Use a customized codeql configration

- Specifying directories to scan
- Refactor build script for WAMR project
  - add functions for wamrc and iwasm builds
  - streamline options handling
  - include LLVM installation steps.
- Filter out source code related to dependencies, testing,
  and wasm applications
- Exclude unimportant issues and coding style problems

.github/actions/install-wasi-sdk-wabt/action.yml

@@ -30,14 +30,23 @@ runs:
       if: ${{ startsWith(inputs.os, 'ubuntu') }}
       shell: bash
       run: |
+        echo "Downloading wasi-sdk for Ubuntu..."
         sudo wget -O wasi-sdk.tar.gz --progress=dot:giga https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-25/wasi-sdk-25.0-x86_64-linux.tar.gz
+
+        echo "Extracting wasi-sdk..."
         sudo tar -xf wasi-sdk.tar.gz
         sudo ln -sf  wasi-sdk-25.0-x86_64-linux/ wasi-sdk
+
+        echo "Downloading wabt for Ubuntu..."
         sudo wget -O wabt.tar.gz     --progress=dot:giga https://github.com/WebAssembly/wabt/releases/download/1.0.37/wabt-1.0.37-ubuntu-20.04.tar.gz
+
+        echo "Extracting wabt..."
         sudo tar -xf wabt.tar.gz
         sudo ln -sf  wabt-1.0.37 wabt
+
         /opt/wasi-sdk/bin/clang --version
         /opt/wabt/bin/wasm-interp --version
+
         echo "::notice::wasi-sdk-25 and wabt-1.0.37 installed on ubuntu"
       working-directory: /opt
 
@@ -45,14 +54,23 @@ runs:
       if: ${{ inputs.os == 'macos-13' }}
       shell: bash
       run: |
+        echo "Downloading wasi-sdk for macOS-13..."
         sudo wget -O wasi-sdk.tar.gz --progress=dot:giga https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-25/wasi-sdk-25.0-x86_64-macos.tar.gz
+
+        echo "Extracting wasi-sdk..."
         sudo tar -xf wasi-sdk.tar.gz
         sudo ln -sf  wasi-sdk-25.0-x86_64-macos wasi-sdk
+
+        echo "Downloading wabt for macOS-13..."
         sudo wget -O wabt.tar.gz     --progress=dot:giga https://github.com/WebAssembly/wabt/releases/download/1.0.36/wabt-1.0.36-macos-12.tar.gz
+
+        echo "Extracting wabt..."
         sudo tar -xf wabt.tar.gz
         sudo ln -sf  wabt-1.0.36 wabt
+
         /opt/wasi-sdk/bin/clang --version
         /opt/wabt/bin/wasm-interp --version
+
         echo "::notice::wasi-sdk-25 and wabt-1.0.36 installed on macos-13"
       working-directory: /opt
 
@@ -60,21 +78,48 @@ runs:
       if: ${{ inputs.os == 'macos-14' }}
       shell: bash
       run: |
+        echo "Downloading wasi-sdk for macOS-14..."
         sudo wget -O wasi-sdk.tar.gz --progress=dot:giga https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-25/wasi-sdk-25.0-arm64-macos.tar.gz
+
+        echo "Extracting wasi-sdk..."
         sudo tar -xf wasi-sdk.tar.gz
         sudo ln -sf  wasi-sdk-25.0-arm64-macos wasi-sdk
+
+        echo "Downloading wabt for macOS-14..."
         sudo wget -O wabt.tar.gz     --progress=dot:giga https://github.com/WebAssembly/wabt/releases/download/1.0.37/wabt-1.0.37-macos-14.tar.gz
+
+        echo "Extracting wabt..."
         sudo tar -xf wabt.tar.gz
         sudo ln -sf  wabt-1.0.37 wabt
+
         /opt/wasi-sdk/bin/clang --version
         /opt/wabt/bin/wasm-interp --version
+
         echo "::notice::wasi-sdk-25 and wabt-1.0.37 installed on macos-14"
       working-directory: /opt
 
