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, 78 insertions, 0 deletions

diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c
new file mode 100644
index 000000000..2fd5712fb
--- /dev/null
+++ b/lib/iomap_copy.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2006 PathScale, Inc.  All Rights Reserved.
+ */
+
+#include <linux/export.h>
+#include <linux/io.h>
+
+/**
+ * __iowrite32_copy - copy data to MMIO space, in 32-bit units
+ * @to: destination, in MMIO space (must be 32-bit aligned)
+ * @from: source (must be 32-bit aligned)
+ * @count: number of 32-bit quantities to copy
+ *
+ * Copy data from kernel space to MMIO space, in units of 32 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+#ifndef __iowrite32_copy
+void __iowrite32_copy(void __iomem *to, const void *from, size_t count)
+{
+	u32 __iomem *dst = to;
+	const u32 *src = from;
+	const u32 *end = src + count;
+
+	while (src < end)
+		__raw_writel(*src++, dst++);
+}
+EXPORT_SYMBOL_GPL(__iowrite32_copy);
+#endif
+
+/**
+ * __ioread32_copy - copy data from MMIO space, in 32-bit units
+ * @to: destination (must be 32-bit aligned)
+ * @from: source, in MMIO space (must be 32-bit aligned)
+ * @count: number of 32-bit quantities to copy
+ *
+ * Copy data from MMIO space to kernel space, in units of 32 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+void __ioread32_copy(void *to, const void __iomem *from, size_t count)
+{
+	u32 *dst = to;
+	const u32 __iomem *src = from;
+	const u32 __iomem *end = src + count;
+
+	while (src < end)
+		*dst++ = __raw_readl(src++);
+}
+EXPORT_SYMBOL_GPL(__ioread32_copy);
+
+/**
+ * __iowrite64_copy - copy data to MMIO space, in 64-bit or 32-bit units
+ * @to: destination, in MMIO space (must be 64-bit aligned)
+ * @from: source (must be 64-bit aligned)
+ * @count: number of 64-bit quantities to copy
+ *
+ * Copy data from kernel space to MMIO space, in units of 32 or 64 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+#ifndef __iowrite64_copy
+void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
+{
+#ifdef CONFIG_64BIT
+	u64 __iomem *dst = to;
+	const u64 *src = from;
+	const u64 *end = src + count;
+
+	while (src < end)
+		__raw_writeq(*src++, dst++);
+#else
+	__iowrite32_copy(to, from, count * 2);
+#endif
+}
+EXPORT_SYMBOL_GPL(__iowrite64_copy);
+#endif