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, 133 insertions, 0 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
new file mode 100644
index 000000000..22142c71d
--- /dev/null
+++ b/include/asm-generic/atomic.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic C implementation of atomic counter operations. Do not include in
+ * machine independent code.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#ifndef __ASM_GENERIC_ATOMIC_H
+#define __ASM_GENERIC_ATOMIC_H
+
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+
+#ifdef CONFIG_SMP
+
+/* we can build all atomic primitives from cmpxchg */
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void generic_atomic_##op(int i, atomic_t *v)		\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = arch_cmpxchg(&v->counter, c, c c_op i)) != c)	\
+		c = old;						\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int generic_atomic_##op##_return(int i, atomic_t *v)	\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = arch_cmpxchg(&v->counter, c, c c_op i)) != c)	\
+		c = old;						\
+									\
+	return c c_op i;						\
+}
+
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int generic_atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = arch_cmpxchg(&v->counter, c, c c_op i)) != c)	\
+		c = old;						\
+									\
+	return c;							\
+}
+
+#else
+
+#include <linux/irqflags.h>
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void generic_atomic_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int generic_atomic_##op##_return(int i, atomic_t *v)	\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = (v->counter = v->counter c_op i);				\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int generic_atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = v->counter;						\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
+#endif /* CONFIG_SMP */
+
+ATOMIC_OP_RETURN(add, +)
+ATOMIC_OP_RETURN(sub, -)
+
+ATOMIC_FETCH_OP(add, +)
+ATOMIC_FETCH_OP(sub, -)
+ATOMIC_FETCH_OP(and, &)
+ATOMIC_FETCH_OP(or, |)
+ATOMIC_FETCH_OP(xor, ^)
+
+ATOMIC_OP(add, +)
+ATOMIC_OP(sub, -)
+ATOMIC_OP(and, &)
+ATOMIC_OP(or, |)
+ATOMIC_OP(xor, ^)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
+#define arch_atomic_add_return			generic_atomic_add_return
+#define arch_atomic_sub_return			generic_atomic_sub_return
+
+#define arch_atomic_fetch_add			generic_atomic_fetch_add
+#define arch_atomic_fetch_sub			generic_atomic_fetch_sub
+#define arch_atomic_fetch_and			generic_atomic_fetch_and
+#define arch_atomic_fetch_or			generic_atomic_fetch_or
+#define arch_atomic_fetch_xor			generic_atomic_fetch_xor
+
+#define arch_atomic_add				generic_atomic_add
+#define arch_atomic_sub				generic_atomic_sub
+#define arch_atomic_and				generic_atomic_and
+#define arch_atomic_or				generic_atomic_or
+#define arch_atomic_xor				generic_atomic_xor
+
+#define arch_atomic_read(v)			READ_ONCE((v)->counter)
+#define arch_atomic_set(v, i)			WRITE_ONCE(((v)->counter), (i))
+
+#endif /* __ASM_GENERIC_ATOMIC_H */