Rollup merge of rust-lang#113355 - Zalathar:ssa, r=oli-obk

Move most coverage code out of `rustc_codegen_ssa`

*This is one step in my larger coverage refactoring ambitions described at <https://github.com/rust-lang/compiler-team/issues/645>.*

The backend implementation of coverage instrumentation was originally split between SSA and LLVM, perhaps in the hopes that it could be used by other backends.

In practice, this split mostly just makes the coverage implementation harder to navigate and harder to modify. It seems unlikely that any backend will actually implement coverage instrumentation in the foreseeable future, especially since many parts of the existing implementation (outside the LLVM backend) are heavily tied to the specific details of LLVM's coverage instrumentation features.

The current shared implementation of `codegen_coverage` is heavily tied to the details of `StatementKind::Coverage`, which makes those details difficult to change. I have reason to want to change those details as part of future fixes/improvements, so this will reduce the amount of interface churn caused by those later changes.

---

This is intended to be a pure refactoring change, with no changes to actual behaviour. All of the “added” code has really just been moved from other files.

Author: compiler-errors

compiler/rustc_codegen_gcc/src/coverageinfo.rs

@@ -1,69 +1,11 @@
-use gccjit::RValue;
-use rustc_codegen_ssa::traits::{CoverageInfoBuilderMethods, CoverageInfoMethods};
-use rustc_hir::def_id::DefId;
-use rustc_middle::mir::coverage::{
-    CodeRegion,
-    CounterValueReference,
-    ExpressionOperandId,
-    InjectedExpressionId,
-    Op,
-};
+use rustc_codegen_ssa::traits::CoverageInfoBuilderMethods;
+use rustc_middle::mir::Coverage;
 use rustc_middle::ty::Instance;
 
 use crate::builder::Builder;
-use crate::context::CodegenCx;
 
 impl<'a, 'gcc, 'tcx> CoverageInfoBuilderMethods<'tcx> for Builder<'a, 'gcc, 'tcx> {
-    fn set_function_source_hash(
-        &mut self,
-        _instance: Instance<'tcx>,
-        _function_source_hash: u64,
-    ) -> bool {
-        unimplemented!();
-    }
-
-    fn add_coverage_counter(&mut self, _instance: Instance<'tcx>, _id: CounterValueReference, _region: CodeRegion) -> bool {
-        // TODO(antoyo)
-        false
-    }
-
-    fn add_coverage_counter_expression(&mut self, _instance: Instance<'tcx>, _id: InjectedExpressionId, _lhs: ExpressionOperandId, _op: Op, _rhs: ExpressionOperandId, _region: Option<CodeRegion>) -> bool {
-        // TODO(antoyo)
-        false
-    }
-
-    fn add_coverage_unreachable(&mut self, _instance: Instance<'tcx>, _region: CodeRegion) -> bool {
+    fn add_coverage(&mut self, _instance: Instance<'tcx>, _coverage: &Coverage) {
         // TODO(antoyo)
-        false
-    }
-}
-
-impl<'gcc, 'tcx> CoverageInfoMethods<'tcx> for CodegenCx<'gcc, 'tcx> {
-    fn coverageinfo_finalize(&self) {
-        // TODO(antoyo)
-    }
-
-    fn get_pgo_func_name_var(&self, _instance: Instance<'tcx>) -> RValue<'gcc> {
-        unimplemented!();
-    }
-
-    /// Functions with MIR-based coverage are normally codegenned _only_ if
-    /// called. LLVM coverage tools typically expect every function to be
-    /// defined (even if unused), with at least one call to LLVM intrinsic
-    /// `instrprof.increment`.
-    ///
-    /// Codegen a small function that will never be called, with one counter
-    /// that will never be incremented.
-    ///
-    /// For used/called functions, the coverageinfo was already added to the
-    /// `function_coverage_map` (keyed by function `Instance`) during codegen.
-    /// But in this case, since the unused function was _not_ previously
-    /// codegenned, collect the coverage `CodeRegion`s from the MIR and add
-    /// them. The first `CodeRegion` is used to add a single counter, with the
-    /// same counter ID used in the injected `instrprof.increment` intrinsic
-    /// call. Since the function is never called, all other `CodeRegion`s can be
-    /// added as `unreachable_region`s.
-    fn define_unused_fn(&self, _def_id: DefId) {
-        unimplemented!();
     }
 }

compiler/rustc_codegen_ssa/src/coverageinfo/ffi.rs renamed to compiler/rustc_codegen_llvm/src/coverageinfo/ffi.rs

