Reapply: Mark drop calls in landing pads cold instead of noinline

This reverts commit 4a56cbe, reversing
changes made to 6e5a6ff.

Author: erikdesjardins

compiler/rustc_codegen_gcc/src/builder.rs

@@ -1403,7 +1403,7 @@ impl<'a, 'gcc, 'tcx> BuilderMethods<'a, 'tcx> for Builder<'a, '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

@@ -23,6 +23,7 @@ use rustc_middle::ty::{self, Ty, TyCtxt};
 use rustc_span::Span;
 use rustc_target::abi::{self, call::FnAbi, Align, Size, WrappingRange};
 use rustc_target::spec::{HasTargetSpec, Target};
+use smallvec::SmallVec;
 use std::borrow::Cow;
 use std::ffi::CStr;
 use std::iter;
@@ -1188,9 +1189,19 @@ impl<'a, 'll, 'tcx> BuilderMethods<'a, 'tcx> for Builder<'a, 'll, 'tcx> {
         unsafe { llvm::LLVMBuildZExt(self.llbuilder, val, dest_ty, UNNAMED) }
     }
 
-    fn do_not_inline(&mut self, llret: &'ll Value) {
-        let noinline = llvm::AttributeKind::NoInline.create_attr(self.llcx);
-        attributes::apply_to_callsite(llret, llvm::AttributePlace::Function, &[noinline]);
+    fn apply_attrs_to_cleanup_callsite(&mut self, llret: &'ll Value) {
+        let mut attrs = SmallVec::<[_; 2]>::new();
+
+        // Cleanup is always the cold path.
+        attrs.push(llvm::AttributeKind::Cold.create_attr(self.llcx));
+
+        // 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) {
+            attrs.push(llvm::AttributeKind::NoInline.create_attr(self.llcx));
+        }
+
+        attributes::apply_to_callsite(llret, llvm::AttributePlace::Function, &attrs);
     }
 }
 

compiler/rustc_codegen_llvm/src/llvm/ffi.rs

@@ -1929,6 +1929,8 @@ extern "C" {
     pub fn LLVMRustVersionMinor() -> u32;
     pub fn LLVMRustVersionPatch() -> u32;
 
+    pub fn LLVMRustIsRustLLVM() -> bool;
+
     /// Add LLVM module flags.
     ///
     /// In order for Rust-C LTO to work, module flags must be compatible with Clang. What

compiler/rustc_codegen_llvm/src/llvm_util.rs

@@ -261,6 +261,12 @@ 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

@@ -166,7 +166,7 @@ impl<'a, 'tcx> TerminatorCodegenHelper<'tcx> {
                 bx.invoke(fn_ty, fn_ptr, &llargs, ret_llbb, unwind_block, self.funclet(fx));
             bx.apply_attrs_callsite(&fn_abi, invokeret);
             if fx.mir[self.bb].is_cleanup {
-                bx.do_not_inline(invokeret);
+                bx.apply_attrs_to_cleanup_callsite(invokeret);
             }
 
             if let Some((ret_dest, target)) = destination {
@@ -178,11 +178,7 @@ impl<'a, 'tcx> TerminatorCodegenHelper<'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 {
@@ -1448,7 +1444,7 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
 
             let llret = bx.call(fn_ty, fn_ptr, &[], None);
             bx.apply_attrs_callsite(&fn_abi, llret);
-            bx.do_not_inline(llret);
+            bx.apply_attrs_to_cleanup_callsite(llret);
 
             bx.unreachable();
 

compiler/rustc_codegen_ssa/src/traits/builder.rs

@@ -479,5 +479,5 @@ pub trait BuilderMethods<'a, 'tcx>:
     ) -> 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

@@ -663,6 +663,14 @@ 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,
     Module::ModFlagBehavior MergeBehavior,

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|invoke) 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();
+}

src/test/codegen/vec-shrink-panik.rs

@@ -16,32 +16,13 @@ pub fn shrink_to_fit(vec: &mut Vec<u32>) {
 // CHECK-LABEL: @issue71861
 #[no_mangle]
 pub fn issue71861(vec: Vec<u32>) -> Box<[u32]> {
-    // CHECK-NOT: panic
-
-    // Call to panic_no_unwind in case of double-panic is expected,
-    // but other panics are not.
-    // CHECK: cleanup
-    // CHECK-NEXT: ; call core::panicking::panic_no_unwind
-    // CHECK-NEXT: panic_no_unwind
-
     // CHECK-NOT: panic
     vec.into_boxed_slice()
 }
 
 // CHECK-LABEL: @issue75636
 #[no_mangle]
 pub fn issue75636<'a>(iter: &[&'a str]) -> Box<[&'a str]> {
-    // CHECK-NOT: panic
-
-    // Call to panic_no_unwind in case of double-panic is expected,
-    // but other panics are not.
-    // CHECK: cleanup
-    // CHECK-NEXT: ; call core::panicking::panic_no_unwind
-    // CHECK-NEXT: panic_no_unwind
-
     // CHECK-NOT: panic
     iter.iter().copied().collect()
 }
-
-// CHECK: ; core::panicking::panic_no_unwind
-// CHECK: declare void @{{.*}}panic_no_unwind