-    #TODO: Add support for Windows
     - name: Set up wasi-sdk and wabt on Windows
       if: ${{ startsWith(inputs.os, 'windows') }}
-      shell: powershell
+      shell: bash
       run: |
-        echo "::notice::Support for Windows is not implemented yet"
-        exit 1
+        choco install -y wget
+
+        mkdir -p /opt/wasi-sdk
+        mkdir -p /opt/wabt
+
+        echo "Downloading wasi-sdk for Windows..."
+        wget -O wasi-sdk.tar.gz --progress=dot:giga https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-25/wasi-sdk-25.0-x86_64-windows.tar.gz
+
+        echo "Extracting wasi-sdk..."
+        tar --strip-components=1 -xf wasi-sdk.tar.gz -C /opt/wasi-sdk
+
+        echo "Downloading wabt for Windows..."
+        wget -O wabt.tar.gz --progress=dot:giga https://github.com/WebAssembly/wabt/releases/download/1.0.37/wabt-1.0.37-windows.tar.gz
+
+        echo "Extracting wabt..."
+        tar --strip-components=1 -xf wabt.tar.gz -C /opt/wabt
+
+        /opt/wasi-sdk/bin/clang --version
+        /opt/wabt/bin/wasm-interp --version
+
+        echo "::notice::wasi-sdk-25 and wabt-1.0.37 installed on Windows"

.github/codeql/codeql_config.yml

@@ -0,0 +1,46 @@
+# Copyright (C) 2019 Intel Corporation.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+paths:
+  - .github
+  - core/iwasm
+  - core/shared/platform/common/
+  - core/shared/platform/include/
+  - core/shared/platform/linux/
+  - product-mini/platforms/common/
+  - product-mini/platforms/linux/
+  # TODO: add other platforms back if able to do cross-compilation
+  # - product-mini/platforms/
+  # TODO: add samples back after buildscript modification
+  # - need to ignore workloads and wasm-apps
+  # - samples
+  - wamr-compiler/
+paths-ignore:
+  # always ignore build
+  - '**/build/**'
+  - '**/test*/**'
+  - '**/wasm-app*/**'
+  - core/deps/
+  # platform specific
+  - core/iwasm/aot/arch/aot_reloc_aarch64.c
+  - core/iwasm/aot/arch/aot_reloc_arc.c
+  - core/iwasm/aot/arch/aot_reloc_arm.c
+  - core/iwasm/aot/arch/aot_reloc_dummy.c
+  - core/iwasm/aot/arch/aot_reloc_mips.c
+  - core/iwasm/aot/arch/aot_reloc_riscv.c
+  - core/iwasm/aot/arch/aot_reloc_thumb.c
+  - core/iwasm/aot/arch/aot_reloc_xtensa.c
+  - core/iwasm/libraries/lib-rats/
+  - core/iwasm/libraries/lib-socket/
+  - core/iwasm/libraries/lib-wasi-threads/*-test/
+  - core/shared/platform/common/freertos/
+  - core/shared/platform/common/math/
+  #TODO: add me back if lldb libraries installed
+  - core/iwasm/compilation/debug/
+  # spend disk space and slow
+  - core/iwasm/libraries/wasi-nn/src/wasi_nn_tflite*
+  #TODO: add me back if openvino installed
+  - core/iwasm/libraries/wasi-nn/src/wasi_nn_openvino*
+  # for wasm
+  - core/iwasm/libraries/wasi-nn/include/wasi_nn.h
+  # reference
+  - core/iwasm/common/arch/invokeNative_general.c

.github/scripts/codeql_buildscript.sh

@@ -5,308 +5,117 @@
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 #
 
-sudo apt update
+# This script is used to build the WAMR project for CodeQL analysis.
 