@@ -1,6 +1,7 @@
 pub use super::ffi::*;
 
 use rustc_index::{IndexSlice, IndexVec};
+use rustc_middle::bug;
 use rustc_middle::mir::coverage::{
     CodeRegion, CounterValueReference, ExpressionOperandId, InjectedExpressionId,
     InjectedExpressionIndex, MappedExpressionIndex, Op,

compiler/rustc_codegen_ssa/src/coverageinfo/map.rs renamed to compiler/rustc_codegen_llvm/src/coverageinfo/map_data.rs

@@ -1,10 +1,10 @@
 use crate::common::CodegenCx;
 use crate::coverageinfo;
+use crate::coverageinfo::map_data::{Counter, CounterExpression};
 use crate::llvm;
 
 use llvm::coverageinfo::CounterMappingRegion;
-use rustc_codegen_ssa::coverageinfo::map::{Counter, CounterExpression};
-use rustc_codegen_ssa::traits::{ConstMethods, CoverageInfoMethods};
+use rustc_codegen_ssa::traits::ConstMethods;
 use rustc_data_structures::fx::FxIndexSet;
 use rustc_hir::def::DefKind;
 use rustc_hir::def_id::DefId;

compiler/rustc_codegen_llvm/src/coverageinfo/mapgen.rs

@@ -3,30 +3,33 @@ use crate::llvm;
 use crate::abi::Abi;
 use crate::builder::Builder;
 use crate::common::CodegenCx;
+use crate::coverageinfo::map_data::{CounterExpression, FunctionCoverage};
 
 use libc::c_uint;
 use llvm::coverageinfo::CounterMappingRegion;
-use rustc_codegen_ssa::coverageinfo::map::{CounterExpression, FunctionCoverage};
 use rustc_codegen_ssa::traits::{
-    BaseTypeMethods, BuilderMethods, ConstMethods, CoverageInfoBuilderMethods, CoverageInfoMethods,
-    MiscMethods, StaticMethods,
+    BaseTypeMethods, BuilderMethods, ConstMethods, CoverageInfoBuilderMethods, MiscMethods,
+    StaticMethods,
 };
 use rustc_data_structures::fx::FxHashMap;
 use rustc_hir as hir;
 use rustc_hir::def_id::DefId;
 use rustc_llvm::RustString;
 use rustc_middle::bug;
 use rustc_middle::mir::coverage::{
-    CodeRegion, CounterValueReference, ExpressionOperandId, InjectedExpressionId, Op,
+    CodeRegion, CounterValueReference, CoverageKind, ExpressionOperandId, InjectedExpressionId, Op,
 };
+use rustc_middle::mir::Coverage;
 use rustc_middle::ty;
-use rustc_middle::ty::layout::FnAbiOf;
+use rustc_middle::ty::layout::{FnAbiOf, HasTyCtxt};
 use rustc_middle::ty::subst::InternalSubsts;
 use rustc_middle::ty::Instance;
 
 use std::cell::RefCell;
 use std::ffi::CString;
 
+mod ffi;
+pub(crate) mod map_data;
 pub mod mapgen;
 
 const UNUSED_FUNCTION_COUNTER_ID: CounterValueReference = CounterValueReference::START;
@@ -53,11 +56,17 @@ impl<'ll, 'tcx> CrateCoverageContext<'ll, 'tcx> {
     }
 }
 
-impl<'ll, 'tcx> CoverageInfoMethods<'tcx> for CodegenCx<'ll, 'tcx> {
-    fn coverageinfo_finalize(&self) {
+// These methods used to be part of trait `CoverageInfoMethods`, which no longer
+// exists after most coverage code was moved out of SSA.
+impl<'ll, 'tcx> CodegenCx<'ll, 'tcx> {
+    pub(crate) fn coverageinfo_finalize(&self) {
         mapgen::finalize(self)
     }
 
