llvm-context: modularize compiler builtin functions (#234)

- Add the revive runtime function interface to minimize boiler plate code. - Outline heavily repeated code into dedicated functions to bring down code size. - The code size tests builds optimized for size. - Function attributes are passed as slices. This significantly brings down the code size for all OpenZeppelin wizard contracts (using all possible features) compiled against OpenZeppelin `v5.0.0` with size optimizations. |contract|| `-Oz` main | `-Oz` PR || `-O3` main | `-O3` PR | |-|-|-|-|-|-|-| |erc1155.sol||100K|67K||114K|147K| |erc20.sol||120K|90K||160K|191K| |erc721.sol||128K|101K||178K|214K| |governor.sol||226K|165K||293K|349K| |rwa.sol||116K|85K||154K|185K| |stable.sol||116K|86K||155K|192K| On the flip side this introduces a heavy penalty for cycle optimized builds. Setting the no-inline attributes for cycle optimized builds helps a lot but heavily penalizes runtime speed (LLVM does not yet inline everything properly - to be investigated later on). Next steps: - Modularize more functions - Refactor the YUL function arguments to use pointers instead of values - Afterwards check if LLVM still has trouble inline-ing properly on O3 or set the no-inline attribute if it does not penalize runtime performance too bad.
2026-04-23 00:18:01 +00:00 · 2025-02-25 16:47:01 +01:00
parent 7ffe64ed7c
commit a07968205b
32 changed files with 1444 additions and 655 deletions
@@ -0,0 +1,147 @@
+//! The revive compiler runtime functions.
+
+use inkwell::values::BasicValue;
+
+use crate::polkavm::context::function::Attribute;
+use crate::polkavm::context::runtime::RuntimeFunction;
+use crate::polkavm::context::Context;
+use crate::polkavm::Dependency;
+use crate::polkavm::WriteLLVM;
+
+/// Pointers are represented as opaque 256 bit integer values in EVM.
+/// In practice, they should never exceed a register sized bit value.
+/// However, we still protect against this possibility here: Heap index
+/// offsets are generally untrusted and potentially represent valid
+/// (but wrong) pointers when truncated.
+pub struct WordToPointer;
+
+impl<D> RuntimeFunction<D> for WordToPointer
+where
+    D: Dependency + Clone,
+{
+    const NAME: &'static str = "__revive_int_truncate";
+
+    const ATTRIBUTES: &'static [Attribute] = &[
+        Attribute::WillReturn,
+        Attribute::NoFree,
+        Attribute::AlwaysInline,
+    ];
+
+    fn r#type<'ctx>(context: &Context<'ctx, D>) -> inkwell::types::FunctionType<'ctx> {
+        context
+            .xlen_type()
+            .fn_type(&[context.word_type().into()], false)
+    }
+
+    fn emit_body<'ctx>(
+        &self,
+        context: &mut Context<'ctx, D>,
+    ) -> anyhow::Result<Option<inkwell::values::BasicValueEnum<'ctx>>> {
+        let value = Self::paramater(context, 0).into_int_value();
+        let truncated =
+            context
+                .builder()
+                .build_int_truncate(value, context.xlen_type(), "offset_truncated")?;
+        let extended = context.builder().build_int_z_extend(
+            truncated,
+            context.word_type(),
+            "offset_extended",
+        )?;
+        let is_overflow = context.builder().build_int_compare(
+            inkwell::IntPredicate::NE,
+            value,
+            extended,
+            "compare_truncated_extended",
+        )?;
+
+        let block_continue = context.append_basic_block("offset_pointer_ok");
+        let block_trap = context.append_basic_block("offset_pointer_overflow");
+        context.build_conditional_branch(is_overflow, block_trap, block_continue)?;
+
+        context.set_basic_block(block_trap);
+        context.build_call(context.intrinsics().trap, &[], "invalid_trap");
+        context.build_unreachable();
+
+        context.set_basic_block(block_continue);
+        Ok(Some(truncated.as_basic_value_enum()))
+    }
+}
+
+impl<D> WriteLLVM<D> for WordToPointer
+where
+    D: Dependency + Clone,
+{
+    fn declare(&mut self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::declare(self, context)
+    }
+
+    fn into_llvm(self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::emit(&self, context)
+    }
+}
+
+/// The revive runtime exit function.
+pub struct Exit;
+
+impl<D> RuntimeFunction<D> for Exit
+where
+    D: Dependency + Clone,
+{
+    const NAME: &'static str = "__revive_exit";
+
+    const ATTRIBUTES: &'static [Attribute] = &[
+        Attribute::NoReturn,
+        Attribute::NoFree,
+        Attribute::AlwaysInline,
+    ];
+
+    fn r#type<'ctx>(context: &Context<'ctx, D>) -> inkwell::types::FunctionType<'ctx> {
+        context.void_type().fn_type(
+            &[
+                context.xlen_type().into(),
+                context.word_type().into(),
+                context.word_type().into(),
+            ],
+            false,
+        )
+    }
+
+    fn emit_body<'ctx>(
+        &self,
+        context: &mut Context<'ctx, D>,
+    ) -> anyhow::Result<Option<inkwell::values::BasicValueEnum<'ctx>>> {
+        let flags = Self::paramater(context, 0).into_int_value();
+        let offset = Self::paramater(context, 1).into_int_value();
+        let length = Self::paramater(context, 2).into_int_value();
+
+        let offset_truncated = context.safe_truncate_int_to_xlen(offset)?;
+        let length_truncated = context.safe_truncate_int_to_xlen(length)?;
+        let heap_pointer = context.build_heap_gep(offset_truncated, length_truncated)?;
+        let offset_pointer = context.builder().build_ptr_to_int(
+            heap_pointer.value,
+            context.xlen_type(),
+            "return_data_ptr_to_int",
+        )?;
+
+        context.build_runtime_call(
+            revive_runtime_api::polkavm_imports::RETURN,
+            &[flags.into(), offset_pointer.into(), length_truncated.into()],
+        );
+        context.build_unreachable();
+
+        Ok(None)
+    }
+}
+
+impl<D> WriteLLVM<D> for Exit
+where
+    D: Dependency + Clone,
+{
+    fn declare(&mut self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::declare(self, context)
+    }
+
+    fn into_llvm(self, context: &mut Context<D>) -> anyhow::Result<()> {
+        <Self as RuntimeFunction<_>>::emit(&self, context)
+    }
+}