-sudo apt install -y build-essential cmake g++-multilib libgcc-12-dev lib32gcc-12-dev ccache ninja-build
+# Pre-requisites
+sudo apt -qq update
+sudo apt install -y -qq build-essential cmake g++-multilib libgcc-12-dev lib32gcc-12-dev ccache ninja-build
 
+LLVM_VER=18.1.8
+pushd /opt
+sudo wget --progress=dot:giga -O clang+llvm-x86_64-linux-gnu.tar.xz https://github.com/llvm/llvm-project/releases/download/llvmorg-${LLVM_VER}/clang+llvm-${LLVM_VER}-x86_64-linux-gnu-ubuntu-18.04.tar.xz \
+  && tar -xf clang+llvm-x86_64-linux-gnu.tar.xz \
+  && mv clang+llvm-${LLVM_VER}-x86_64-linux-gnu-ubuntu-18.04 llvm-${LLVM_VER}
+popd
+
+# libtinfo.so.5 for /opt/llvm-18.1.8/lib/libomptarget.rtl.amdgpu.so.18.1
+sudo apt -qq update
+wget http://security.ubuntu.com/ubuntu/pool/universe/n/ncurses/libtinfo5_6.3-2ubuntu0.1_amd64.deb
+sudo apt install -y -qq ./libtinfo5_6.3-2ubuntu0.1_amd64.deb
+
+# Start the build process
 WAMR_DIR=${PWD}
+LLVM_DIR=/opt/llvm-${LLVM_VER}/lib/cmake/llvm
 
-# TODO: use pre-built llvm binary to build wamrc to
-#       avoid static code analysing for llvm
-: '
-# build wamrc
-cd ${WAMR_DIR}/wamr-compiler
-./build_llvm.sh
-rm -fr build && mkdir build && cd build
-cmake ..
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build wamrc!"
-    exit 1;
-fi
-'
+# Function to build wamrc
+build_wamrc() {
+    local options="$1"
+    echo "Building wamrc with options: $options"
 
-# build iwasm with default features enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -fr build && mkdir build && cd build
-cmake ..
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with default features enabled!"
-    exit 1;
-fi
+    pushd ${WAMR_DIR}/wamr-compiler
+    rm -rf build
+    cmake -S . -B build \
+        -G Ninja \
+        -DCMAKE_BUILD_TYPE=Debug \
+        -DWAMR_BUILD_WITH_CUSTOM_LLVM=1 -DLLVM_DIR=${LLVM_DIR} \
+        $options
+    cmake --build build --target wamrc --parallel
+    if [[ $? != 0 ]]; then
+        echo "Failed to build wamrc with options: $options"
+        exit 1
+    fi
+    popd
+}
 
-# build iwasm with default features enabled on x86_32
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -fr build && mkdir build && cd build
-cmake .. -DWAMR_BUILD_TARGET=X86_32
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with default features enabled on x86_32!"
-    exit 1;
-fi
+# Function to build iwasm
+build_iwasm() {
+    local options="$1"
+    echo "Building iwasm with options: $options"
 
-# build iwasm with classic interpreter enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_FAST_INTERP=0
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with classic interpreter enabled!"
-    exit 1;
-fi
+    pushd ${WAMR_DIR}/product-mini/platforms/linux
+    rm -rf build
+    cmake -S . -B build \
+        -G Ninja \
+        -DCMAKE_BUILD_TYPE=Debug \
+        -DLLVM_DIR=${LLVM_DIR} \
+        $options
+    cmake --build build --target iwasm --parallel
+    if [[ $? != 0 ]]; then
+        echo "Failed to build iwasm with options: $options"
+        exit 1
+    fi
+    popd
+}
 
-# build iwasm with extra features enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -fr build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug \
-    -DWAMR_BUILD_LIB_PTHREAD=1 -DWAMR_BUILD_LIB_PTHREAD_SEMAPHORE=1 \
-    -DWAMR_BUILD_MULTI_MODULE=1 -DWAMR_BUILD_SIMD=1 \
-    -DWAMR_BUILD_TAIL_CALL=1 -DWAMR_BUILD_REF_TYPES=1 \
-    -DWAMR_BUILD_CUSTOM_NAME_SECTION=1 -DWAMR_BUILD_MEMORY_PROFILING=1 \
-    -DWAMR_BUILD_PERF_PROFILING=1 -DWAMR_BUILD_DUMP_CALL_STACK=1 \
-    -DWAMR_BUILD_LOAD_CUSTOM_SECTION=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build wamrc iwasm with extra features enabled!"
-    exit 1;
-fi
+# List of compilation options for wamrc
+wamrc_options_list=(
+    #default
+    ""
+)
 
