rustc_codegen_llvm: add support for writing summary bitcode

Typical uses of ThinLTO don't have any use for this as a standalone
file, but distributed ThinLTO uses this to make the linker phase more
efficient. With clang you'd do something like `clang -flto=thin
-fthin-link-bitcode=foo.indexing.o -c foo.c` and then get both foo.o
(full of bitcode) and foo.indexing.o (just the summary or index part of
the bitcode). That's then usable by a two-stage linking process that's
more friendly to distributed build systems like bazel, which is why I'm
working on this area.

I talked some to @teresajohnson about naming in this area, as things
seem to be a little confused between various blog posts and build
systems. "bitcode index" and "bitcode summary" tend to be a little too
ambiguous, and she tends to use "thin link bitcode" and "minimized
bitcode" (which matches the descriptions in LLVM). Since the clang
option is thin-link-bitcode, I went with that to try and not add a new
spelling in the world.

Per @dtolnay, you can work around the lack of this by using `lld
--thinlto-index-only` to do the indexing on regular .o files of
bitcode, but that is a bit wasteful on actions when we already have all
the information in rustc and could just write out the matching minimized
bitcode. I didn't test that at all in our infrastructure, because by the
time I learned that I already had this patch largely written.

3 files changed, 37 insertions, 5 deletions

diff --git a/compiler/rustc_codegen_llvm/src/back/lto.rs b/compiler/rustc_codegen_llvm/src/back/lto.rs
index e61af863dc0..740939eb6bb 100644
--- a/compiler/rustc_codegen_llvm/src/back/lto.rs
+++ b/compiler/rustc_codegen_llvm/src/back/lto.rs
@@ -687,6 +687,14 @@ impl ThinBufferMethods for ThinBuffer {
             slice::from_raw_parts(ptr, len)
         }
     }
+
+    fn thin_link_data(&self) -> &[u8] {
+        unsafe {
+            let ptr = llvm::LLVMRustThinLTOBufferThinLinkDataPtr(self.0) as *const _;
+            let len = llvm::LLVMRustThinLTOBufferThinLinkDataLen(self.0);
+            slice::from_raw_parts(ptr, len)
+        }
+    }
 }
 
 impl Drop for ThinBuffer {
diff --git a/compiler/rustc_codegen_llvm/src/back/write.rs b/compiler/rustc_codegen_llvm/src/back/write.rs
index 49f9d7ddab6..de12ae4ecc8 100644
--- a/compiler/rustc_codegen_llvm/src/back/write.rs
+++ b/compiler/rustc_codegen_llvm/src/back/write.rs
@@ -708,6 +708,8 @@ pub(crate) unsafe fn codegen(
         //   asm from LLVM and use `gcc` to create the object file.
 
         let bc_out = cgcx.output_filenames.temp_path(OutputType::Bitcode, module_name);
+        let bc_index_out =
+            cgcx.output_filenames.temp_path(OutputType::ThinLinkBitcode, module_name);
         let obj_out = cgcx.output_filenames.temp_path(OutputType::Object, module_name);
 
         if config.bitcode_needed() {
@@ -716,6 +718,7 @@ pub(crate) unsafe fn codegen(
                 .generic_activity_with_arg("LLVM_module_codegen_make_bitcode", &*module.name);
             let thin = ThinBuffer::new(llmod, config.emit_thin_lto);
             let data = thin.data();
+            let index_data = thin.thin_link_data();
 
             if let Some(bitcode_filename) = bc_out.file_name() {
                 cgcx.prof.artifact_size(
@@ -725,12 +728,31 @@ pub(crate) unsafe fn codegen(
                 );
             }
 
+            if let Some(thin_link_bitcode_filename) = bc_index_out.file_name() {
+                cgcx.prof.artifact_size(
+                    "llvm_bitcode_summary",
+                    thin_link_bitcode_filename.to_string_lossy(),
+                    index_data.len() as u64,
+                );
+
+                let _timer = cgcx.prof.generic_activity_with_arg(
+                    "LLVM_module_codegen_emit_bitcode_index",
+                    &*module.name,
+                );
+                if let Err(err) = fs::write(&bc_index_out, index_data) {
+                    dcx.emit_err(WriteBytecode { path: &bc_index_out, err });
+                }
+            }
+
             if config.emit_bc || config.emit_obj == EmitObj::Bitcode {
-                let _timer = cgcx
-                    .prof
-                    .generic_activity_with_arg("LLVM_module_codegen_emit_bitcode", &*module.name);
-                if let Err(err) = fs::write(&bc_out, data) {
-                    dcx.emit_err(WriteBytecode { path: &bc_out, err });
+                {
+                    let _timer = cgcx.prof.generic_activity_with_arg(
+                        "LLVM_module_codegen_emit_bitcode",
+                        &*module.name,
+                    );
+                    if let Err(err) = fs::write(&bc_out, data) {
+                        dcx.emit_err(WriteBytecode { path: &bc_out, err });
+                    }
                 }
             }
 
diff --git a/compiler/rustc_codegen_llvm/src/llvm/ffi.rs b/compiler/rustc_codegen_llvm/src/llvm/ffi.rs
index 7a34e21628d..648e7f12890 100644
--- a/compiler/rustc_codegen_llvm/src/llvm/ffi.rs
+++ b/compiler/rustc_codegen_llvm/src/llvm/ffi.rs
@@ -2354,6 +2354,8 @@ extern "C" {
     pub fn LLVMRustThinLTOBufferFree(M: &'static mut ThinLTOBuffer);
     pub fn LLVMRustThinLTOBufferPtr(M: &ThinLTOBuffer) -> *const c_char;
     pub fn LLVMRustThinLTOBufferLen(M: &ThinLTOBuffer) -> size_t;
+    pub fn LLVMRustThinLTOBufferThinLinkDataPtr(M: &ThinLTOBuffer) -> *const c_char;
+    pub fn LLVMRustThinLTOBufferThinLinkDataLen(M: &ThinLTOBuffer) -> size_t;
     pub fn LLVMRustCreateThinLTOData(
         Modules: *const ThinLTOModule,
         NumModules: c_uint,