Auto merge of #117500 - RalfJung:aggregate-abi, r=davidtwco

Ensure sanity of all computed ABIs

This moves the ABI sanity assertions from the codegen backend to the ABI computation logic. Sadly, due to past mistakes, we [have to](https://github.com/rust-lang/rust/pull/117351#issuecomment-1788495503) be able to compute a sane ABI for nonsensical function types like `extern "C" fn(str) -> str`.  So to make the sanity check pass we first need to make all ABI adjustment deal with unsized types... and we have no shared infrastructure for those adjustments, so that's a bunch of copy-paste. At least we have assertions failing loudly when one accidentally sets a different mode for an unsized argument.

To achieve this, this re-lands the parts of https://github.com/rust-lang/rust/pull/80594 that got reverted in https://github.com/rust-lang/rust/pull/81388.  To avoid breaking wasm ABI again, that ABI now explicitly opts-in to the (wrong, broken) ABI that we currently keep for backwards compatibility. That's still better than having *every* ABI use the wrong broken default!

Cc `@bjorn3`
Fixes https://github.com/rust-lang/rust/issues/115845

compiler/rustc_target/src/abi/call/aarch64.rs

@@ -40,6 +40,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !ret.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !ret.layout.is_aggregate() {
         if kind == AbiKind::DarwinPCS {
             // On Darwin, when returning an i8/i16, it must be sign-extended to 32 bits,
@@ -67,6 +71,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !arg.layout.is_aggregate() {
         if kind == AbiKind::DarwinPCS {
             // On Darwin, when passing an i8/i16, it must be sign-extended to 32 bits,

compiler/rustc_target/src/abi/call/arm.rs

@@ -30,6 +30,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !ret.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !ret.layout.is_aggregate() {
         ret.extend_integer_width_to(32);
         return;
@@ -56,6 +60,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !arg.layout.is_aggregate() {
         arg.extend_integer_width_to(32);
         return;

compiler/rustc_target/src/abi/call/csky.rs

@@ -7,6 +7,10 @@
 use crate::abi::call::{ArgAbi, FnAbi, Reg, Uniform};
 
 fn classify_ret<Ty>(arg: &mut ArgAbi<'_, Ty>) {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     // For return type, aggregate which <= 2*XLen will be returned in registers.
     // Otherwise, aggregate will be returned indirectly.
     if arg.layout.is_aggregate() {
@@ -24,6 +28,10 @@ fn classify_ret<Ty>(arg: &mut ArgAbi<'_, Ty>) {
 }
 
 fn classify_arg<Ty>(arg: &mut ArgAbi<'_, Ty>) {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     // For argument type, the first 4*XLen parts of aggregate will be passed
     // in registers, and the rest will be passed in stack.
     // So we can coerce to integers directly and let backend handle it correctly.

compiler/rustc_target/src/abi/call/loongarch.rs

@@ -152,6 +152,10 @@ fn classify_ret<'a, Ty, C>(cx: &C, arg: &mut ArgAbi<'a, Ty>, xlen: u64, flen: u6
 where
     Ty: TyAbiInterface<'a, C> + Copy,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return false; // I guess? return value of this function is not documented
+    }
     if let Some(conv) = should_use_fp_conv(cx, &arg.layout, xlen, flen) {
         match conv {
             FloatConv::Float(f) => {
@@ -214,6 +218,10 @@ fn classify_arg<'a, Ty, C>(
 ) where
     Ty: TyAbiInterface<'a, C> + Copy,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !is_vararg {
         match should_use_fp_conv(cx, &arg.layout, xlen, flen) {
             Some(FloatConv::Float(f)) if *avail_fprs >= 1 => {

compiler/rustc_target/src/abi/call/m68k.rs

@@ -9,6 +9,10 @@ fn classify_ret<Ty>(ret: &mut ArgAbi<'_, Ty>) {
 }
 
 fn classify_arg<Ty>(arg: &mut ArgAbi<'_, Ty>) {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if arg.layout.is_aggregate() {
         arg.make_indirect_byval(None);
     } else {

