Implement canon lower of a canon lift function in the same component (#4347)

* Implement `canon lower` of a `canon lift` function in the same component

This commit implements the "degenerate" logic for implementing a
function within a component that is lifted and then immediately lowered
again. In this situation the lowered function will immediately generate
a trap and doesn't need to implement anything else.

The implementation in this commit is somewhat heavyweight but I think is
probably justified moreso in future additions to the component model
rather than what exactly is here right now. It's not expected that this
"always trap" functionality will really be used all that often since it
would generally mean a buggy component, but the functionality plumbed
through here is hopefully going to be useful for implementing
component-to-component adapter trampolines.

Specifically this commit implements a strategy where the `canon.lower`'d
function is generated by Cranelift and simply has a single trap
instruction when called, doing nothing else. The main complexity comes
from juggling around all the data associated with these functions,
primarily plumbing through the traps into the `ModuleRegistry` to
ensure that the global `is_wasm_trap_pc` function returns `true` and at
runtime when we lookup information about the trap it's all readily
available (e.g. translating the trapping pc to a `TrapCode`).

* Fix non-component build

* Fix some offset calculations

* Only create one "always trap" per signature

Use an internal map to deduplicate during compilation.

crates/environ/src/component/vmcomponent_offsets.rs

@@ -5,6 +5,7 @@
 //      store: *mut dyn Store,
 //      flags: [VMComponentFlags; component.num_runtime_component_instances],
 //      lowering_anyfuncs: [VMCallerCheckedAnyfunc; component.num_lowerings],
+//      always_trap_anyfuncs: [VMCallerCheckedAnyfunc; component.num_always_trap],
 //      lowerings: [VMLowering; component.num_lowerings],
 //      memories: [*mut VMMemoryDefinition; component.num_memories],
 //      reallocs: [*mut VMCallerCheckedAnyfunc; component.num_reallocs],
@@ -12,8 +13,8 @@
 // }
 
 use crate::component::{
-    Component, LoweredIndex, RuntimeComponentInstanceIndex, RuntimeMemoryIndex,
-    RuntimePostReturnIndex, RuntimeReallocIndex,
+    Component, LoweredIndex, RuntimeAlwaysTrapIndex, RuntimeComponentInstanceIndex,
+    RuntimeMemoryIndex, RuntimePostReturnIndex, RuntimeReallocIndex,
 };
 use crate::PtrSize;
 
@@ -52,12 +53,16 @@ pub struct VMComponentOffsets<P> {
     /// Number of component instances internally in the component (always at
     /// least 1).
     pub num_runtime_component_instances: u32,
+    /// Number of "always trap" functions which have their
+    /// `VMCallerCheckedAnyfunc` stored inline in the `VMComponentContext`.
+    pub num_always_trap: u32,
 
     // precalculated offsets of various member fields
     magic: u32,
     store: u32,
     flags: u32,
     lowering_anyfuncs: u32,
+    always_trap_anyfuncs: u32,
     lowerings: u32,
     memories: u32,
     reallocs: u32,
@@ -85,10 +90,12 @@ impl<P: PtrSize> VMComponentOffsets<P> {
                 .num_runtime_component_instances
                 .try_into()
                 .unwrap(),
+            num_always_trap: component.num_always_trap,
             magic: 0,
             store: 0,
             flags: 0,
             lowering_anyfuncs: 0,
+            always_trap_anyfuncs: 0,
             lowerings: 0,
             memories: 0,
             reallocs: 0,
@@ -127,6 +134,7 @@ impl<P: PtrSize> VMComponentOffsets<P> {
             size(flags) = cmul(ret.num_runtime_component_instances, ret.size_of_vmcomponent_flags()),
             align(u32::from(ret.ptr.size())),
             size(lowering_anyfuncs) = cmul(ret.num_lowerings, ret.ptr.size_of_vmcaller_checked_anyfunc()),
+            size(always_trap_anyfuncs) = cmul(ret.num_always_trap, ret.ptr.size_of_vmcaller_checked_anyfunc()),
             size(lowerings) = cmul(ret.num_lowerings, ret.ptr.size() * 2),
             size(memories) = cmul(ret.num_runtime_memories, ret.ptr.size()),
             size(reallocs) = cmul(ret.num_runtime_reallocs, ret.ptr.size()),
@@ -188,6 +196,20 @@ impl<P: PtrSize> VMComponentOffsets<P> {
             + index.as_u32() * u32::from(self.ptr.size_of_vmcaller_checked_anyfunc())
     }
 
+    /// The offset of the `always_trap_anyfuncs` field.
+    #[inline]
+    pub fn always_trap_anyfuncs(&self) -> u32 {
+        self.always_trap_anyfuncs
+    }
+
+    /// The offset of `VMCallerCheckedAnyfunc` for the `index` specified.
+    #[inline]
+    pub fn always_trap_anyfunc(&self, index: RuntimeAlwaysTrapIndex) -> u32 {
+        assert!(index.as_u32() < self.num_always_trap);
+        self.always_trap_anyfuncs()
+            + index.as_u32() * u32::from(self.ptr.size_of_vmcaller_checked_anyfunc())
+    }
+
     /// The offset of the `lowerings` field.
     #[inline]
     pub fn lowerings(&self) -> u32 {