-# build iwasm with global heap pool enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -fr build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug \
-    -DWAMR_BUILD_ALLOC_WITH_USER_DATA=1 \
-    -DWAMR_DISABLE_STACK_HW_BOUND_CHECK=1 \
-    -DWAMR_BUILD_GLOBAL_HEAP_POOL=1 \
-    -DWAMR_BUILD_GLOBAL_HEAP_SIZE=131072
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with global heap pool enabled!"
-    exit 1;
-fi
+# List of compilation options for iwasm
+iwasm_options_list=(
+    #default
+    ""
+    # +classic interp
+    "-DWAMR_BUILD_FAST_INTERP=0"
+    # +llvm jit + fast jit
+    "-DWAMR_BUILD_JIT=1 -DWAMR_BUILD_FAST_JIT=1 -DWAMR_BUILD_FAST_JIT_DUMP=1"
+    #
+    "-DWAMR_BUILD_TARGET=X86_32"
+    #
+    # libraries
+    "-DWAMR_BUILD_LIBC_BUILTIN=0 -DWAMR_BUILD_LIBC_UVWASI=1 -DWAMR_BUILD_LIBC_EMCC=1"
+    "-DWAMR_BUILD_THREAD_MGR=1 -DWAMR_BUILD_LIB_PTHREAD=1      -DWAMR_BUILD_SHARED_MEMORY=1 -DWAMR_BUILD_LIB_PTHREAD_SEMAPHORE=1"
+    "-DWAMR_BUILD_THREAD_MGR=1 -DWAMR_BUILD_LIB_WASI_THREADS=1 -DWAMR_BUILD_SHARED_MEMORY=1 -DWAMR_BUILD_LIB_PTHREAD_SEMAPHORE=1"
+    "-DWAMR_BUILD_WASI_NN=1 -DWAMR_BUILD_WASI_NN_LLAMACPP=1"
+    #
+    # Wasm specs
+    "-DWAMR_BUILD_GC=1 -DWAMR_BUILD_EXCE_HANDLING=1 -DWAMR_BUILD_STRINGREF=1 -DWAMR_STRINGREF_IMPL_SOURCE=STUB"
+    "-DWAMR_BUILD_MEMORY64=1 -DWAMR_BUILD_MULTI_MEMORY=1"
+    #
+    # WARM features
+    "-DWAMR_BUILD_MULTI_MODULE=1 -DWAMR_BUILD_MINI_LOADER=1 -DWAMR_BUILD_SHARED_HEAP=1"
+    "-DWAMR_DISABLE_HW_BOUND_CHECK=1"
+    "-DWAMR_CONFIGURABLE_BOUNDS_CHECKS=1"
+    # - Debug
+    "-DWAMR_BUILD_DEBUG_INTERP=1 -DWAMR_BUILD_DEBUG_AOT=1 -DWAMR_BUILD_DYNAMIC_AOT_DEBUG=1"
+    # - developer options
+    "-DWAMR_BUILD_CUSTOM_NAME_SECTION=1  -DWAMR_BUILD_LOAD_CUSTOM_SECTION=1 -DWAMR_BUILD_DUMP_CALL_STACK=1 -DWAMR_BUILD_LINUX_PERF=1 -DWAMR_BUILD_AOT_VALIDATOR=1 -DWAMR_BUILD_MEMORY_PROFILING=1 -DWAMR_BUILD_PERF_PROFILING=1"
+    # - global heap
+    "-DWAMR_BUILD_ALLOC_WITH_USER_DATA=1  -DWAMR_BUILD_GLOBAL_HEAP_POOL=1 -DWAMR_BUILD_GLOBAL_HEAP_SIZE=131072"
+    "-DWAMR_BUILD_QUICK_AOT_ENTRY=0 -DWAMR_DISABLE_WAKEUP_BLOCKING_OP=1 -DWAMR_BUILD_MODULE_INST_CONTEXT=0"
+    # - pgo
+    "-DWAMR_BUILD_STATIC_PGO=1"
+    # TODO: SGX specifics.
+)
 
