Use WASM function names in compiled objects (#8627)

* Use WASM function names in compiled objects

Instead of generating symbol names in the format
"wasm[$MODULE_ID]::function[$FUNCTION_INDEX]", generate (if possible)
something more readable, such as "wasm[$MODULE_ID]::$FUNCTION_NAME".
This helps when debugging or profiling the generated code.

Co-authored-by: Jamey Sharp <jsharp@fastly.com>

* Ensure symbol names are cleaned up and have function indexes

Filter symbol names to include only characters that are usually used
for function names, and that might be produced by name mangling.
Replace everything else with a question mark (and all repeated question
marks by a single one), and then truncate to a length of 96 characters.

This should be enough to not only avoid passing user-controlled strings
to tools such as "perf" and "objdump", and make it easier to
disambiguate symbols that might have the same name but different
indices.

* Make symbol cleaning slightly more efficient

* Update symbol names to be closer to what tests expect

* Ensure only alphanumeric ASCII characters are allowed in a symbol name

* Ensure sliced symbol name is within its bounds

* Update test expectations after adding function name to symbol name

---------

Co-authored-by: Jamey Sharp <jsharp@fastly.com>

crates/wasmtime/src/compile.rs

@@ -27,6 +27,7 @@ use crate::Engine;
 use anyhow::{Context, Result};
 use std::{
     any::Any,
+    borrow::Cow,
     collections::{btree_map, BTreeMap, BTreeSet, HashMap, HashSet},
     mem,
 };
@@ -419,6 +420,35 @@ impl<'a> CompileInputs<'a> {
         ret
     }
 
+    fn clean_symbol(name: &str) -> Cow<str> {
+        /// Maximum length of symbols generated in objects.
+        const MAX_SYMBOL_LEN: usize = 96;
+
+        // Just to be on the safe side, avoid passing user-provided data to tools
+        // like "perf" or "objdump", and filter the name.  Let only characters usually
+        // used for function names, plus some characters that might be used in name
+        // mangling.
+        let bad_char = |c: char| !c.is_ascii_alphanumeric() && !r"<>[]_-:@$".contains(c);
+        if name.chars().any(bad_char) {
+            let mut last_char_seen = '\u{0000}';
+            Cow::Owned(
+                name.chars()
+                    .map(|c| if bad_char(c) { '?' } else { c })
+                    .filter(|c| {
+                        let skip = last_char_seen == '?' && *c == '?';
+                        last_char_seen = *c;
+                        !skip
+                    })
+                    .take(MAX_SYMBOL_LEN)
+                    .collect::<String>(),
+            )
+        } else if name.len() <= MAX_SYMBOL_LEN {
+            Cow::Borrowed(&name[..])
+        } else {
+            Cow::Borrowed(&name[..MAX_SYMBOL_LEN])
+        }
+    }
+
     fn collect_inputs_in_translations(
         &mut self,
         types: &'a ModuleTypesBuilder,
@@ -436,13 +466,28 @@ impl<'a> CompileInputs<'a> {
                     let func_index = translation.module.func_index(def_func_index);
                     let (info, function) =
                         compiler.compile_function(translation, def_func_index, func_body, types)?;
-                    Ok(CompileOutput {
-                        key: CompileKey::wasm_function(module, def_func_index),
-                        symbol: format!(
+                    let symbol = match translation
+                        .debuginfo
+                        .name_section
+                        .func_names
+                        .get(&func_index)
+                    {
+                        Some(name) => format!(
+                            "wasm[{}]::function[{}]::{}",
+                            module.as_u32(),
+                            func_index.as_u32(),
+                            Self::clean_symbol(&name)
+                        ),
+                        None => format!(
                             "wasm[{}]::function[{}]",
                             module.as_u32(),
                             func_index.as_u32()
                         ),
+                    };
+
+                    Ok(CompileOutput {
+                        key: CompileKey::wasm_function(module, def_func_index),
+                        symbol,
                         function: CompiledFunction::Function(function),
                         info: Some(info),
                     })

tests/disas/winch/x64/block/as_if_cond.wat

@@ -8,7 +8,7 @@
   )
 )
 
