* Optimize `Func::call` and its C API This commit is an alternative to #3298 which achieves effectively the same goal of optimizing the `Func::call` API as well as its C API sibling of `wasmtime_func_call`. The strategy taken here is different than #3298 though where a new API isn't created, rather a small tweak to an existing API is done. Specifically this commit handles the major sources of slowness with `Func::call` with: * Looking up the type of a function, to typecheck the arguments with and use to guide how the results should be loaded, no longer hits the rwlock in the `Engine` but instead each `Func` contains its own `FuncType`. This can be an unnecessary allocation for funcs not used with `Func::call`, so this is a downside of this implementation relative to #3298. A mitigating factor, though, is that instance exports are loaded lazily into the `Store` and in theory not too many funcs are active in the store as `Func` objects. * Temporary storage is amortized with a long-lived `Vec` in the `Store` rather than allocating a new vector on each call. This is basically the same strategy as #3294 only applied to different types in different places. Specifically `wasmtime::Store` now retains a `Vec<u128>` for `Func::call`, and the C API retains a `Vec<Val>` for calling `Func::call`. * Finally, an API breaking change is made to `Func::call` and its type signature (as well as `Func::call_async`). Instead of returning `Box<[Val]>` as it did before this function now takes a `results: &mut [Val]` parameter. This allows the caller to manage the allocation and we can amortize-remove it in `wasmtime_func_call` by using space after the parameters in the `Vec<Val>` we're passing in. This change is naturally a breaking change and we'll want to consider it carefully, but mitigating factors are that most embeddings are likely using `TypedFunc::call` instead and this signature taking a mutable slice better aligns with `Func::new` which receives a mutable slice for the results. Overall this change, in the benchmark of "call a nop function from the C API" is not quite as good as #3298. It's still a bit slower, on the order of 15ns, because there's lots of capacity checks around vectors and the type checks are slightly less optimized than before. Overall though this is still significantly better than today because allocations and the rwlock to acquire the type information are both avoided. I personally feel that this change is the best to do because it has less of an API impact than #3298. * Rebase issues
140 lines
4.0 KiB
Rust
140 lines
4.0 KiB
Rust
use wasmtime::{Engine, Linker, Module, Store, Val};
|
|
|
|
// from_witx invocation says the func is async. This context doesn't support async!
|
|
wiggle::from_witx!({
|
|
witx: ["$CARGO_MANIFEST_DIR/tests/atoms.witx"],
|
|
async: {
|
|
atoms::{double_int_return_float}
|
|
}
|
|
});
|
|
|
|
pub mod integration {
|
|
// The integration invocation says the func is blocking, so it will still work.
|
|
wiggle::wasmtime_integration!({
|
|
target: crate,
|
|
witx: ["$CARGO_MANIFEST_DIR/tests/atoms.witx"],
|
|
block_on: {
|
|
atoms::{double_int_return_float}
|
|
}
|
|
});
|
|
}
|
|
|
|
pub struct Ctx;
|
|
impl wiggle::GuestErrorType for types::Errno {
|
|
fn success() -> Self {
|
|
types::Errno::Ok
|
|
}
|
|
}
|
|
|
|
#[wiggle::async_trait]
|
|
impl atoms::Atoms for Ctx {
|
|
fn int_float_args(&mut self, an_int: u32, an_float: f32) -> Result<(), types::Errno> {
|
|
println!("INT FLOAT ARGS: {} {}", an_int, an_float);
|
|
Ok(())
|
|
}
|
|
async fn double_int_return_float(
|
|
&mut self,
|
|
an_int: u32,
|
|
) -> Result<types::AliasToFloat, types::Errno> {
|
|
Ok((an_int as f32) * 2.0)
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_sync_host_func() {
|
|
let engine = Engine::default();
|
|
let mut linker = Linker::new(&engine);
|
|
integration::add_atoms_to_linker(&mut linker, |cx| cx).unwrap();
|
|
let mut store = store(&engine);
|
|
let shim_mod = shim_module(&engine);
|
|
let shim_inst = linker.instantiate(&mut store, &shim_mod).unwrap();
|
|
|
|
let mut results = [Val::I32(0)];
|
|
shim_inst
|
|
.get_func(&mut store, "int_float_args_shim")
|
|
.unwrap()
|
|
.call(&mut store, &[0i32.into(), 123.45f32.into()], &mut results)
|
|
.unwrap();
|
|
|
|
assert_eq!(
|
|
results[0].unwrap_i32(),
|
|
types::Errno::Ok as i32,
|
|
"int_float_args errno"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_async_host_func() {
|
|
let engine = Engine::default();
|
|
let mut linker = Linker::new(&engine);
|
|
integration::add_atoms_to_linker(&mut linker, |cx| cx).unwrap();
|
|
let mut store = store(&engine);
|
|
|
|
let shim_mod = shim_module(&engine);
|
|
let shim_inst = linker.instantiate(&mut store, &shim_mod).unwrap();
|
|
|
|
let input: i32 = 123;
|
|
let result_location: i32 = 0;
|
|
|
|
let mut results = [Val::I32(0)];
|
|
shim_inst
|
|
.get_func(&mut store, "double_int_return_float_shim")
|
|
.unwrap()
|
|
.call(
|
|
&mut store,
|
|
&[input.into(), result_location.into()],
|
|
&mut results,
|
|
)
|
|
.unwrap();
|
|
|
|
assert_eq!(
|
|
results[0].unwrap_i32(),
|
|
types::Errno::Ok as i32,
|
|
"double_int_return_float errno"
|
|
);
|
|
|
|
// The actual result is in memory:
|
|
let mem = shim_inst.get_memory(&mut store, "memory").unwrap();
|
|
let mut result_bytes: [u8; 4] = [0, 0, 0, 0];
|
|
mem.read(&store, result_location as usize, &mut result_bytes)
|
|
.unwrap();
|
|
let result = f32::from_le_bytes(result_bytes);
|
|
assert_eq!((input * 2) as f32, result);
|
|
}
|
|
|
|
fn store(engine: &Engine) -> Store<Ctx> {
|
|
Store::new(engine, Ctx)
|
|
}
|
|
|
|
// Wiggle expects the caller to have an exported memory. Wasmtime can only
|
|
// provide this if the caller is a WebAssembly module, so we need to write
|
|
// a shim module:
|
|
fn shim_module(engine: &Engine) -> Module {
|
|
Module::new(
|
|
engine,
|
|
r#"
|
|
(module
|
|
(import "atoms" "int_float_args" (func $int_float_args (param i32 f32) (result i32)))
|
|
(import "atoms" "double_int_return_float" (func $double_int_return_float (param i32 i32) (result i32)))
|
|
|
|
(memory 1)
|
|
(export "memory" (memory 0))
|
|
|
|
(func $int_float_args_shim (param i32 f32) (result i32)
|
|
local.get 0
|
|
local.get 1
|
|
call $int_float_args
|
|
)
|
|
(func $double_int_return_float_shim (param i32 i32) (result i32)
|
|
local.get 0
|
|
local.get 1
|
|
call $double_int_return_float
|
|
)
|
|
(export "int_float_args_shim" (func $int_float_args_shim))
|
|
(export "double_int_return_float_shim" (func $double_int_return_float_shim))
|
|
)
|
|
"#,
|
|
)
|
|
.unwrap()
|
|
}
|