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, 283 insertions, 0 deletions

diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
new file mode 100644
index 000000000..3bf296581
--- /dev/null
+++ b/scripts/generate_rust_target.rs
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! The custom target specification file generator for `rustc`.
+//!
+//! To configure a target from scratch, a JSON-encoded file has to be passed
+//! to `rustc` (introduced in [RFC 131]). These options and the file itself are
+//! unstable. Eventually, `rustc` should provide a way to do this in a stable
+//! manner. For instance, via command-line arguments. Therefore, this file
+//! should avoid using keys which can be set via `-C` or `-Z` options.
+//!
+//! [RFC 131]: https://rust-lang.github.io/rfcs/0131-target-specification.html
+
+use std::{
+    collections::HashMap,
+    fmt::{Display, Formatter, Result},
+    io::BufRead,
+};
+
+enum Value {
+    Boolean(bool),
+    Number(i32),
+    String(String),
+    Array(Vec<Value>),
+    Object(Object),
+}
+
+type Object = Vec<(String, Value)>;
+
+fn comma_sep<T>(
+    seq: &[T],
+    formatter: &mut Formatter<'_>,
+    f: impl Fn(&mut Formatter<'_>, &T) -> Result,
+) -> Result {
+    if let [ref rest @ .., ref last] = seq[..] {
+        for v in rest {
+            f(formatter, v)?;
+            formatter.write_str(",")?;
+        }
+        f(formatter, last)?;
+    }
+    Ok(())
+}
+
+/// Minimal "almost JSON" generator (e.g. no `null`s, no escaping),
+/// enough for this purpose.
+impl Display for Value {
+    fn fmt(&self, formatter: &mut Formatter<'_>) -> Result {
+        match self {
+            Value::Boolean(boolean) => write!(formatter, "{}", boolean),
+            Value::Number(number) => write!(formatter, "{}", number),
+            Value::String(string) => write!(formatter, "\"{}\"", string),
+            Value::Array(values) => {
+                formatter.write_str("[")?;
+                comma_sep(&values[..], formatter, |formatter, v| v.fmt(formatter))?;
+                formatter.write_str("]")
+            }
+            Value::Object(object) => {
+                formatter.write_str("{")?;
+                comma_sep(&object[..], formatter, |formatter, v| {
+                    write!(formatter, "\"{}\": {}", v.0, v.1)
+                })?;
+                formatter.write_str("}")
+            }
+        }
+    }
+}
+
+impl From<bool> for Value {
+    fn from(value: bool) -> Self {
+        Self::Boolean(value)
+    }
+}
+
+impl From<i32> for Value {
+    fn from(value: i32) -> Self {
+        Self::Number(value)
+    }
+}
+
+impl From<String> for Value {
+    fn from(value: String) -> Self {
+        Self::String(value)
+    }
+}
+
+impl From<&str> for Value {
+    fn from(value: &str) -> Self {
+        Self::String(value.to_string())
+    }
+}
+
+impl From<Object> for Value {
+    fn from(object: Object) -> Self {
+        Self::Object(object)
+    }
+}
+
+impl<T: Into<Value>, const N: usize> From<[T; N]> for Value {
+    fn from(i: [T; N]) -> Self {
+        Self::Array(i.into_iter().map(|v| v.into()).collect())
+    }
+}
+
+struct TargetSpec(Object);
+
+impl TargetSpec {
+    fn new() -> TargetSpec {
+        TargetSpec(Vec::new())
+    }
+
+    fn push(&mut self, key: &str, value: impl Into<Value>) {
+        self.0.push((key.to_string(), value.into()));
+    }
+}
+
+impl Display for TargetSpec {
+    fn fmt(&self, formatter: &mut Formatter<'_>) -> Result {
+        // We add some newlines for clarity.
+        formatter.write_str("{\n")?;
+        if let [ref rest @ .., ref last] = self.0[..] {
+            for (key, value) in rest {
+                write!(formatter, "    \"{}\": {},\n", key, value)?;
+            }
+            write!(formatter, "    \"{}\": {}\n", last.0, last.1)?;
+        }
+        formatter.write_str("}")
+    }
+}
+
+struct KernelConfig(HashMap<String, String>);
+
+impl KernelConfig {
+    /// Parses `include/config/auto.conf` from `stdin`.
+    fn from_stdin() -> KernelConfig {
+        let mut result = HashMap::new();
+
+        let stdin = std::io::stdin();
+        let mut handle = stdin.lock();
+        let mut line = String::new();
+
+        loop {
+            line.clear();
+
+            if handle.read_line(&mut line).unwrap() == 0 {
+                break;
+            }
+
+            if line.starts_with('#') {
+                continue;
+            }
+
+            let (key, value) = line.split_once('=').expect("Missing `=` in line.");
+            result.insert(key.to_string(), value.trim_end_matches('\n').to_string());
+        }
+
+        KernelConfig(result)
+    }
+
+    /// Does the option exist in the configuration (any value)?
+    ///
+    /// The argument must be passed without the `CONFIG_` prefix.
