shift))
+		reg_shift = 0;
+	else
+		reg_shift = be32_to_cpu(reg_shift);
+
+	scdp->open = ns16550_open;
+	scdp->putc = ns16550_putc;
+	scdp->getc = ns16550_getc;
+	scdp->tstc = ns16550_tstc;
+	scdp->close = NULL;
+
+	return 0;
+}