Auto merge of rust-lang#69718 - arlosi:debughash, r=eddyb

Add hash of source files in debug info

LLVM supports placing the hash of source files inside the debug info.
This information can be used by a debugger to verify that the source code matches
the executable.

This change adds support for both hash algorithms supported by LLVM, MD5 and SHA1, controlled by a target option.

* DWARF only supports MD5
* LLVM IR supports MD5 and SHA1 (and SHA256 in LLVM 11).
* CodeView (.PDB) supports MD5, SHA1, and SHA256.

Fixes rust-lang#68980.

Tracking issue: rust-lang#70401

rustc dev guide PR with further details: rust-lang/rustc-dev-guide#623

Author: bors

Cargo.lock

@@ -87,12 +87,6 @@ dependencies = [
  "scoped_threadpool",
 ]
 
-[[package]]
-name = "arrayref"
-version = "0.3.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d382e583f07208808f6b1249e60848879ba3543f57c32277bf52d69c2f0f0ee"
-
 [[package]]
 name = "arrayvec"
 version = "0.4.7"
@@ -187,11 +181,22 @@ dependencies = [
 
 [[package]]
 name = "block-buffer"
-version = "0.3.3"
+version = "0.7.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0940dc441f31689269e10ac70eb1002a3a1d3ad1390e030043662eb7fe4688b"
+dependencies = [
+ "block-padding",
+ "byte-tools",
+ "byteorder",
+ "generic-array",
+]
+
+[[package]]
+name = "block-padding"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a076c298b9ecdb530ed9d967e74a6027d6a7478924520acddcddc24c1c8ab3ab"
+checksum = "fa79dedbb091f449f1f39e53edf88d5dbe95f895dae6135a8d7b881fb5af73f5"
 dependencies = [
- "arrayref",
  "byte-tools",
 ]
 
@@ -240,9 +245,9 @@ version = "0.1.0"
 
 [[package]]
 name = "byte-tools"
-version = "0.2.0"
+version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "560c32574a12a89ecd91f5e742165893f86e3ab98d21f8ea548658eb9eef5f40"
+checksum = "e3b5ca7a04898ad4bcd41c90c5285445ff5b791899bb1b0abdd2a2aa791211d7"
 
 [[package]]
 name = "bytecount"
@@ -897,9 +902,9 @@ checksum = "524cbf6897b527295dff137cec09ecf3a05f4fddffd7dfcd1585403449e74198"
 
 [[package]]
 name = "digest"
-version = "0.7.6"
+version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03b072242a8cbaf9c145665af9d250c59af3b958f83ed6824e13533cf76d5b90"
+checksum = "f3d0c8c8752312f9713efd397ff63acb9f85585afbf179282e720e7704954dd5"
 dependencies = [
  "generic-array",
 ]
@@ -1226,9 +1231,9 @@ dependencies = [
 
 [[package]]
 name = "generic-array"
-version = "0.9.0"
+version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef25c5683767570c2bbd7deba372926a55eaae9982d7726ee2a1050239d45b9d"
+checksum = "c68f0274ae0e023facc3c97b2e00f076be70e254bc851d972503b328db79b2ec"
 dependencies = [
  "typenum",
 ]
@@ -1962,6 +1967,17 @@ version = "0.1.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7ffc5c5338469d4d3ea17d269fa8ea3512ad247247c30bd2df69e68309ed0a08"
 
+[[package]]
+name = "md-5"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a18af3dcaf2b0219366cdb4e2af65a6101457b415c3d1a5c71dd9c2b7c77b9c8"
+dependencies = [
+ "block-buffer",
+ "digest",
+ "opaque-debug",
+]
+
 [[package]]
 name = "mdbook"
 version = "0.3.5"
@@ -2250,6 +2266,12 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d6a04cb71e910d0034815600180f62a95bf6e67942d7ab52a166a68c7d7e9cd0"
 