compiler/rustc_target/src/abi/call/mips.rs

@@ -17,6 +17,10 @@ fn classify_arg<Ty, C>(cx: &C, arg: &mut ArgAbi<'_, Ty>, offset: &mut Size)
 where
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     let dl = cx.data_layout();
     let size = arg.layout.size;
     let align = arg.layout.align.max(dl.i32_align).min(dl.i64_align).abi;

compiler/rustc_target/src/abi/call/mod.rs

@@ -422,7 +422,7 @@ impl<'a, Ty> TyAndLayout<'a, Ty> {
                 }))
             }
 
-            Abi::ScalarPair(..) | Abi::Aggregate { .. } => {
+            Abi::ScalarPair(..) | Abi::Aggregate { sized: true } => {
                 // Helper for computing `homogeneous_aggregate`, allowing a custom
                 // starting offset (used below for handling variants).
                 let from_fields_at =
@@ -520,6 +520,7 @@ impl<'a, Ty> TyAndLayout<'a, Ty> {
                     Ok(result)
                 }
             }
+            Abi::Aggregate { sized: false } => Err(Heterogeneous),
         }
     }
 }
@@ -555,8 +556,7 @@ impl<'a, Ty> ArgAbi<'a, Ty> {
                 scalar_attrs(&layout, b, a.size(cx).align_to(b.align(cx).abi)),
             ),
             Abi::Vector { .. } => PassMode::Direct(ArgAttributes::new()),
-            // The `Aggregate` ABI should always be adjusted later.
-            Abi::Aggregate { .. } => PassMode::Direct(ArgAttributes::new()),
+            Abi::Aggregate { .. } => Self::indirect_pass_mode(&layout),
         };
         ArgAbi { layout, mode }
     }
@@ -580,14 +580,30 @@ impl<'a, Ty> ArgAbi<'a, Ty> {
         PassMode::Indirect { attrs, meta_attrs, on_stack: false }
     }
 
+    /// Pass this argument directly instead. Should NOT be used!
+    /// Only exists because of past ABI mistakes that will take time to fix
+    /// (see <https://github.com/rust-lang/rust/issues/115666>).
+    pub fn make_direct_deprecated(&mut self) {
+        match self.mode {
+            PassMode::Indirect { .. } => {
+                self.mode = PassMode::Direct(ArgAttributes::new());
+            }
+            PassMode::Ignore | PassMode::Direct(_) | PassMode::Pair(_, _) => return, // already direct
+            _ => panic!("Tried to make {:?} direct", self.mode),
+        }
+    }
+
     pub fn make_indirect(&mut self) {
         match self.mode {
-            PassMode::Direct(_) | PassMode::Pair(_, _) => {}
-            PassMode::Indirect { attrs: _, meta_attrs: None, on_stack: false } => return,
+            PassMode::Direct(_) | PassMode::Pair(_, _) => {
+                self.mode = Self::indirect_pass_mode(&self.layout);
+            }
+            PassMode::Indirect { attrs: _, meta_attrs: _, on_stack: false } => {
+                // already indirect
+                return;
+            }
             _ => panic!("Tried to make {:?} indirect", self.mode),
         }
-
-        self.mode = Self::indirect_pass_mode(&self.layout);
     }
 
     pub fn make_indirect_byval(&mut self, byval_align: Option<Align>) {

compiler/rustc_target/src/abi/call/nvptx64.rs

@@ -4,12 +4,18 @@ use crate::abi::{HasDataLayout, TyAbiInterface};
 fn classify_ret<Ty>(ret: &mut ArgAbi<'_, Ty>) {
     if ret.layout.is_aggregate() && ret.layout.size.bits() > 64 {
         ret.make_indirect();
+    } else {
+        // FIXME: this is wrong! Need to decide which ABI we really want here.
+        ret.make_direct_deprecated();
     }
 }
 
 fn classify_arg<Ty>(arg: &mut ArgAbi<'_, Ty>) {
     if arg.layout.is_aggregate() && arg.layout.size.bits() > 64 {
         arg.make_indirect();
+    } else {
+        // FIXME: this is wrong! Need to decide which ABI we really want here.
+        arg.make_direct_deprecated();
     }
 }
 
