Auto merge of #92419 - erikdesjardins:coldland, r=nagisa

Mark drop calls in landing pads `cold` instead of `noinline`

Now that deferred inlining has been disabled in LLVM (#92110), this shouldn't cause catastrophic size blowup.

I confirmed that the test cases from https://github.com/rust-lang/rust/issues/41696#issuecomment-298696944 still compile quickly (<1s) after this change. ~Although note that I wasn't able to reproduce the original issue using a recent rustc/llvm with deferred inlining enabled, so those tests may no longer be representative. I was also unable to create a modified test case that reproduced the original issue.~ (edit: I reproduced it on CI by accident--the first commit timed out on the LLVM 12 builder, because I forgot to make it conditional on LLVM version)

r? `@nagisa`
cc `@arielb1` (this effectively reverts #42771 "mark calls in the unwind path as !noinline")
cc `@RalfJung` (fixes #46515)

edit: also fixes #87055

compiler/rustc_codegen_gcc/src/builder.rs

@@ -1403,7 +1403,7 @@ fn cx(&self) -> &CodegenCx<'gcc, 'tcx> {
         self.cx
     }
 
-    fn do_not_inline(&mut self, _llret: RValue<'gcc>) {
+    fn apply_attrs_to_cleanup_callsite(&mut self, _llret: RValue<'gcc>) {
         unimplemented!();
     }
 

compiler/rustc_codegen_llvm/src/builder.rs

@@ -1201,8 +1201,15 @@ fn zext(&mut self, val: &'ll Value, dest_ty: &'ll Type) -> &'ll Value {
         unsafe { llvm::LLVMBuildZExt(self.llbuilder, val, dest_ty, UNNAMED) }
     }
 
-    fn do_not_inline(&mut self, llret: &'ll Value) {
-        llvm::Attribute::NoInline.apply_callsite(llvm::AttributePlace::Function, llret);
+    fn apply_attrs_to_cleanup_callsite(&mut self, llret: &'ll Value) {
+        // Cleanup is always the cold path.
+        llvm::Attribute::Cold.apply_callsite(llvm::AttributePlace::Function, llret);
+
+        // In LLVM versions with deferred inlining (currently, system LLVM < 14),
+        // inlining drop glue can lead to exponential size blowup, see #41696 and #92110.
+        if !llvm_util::is_rust_llvm() && llvm_util::get_version() < (14, 0, 0) {
+            llvm::Attribute::NoInline.apply_callsite(llvm::AttributePlace::Function, llret);
+        }
     }
 }
 

compiler/rustc_codegen_llvm/src/llvm/ffi.rs

@@ -1902,6 +1902,8 @@ pub fn LLVMRustCoverageWriteMappingToBuffer(
     pub fn LLVMRustVersionMinor() -> u32;
     pub fn LLVMRustVersionPatch() -> u32;
 
+    pub fn LLVMRustIsRustLLVM() -> bool;
+
     pub fn LLVMRustAddModuleFlag(M: &Module, name: *const c_char, value: u32);
 
     pub fn LLVMRustMetadataAsValue<'a>(C: &'a Context, MD: &'a Metadata) -> &'a Value;

compiler/rustc_codegen_llvm/src/llvm_util.rs

@@ -223,6 +223,12 @@ pub fn get_version() -> (u32, u32, u32) {
     }
 }
 
+/// Returns `true` if this LLVM is Rust's bundled LLVM (and not system LLVM).
+pub fn is_rust_llvm() -> bool {
+    // Can be called without initializing LLVM
+    unsafe { llvm::LLVMRustIsRustLLVM() }
+}
+
 pub fn print_passes() {
     // Can be called without initializing LLVM
     unsafe {

