Auto merge of #39490 - RReverser:em-linker, r=alexcrichton

Add Emscripten-specific linker

Emscripten claims to accept most GNU linker options, but in fact most of `-Wl,...` are useless for it and instead it requires some additional special options which are easier to handle in a separate trait.

Currently added:
 - `export_symbols`: works on executables as special Emscripten case since staticlibs/dylibs aren't compiled to JS, while exports are required to be accessible from JS.
Fixes #39171.
 - `optimize` - translates Rust's optimization level to Emscripten optimization level (whether passed via `-C opt-level=...` or `-O...`).
Fixes #36899.
 - `debuginfo` - translates debug info; Emscripten has 5 debug levels while Rust has 3, so chose to translate `-C debuginfo=1` to `-g3` (preserves whitespace, variable and function names for easy debugging).
Fixes #36901.
 - `no_default_libraries` - tells Emscripten to exclude `memcpy` and co.

TODO (in future PR): dynamic linking via `SIDE_MODULE` / `MAIN_MODULE` mechanism.

src/Cargo.lock

@@ -551,6 +551,7 @@ dependencies = [
  "rustc_incremental 0.0.0",
  "rustc_llvm 0.0.0",
  "rustc_platform_intrinsics 0.0.0",
+ "serialize 0.0.0",
  "syntax 0.0.0",
  "syntax_pos 0.0.0",
 ]

src/librustc_trans/Cargo.toml

@@ -22,5 +22,6 @@ rustc_errors = { path = "../librustc_errors" }
 rustc_incremental = { path = "../librustc_incremental" }
 rustc_llvm = { path = "../librustc_llvm" }
 rustc_platform_intrinsics = { path = "../librustc_platform_intrinsics" }
+serialize = { path = "../libserialize" }
 syntax = { path = "../libsyntax" }
 syntax_pos = { path = "../libsyntax_pos" }

src/librustc_trans/back/link.rs

@@ -722,9 +722,13 @@ fn link_natively(sess: &Session,
         cmd.arg(root.join(obj));
     }
 
-    if sess.target.target.options.is_like_emscripten &&
-       sess.panic_strategy() == PanicStrategy::Abort {
-        cmd.args(&["-s", "DISABLE_EXCEPTION_CATCHING=1"]);
+    if sess.target.target.options.is_like_emscripten {
+        cmd.arg("-s");
+        cmd.arg(if sess.panic_strategy() == PanicStrategy::Abort {
+            "DISABLE_EXCEPTION_CATCHING=1"
+        } else {
+            "DISABLE_EXCEPTION_CATCHING=0"
+        });
     }
 
     {
@@ -830,7 +834,8 @@ fn link_args(cmd: &mut Linker,
 
     // If we're building a dynamic library then some platforms need to make sure
     // that all symbols are exported correctly from the dynamic library.
-    if crate_type != config::CrateTypeExecutable {
+    if crate_type != config::CrateTypeExecutable ||
+       sess.target.target.options.is_like_emscripten {
         cmd.export_symbols(tmpdir, crate_type);
     }
 

src/librustc_trans/back/linker.rs

@@ -23,8 +23,8 @@ use back::symbol_export::{self, ExportedSymbols};
 use middle::dependency_format::Linkage;
 use rustc::hir::def_id::{LOCAL_CRATE, CrateNum};
 use session::Session;
-use session::config::CrateType;
-use session::config;
+use session::config::{self, CrateType, OptLevel, DebugInfoLevel};
+use serialize::{json, Encoder};
 
 /// For all the linkers we support, and information they might
 /// need out of the shared crate context before we get rid of it.
@@ -51,6 +51,12 @@ impl<'a, 'tcx> LinkerInfo {
                 sess: sess,
                 info: self
             }) as Box<Linker>
+        } else if sess.target.target.options.is_like_emscripten {
+            Box::new(EmLinker {
+                cmd: cmd,
+                sess: sess,
+                info: self
+            }) as Box<Linker>
         } else {
             Box::new(GnuLinker {
                 cmd: cmd,
@@ -488,6 +494,154 @@ impl<'a> Linker for MsvcLinker<'a> {
     }
 }
 