@@ -30,6 +36,9 @@ where
             _ => unreachable!("Align is given as power of 2 no larger than 16 bytes"),
         };
         arg.cast_to(Uniform { unit, total: Size::from_bytes(2 * align_bytes) });
+    } else {
+        // FIXME: find a better way to do this. See https://github.com/rust-lang/rust/issues/117271.
+        arg.make_direct_deprecated();
     }
 }
 

compiler/rustc_target/src/abi/call/powerpc64.rs

@@ -46,6 +46,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !ret.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !ret.layout.is_aggregate() {
         ret.extend_integer_width_to(64);
         return;
@@ -89,6 +93,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !arg.layout.is_aggregate() {
         arg.extend_integer_width_to(64);
         return;

compiler/rustc_target/src/abi/call/riscv.rs

@@ -158,6 +158,10 @@ fn classify_ret<'a, Ty, C>(cx: &C, arg: &mut ArgAbi<'a, Ty>, xlen: u64, flen: u6
 where
     Ty: TyAbiInterface<'a, C> + Copy,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return false; // I guess? return value of this function is not documented
+    }
     if let Some(conv) = should_use_fp_conv(cx, &arg.layout, xlen, flen) {
         match conv {
             FloatConv::Float(f) => {
@@ -220,6 +224,10 @@ fn classify_arg<'a, Ty, C>(
 ) where
     Ty: TyAbiInterface<'a, C> + Copy,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !is_vararg {
         match should_use_fp_conv(cx, &arg.layout, xlen, flen) {
             Some(FloatConv::Float(f)) if *avail_fprs >= 1 => {

compiler/rustc_target/src/abi/call/s390x.rs

@@ -17,6 +17,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     if !arg.layout.is_aggregate() && arg.layout.size.bits() <= 64 {
         arg.extend_integer_width_to(64);
         return;

compiler/rustc_target/src/abi/call/sparc.rs

@@ -17,6 +17,10 @@ fn classify_arg<Ty, C>(cx: &C, arg: &mut ArgAbi<'_, Ty>, offset: &mut Size)
 where
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     let dl = cx.data_layout();
     let size = arg.layout.size;
     let align = arg.layout.align.max(dl.i32_align).min(dl.i64_align).abi;

compiler/rustc_target/src/abi/call/wasm.rs

@@ -34,6 +34,10 @@ where
     Ty: TyAbiInterface<'a, C> + Copy,
     C: HasDataLayout,
 {
+    if !arg.layout.is_sized() {
+        // Not touching this...
+        return;
+    }
     arg.extend_integer_width_to(32);
     if arg.layout.is_aggregate() && !unwrap_trivial_aggregate(cx, arg) {
         arg.make_indirect_byval(None);
@@ -67,21 +71,33 @@ where
 /// Also see <https://github.com/rust-lang/rust/issues/115666>.
 pub fn compute_wasm_abi_info<Ty>(fn_abi: &mut FnAbi<'_, Ty>) {
     if !fn_abi.ret.is_ignore() {
-        classify_ret(&mut fn_abi.ret);
+        classify_ret_wasm_abi(&mut fn_abi.ret);
     }
 
     for arg in fn_abi.args.iter_mut() {
         if arg.is_ignore() {
             continue;
         }
-        classify_arg(arg);
+        classify_arg_wasm_abi(arg);
     }
 
-    fn classify_ret<Ty>(ret: &mut ArgAbi<'_, Ty>) {
+    fn classify_ret_wasm_abi<Ty>(ret: &mut ArgAbi<'_, Ty>) {
+        if !ret.layout.is_sized() {
+            // Not touching this...
+            return;
+        }
+        // FIXME: this is bad! https://github.com/rust-lang/rust/issues/115666
+        ret.make_direct_deprecated();
         ret.extend_integer_width_to(32);
     }
 