+    /// This avoids repetition and it also avoids `fixdep` making us
+    /// depend on it.
+    fn has(&self, option: &str) -> bool {
+        let option = "CONFIG_".to_owned() + option;
+        self.0.contains_key(&option)
+    }
+
+    /// Is the rustc version at least `major.minor.patch`?
+    fn rustc_version_atleast(&self, major: u32, minor: u32, patch: u32) -> bool {
+        let check_version = 100000 * major + 100 * minor + patch;
+        let actual_version = self
+            .0
+            .get("CONFIG_RUSTC_VERSION")
+            .unwrap()
+            .parse::<u32>()
+            .unwrap();
+        check_version <= actual_version
+    }
+}
+
+fn main() {
+    let cfg = KernelConfig::from_stdin();
+    let mut ts = TargetSpec::new();
+
+    // `llvm-target`s are taken from `scripts/Makefile.clang`.
+    if cfg.has("ARM") {
+        panic!("arm uses the builtin rustc target");
+    } else if cfg.has("ARM64") {
+        panic!("arm64 uses the builtin rustc aarch64-unknown-none target");
+    } else if cfg.has("RISCV") {
+        if cfg.has("64BIT") {
+            panic!("64-bit RISC-V uses the builtin rustc riscv64-unknown-none-elf target");
+        } else {
+            panic!("32-bit RISC-V is an unsupported architecture");
+        }
+    } else if cfg.has("X86_64") {
+        ts.push("arch", "x86_64");
+        if cfg.rustc_version_atleast(1, 98, 0) {
+            ts.push("rustc-abi", "softfloat");
+        } else if cfg.rustc_version_atleast(1, 86, 0) {
+            ts.push("rustc-abi", "x86-softfloat");
+        }
+        ts.push(
+            "data-layout",
+            "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128",
+        );
+        let mut features = "-mmx,+soft-float".to_string();
+        if cfg.has("MITIGATION_RETPOLINE") {
+            // The kernel uses `-mretpoline-external-thunk` (for Clang), which Clang maps to the
+            // target feature of the same name plus the other two target features in
+            // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via
+            // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated
+            // flag); see <https://github.com/rust-lang/rust/issues/116852>.
+            features += ",+retpoline-external-thunk";
+            features += ",+retpoline-indirect-branches";
+            features += ",+retpoline-indirect-calls";
+        }
+        if cfg.has("MITIGATION_SLS") {
+            // The kernel uses `-mharden-sls=all`, which Clang maps to both these target features in
+            // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via
+            // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated
+            // flag); see <https://github.com/rust-lang/rust/issues/116851>.
+            features += ",+harden-sls-ijmp";
+            features += ",+harden-sls-ret";
+        }
+        ts.push("features", features);
+        ts.push("llvm-target", "x86_64-linux-gnu");
+        ts.push("supported-sanitizers", ["kcfi", "kernel-address"]);
+        if cfg.rustc_version_atleast(1, 91, 0) {
+            ts.push("target-pointer-width", 64);
+        } else {
+            ts.push("target-pointer-width", "64");
+        }
+    } else if cfg.has("X86_32") {
+        // This only works on UML, as i386 otherwise needs regparm support in rustc
+        if !cfg.has("UML") {
+            panic!("32-bit x86 only works under UML");
+        }
+        ts.push("arch", "x86");
+        if cfg.rustc_version_atleast(1, 98, 0) {
+            ts.push("rustc-abi", "softfloat");
+        } else if cfg.rustc_version_atleast(1, 86, 0) {
+            ts.push("rustc-abi", "x86-softfloat");
+        }
+        ts.push(
+            "data-layout",
+            "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128",
+        );
+        let mut features = "-mmx,+soft-float".to_string();
+        if cfg.has("MITIGATION_RETPOLINE") {
+            features += ",+retpoline-external-thunk";
+        }
+        ts.push("features", features);
+        ts.push("llvm-target", "i386-unknown-linux-gnu");
+        if cfg.rustc_version_atleast(1, 91, 0) {
+            ts.push("target-pointer-width", 32);
+        } else {
+            ts.push("target-pointer-width", "32");
+        }
+    } else if cfg.has("LOONGARCH") {
+        panic!("loongarch uses the builtin rustc loongarch64-unknown-none-softfloat target");
+    } else if cfg.has("S390") {
+        panic!("s390 uses the builtin rustc s390x-unknown-none-softfloat target");
+    } else {
+        panic!("Unsupported architecture");
+    }
+
+    ts.push("emit-debug-gdb-scripts", false);
+    ts.push("frame-pointer", "may-omit");
+    ts.push(
+        "stack-probes",
+        vec![("kind".to_string(), Value::String("none".to_string()))],
+    );
+
+    // Everything else is LE, whether `CPU_LITTLE_ENDIAN` is declared or not
+    // (e.g. x86). It is also `rustc`'s default.
+    if cfg.has("CPU_BIG_ENDIAN") {
+        ts.push("target-endian", "big");
+    }
+
+    println!("{}", ts);
+}