+    /// For LLVM codegen, returns a function-specific `Value` for a global
+    /// string, to hold the function name passed to LLVM intrinsic
+    /// `instrprof.increment()`. The `Value` is only created once per instance.
+    /// Multiple invocations with the same instance return the same `Value`.
     fn get_pgo_func_name_var(&self, instance: Instance<'tcx>) -> &'ll llvm::Value {
         if let Some(coverage_context) = self.coverage_context() {
             debug!("getting pgo_func_name_var for instance={:?}", instance);
@@ -94,6 +103,54 @@ impl<'ll, 'tcx> CoverageInfoMethods<'tcx> for CodegenCx<'ll, 'tcx> {
 }
 
 impl<'tcx> CoverageInfoBuilderMethods<'tcx> for Builder<'_, '_, 'tcx> {
+    fn add_coverage(&mut self, instance: Instance<'tcx>, coverage: &Coverage) {
+        let bx = self;
+
+        let Coverage { kind, code_region } = coverage.clone();
+        match kind {
+            CoverageKind::Counter { function_source_hash, id } => {
+                if bx.set_function_source_hash(instance, function_source_hash) {
+                    // If `set_function_source_hash()` returned true, the coverage map is enabled,
+                    // so continue adding the counter.
+                    if let Some(code_region) = code_region {
+                        // Note: Some counters do not have code regions, but may still be referenced
+                        // from expressions. In that case, don't add the counter to the coverage map,
+                        // but do inject the counter intrinsic.
+                        bx.add_coverage_counter(instance, id, code_region);
+                    }
+
+                    let coverageinfo = bx.tcx().coverageinfo(instance.def);
+
+                    let fn_name = bx.get_pgo_func_name_var(instance);
+                    let hash = bx.const_u64(function_source_hash);
+                    let num_counters = bx.const_u32(coverageinfo.num_counters);
+                    let index = bx.const_u32(id.zero_based_index());
+                    debug!(
+                        "codegen intrinsic instrprof.increment(fn_name={:?}, hash={:?}, num_counters={:?}, index={:?})",
+                        fn_name, hash, num_counters, index,
+                    );
+                    bx.instrprof_increment(fn_name, hash, num_counters, index);
+                }
+            }
+            CoverageKind::Expression { id, lhs, op, rhs } => {
+                bx.add_coverage_counter_expression(instance, id, lhs, op, rhs, code_region);
+            }
+            CoverageKind::Unreachable => {
+                bx.add_coverage_unreachable(
+                    instance,
+                    code_region.expect("unreachable regions always have code regions"),
+                );
+            }
+        }
+    }
+}
+
+// These methods used to be part of trait `CoverageInfoBuilderMethods`, but
+// after moving most coverage code out of SSA they are now just ordinary methods.
+impl<'tcx> Builder<'_, '_, 'tcx> {
+    /// Returns true if the function source hash was added to the coverage map (even if it had
+    /// already been added, for this instance). Returns false *only* if `-C instrument-coverage` is
+    /// not enabled (a coverage map is not being generated).
     fn set_function_source_hash(
         &mut self,
         instance: Instance<'tcx>,
@@ -115,6 +172,8 @@ impl<'tcx> CoverageInfoBuilderMethods<'tcx> for Builder<'_, '_, 'tcx> {
         }
     }
 
+    /// Returns true if the counter was added to the coverage map; false if `-C instrument-coverage`
+    /// is not enabled (a coverage map is not being generated).
     fn add_coverage_counter(
         &mut self,
         instance: Instance<'tcx>,
@@ -137,6 +196,8 @@ impl<'tcx> CoverageInfoBuilderMethods<'tcx> for Builder<'_, '_, 'tcx> {
         }
     }
 
+    /// Returns true if the expression was added to the coverage map; false if
+    /// `-C instrument-coverage` is not enabled (a coverage map is not being generated).
     fn add_coverage_counter_expression(
         &mut self,
         instance: Instance<'tcx>,
@@ -163,6 +224,8 @@ impl<'tcx> CoverageInfoBuilderMethods<'tcx> for Builder<'_, '_, 'tcx> {
         }
     }
 