-    fn classify_arg<Ty>(arg: &mut ArgAbi<'_, Ty>) {
+    fn classify_arg_wasm_abi<Ty>(arg: &mut ArgAbi<'_, Ty>) {
+        if !arg.layout.is_sized() {
+            // Not touching this...
+            return;
+        }
+        // FIXME: this is bad! https://github.com/rust-lang/rust/issues/115666
+        arg.make_direct_deprecated();
         arg.extend_integer_width_to(32);
     }
 }

compiler/rustc_target/src/abi/call/x86.rs

@@ -14,7 +14,7 @@ where
     C: HasDataLayout + HasTargetSpec,
 {
     if !fn_abi.ret.is_ignore() {
-        if fn_abi.ret.layout.is_aggregate() {
+        if fn_abi.ret.layout.is_aggregate() && fn_abi.ret.layout.is_sized() {
             // Returning a structure. Most often, this will use
             // a hidden first argument. On some platforms, though,
             // small structs are returned as integers.
@@ -50,7 +50,7 @@ where
     }
 
     for arg in fn_abi.args.iter_mut() {
-        if arg.is_ignore() {
+        if arg.is_ignore() || !arg.layout.is_sized() {
             continue;
         }
 

compiler/rustc_target/src/abi/call/x86_64.rs

@@ -153,9 +153,9 @@ fn reg_component(cls: &[Option<Class>], i: &mut usize, size: Size) -> Option<Reg
     }
 }
 
-fn cast_target(cls: &[Option<Class>], size: Size) -> Option<CastTarget> {
+fn cast_target(cls: &[Option<Class>], size: Size) -> CastTarget {
     let mut i = 0;
-    let lo = reg_component(cls, &mut i, size)?;
+    let lo = reg_component(cls, &mut i, size).unwrap();
     let offset = Size::from_bytes(8) * (i as u64);
     let mut target = CastTarget::from(lo);
     if size > offset {
@@ -164,7 +164,7 @@ fn cast_target(cls: &[Option<Class>], size: Size) -> Option<CastTarget> {
         }
     }
     assert_eq!(reg_component(cls, &mut i, Size::ZERO), None);
-    Some(target)
+    target
 }
 
 const MAX_INT_REGS: usize = 6; // RDI, RSI, RDX, RCX, R8, R9
@@ -179,6 +179,10 @@ where
     let mut sse_regs = MAX_SSE_REGS;
 
     let mut x86_64_arg_or_ret = |arg: &mut ArgAbi<'a, Ty>, is_arg: bool| {
+        if !arg.layout.is_sized() {
+            // Not touching this...
+            return;
+        }
         let mut cls_or_mem = classify_arg(cx, arg);
 
         if is_arg {
@@ -227,9 +231,7 @@ where
                 // split into sized chunks passed individually
                 if arg.layout.is_aggregate() {
                     let size = arg.layout.size;
-                    if let Some(cast_target) = cast_target(cls, size) {
-                        arg.cast_to(cast_target);
-                    }
+                    arg.cast_to(cast_target(cls, size));
                 } else {
                     arg.extend_integer_width_to(32);
                 }

compiler/rustc_target/src/abi/call/x86_win64.rs

@@ -6,8 +6,8 @@ use crate::abi::Abi;
 pub fn compute_abi_info<Ty>(fn_abi: &mut FnAbi<'_, Ty>) {
     let fixup = |a: &mut ArgAbi<'_, Ty>| {
         match a.layout.abi {
-            Abi::Uninhabited => {}
-            Abi::ScalarPair(..) | Abi::Aggregate { .. } => match a.layout.size.bits() {
+            Abi::Uninhabited | Abi::Aggregate { sized: false } => {}
+            Abi::ScalarPair(..) | Abi::Aggregate { sized: true } => match a.layout.size.bits() {
                 8 => a.cast_to(Reg::i8()),
                 16 => a.cast_to(Reg::i16()),
                 32 => a.cast_to(Reg::i32()),