Add initial support for code metadata (#1840)

See https://github.com/WebAssembly/tool-conventions/blob/main/CodeMetadata.md  for the specification.

In particular this pr implements the following:

- Parsing code metadata sections in BinaryReader, providing appropriate callbacks that a BinaryReaderDelegate can implement:
    - BinaryReaderObjdump: show the sections in a human-readable form
    - BinaryReaderIr: add code metadata in the IR as expressions
- Parsing code metadata annotations in text format, adding them in the IR like the BinaryReaderIR does
- Writing the code metadata present in the IR in the proper sections when converting IR to binary
- Support in wasm-decompiler for showing code metadata as comments in the pseudo-code

All the features have corresponding tests.

Support for code metadata is gated through the --enable-code-metadata feature. For reading/writing in the text format, --enable-annotations is also required.

Missing features:

    Support for function-level code metadata (offset 0)
    Extensive validation in validator.cc (like making sure that all metadata instances are at the same code offset of an instruction)

8 files changed, 538 insertions, 0 deletions

diff --git a/test/binary/bad-code-metadata-function-count.txt b/test/binary/bad-code-metadata-function-count.txt
new file mode 100644
index 00000000..50da843a
--- /dev/null
+++ b/test/binary/bad-code-metadata-function-count.txt
@@ -0,0 +1,65 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[2]
+  function_index[0]
+  ann_count[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+0000033: warning: unable to read u32 leb128: function index
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-function-count.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[0]:
+    - meta[1]:
+     - 0000000: 01                                       .
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+000037 func[0]:
+ 000038: 41 01                      | i32.const 1
+ 00003a: 0f                         | return
+ 00003b: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/bad-code-metadata-function-duplicate.txt b/test/binary/bad-code-metadata-function-duplicate.txt
new file mode 100644
index 00000000..4173ece2
--- /dev/null
+++ b/test/binary/bad-code-metadata-function-duplicate.txt
@@ -0,0 +1,67 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[2]
+  function_index[0]
+  ann_count[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+  function_index[0]
+  ann_count[0]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+0000034: warning: duplicate function index: 0
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-function-duplicate.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[0]:
+    - meta[1]:
+     - 0000000: 01                                       .
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+000039 func[0]:
+ 00003a: 41 01                      | i32.const 1
+ 00003c: 0f                         | return
+ 00003d: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/bad-code-metadata-function-index.txt b/test/binary/bad-code-metadata-function-index.txt
new file mode 100644
index 00000000..48bd19c6
--- /dev/null
+++ b/test/binary/bad-code-metadata-function-index.txt
@@ -0,0 +1,62 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[1]
+  function_index[2]
+  ann_count[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+000002f: warning: invalid function index: 2
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-function-index.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+000037 func[0]:
+ 000038: 41 01                      | i32.const 1
+ 00003a: 0f                         | return
+ 00003b: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/bad-code-metadata-function-out-of-order.txt b/test/binary/bad-code-metadata-function-out-of-order.txt
new file mode 100644
index 00000000..b0c05890
--- /dev/null
+++ b/test/binary/bad-code-metadata-function-out-of-order.txt
@@ -0,0 +1,82 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[2]
+  type[0]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[2]
+  function_index[1]
+  ann_count[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+  function_index[0]
+  ann_count[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[2]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+0000035: warning: function index out of order: 0
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-function-out-of-order.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[2]:
+ - func[0] sig=0
+ - func[1] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[1]:
+    - meta[1]:
+     - 0000000: 01                                       .
+Code[2]:
+ - func[0] size=5
+ - func[1] size=5
+
+Code Disassembly:
+
+00003d func[0]:
+ 00003e: 41 01                      | i32.const 1
+ 000040: 0f                         | return
+ 000041: 0b                         | end
+000043 func[1]:
+ 000044: 41 01                      | i32.const 1
+ 000046: 0f                         | return
+ 000047: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/bad-code-metadata-instance-count.txt b/test/binary/bad-code-metadata-instance-count.txt
new file mode 100644
index 00000000..c8be5895
--- /dev/null
+++ b/test/binary/bad-code-metadata-instance-count.txt
@@ -0,0 +1,65 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[1]
+  function_index[0]
+  ann_count[2]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+0000033: warning: unable to read u32 leb128: code offset
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-instance-count.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[0]:
+    - meta[1]:
+     - 0000000: 01                                       .
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+000037 func[0]:
+ 000038: 41 01                      | i32.const 1
+ 00003a: 0f                         | return
+ 00003b: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/bad-code-metadata-instance-duplicate.txt b/test/binary/bad-code-metadata-instance-duplicate.txt
new file mode 100644
index 00000000..95723713
--- /dev/null
+++ b/test/binary/bad-code-metadata-instance-duplicate.txt
@@ -0,0 +1,68 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[1]
+  function_index[0]
+  ann_count[2]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+0000034: warning: duplicate code offset: 1
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-instance-duplicate.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[0]:
+    - meta[1]:
+     - 0000000: 01                                       .
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+00003a func[0]:
+ 00003b: 41 01                      | i32.const 1
+ 00003d: 0f                         | return
+ 00003e: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/bad-code-metadata-instance-out-of-order.txt b/test/binary/bad-code-metadata-instance-out-of-order.txt
new file mode 100644
index 00000000..4efb85d8
--- /dev/null
+++ b/test/binary/bad-code-metadata-instance-out-of-order.txt
@@ -0,0 +1,68 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS1: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[1]
+  function_index[0]
+  ann_count[2]
+  ann_offset[3]
+  ann_data_size[1]
+  ann_data[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+
+(;; STDERR ;;;
+0000034: warning: code offset out of order: 1
+;;; STDERR ;;)
+(;; STDOUT ;;;
+
+bad-code-metadata-instance-out-of-order.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[0]:
+    - meta[3]:
+     - 0000000: 01                                       .
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+00003a func[0]:
+ 00003b: 41 01                      | i32.const 1
+ 00003d: 0f                         | return
+ 00003e: 0b                         | end
+;;; STDOUT ;;)
diff --git a/test/binary/code-metadata-section.txt b/test/binary/code-metadata-section.txt
new file mode 100644
index 00000000..9625f602
--- /dev/null
+++ b/test/binary/code-metadata-section.txt
@@ -0,0 +1,61 @@
+;;; TOOL: run-objdump-gen-wasm
+;;; ARGS: -x
+magic
+version
+section(TYPE) {
+  count[1]
+  function params[0] results[1] i32
+}
+section(FUNCTION) {
+  count[1]
+  type[0]
+}
+section(MEMORY) {
+  count[1]
+  has_max[0]
+  initial[0]
+}
+section("metadata.code.test") {
+  function_count[1]
+  function_index[0]
+  ann_count[1]
+  ann_offset[1]
+  ann_data_size[1]
+  ann_data[1]
+}
+
+section(CODE) {
+  count[1]
+  func {
+    local_decls[0]
+    i32.const 1
+    return
+  }
+}
+(;; STDOUT ;;;
+
+code-metadata-section.wasm:	file format wasm 0x1
+
+Section Details:
+
+Type[1]:
+ - type[0] () -> i32
+Function[1]:
+ - func[0] sig=0
+Memory[1]:
+ - memory[0] pages: initial=0
+Custom:
+ - name: "metadata.code.test"
+   - func[0]:
+    - meta[1]:
+     - 0000000: 01                                       .
+Code[1]:
+ - func[0] size=5
+
+Code Disassembly:
+
+000037 func[0]:
+ 000038: 41 01                      | i32.const 1
+ 00003a: 0f                         | return
+ 00003b: 0b                         | end
+;;; STDOUT ;;)