+    /// Returns true if the region was added to the coverage map; false if `-C instrument-coverage`
+    /// is not enabled (a coverage map is not being generated).
     fn add_coverage_unreachable(&mut self, instance: Instance<'tcx>, region: CodeRegion) -> bool {
         if let Some(coverage_context) = self.coverage_context() {
             debug!(

compiler/rustc_codegen_llvm/src/coverageinfo/mod.rs

@@ -1,7 +1,7 @@
 #![allow(non_camel_case_types)]
 #![allow(non_upper_case_globals)]
 
-use rustc_codegen_ssa::coverageinfo::map as coverage_map;
+use crate::coverageinfo::map_data as coverage_map;
 
 use super::debuginfo::{
     DIArray, DIBasicType, DIBuilder, DICompositeType, DIDerivedType, DIDescriptor, DIEnumerator,

compiler/rustc_codegen_llvm/src/llvm/ffi.rs

@@ -48,7 +48,6 @@ pub mod back;
 pub mod base;
 pub mod codegen_attrs;
 pub mod common;
-pub mod coverageinfo;
 pub mod debuginfo;
 pub mod errors;
 pub mod glue;

compiler/rustc_codegen_ssa/src/coverageinfo/mod.rs

@@ -1,55 +1,20 @@
 use crate::traits::*;
 
-use rustc_middle::mir::coverage::*;
 use rustc_middle::mir::Coverage;
 use rustc_middle::mir::SourceScope;
 
 use super::FunctionCx;
 
 impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
-    pub fn codegen_coverage(&self, bx: &mut Bx, coverage: Coverage, scope: SourceScope) {
+    pub fn codegen_coverage(&self, bx: &mut Bx, coverage: &Coverage, scope: SourceScope) {
         // Determine the instance that coverage data was originally generated for.
         let instance = if let Some(inlined) = scope.inlined_instance(&self.mir.source_scopes) {
             self.monomorphize(inlined)
         } else {
             self.instance
         };
 
-        let Coverage { kind, code_region } = coverage;
-        match kind {
-            CoverageKind::Counter { function_source_hash, id } => {
-                if bx.set_function_source_hash(instance, function_source_hash) {
-                    // If `set_function_source_hash()` returned true, the coverage map is enabled,
-                    // so continue adding the counter.
-                    if let Some(code_region) = code_region {
-                        // Note: Some counters do not have code regions, but may still be referenced
-                        // from expressions. In that case, don't add the counter to the coverage map,
-                        // but do inject the counter intrinsic.
-                        bx.add_coverage_counter(instance, id, code_region);
-                    }
-
-                    let coverageinfo = bx.tcx().coverageinfo(instance.def);
-
-                    let fn_name = bx.get_pgo_func_name_var(instance);
-                    let hash = bx.const_u64(function_source_hash);
-                    let num_counters = bx.const_u32(coverageinfo.num_counters);
-                    let index = bx.const_u32(id.zero_based_index());
-                    debug!(
-                        "codegen intrinsic instrprof.increment(fn_name={:?}, hash={:?}, num_counters={:?}, index={:?})",
-                        fn_name, hash, num_counters, index,
-                    );
-                    bx.instrprof_increment(fn_name, hash, num_counters, index);
-                }
-            }
-            CoverageKind::Expression { id, lhs, op, rhs } => {
-                bx.add_coverage_counter_expression(instance, id, lhs, op, rhs, code_region);
-            }
-            CoverageKind::Unreachable => {
-                bx.add_coverage_unreachable(
-                    instance,
-                    code_region.expect("unreachable regions always have code regions"),
-                );
-            }
-        }
+        // Handle the coverage info in a backend-specific way.
+        bx.add_coverage(instance, coverage);
     }
 }

compiler/rustc_codegen_ssa/src/lib.rs

@@ -65,7 +65,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
                 }
             }
             mir::StatementKind::Coverage(box ref coverage) => {
-                self.codegen_coverage(bx, coverage.clone(), statement.source_info.scope);
+                self.codegen_coverage(bx, coverage, statement.source_info.scope);
             }
             mir::StatementKind::Intrinsic(box NonDivergingIntrinsic::Assume(ref op)) => {
                 let op_val = self.codegen_operand(bx, op);