wasmtime: Privately expose a module's address map and its function's bytes (#5973)

This will allow us to build developer tools for Wasmtime and Cranelift like WAT
and asm side-by-side viewers (a la Godbolt).

These are not proper public APIs, so they are marked `doc(hidden)` and have
comments saying they are only for use within this repo's workspace.

crates/environ/src/address_map.rs

@@ -116,6 +116,23 @@ impl AddressMapSection {
     }
 }
 
+/// Parse an `ELF_WASMTIME_ADDRMAP` section, returning the slice of code offsets
+/// and the slice of associated file positions for each offset.
+fn parse_address_map(
+    section: &[u8],
+) -> Option<(&[U32Bytes<LittleEndian>], &[U32Bytes<LittleEndian>])> {
+    let mut section = Bytes(section);
+    // NB: this matches the encoding written by `append_to` above.
+    let count = section.read::<U32Bytes<LittleEndian>>().ok()?;
+    let count = usize::try_from(count.get(LittleEndian)).ok()?;
+    let (offsets, section) =
+        object::slice_from_bytes::<U32Bytes<LittleEndian>>(section.0, count).ok()?;
+    let (positions, section) =
+        object::slice_from_bytes::<U32Bytes<LittleEndian>>(section, count).ok()?;
+    debug_assert!(section.is_empty());
+    Some((offsets, positions))
+}
+
 /// Lookup an `offset` within an encoded address map section, returning the
 /// original `FilePos` that corresponds to the offset, if found.
 ///
@@ -127,15 +144,7 @@ impl AddressMapSection {
 /// section of the pc that is being looked up. If `offset` is out of range or
 /// doesn't correspond to anything in this file then `None` is returned.
 pub fn lookup_file_pos(section: &[u8], offset: usize) -> Option<FilePos> {
-    let mut section = Bytes(section);
+    let (offsets, positions) = parse_address_map(section)?;
-    // NB: this matches the encoding written by `append_to` above.
-    let count = section.read::<U32Bytes<LittleEndian>>().ok()?;
-    let count = usize::try_from(count.get(LittleEndian)).ok()?;
-    let (offsets, section) =
-        object::slice_from_bytes::<U32Bytes<LittleEndian>>(section.0, count).ok()?;
-    let (positions, section) =
-        object::slice_from_bytes::<U32Bytes<LittleEndian>>(section, count).ok()?;
-    debug_assert!(section.is_empty());
 
     // First perform a binary search on the `offsets` array. This is a sorted
     // array of offsets within the text section, which is conveniently what our
@@ -160,3 +169,24 @@ pub fn lookup_file_pos(section: &[u8], offset: usize) -> Option<FilePos> {
     let pos = positions.get(index)?;
     Some(FilePos(pos.get(LittleEndian)))
 }
+
+/// Iterate over the address map contained in the given address map section.
+///
+/// This function takes a `section` as its first argument which must have been
+/// created with `AddressMapSection` above. This is intended to be the raw
+/// `ELF_WASMTIME_ADDRMAP` section from the compilation artifact.
+///
+/// The yielded offsets are relative to the start of the text section for this
+/// map's code object.
+pub fn iterate_address_map<'a>(
+    section: &'a [u8],
+) -> Option<impl Iterator<Item = (u32, FilePos)> + 'a> {
+    let (offsets, positions) = parse_address_map(section)?;
+
+    Some(
+        offsets
+            .iter()
+            .map(|o| o.get(LittleEndian))
+            .zip(positions.iter().map(|pos| FilePos(pos.get(LittleEndian)))),
+    )
+}

crates/wasmtime/src/module.rs

@@ -1042,6 +1042,73 @@ impl Module {
         self.inner.memory_images()?;
         Ok(())
     }
+
+    /// Get the map from `.text` section offsets to Wasm binary offsets for this
+    /// module.
+    ///
+    /// Each entry is a (`.text` section offset, Wasm binary offset) pair.
+    ///
+    /// Entries are yielded in order of `.text` section offset.
+    ///
+    /// Some entries are missing a Wasm binary offset. This is for code that is
+    /// not associated with any single location in the Wasm binary, or for when
+    /// source information was optimized away.
+    ///
+    /// Not every module has an address map, since address map generation can be
+    /// turned off on `Config`.
+    ///
+    /// There is not an entry for every `.text` section offset. Every offset
+    /// after an entry's offset, but before the next entry's offset, is
+    /// considered to map to the same Wasm binary offset as the original
+    /// entry. For example, the address map will not contain the following
+    /// sequnce of entries:
+    ///
+    /// ```ignore
+    /// [
+    ///     // ...
+    ///     (10, Some(42)),
+    ///     (11, Some(42)),
+    ///     (12, Some(42)),
+    ///     (13, Some(43)),
+    ///     // ...
+    /// ]
+    /// ```
+    ///
+    /// Instead, it will drop the entries for offsets `11` and `12` since they
+    /// are the same as the entry for offset `10`:
+    ///
+    /// ```ignore
+    /// [
+    ///     // ...
+    ///     (10, Some(42)),
+    ///     (13, Some(43)),
+    ///     // ...
+    /// ]
+    /// ```
+    pub fn address_map<'a>(&'a self) -> Option<impl Iterator<Item = (usize, Option<u32>)> + 'a> {
+        Some(
+            wasmtime_environ::iterate_address_map(
+                self.code_object().code_memory().address_map_data(),
+            )?
+            .map(|(offset, file_pos)| (offset as usize, file_pos.file_offset())),
+        )
+    }
+
+    /// Get this module's code object's `.text` section, containing its compiled
+    /// executable code.
+    pub fn text(&self) -> &[u8] {
+        self.code_object().code_memory().text()
+    }
+
+    /// Get the locations of functions in this module's `.text` section.
+    ///
+    /// Each function's locartion is a (`.text` section offset, length) pair.
+    pub fn function_locations<'a>(&'a self) -> impl ExactSizeIterator<Item = (usize, usize)> + 'a {
+        self.compiled_module().finished_functions().map(|(f, _)| {
+            let loc = self.compiled_module().func_loc(f);
+            (loc.start as usize, loc.length as usize)
+        })
+    }
 }
 
 impl ModuleInner {