+[[package]]
+name = "opaque-debug"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2839e79665f131bdb5782e51f2c6c9599c133c6098982a54c794358bf432529c"
+
 [[package]]
 name = "open"
 version = "1.2.1"
@@ -2467,9 +2489,9 @@ dependencies = [
 
 [[package]]
 name = "pest_meta"
-version = "2.1.0"
+version = "2.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f5a3492a4ed208ffc247adcdcc7ba2a95be3104f58877d0d02f0df39bf3efb5e"
+checksum = "54be6e404f5317079812fc8f9f5279de376d8856929e21c184ecf6bbd692a11d"
 dependencies = [
  "maplit",
  "pest",
@@ -4155,11 +4177,13 @@ dependencies = [
  "arena",
  "cfg-if",
  "log",
+ "md-5",
  "rustc_data_structures",
  "rustc_index",
  "rustc_macros",
  "scoped-tls",
  "serialize",
+ "sha-1",
  "unicode-width",
 ]
 
@@ -4535,14 +4559,14 @@ dependencies = [
 
 [[package]]
 name = "sha-1"
-version = "0.7.0"
+version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "51b9d1f3b5de8a167ab06834a7c883bd197f2191e1dda1a22d9ccfeedbf9aded"
+checksum = "f7d94d0bede923b3cea61f3f1ff57ff8cdfd77b400fb8f9998949e0cf04163df"
 dependencies = [
  "block-buffer",
- "byte-tools",
  "digest",
  "fake-simd",
+ "opaque-debug",
 ]
 
 [[package]]

src/doc/unstable-book/src/compiler-flags/src-hash-algorithm.md

@@ -0,0 +1,11 @@
+# `src-hash-algorithm`
+
+The tracking issue for this feature is: [#70401](https://github.com/rust-lang/rust/issues/70401).
+
+------------------------
+
+The `-Z src-hash-algorithm` compiler flag controls which algorithm is used when hashing each source file. The hash is stored in the debug info and can be used by a debugger to verify the source code matches the executable.
+
+Supported hash algorithms are: `md5`, and `sha1`. Note that not all hash algorithms are supported by all debug info formats.
+
+By default, the compiler chooses the hash algorithm based on the target specification.

src/librustc_codegen_llvm/debuginfo/metadata.rs

@@ -41,7 +41,7 @@ use rustc_middle::ty::{self, AdtKind, ParamEnv, Ty, TyCtxt};
 use rustc_middle::{bug, span_bug};
 use rustc_session::config::{self, DebugInfo};
 use rustc_span::symbol::{Interner, Symbol};
-use rustc_span::{self, FileName, Span};
+use rustc_span::{self, FileName, SourceFileHash, Span};
 use rustc_target::abi::{Abi, Align, DiscriminantKind, HasDataLayout, Integer, LayoutOf};
 use rustc_target::abi::{Int, Pointer, F32, F64};
 use rustc_target::abi::{Primitive, Size, VariantIdx, Variants};
@@ -751,13 +751,23 @@ pub fn type_metadata(cx: &CodegenCx<'ll, 'tcx>, t: Ty<'tcx>, usage_site_span: Sp
     metadata
 }
 
+fn hex_encode(data: &[u8]) -> String {
+    let mut hex_string = String::with_capacity(data.len() * 2);
+    for byte in data.iter() {
+        write!(&mut hex_string, "{:02x}", byte).unwrap();
+    }
+    hex_string
+}
+
 pub fn file_metadata(
     cx: &CodegenCx<'ll, '_>,
     file_name: &FileName,
     defining_crate: CrateNum,
 ) -> &'ll DIFile {
     debug!("file_metadata: file_name: {}, defining_crate: {}", file_name, defining_crate);
 