compiler/rustc_codegen_ssa/src/mir/block.rs

@@ -160,11 +160,7 @@ fn do_call<Bx: BuilderMethods<'a, 'tcx>>(
             let llret = bx.call(fn_ty, fn_ptr, &llargs, self.funclet(fx));
             bx.apply_attrs_callsite(&fn_abi, llret);
             if fx.mir[self.bb].is_cleanup {
-                // Cleanup is always the cold path. Don't inline
-                // drop glue. Also, when there is a deeply-nested
-                // struct, there are "symmetry" issues that cause
-                // exponential inlining - see issue #41696.
-                bx.do_not_inline(llret);
+                bx.apply_attrs_to_cleanup_callsite(llret);
             }
 
             if let Some((ret_dest, target)) = destination {

compiler/rustc_codegen_ssa/src/traits/builder.rs

@@ -311,5 +311,5 @@ fn call(
     ) -> Self::Value;
     fn zext(&mut self, val: Self::Value, dest_ty: Self::Type) -> Self::Value;
 
-    fn do_not_inline(&mut self, llret: Self::Value);
+    fn apply_attrs_to_cleanup_callsite(&mut self, llret: Self::Value);
 }

compiler/rustc_llvm/llvm-wrapper/RustWrapper.cpp

@@ -716,6 +716,14 @@ extern "C" uint32_t LLVMRustVersionMinor() { return LLVM_VERSION_MINOR; }
 
 extern "C" uint32_t LLVMRustVersionMajor() { return LLVM_VERSION_MAJOR; }
 
+extern "C" bool LLVMRustIsRustLLVM() {
+#ifdef LLVM_RUSTLLVM
+  return true;
+#else
+  return false;
+#endif
+}
+
 extern "C" void LLVMRustAddModuleFlag(LLVMModuleRef M, const char *Name,
                                       uint32_t Value) {
   unwrap(M)->addModuleFlag(Module::Warning, Name, Value);

src/test/codegen/unwind-landingpad-cold.rs

@@ -0,0 +1,15 @@
+// no-system-llvm: needs #92110
+// compile-flags: -Cno-prepopulate-passes
+#![crate_type = "lib"]
+
+// This test checks that drop calls in unwind landing pads
+// get the `cold` attribute.
+
+// CHECK-LABEL: @check_cold
+// CHECK: call void {{.+}}drop_in_place{{.+}} [[ATTRIBUTES:#[0-9]+]]
+// CHECK: attributes [[ATTRIBUTES]] = { cold }
+#[no_mangle]
+pub fn check_cold(f: fn(), x: Box<u32>) {
+    // this may unwind
+    f();
+}

src/test/codegen/unwind-landingpad-inline.rs

@@ -0,0 +1,37 @@
+// no-system-llvm: needs #92110 + patch for Rust alloc/dealloc functions
+// compile-flags: -Copt-level=3
+#![crate_type = "lib"]
+
+// This test checks that we can inline drop_in_place in
+// unwind landing pads.
+
+// Without inlining, the box pointers escape via the call to drop_in_place,
+// and LLVM will not optimize out the pointer comparison.
+// With inlining, everything should be optimized out.
+// See https://github.com/rust-lang/rust/issues/46515
+// CHECK-LABEL: @check_no_escape_in_landingpad
+// CHECK: start:
+// CHECK-NEXT: ret void
+#[no_mangle]
+pub fn check_no_escape_in_landingpad(f: fn()) {
+    let x = &*Box::new(0);
+    let y = &*Box::new(0);
+
+    if x as *const _ == y as *const _ {
+        f();
+    }
+}
+
+// Without inlining, the compiler can't tell that
+// dropping an empty string (in a landing pad) does nothing.
+// With inlining, the landing pad should be optimized out.
+// See https://github.com/rust-lang/rust/issues/87055
+// CHECK-LABEL: @check_eliminate_noop_drop
+// CHECK: start:
+// CHECK-NEXT: call void %g()
+// CHECK-NEXT: ret void
+#[no_mangle]
+pub fn check_eliminate_noop_drop(g: fn()) {
+    let _var = String::new();
+    g();
+}