-# build iwasm with wasi-threads enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -fr build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_LIB_WASI_THREADS=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with wasi-threads enabled!"
-    exit 1;
-fi
+# Loop through all iwasm options and build
+for options in "${iwasm_options_list[@]}"; do
+    build_iwasm "$options"
+done
 
-# build iwasm with GC enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_GC=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with GC enabled!"
-    exit 1;
-fi
-
-# build iwasm with exception handling enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_EXCE_HANDLING=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with exception handling enabled!"
-    exit 1;
-fi
-
-# build iwasm with memory64 enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_MEMORY64=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with memory64 enabled!"
-    exit 1;
-fi
-
-# build iwasm with multi-memory enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_MULTI_MEMORY=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with multi-memory enabled!"
-    exit 1;
-fi
-
-# build iwasm with hardware boundary check disabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_DISABLE_HW_BOUND_CHECK=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with hardware boundary check disabled!"
-    exit 1;
-fi
-
-# build iwasm with quick AOT entry disabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_QUICK_AOT_ENTRY=0
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with quick AOT entry disabled!"
-    exit 1;
-fi
-
-# build iwasm with wakeup of blocking operations disabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_DISABLE_WAKEUP_BLOCKING_OP=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with wakeup of blocking operations disabled!"
-    exit 1;
-fi
-
-# build iwasm with module instance context disabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_MODULE_INST_CONTEXT=0 \
-         -DWAMR_BUILD_LIBC_BUILTIN=0 -DWAMR_BUILD_LIBC_WASI=0
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with module instance context disabled!"
-    exit 1;
-fi
-
-# build iwasm with libc-uvwasi enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -fr build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_LIBC_UVWASI=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with libc-uvwasi enabled!"
-    exit 1;
-fi
-
-# build iwasm with fast jit lazy mode enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_FAST_JIT=1 -DWAMR_BUILD_FAST_JIT_DUMP=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with fast jit lazy mode enabled!"
-    exit 1;
-fi
-
-# build iwasm with fast jit eager mode enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_FAST_JIT=1 -DWAMR_BUILD_FAST_JIT_DUMP=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with fast jit eager mode enabled!"
-    exit 1;
-fi
-
-# TODO: use pre-built llvm binary to build llvm-jit and multi-tier-jit
-: '
-# build iwasm with llvm jit lazy mode enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_JIT=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build llvm jit lazy mode enabled!"
-    exit 1;
-fi
-
-# build iwasm with llvm jit eager mode enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_JIT=1 -DWAMR_BUILD_LAZY_JIT=0
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build llvm jit eager mode enabled!"
-    exit 1;
-fi
-
-# build iwasm with multi-tier jit enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_FAST_JIT=1 -DWAMR_BUILD_JIT=1 \
-                                    -DWAMR_BUILD_FAST_JIT_DUMP=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with multi-tier jit enabled!"
-    exit 1;
-fi
-'
-
-# build iwasm with wasm mini-loader enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_MINI_LOADER=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build with wasm mini-loader enabled!"
-    exit 1;
-fi
-
-# build iwasm with source debugging enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_DEBUG_INTERP=1 -DWAMR_BUILD_DEBUG_AOT=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with source debugging enabled!"
-    exit 1;
-fi
-
-# build iwasm with AOT static PGO enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_STATIC_PGO=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with AOT static PGO enabled!"
-    exit 1;
-fi
-
-# build iwasm with configurable bounds checks enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_CONFIGURABLE_BOUNDS_CHECKS=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with configurable bounds checks enabled!"
-    exit 1;
-fi
-
-# build iwasm with linux perf support enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux/
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_LINUX_PERF=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with linux perf support enabled!"
-    exit 1;
-fi
-
-# build iwasm with shared heap enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_SHARED_HEAP=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm with shared heap enabled!"
-    exit 1;
-fi
-
-# build iwasm with dynamic aot debug enabled
-cd ${WAMR_DIR}/product-mini/platforms/linux
-rm -rf build && mkdir build && cd build
-cmake .. -DCMAKE_BUILD_TYPE=Debug -DWAMR_BUILD_DYNAMIC_AOT_DEBUG=1
-make -j
-if [[ $? != 0 ]]; then
-    echo "Failed to build iwasm dynamic aot debug enabled!"
-    exit 1;
-fi
+# Loop through all wamrc options and build
+for options in "${wamrc_options_list[@]}"; do
+    build_wamrc "$options"
+done