+    let source_file = cx.sess().source_map().get_source_file(file_name);
+    let hash = source_file.as_ref().map(|f| &f.src_hash);
     let file_name = Some(file_name.to_string());
     let directory = if defining_crate == LOCAL_CRATE {
         Some(cx.sess().working_dir.0.to_string_lossy().to_string())
@@ -766,17 +776,18 @@ pub fn file_metadata(
         // independent of the compiler's working directory one way or another.
         None
     };
-    file_metadata_raw(cx, file_name, directory)
+    file_metadata_raw(cx, file_name, directory, hash)
 }
 
 pub fn unknown_file_metadata(cx: &CodegenCx<'ll, '_>) -> &'ll DIFile {
-    file_metadata_raw(cx, None, None)
+    file_metadata_raw(cx, None, None, None)
 }
 
 fn file_metadata_raw(
     cx: &CodegenCx<'ll, '_>,
     file_name: Option<String>,
     directory: Option<String>,
+    hash: Option<&SourceFileHash>,
 ) -> &'ll DIFile {
     let key = (file_name, directory);
 
@@ -789,13 +800,27 @@ fn file_metadata_raw(
             let file_name = file_name.as_deref().unwrap_or("<unknown>");
             let directory = directory.as_deref().unwrap_or("");
 
+            let (hash_kind, hash_value) = match hash {
+                Some(hash) => {
+                    let kind = match hash.kind {
+                        rustc_span::SourceFileHashAlgorithm::Md5 => llvm::ChecksumKind::MD5,
+                        rustc_span::SourceFileHashAlgorithm::Sha1 => llvm::ChecksumKind::SHA1,
+                    };
+                    (kind, hex_encode(hash.hash_bytes()))
+                }
+                None => (llvm::ChecksumKind::None, String::new()),
+            };
+
             let file_metadata = unsafe {
                 llvm::LLVMRustDIBuilderCreateFile(
                     DIB(cx),
                     file_name.as_ptr().cast(),
                     file_name.len(),
                     directory.as_ptr().cast(),
                     directory.len(),
+                    hash_kind,
+                    hash_value.as_ptr().cast(),
+                    hash_value.len(),
                 )
             };
 
@@ -920,6 +945,9 @@ pub fn compile_unit_metadata(
             name_in_debuginfo.len(),
             work_dir.as_ptr().cast(),
             work_dir.len(),
+            llvm::ChecksumKind::None,
+            ptr::null(),
+            0,
         );
 
         let unit_metadata = llvm::LLVMRustDIBuilderCreateCompileUnit(

src/librustc_codegen_llvm/llvm/ffi.rs

@@ -546,6 +546,15 @@ pub enum ThreadLocalMode {
     LocalExec,
 }
 
+/// LLVMRustChecksumKind
+#[derive(Copy, Clone)]
+#[repr(C)]
+pub enum ChecksumKind {
+    None,
+    MD5,
+    SHA1,
+}
+
 extern "C" {
     type Opaque;
 }
@@ -1640,6 +1649,9 @@ extern "C" {
         FilenameLen: size_t,
         Directory: *const c_char,
         DirectoryLen: size_t,
+        CSKind: ChecksumKind,
+        Checksum: *const c_char,
+        ChecksumLen: size_t,
     ) -> &'a DIFile;
 
     pub fn LLVMRustDIBuilderCreateSubroutineType(

src/librustc_interface/util.rs

@@ -22,7 +22,7 @@ use rustc_session::parse::CrateConfig;
 use rustc_session::CrateDisambiguator;
 use rustc_session::{config, early_error, filesearch, output, DiagnosticOutput, Session};
 use rustc_span::edition::Edition;
-use rustc_span::source_map::{FileLoader, RealFileLoader, SourceMap};
+use rustc_span::source_map::{FileLoader, SourceMap};
 use rustc_span::symbol::{sym, Symbol};
 use smallvec::SmallVec;
 use std::env;
@@ -62,15 +62,13 @@ pub fn create_session(
     lint_caps: FxHashMap<lint::LintId, lint::Level>,
     descriptions: Registry,
 ) -> (Lrc<Session>, Lrc<Box<dyn CodegenBackend>>, Lrc<SourceMap>) {
-    let loader = file_loader.unwrap_or(box RealFileLoader);
-    let source_map = Lrc::new(SourceMap::with_file_loader(loader, sopts.file_path_mapping()));
-    let mut sess = session::build_session_with_source_map(
+    let (mut sess, source_map) = session::build_session_with_source_map(
         sopts,
         input_path,
         descriptions,
-        source_map.clone(),
         diagnostic_output,
         lint_caps,
+        file_loader,
     );
 
