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, 160 insertions, 0 deletions

diff --git a/rust/pin-init/src/alloc.rs b/rust/pin-init/src/alloc.rs
new file mode 100644
index 000000000..471652e86
--- /dev/null
+++ b/rust/pin-init/src/alloc.rs
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+#[cfg(all(feature = "alloc", not(feature = "std")))]
+use alloc::{boxed::Box, sync::Arc};
+#[cfg(feature = "alloc")]
+use core::alloc::AllocError;
+use core::{mem::MaybeUninit, pin::Pin};
+#[cfg(feature = "std")]
+use std::sync::Arc;
+
+#[cfg(not(feature = "alloc"))]
+type AllocError = core::convert::Infallible;
+
+use crate::{
+    init_from_closure, pin_init_from_closure, InPlaceWrite, Init, PinInit, ZeroableOption,
+};
+
+pub extern crate alloc;
+
+// SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
+// <https://doc.rust-lang.org/stable/std/option/index.html#representation>).
+unsafe impl<T> ZeroableOption for Box<T> {}
+
+/// Smart pointer that can initialize memory in-place.
+pub trait InPlaceInit<T>: Sized {
+    /// Use the given pin-initializer to pin-initialize a `T` inside of a new smart pointer of this
+    /// type.
+    ///
+    /// If `T: !Unpin` it will not be able to move afterwards.
+    fn try_pin_init<E>(init: impl PinInit<T, E>) -> Result<Pin<Self>, E>
+    where
+        E: From<AllocError>;
+
+    /// Use the given pin-initializer to pin-initialize a `T` inside of a new smart pointer of this
+    /// type.
+    ///
+    /// If `T: !Unpin` it will not be able to move afterwards.
+    #[inline]
+    fn pin_init(init: impl PinInit<T>) -> Result<Pin<Self>, AllocError> {
+        // SAFETY: We delegate to `init` and only change the error type.
+        let init = unsafe {
+            pin_init_from_closure(|slot| match init.__init(slot) {
+                Ok(()) => Ok(()),
+                Err(i) => match i {},
+            })
+        };
+        Self::try_pin_init(init)
+    }
+
+    /// Use the given initializer to in-place initialize a `T`.
+    fn try_init<E>(init: impl Init<T, E>) -> Result<Self, E>
+    where
+        E: From<AllocError>;
+
+    /// Use the given initializer to in-place initialize a `T`.
+    #[inline]
+    fn init(init: impl Init<T>) -> Result<Self, AllocError> {
+        // SAFETY: We delegate to `init` and only change the error type.
+        let init = unsafe {
+            init_from_closure(|slot| match init.__init(slot) {
+                Ok(()) => Ok(()),
+                Err(i) => match i {},
+            })
+        };
+        Self::try_init(init)
+    }
+}
+
+#[cfg(feature = "alloc")]
+macro_rules! try_new_uninit {
+    ($type:ident) => {
+        $type::try_new_uninit()?
+    };
+}
+#[cfg(all(feature = "std", not(feature = "alloc")))]
+macro_rules! try_new_uninit {
+    ($type:ident) => {
+        $type::new_uninit()
+    };
+}
+
+impl<T> InPlaceInit<T> for Box<T> {
+    #[inline]
+    fn try_pin_init<E>(init: impl PinInit<T, E>) -> Result<Pin<Self>, E>
+    where
+        E: From<AllocError>,
+    {
+        try_new_uninit!(Box).write_pin_init(init)
+    }
+
+    #[inline]
+    fn try_init<E>(init: impl Init<T, E>) -> Result<Self, E>
+    where
+        E: From<AllocError>,
+    {
+        try_new_uninit!(Box).write_init(init)
+    }
+}
+
+impl<T> InPlaceInit<T> for Arc<T> {
+    #[inline]
+    fn try_pin_init<E>(init: impl PinInit<T, E>) -> Result<Pin<Self>, E>
+    where
+        E: From<AllocError>,
+    {
+        let mut this = try_new_uninit!(Arc);
+        let Some(slot) = Arc::get_mut(&mut this) else {
+            // SAFETY: the Arc has just been created and has no external references
+            unsafe { core::hint::unreachable_unchecked() }
+        };
+        let slot = slot.as_mut_ptr();
+        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
+        // slot is valid and will not be moved, because we pin it later.
+        unsafe { init.__init(slot)? };
+        // SAFETY: All fields have been initialized and this is the only `Arc` to that data.
+        Ok(unsafe { Pin::new_unchecked(this.assume_init()) })
+    }
+
+    #[inline]
+    fn try_init<E>(init: impl Init<T, E>) -> Result<Self, E>
+    where
+        E: From<AllocError>,
+    {
+        let mut this = try_new_uninit!(Arc);
+        let Some(slot) = Arc::get_mut(&mut this) else {
+            // SAFETY: the Arc has just been created and has no external references
+            unsafe { core::hint::unreachable_unchecked() }
+        };
+        let slot = slot.as_mut_ptr();
+        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
+        // slot is valid.
+        unsafe { init.__init(slot)? };
+        // SAFETY: All fields have been initialized.
+        Ok(unsafe { this.assume_init() })
+    }
+}
+
+impl<T> InPlaceWrite<T> for Box<MaybeUninit<T>> {
+    type Initialized = Box<T>;
+
+    #[inline]
+    fn write_init<E>(mut self, init: impl Init<T, E>) -> Result<Self::Initialized, E> {
+        let slot = self.as_mut_ptr();
+        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
+        // slot is valid.
+        unsafe { init.__init(slot)? };
+        // SAFETY: All fields have been initialized.
+        Ok(unsafe { self.assume_init() })
+    }
+
+    #[inline]
+    fn write_pin_init<E>(mut self, init: impl PinInit<T, E>) -> Result<Pin<Self::Initialized>, E> {
+        let slot = self.as_mut_ptr();
+        // SAFETY: When init errors/panics, slot will get deallocated but not dropped,
+        // slot is valid and will not be moved, because we pin it later.
+        unsafe { init.__init(slot)? };
+        // SAFETY: All fields have been initialized.
+        Ok(unsafe { self.assume_init() }.into())
+    }
+}