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/block/deep.wat

@@ -45,7 +45,7 @@
     ))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/block/empty.wat

@@ -9,7 +9,7 @@
     (block $l)
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/block/nested.wat

@@ -10,7 +10,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_block_first.wat

@@ -7,7 +7,7 @@
     (block (br 0) (call $dummy))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_block_last.wat

@@ -7,7 +7,7 @@
     (block (nop) (call $dummy) (br 0))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_block_mid.wat

@@ -7,7 +7,7 @@
     (block (call $dummy) (br 0) (call $dummy))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_block_value.wat

@@ -7,7 +7,7 @@
     (block (result i32) (nop) (call $dummy) (br 0 (i32.const 2)))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_call_all.wat

@@ -6,7 +6,7 @@
     (block (result i32) (call $f (br 0 (i32.const 15))))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_call_first.wat

@@ -9,7 +9,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_call_last.wat

@@ -8,7 +8,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_call_mid.wat

@@ -9,7 +9,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_loop_last.wat

@@ -8,7 +8,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br/as_loop_mid.wat

@@ -9,7 +9,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_block_last.wat

@@ -6,7 +6,7 @@
     (block (call $dummy) (call $dummy) (br_if 0 (local.get 0)))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_block_last_value.wat

@@ -8,7 +8,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_call_first.wat

@@ -10,7 +10,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_call_last.wat

@@ -10,7 +10,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_call_mid.wat

@@ -10,7 +10,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_if_else.wat

@@ -9,7 +9,7 @@
   )
 )
 
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_if_then.wat

@@ -8,7 +8,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/br_if/as_loop_last.wat

@@ -6,7 +6,7 @@
     (loop (call $dummy) (br_if 1 (local.get 0)))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/call/params.wat

@@ -119,7 +119,7 @@
 ;;       retq
 ;;  152: ud2
 ;;
-;; wasm[0]::function[1]:
+;; wasm[0]::function[1]::add:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/call/recursive.wat

@@ -23,7 +23,7 @@
   )
   (export "fib" (func $fibonacci8))
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::fibonacci8:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/call/simple.wat

@@ -14,7 +14,7 @@
     (local.get 1)
     (i32.mul))
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::main:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11
@@ -53,7 +53,7 @@
 ;;       retq
 ;;   8b: ud2
 ;;
-;; wasm[0]::function[1]:
+;; wasm[0]::function[1]::product:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/f32_const/call_id.wat

@@ -5,7 +5,7 @@
   (func $id-f32 (param f32) (result f32) (local.get 0))
   (func (export "type-first-f32") (result f32) (call $id-f32 (f32.const 1.32)))
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::id-f32:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/f64_const/call_id.wat

@@ -5,7 +5,7 @@
   (func $id-f64 (param f64) (result f64) (local.get 0))
   (func (export "type-first-f64") (result f64) (call $id-f64 (f64.const 1.32)))
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::id-f64:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/if/as_binop.wat

@@ -16,7 +16,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/if/as_br_if_last.wat

@@ -15,7 +15,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/if/as_if_cond.wat

@@ -13,7 +13,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/if/as_testop.wat

@@ -11,7 +11,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/if/nested.wat

@@ -23,7 +23,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/if/singular.wat

@@ -9,7 +9,7 @@
     (if (result i32) (local.get 0) (then (i32.const 7)) (else (i32.const 8)))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/loop/as_binary_operand.wat

@@ -9,7 +9,7 @@
     )
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::dummy:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11

tests/disas/winch/x64/loop/as_call_value.wat

@@ -6,7 +6,7 @@
     (call $f (loop (result i32) (i32.const 1)))
   )
 )
-;; wasm[0]::function[0]:
+;; wasm[0]::function[0]::f:
 ;;       pushq   %rbp
 ;;       movq    %rsp, %rbp
 ;;       movq    8(%rdi), %r11