Auto merge of #122597 - pacak:master, r=bjorn3

Show files produced by `--emit foo` in json artifact notifications

Right now it is possible to ask `rustc` to save some intermediate representation into one or more files with `--emit=foo`, but figuring out what exactly was produced is difficult. This pull request adds information about `llvm_ir` and `asm` intermediate files into notifications produced by `--json=artifacts`.

Related discussion: https://internals.rust-lang.org/t/easier-access-to-files-generated-by-emit-foo/20477

Motivation - `cargo-show-asm` parses those intermediate files and presents them in a user friendly way, but right now I have to apply some dirty hacks. Hacks make behavior confusing: https://github.com/hintron/computer-enhance/issues/35

This pull request introduces a new behavior: now `rustc` will emit a new artifact notification for every artifact type user asked to `--emit`, for example for `--emit asm` those will include all the `.s` files.

Most users won't notice this behavior, to be affected by it all of the following must hold:
- user must use `rustc` binary directly (when `cargo` invokes `rustc` - it consumes artifact notifications and doesn't emit anything)
- user must specify both `--emit xxx` and `--json artifacts`
- user must refuse to handle unknown artifact types
- user must disable incremental compilation (or deal with it better than cargo does, or use a workaround like `save-temps`) in order not to hit #88829 / #89149

compiler/rustc_codegen_cranelift/src/driver/aot.rs

@@ -288,6 +288,29 @@ fn produce_final_output_artifacts(
         }
     }
 
+    if sess.opts.json_artifact_notifications {
+        if codegen_results.modules.len() == 1 {
+            codegen_results.modules[0].for_each_output(|_path, ty| {
+                if sess.opts.output_types.contains_key(&ty) {
+                    let descr = ty.shorthand();
+                    // for single cgu file is renamed to drop cgu specific suffix
+                    // so we regenerate it the same way
+                    let path = crate_output.path(ty);
+                    sess.dcx().emit_artifact_notification(path.as_path(), descr);
+                }
+            });
+        } else {
+            for module in &codegen_results.modules {
+                module.for_each_output(|path, ty| {
+                    if sess.opts.output_types.contains_key(&ty) {
+                        let descr = ty.shorthand();
+                        sess.dcx().emit_artifact_notification(&path, descr);
+                    }
+                });
+            }
+        }
+    }
+
     // We leave the following files around by default:
     //  - #crate#.o
     //  - #crate#.crate.metadata.o

compiler/rustc_codegen_ssa/src/back/write.rs

@@ -717,6 +717,29 @@ fn produce_final_output_artifacts(
         }
     }
 
+    if sess.opts.json_artifact_notifications {
+        if compiled_modules.modules.len() == 1 {
+            compiled_modules.modules[0].for_each_output(|_path, ty| {
+                if sess.opts.output_types.contains_key(&ty) {
+                    let descr = ty.shorthand();
+                    // for single cgu file is renamed to drop cgu specific suffix
+                    // so we regenerate it the same way
+                    let path = crate_output.path(ty);
+                    sess.dcx().emit_artifact_notification(path.as_path(), descr);
+                }
+            });
+        } else {
+            for module in &compiled_modules.modules {
+                module.for_each_output(|path, ty| {
+                    if sess.opts.output_types.contains_key(&ty) {
+                        let descr = ty.shorthand();
+                        sess.dcx().emit_artifact_notification(&path, descr);
+                    }
+                });
+            }
+        }
+    }
+
     // We leave the following files around by default:
     //  - #crate#.o
     //  - #crate#.crate.metadata.o

compiler/rustc_codegen_ssa/src/lib.rs

@@ -106,6 +106,24 @@ pub struct CompiledModule {
     pub llvm_ir: Option<PathBuf>,  // --emit=llvm-ir, llvm-bc is in bytecode
 }
 
