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, 77 insertions, 0 deletions

diff --git a/lib/stmp_device.c b/lib/stmp_device.c
new file mode 100644
index 000000000..a4f77b6a9
--- /dev/null
+++ b/lib/stmp_device.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 1999 ARM Limited
+ * Copyright (C) 2000 Deep Blue Solutions Ltd
+ * Copyright 2006-2007,2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright 2008 Juergen Beisert, kernel@pengutronix.de
+ * Copyright 2009 Ilya Yanok, Emcraft Systems Ltd, yanok@emcraft.com
+ * Copyright (C) 2011 Wolfram Sang, Pengutronix e.K.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <linux/stmp_device.h>
+
+#define STMP_MODULE_CLKGATE	(1 << 30)
+#define STMP_MODULE_SFTRST	(1 << 31)
+
+/*
+ * Clear the bit and poll it cleared.  This is usually called with
+ * a reset address and mask being either SFTRST(bit 31) or CLKGATE
+ * (bit 30).
+ */
+static int stmp_clear_poll_bit(void __iomem *addr, u32 mask)
+{
+	int timeout = 0x400;
+
+	writel(mask, addr + STMP_OFFSET_REG_CLR);
+	udelay(1);
+	while ((readl(addr) & mask) && --timeout)
+		/* nothing */;
+
+	return !timeout;
+}
+
+int stmp_reset_block(void __iomem *reset_addr)
+{
+	int ret;
+	int timeout = 0x400;
+
+	/* clear and poll SFTRST */
+	ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_SFTRST);
+	if (unlikely(ret))
+		goto error;
+
+	/* clear CLKGATE */
+	writel(STMP_MODULE_CLKGATE, reset_addr + STMP_OFFSET_REG_CLR);
+
+	/* set SFTRST to reset the block */
+	writel(STMP_MODULE_SFTRST, reset_addr + STMP_OFFSET_REG_SET);
+	udelay(1);
+
+	/* poll CLKGATE becoming set */
+	while ((!(readl(reset_addr) & STMP_MODULE_CLKGATE)) && --timeout)
+		/* nothing */;
+	if (unlikely(!timeout))
+		goto error;
+
+	/* clear and poll SFTRST */
+	ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_SFTRST);
+	if (unlikely(ret))
+		goto error;
+
+	/* clear and poll CLKGATE */
+	ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_CLKGATE);
+	if (unlikely(ret))
+		goto error;
+
+	return 0;
+
+error:
+	pr_err("%s(%p): module reset timeout\n", __func__, reset_addr);
+	return -ETIMEDOUT;
+}
+EXPORT_SYMBOL(stmp_reset_block);