+pub struct EmLinker<'a> {
+    cmd: &'a mut Command,
+    sess: &'a Session,
+    info: &'a LinkerInfo
+}
+
+impl<'a> Linker for EmLinker<'a> {
+    fn include_path(&mut self, path: &Path) {
+        self.cmd.arg("-L").arg(path);
+    }
+
+    fn link_staticlib(&mut self, lib: &str) {
+        self.cmd.arg("-l").arg(lib);
+    }
+
+    fn output_filename(&mut self, path: &Path) {
+        self.cmd.arg("-o").arg(path);
+    }
+
+    fn add_object(&mut self, path: &Path) {
+        self.cmd.arg(path);
+    }
+
+    fn link_dylib(&mut self, lib: &str) {
+        // Emscripten always links statically
+        self.link_staticlib(lib);
+    }
+
+    fn link_whole_staticlib(&mut self, lib: &str, _search_path: &[PathBuf]) {
+        // not supported?
+        self.link_staticlib(lib);
+    }
+
+    fn link_whole_rlib(&mut self, lib: &Path) {
+        // not supported?
+        self.link_rlib(lib);
+    }
+
+    fn link_rust_dylib(&mut self, lib: &str, _path: &Path) {
+        self.link_dylib(lib);
+    }
+
+    fn link_rlib(&mut self, lib: &Path) {
+        self.add_object(lib);
+    }
+
+    fn position_independent_executable(&mut self) {
+        // noop
+    }
+
+    fn args(&mut self, args: &[String]) {
+        self.cmd.args(args);
+    }
+
+    fn framework_path(&mut self, _path: &Path) {
+        bug!("frameworks are not supported on Emscripten")
+    }
+
+    fn link_framework(&mut self, _framework: &str) {
+        bug!("frameworks are not supported on Emscripten")
+    }
+
+    fn gc_sections(&mut self, _keep_metadata: bool) {
+        // noop
+    }
+
+    fn optimize(&mut self) {
+        // Emscripten performs own optimizations
+        self.cmd.arg(match self.sess.opts.optimize {
+            OptLevel::No => "-O0",
+            OptLevel::Less => "-O1",
+            OptLevel::Default => "-O2",
+            OptLevel::Aggressive => "-O3",
+            OptLevel::Size => "-Os",
+            OptLevel::SizeMin => "-Oz"
+        });
+        // Unusable until https://github.com/rust-lang/rust/issues/38454 is resolved
+        self.cmd.args(&["--memory-init-file", "0"]);
+    }
+
+    fn debuginfo(&mut self) {
+        // Preserve names or generate source maps depending on debug info
+        self.cmd.arg(match self.sess.opts.debuginfo {
+            DebugInfoLevel::NoDebugInfo => "-g0",
+            DebugInfoLevel::LimitedDebugInfo => "-g3",
+            DebugInfoLevel::FullDebugInfo => "-g4"
+        });
+    }
+
+    fn no_default_libraries(&mut self) {
+        self.cmd.args(&["-s", "DEFAULT_LIBRARY_FUNCS_TO_INCLUDE=[]"]);
+    }
+
+    fn build_dylib(&mut self, _out_filename: &Path) {
+        bug!("building dynamic library is unsupported on Emscripten")
+    }
+
+    fn whole_archives(&mut self) {
+        // noop
+    }
+
+    fn no_whole_archives(&mut self) {
+        // noop
+    }
+
+    fn hint_static(&mut self) {
+        // noop
+    }
+
+    fn hint_dynamic(&mut self) {
+        // noop
+    }
+
+    fn export_symbols(&mut self, _tmpdir: &Path, crate_type: CrateType) {
+        let symbols = &self.info.exports[&crate_type];
+
+        debug!("EXPORTED SYMBOLS:");
+
+        self.cmd.arg("-s");
+
+        let mut arg = OsString::from("EXPORTED_FUNCTIONS=");
+        let mut encoded = String::new();
+
+        {
+            let mut encoder = json::Encoder::new(&mut encoded);
+            let res = encoder.emit_seq(symbols.len(), |encoder| {
+                for (i, sym) in symbols.iter().enumerate() {
+                    encoder.emit_seq_elt(i, |encoder| {
+                        encoder.emit_str(&("_".to_string() + sym))
+                    })?;
+                }
+                Ok(())
+            });
+            if let Err(e) = res {
+                self.sess.fatal(&format!("failed to encode exported symbols: {}", e));
+            }
+        }
+        debug!("{}", encoded);
+        arg.push(encoded);
+
+        self.cmd.arg(arg);
+    }
+
+    fn subsystem(&mut self, _subsystem: &str) {
+        // noop
+    }
+}
+
 fn exported_symbols(scx: &SharedCrateContext,
                     exported_symbols: &ExportedSymbols,
                     crate_type: CrateType)

src/librustc_trans/lib.rs

@@ -59,6 +59,7 @@ extern crate rustc_bitflags;
 #[macro_use] extern crate syntax;
 extern crate syntax_pos;
 extern crate rustc_errors as errors;
+extern crate serialize;
 
 pub use rustc::session;
 pub use rustc::middle;