+impl CompiledModule {
+    /// Call `emit` function with every artifact type currently compiled
+    pub fn for_each_output(&self, mut emit: impl FnMut(&Path, OutputType)) {
+        if let Some(path) = self.object.as_deref() {
+            emit(path, OutputType::Object);
+        }
+        if let Some(path) = self.bytecode.as_deref() {
+            emit(path, OutputType::Bitcode);
+        }
+        if let Some(path) = self.llvm_ir.as_deref() {
+            emit(path, OutputType::LlvmAssembly);
+        }
+        if let Some(path) = self.assembly.as_deref() {
+            emit(path, OutputType::Assembly);
+        }
+    }
+}
+
 pub struct CachedModuleCodegen {
     pub name: String,
     pub source: WorkProduct,

compiler/rustc_mir_transform/src/dump_mir.rs

@@ -28,6 +28,9 @@ pub fn emit_mir(tcx: TyCtxt<'_>) -> io::Result<()> {
         OutFileName::Real(path) => {
             let mut f = io::BufWriter::new(File::create(&path)?);
             write_mir_pretty(tcx, None, &mut f)?;
+            if tcx.sess.opts.json_artifact_notifications {
+                tcx.dcx().emit_artifact_notification(&path, "mir");
+            }
         }
     }
     Ok(())

src/doc/rustc/src/json.md

@@ -217,7 +217,8 @@ Diagnostics have the following format:
 Artifact notifications are emitted when the [`--json=artifacts`
 flag][option-json] is used. They indicate that a file artifact has been saved
 to disk. More information about emit kinds may be found in the [`--emit`
-flag][option-emit] documentation.
+flag][option-emit] documentation. Notifications can contain more than one file
+for each type, for example when using multiple codegen units.
 
 ```javascript
 {
@@ -229,6 +230,11 @@ flag][option-emit] documentation.
        - "link": The generated crate as specified by the crate-type.
        - "dep-info": The `.d` file with dependency information in a Makefile-like syntax.
        - "metadata": The Rust `.rmeta` file containing metadata about the crate.
+       - "asm": The `.s` file with generated assembly
+       - "llvm-ir": The `.ll` file with generated textual LLVM IR
+       - "llvm-bc": The `.bc` file with generated LLVM bitcode
+       - "mir": The `.mir` file with rustc's mid-level intermediate representation.
+       - "obj": The `.o` file with generated native object code
     */
     "emit": "link"
 }

tests/run-make/notify-all-emit-artifacts/lib.rs

@@ -0,0 +1,21 @@
+fn one() -> usize {
+    1
+}
+
+pub mod a {
+    pub fn two() -> usize {
+        ::one() + ::one()
+    }
+}
+
+pub mod b {
+    pub fn three() -> usize {
+        ::one() + ::a::two()
+    }
+}
+
+#[inline(never)]
+pub fn main() {
+    a::two();
+    b::three();
+}

tests/run-make/notify-all-emit-artifacts/rmake.rs

@@ -0,0 +1,45 @@
+// rust should produce artifact notifications about files it was asked to --emit.
+//
+// It should work in incremental mode both on the first pass where files are generated as well
+// as on subsequent passes where they are taken from the incremental cache
+//
+// See <https://internals.rust-lang.org/t/easier-access-to-files-generated-by-emit-foo/20477>
+extern crate run_make_support;
+
+use run_make_support::{rustc, tmp_dir};
+
+fn main() {
+    let inc_dir = tmp_dir();
+
+    // With single codegen unit files are renamed to match the source file name
+    for _ in 0..=1 {
+        let output = rustc()
+            .input("lib.rs")
+            .emit("obj,asm,llvm-ir,llvm-bc,mir")
+            .codegen_units(1)
+            .json("artifacts")
+            .error_format("json")
+            .incremental(&inc_dir)
+            .run();
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        for file in &["lib.o", "lib.ll", "lib.bc", "lib.s"] {
+            assert!(stderr.contains(file), "No {:?} in {:?}", file, stderr);
+        }
+    }
+
+    // with multiple codegen units files keep codegen unit id part.
+    for _ in 0..=1 {
+        let output = rustc()
+            .input("lib.rs")
+            .emit("obj,asm,llvm-ir,llvm-bc,mir")
+            .codegen_units(2)
+            .json("artifacts")
+            .error_format("json")
+            .incremental(&inc_dir)
+            .run();
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        for file in &["rcgu.o", "rcgu.ll", "rcgu.bc", "rcgu.s"] {
+            assert!(stderr.contains(file), "No {:?} in {:?}", file, stderr);
+        }
+    }
+}