     let codegen_backend = get_codegen_backend(&sess);

src/librustc_middle/ich/impls_syntax.rs

@@ -61,7 +61,7 @@ impl<'a> HashStable<StableHashingContext<'a>> for SourceFile {
             cnum,
             // Do not hash the source as it is not encoded
             src: _,
-            src_hash,
+            ref src_hash,
             external_src: _,
             start_pos,
             end_pos: _,

src/librustc_session/config.rs

@@ -18,9 +18,10 @@ use rustc_feature::UnstableFeatures;
 use rustc_span::edition::{Edition, DEFAULT_EDITION, EDITION_NAME_LIST};
 use rustc_span::source_map::{FileName, FilePathMapping};
 use rustc_span::symbol::{sym, Symbol};
+use rustc_span::SourceFileHashAlgorithm;
 
 use rustc_errors::emitter::HumanReadableErrorType;
-use rustc_errors::{ColorConfig, FatalError, Handler, HandlerFlags};
+use rustc_errors::{ColorConfig, HandlerFlags};
 
 use std::collections::btree_map::{
     Iter as BTreeMapIter, Keys as BTreeMapKeysIter, Values as BTreeMapValuesIter,
@@ -748,25 +749,30 @@ pub fn build_configuration(sess: &Session, mut user_cfg: CrateConfig) -> CrateCo
     user_cfg
 }
 
-pub fn build_target_config(opts: &Options, sp: &Handler) -> Config {
+pub fn build_target_config(opts: &Options, error_format: ErrorOutputType) -> Config {
     let target = Target::search(&opts.target_triple).unwrap_or_else(|e| {
-        sp.struct_fatal(&format!("Error loading target specification: {}", e))
-            .help("Use `--print target-list` for a list of built-in targets")
-            .emit();
-        FatalError.raise();
+        early_error(
+            error_format,
+            &format!(
+                "Error loading target specification: {}. \
+            Use `--print target-list` for a list of built-in targets",
+                e
+            ),
+        )
     });
 
     let ptr_width = match &target.target_pointer_width[..] {
         "16" => 16,
         "32" => 32,
         "64" => 64,
-        w => sp
-            .fatal(&format!(
+        w => early_error(
+            error_format,
+            &format!(
                 "target specification was invalid: \
              unrecognized target-pointer-width {}",
                 w
-            ))
-            .raise(),
+            ),
+        ),
     };
 
     Config { target, ptr_width }
@@ -1971,7 +1977,8 @@ impl PpMode {
 crate mod dep_tracking {
     use super::{
         CFGuard, CrateType, DebugInfo, ErrorOutputType, LinkerPluginLto, LtoCli, OptLevel,
-        OutputTypes, Passes, Sanitizer, SwitchWithOptPath, SymbolManglingVersion,
+        OutputTypes, Passes, Sanitizer, SourceFileHashAlgorithm, SwitchWithOptPath,
+        SymbolManglingVersion,
     };
     use crate::lint;
     use crate::utils::NativeLibraryKind;
@@ -2049,6 +2056,7 @@ crate mod dep_tracking {
     impl_dep_tracking_hash_via_hash!(LinkerPluginLto);
     impl_dep_tracking_hash_via_hash!(SwitchWithOptPath);
     impl_dep_tracking_hash_via_hash!(SymbolManglingVersion);
+    impl_dep_tracking_hash_via_hash!(Option<SourceFileHashAlgorithm>);
 
     impl_dep_tracking_hash_for_sortable_vec_of!(String);
     impl_dep_tracking_hash_for_sortable_vec_of!(PathBuf);