.github/workflows/build_iwasm_release.yml

@@ -23,7 +23,7 @@ on:
         type: string
         required: true
       upload_url:
-        description: a semantic version number. it is required when `release` is true.
+        description: upload binary assets to the URL of release
         type: string
         required: false
       ver_num:
@@ -137,7 +137,8 @@ jobs:
       - name: compress the binary on non-Windows
         if: inputs.runner != 'windows-latest'
         run: |
-          tar czf iwasm${{ matrix.suffix }}-${{ inputs.ver_num }}-${{ inputs.runner }}.tar.gz iwasm
+          # Follow the symlink to the actual binary file
+          tar --dereference -czf iwasm${{ matrix.suffix }}-${{ inputs.ver_num }}-${{ inputs.runner }}.tar.gz iwasm
           zip iwasm${{ matrix.suffix }}-${{ inputs.ver_num }}-${{ inputs.runner }}.zip iwasm
         working-directory: ${{ inputs.cwd }}/build
 

.github/workflows/build_wamr_wasi_extensions.yml

@@ -0,0 +1,57 @@
+# Copyright (C) 2019 Intel Corporation.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+name: build wamr_wasi_extensions release
+
+on:
+  workflow_call:
+    inputs:
+      upload_url:
+        description: upload binary assets to the URL of release
+        type: string
+        required: false
+      ver_num:
+        description: a semantic version number. it is required when `release` is true.
+        type: string
+        required: false
+
+permissions:
+  contents: read
+
+jobs:
+  build_wamr_wasi_extensions:
+    runs-on: ${{ matrix.os }}
+    permissions:
+      contents: write # for uploading release artifacts
+    strategy:
+      matrix:
+        os: [ubuntu-22.04]
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: install-wasi-sdk-wabt
+        uses: ./.github/actions/install-wasi-sdk-wabt
+        with:
+          os: ${{ matrix.os }}
+
+      - name: Build wamr-wasi-extensions
+        run: |
+          mkdir dist
+          ./build_libs.sh $(pwd)/dist/wamr-wasi-extensions
+        working-directory: wamr-wasi-extensions
+
+      - name: Compress the binary
+        run: |
+          zip -r wamr-wasi-extensions-${{ inputs.ver_num }}.zip wamr-wasi-extensions
+        working-directory: wamr-wasi-extensions/dist
+
+      - name: Upload release zip
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ inputs.upload_url }}
+          asset_path: wamr-wasi-extensions/dist/wamr-wasi-extensions-${{ inputs.ver_num }}.zip
+          asset_name: wamr-wasi-extensions-${{ inputs.ver_num }}.zip
+          asset_content_type: application/zip

.github/workflows/build_wamrc.yml

@@ -23,7 +23,7 @@ on:
         type: string
         required: true
       upload_url:
-        description: a semantic version number. it is required when `release` is true.
+        description: upload binary assets to the URL of release
         type: string
         required: false
       ver_num:
@@ -73,7 +73,8 @@ jobs:
       - name: compress the binary on non-Windows
         if: inputs.runner != 'windows-latest' && inputs.release
         run: |
-          tar czf wamrc-${{ inputs.ver_num }}-${{ inputs.runner }}.tar.gz wamrc
+          # Follow the symlink to the actual binary file
+          tar --dereference -czf wamrc-${{ inputs.ver_num }}-${{ inputs.runner }}.tar.gz wamrc
           zip wamrc-${{ inputs.ver_num }}-${{ inputs.runner }}.zip wamrc
         working-directory: wamr-compiler/build
 

