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, 57 insertions, 0 deletions

diff --git a/include/asm-generic/local.h b/include/asm-generic/local.h
new file mode 100644
index 000000000..7f97018df
--- /dev/null
+++ b/include/asm-generic/local.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_LOCAL_H
+#define _ASM_GENERIC_LOCAL_H
+
+#include <linux/percpu.h>
+#include <linux/atomic.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic_long_t.  Which is
+ * rather pointless.  The whole point behind local_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct
+{
+	atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l,i)	atomic_long_set((&(l)->a),(i))
+#define local_inc(l)	atomic_long_inc(&(l)->a)
+#define local_dec(l)	atomic_long_dec(&(l)->a)
+#define local_add(i,l)	atomic_long_add((i),(&(l)->a))
+#define local_sub(i,l)	atomic_long_sub((i),(&(l)->a))
+
+#define local_sub_and_test(i, l) atomic_long_sub_and_test((i), (&(l)->a))
+#define local_dec_and_test(l) atomic_long_dec_and_test(&(l)->a)
+#define local_inc_and_test(l) atomic_long_inc_and_test(&(l)->a)
+#define local_add_negative(i, l) atomic_long_add_negative((i), (&(l)->a))
+#define local_add_return(i, l) atomic_long_add_return((i), (&(l)->a))
+#define local_sub_return(i, l) atomic_long_sub_return((i), (&(l)->a))
+#define local_inc_return(l) atomic_long_inc_return(&(l)->a)
+
+#define local_cmpxchg(l, o, n) atomic_long_cmpxchg((&(l)->a), (o), (n))
+#define local_try_cmpxchg(l, po, n) atomic_long_try_cmpxchg((&(l)->a), (po), (n))
+#define local_xchg(l, n) atomic_long_xchg((&(l)->a), (n))
+#define local_add_unless(l, _a, u) atomic_long_add_unless((&(l)->a), (_a), (u))
+#define local_inc_not_zero(l) atomic_long_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local_inc(l)		local_set((l), local_read(l) + 1)
+#define __local_dec(l)		local_set((l), local_read(l) - 1)
+#define __local_add(i,l)	local_set((l), local_read(l) + (i))
+#define __local_sub(i,l)	local_set((l), local_read(l) - (i))
+
+#endif /* _ASM_GENERIC_LOCAL_H */