Flang currently lowers internal procedures passed as actual arguments using LLVM's `llvm.init.trampoline` / `llvm.adjust.trampoline` intrinsics, which require an executable stack. On modern Linux toolchains and security-hardened kernels that enforce W^X (Write XOR Execute), this causes link-time failures (`ld.lld: error: ... requires an executable stack`) or runtime `SEGV` from NX violations. This patch introduces a runtime trampoline pool that allocates trampolines from a dedicated `mmap`'d region instead of the stack. The pool toggles page permissions between writable (for patching) and executable (for dispatch), so the stack stays non-executable throughout. On macOS, MAP_JIT and `pthread_jit_write_protect_np` are used for the same effect. An i-cache flush (`__builtin___clear_cache` on Linux, `sys_icache_invalidate` on macOS) is performed after each write→exec transition. The feature is gated behind a new driver flag, `-fsafe-trampoline` (off by default), which threads through the frontend into the `BoxedProcedurePass`. When enabled, the pass emits calls to `_FortranATrampolineInit`, `_FortranATrampolineAdjust`, and `_FortranATrampolineFree` instead of the legacy intrinsics. The legacy path is completely untouched when the flag is off. The pool is a singleton with a fixed capacity (default 1024 slots, overridable via `FLANG_TRAMPOLINE_POOL_SIZE`). Slot size varies by target (32 bytes on x86-64/AArch64, 48 on PPC64, 64 fallback). Each slot holds a small architecture-specific stub, currently x86-64 (17 bytes, using `r10` as the nest/static-chain register) and AArch64 (24 bytes, using `x15`). The implementation compiles on all architectures but will crash at runtime with a clear diagnostic if trampoline emission is actually attempted on an unsupported target. This avoids breaking the flang-rt build on e.g. RISC-V or PPC64. Freed slots are poisoned (the callee pointer is overwritten with a sentinel) and recycled into a freelist, so the pool can sustain long-running programs that repeatedly create and destroy closures. A few design choices worth calling out: The runtime avoids all C++ runtime dependencies, no `std::mutex`, no `operator new`, no function-local statics with hidden guard variables. Locking is via flang-rt's own `Lock` / `CriticalSection`, memory is via `AllocateMemoryOrCrash` / `FreeMemory`, and the singleton uses explicit double-checked locking with a raw pointer. This was done so the trampoline pool links cleanly in minimal / freestanding flang-rt configurations. `_FortranATrampolineFree` calls are inserted immediately before every `func.return` in the enclosing host function. This is a conservative but correct strategy. The trampoline handle cannot outlive the host's stack frame since the closure captures the host's local variables by reference. The GNU_STACK note is verified via a dedicated integration test (`safe-trampoline-gnustack.f90`) that compiles and links a Fortran program using the runtime path, then inspects the ELF with `llvm-readelf` to confirm the stack segment is `RW` (not `RWE`). **Test coverage:** - `flang/test/Driver/fsafe-trampoline.f90` — flag forwarding (on, off, default) - `flang/test/Fir/boxproc-safe-trampoline.fir` — FIR-level FileCheck for emitted runtime calls - `flang/test/Lower/safe-trampoline.f90` — end-to-end lowering - `flang-rt/test/Driver/safe-trampoline-gnustack.f90` — GNU_STACK ELF verification Closes #182813 Co-authored-by: Sairudra More <moresair@pe31.hpc.amslabs.hpecorp.net>
83 lines
3.7 KiB
C++
83 lines
3.7 KiB
C++
//===-- CommandLineOpts.cpp -- shared command line options ------*- C++ -*-===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/// This file defines some shared command-line options that can be used when
|
|
/// debugging the test tools.
|
|
|
|
#include "flang/Optimizer/Passes/CommandLineOpts.h"
|
|
|
|
using namespace llvm;
|
|
|
|
#define DisableOption(DOName, DOOption, DODescription) \
|
|
cl::opt<bool> disable##DOName("disable-" DOOption, \
|
|
cl::desc("disable " DODescription " pass"), \
|
|
cl::init(false), cl::Hidden)
|
|
#define EnableOption(EOName, EOOption, EODescription) \
|
|
cl::opt<bool> enable##EOName("enable-" EOOption, \
|
|
cl::desc("enable " EODescription " pass"), \
|
|
cl::init(false), cl::Hidden)
|
|
|
|
cl::opt<bool> dynamicArrayStackToHeapAllocation(
|
|
"fdynamic-heap-array",
|
|
cl::desc("place all array allocations of dynamic size on the heap"),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
cl::opt<std::size_t> arrayStackAllocationThreshold(
|
|
"fstack-array-size",
|
|
cl::desc(
|
|
"place all array allocations more than <size> elements on the heap"),
|
|
cl::init(~static_cast<std::size_t>(0)), cl::Hidden);
|
|
|
|
cl::opt<bool> ignoreMissingTypeDescriptors(
|
|
"ignore-missing-type-desc",
|
|
cl::desc("ignore failures to find derived type descriptors when "
|
|
"translating FIR to LLVM"),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
cl::opt<bool> skipExternalRttiDefinition(
|
|
"skip-external-rtti-definition", llvm::cl::init(false),
|
|
llvm::cl::desc("do not define rtti static objects for types belonging to "
|
|
"other compilation units"),
|
|
cl::Hidden);
|
|
|
|
OptimizationLevel defaultOptLevel{OptimizationLevel::O0};
|
|
|
|
codegenoptions::DebugInfoKind noDebugInfo{codegenoptions::NoDebugInfo};
|
|
|
|
/// Optimizer Passes
|
|
DisableOption(CfgConversion, "cfg-conversion", "disable FIR to CFG pass");
|
|
DisableOption(FirAvc, "avc", "array value copy analysis and transformation");
|
|
DisableOption(FirMao, "memory-allocation-opt",
|
|
"memory allocation optimization");
|
|
|
|
DisableOption(FirAliasTags, "fir-alias-tags", "fir alias analysis");
|
|
cl::opt<bool> useOldAliasTags(
|
|
"use-old-alias-tags",
|
|
cl::desc("Use a single TBAA tree for all functions and do not use "
|
|
"the FIR alias tags pass"),
|
|
cl::init(false), cl::Hidden);
|
|
EnableOption(FirLICM, "fir-licm", "FIR loop invariant code motion");
|
|
|
|
/// CodeGen Passes
|
|
DisableOption(CodeGenRewrite, "codegen-rewrite", "rewrite FIR for codegen");
|
|
DisableOption(TargetRewrite, "target-rewrite", "rewrite FIR for target");
|
|
DisableOption(DebugInfo, "debug-info", "Add debug info");
|
|
DisableOption(FirToLlvmIr, "fir-to-llvmir", "FIR to LLVM-IR dialect");
|
|
DisableOption(LlvmIrToLlvm, "llvm", "conversion to LLVM");
|
|
DisableOption(BoxedProcedureRewrite, "boxed-procedure-rewrite",
|
|
"rewrite boxed procedures");
|
|
EnableOption(SafeTrampoline, "safe-trampoline",
|
|
"W^X compliant runtime trampoline pool");
|
|
|
|
DisableOption(ExternalNameConversion, "external-name-interop",
|
|
"convert names with external convention");
|
|
EnableOption(ConstantArgumentGlobalisation, "constant-argument-globalisation",
|
|
"the local constant argument to global constant conversion");
|
|
DisableOption(CompilerGeneratedNamesConversion, "compiler-generated-names",
|
|
"replace special symbols in compiler generated names");
|