.github/workflows/codeql.yml

@@ -1,29 +1,24 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-#
+# Copyright (C) 2019 Intel Corporation.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
 name: "CodeQL"
 
 on:
-  #pull_request:
-  #  types:
-  #    - opened
-  #  branches: '*'
-  #push:
-  #   branches: [ "main" ]
-  # midnight UTC
+  # run on every push to the feature-development branch
+  # the main branch is covered by below cron plan
+  push:
+    branches:
+      - dev/**
+  # midnight UTC on the latest commit on the main branch
   schedule:
-    - cron: '0 0 * * *'
+    - cron: "0 0 * * *"
   # allow to be triggered manually
   workflow_dispatch:
 
-permissions:
-  contents: read
-
 jobs:
   analyze:
+    # only run this job if the repository is not a fork
+    # if want to run this job on a fork, please remove the if condition
     if: github.repository == 'bytecodealliance/wasm-micro-runtime'
     name: Analyze
     # Runner size impacts CodeQL analysis time. To learn more, please see:
@@ -31,14 +26,15 @@ jobs:
     #   - https://gh.io/supported-runners-and-hardware-resources
     #   - https://gh.io/using-larger-runners
     # Consider using larger runners for possible analysis time improvements.
-    runs-on: ${{ (matrix.language == 'swift' && 'macos-13') || 'ubuntu-22.04' }}
-    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
+    # But it is not free, so please be aware of the cost.
+    runs-on: ubuntu-22.04
+    timeout-minutes: 360
 
     strategy:
       fail-fast: false
       matrix:
-        language: [ 'cpp' ]
-        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby', 'swift' ]
+        #TODO: add actions
+        language: ["cpp"]
 
     permissions:
       contents: read
@@ -46,76 +42,95 @@ jobs:
       security-events: write
 
     steps:
-    - name: Checkout repository
-      uses: actions/checkout@v3
-      with:
-        submodules: recursive
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          submodules: recursive
 
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3.28.17
-      with:
-        languages: ${{ matrix.language }}
+      # Initializes the CodeQL tools for scanning.
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v3.29.1
+        with:
+          languages: ${{ matrix.language }}
+          # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+          # queries: security-extended,security-and-quality
+          queries: security-and-quality
+          config-file: ./.github/codeql/codeql_config.yml
 
-        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
-        # queries: security-extended,security-and-quality
-        queries: security-and-quality
+      - run: |
+          ./.github/scripts/codeql_buildscript.sh
 
-    # Command-line programs to run using the OS shell.
-    # See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v3.29.1
+        with:
+          category: "/language:${{matrix.language}}"
+          upload: false
+        id: step1
 
-    #   If the Autobuild fails above, remove it and uncomment the following three lines.
-    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+      # - cpp/alloca-in-loop is about touch_pages() which is intended to
+      # - cpp/command-line-injection is about bh_system() which is used to
+      # - cpp/path-injection is used in bh_read_file_to_buffer() to load a .wasm.
+      #   or operate a stack usage file which is not sensitive or generate a .aot
+      # - cpp/suspicious-pointer-scaling
+      #   - wasm_runtime_invoke_native() used to trivial registers
+      # - cpp/uncontrolled-process-operation is about dlopen() which is used by
+      #   native libraries registrations.
+      # - cpp/world-writable-file-creation is about fopen() a temporary file
+      #   for perf-PID.map or .aot(wamrc). The permission isn't sensitive.
+      #   file.
+      #
+      # execute customized compiler
+      - name: Filter out unwanted errors and warnings
+        uses: advanced-security/filter-sarif@v1
+        with:
+          patterns: |
+            ## Exclude files and directories
+            -**/build/**
+            -**/core/deps/**
+            -**/cmake*/Modules/**
+            -**/test*/**
+            -**/wasm-app*/**
+            ## Exclude rules 1. Related to formatting, style
+            -**:cpp/commented-out-code
+            -**:cpp/complex-condition
+            -**:cpp/empty-if
+            -**:cpp/fixme-comment
+            -**:cpp/include-non-header
+            -**:cpp/long-switch
+            -**:cpp/poorly-documented-function
+            -**:cpp/trivial-switch
+            -**:cpp/unused-local-variable
+            -**:cpp/unused-static-function
+            -**:cpp/unused-static-variable
+            -**:cpp/use-of-goto 
+            ## Exclude rules 2. Related to special usage of APIs
+            -**:cpp/alloca-in-loop
+            -**:cpp/command-line-injection
+            -**:cpp/path-injection
+            -core/iwasm/common/wasm_runtime_common.c:cpp/suspicious-pointer-scaling
+            -**:cpp/uncontrolled-process-operation
+            -**:cpp/world-writable-file-creation
+          input: ${{ steps.step1.outputs.sarif-output }}/cpp.sarif
+          output: ${{ steps.step1.outputs.sarif-output }}/cpp.sarif
 
-    - run: |
-        ./.github/scripts/codeql_buildscript.sh
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3.28.17
-      with:
-        category: "/language:${{matrix.language}}"
-        upload: false
-      id: step1
+      - name: Upload CodeQL results to code scanning
+        uses: github/codeql-action/upload-sarif@v3.29.1
+        with:
+          sarif_file: ${{ steps.step1.outputs.sarif-output }}
+          category: "/language:${{matrix.language}}"
 
-    # Filter out rules with low severity or high false positve rate
-    # Also filter out warnings in third-party code
-    - name: Filter out unwanted errors and warnings
-      uses: advanced-security/filter-sarif@v1
-      with:
-        patterns: |
-          -**:cpp/path-injection
-          -**:cpp/world-writable-file-creation
-          -**:cpp/poorly-documented-function
-          -**:cpp/potentially-dangerous-function
-          -**:cpp/use-of-goto
-          -**:cpp/integer-multiplication-cast-to-long
-          -**:cpp/comparison-with-wider-type
-          -**:cpp/leap-year/*
-          -**:cpp/ambiguously-signed-bit-field
-          -**:cpp/suspicious-pointer-scaling
-          -**:cpp/suspicious-pointer-scaling-void
-          -**:cpp/unsigned-comparison-zero
-          -**/cmake*/Modules/**
-        input: ${{ steps.step1.outputs.sarif-output }}/cpp.sarif
-        output: ${{ steps.step1.outputs.sarif-output }}/cpp.sarif
+      - name: Upload CodeQL results as an artifact
+        if: success() || failure()
+        uses: actions/upload-artifact@v4.6.2
+        with:
+          name: codeql-results
+          path: ${{ steps.step1.outputs.sarif-output }}
+          retention-days: 10
 
-    - name: Upload CodeQL results to code scanning
-      uses: github/codeql-action/upload-sarif@v3.28.17
-      with:
-        sarif_file: ${{ steps.step1.outputs.sarif-output }}
-        category: "/language:${{matrix.language}}"
-
-    - name: Upload CodeQL results as an artifact
-      if: success() || failure()
-      uses: actions/upload-artifact@v4.6.2
-      with:
-        name: codeql-results
-        path: ${{ steps.step1.outputs.sarif-output }}
-        retention-days: 10
-
-    - name: Fail if an error is found
-      run: |
-        ./.github/scripts/codeql_fail_on_error.py \
-          ${{ steps.step1.outputs.sarif-output }}/cpp.sarif
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        GITHUB_REPOSITORY: ${{ github.repository }}
+      - name: Fail if an error is found
+        run: |
+          ./.github/scripts/codeql_fail_on_error.py \
+            ${{ steps.step1.outputs.sarif-output }}/cpp.sarif
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_REPOSITORY: ${{ github.repository }}

.github/workflows/compilation_on_android_ubuntu.yml

@@ -315,6 +315,10 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-22.04]
+        build_target: [
+          "X86_64",
+          "X86_32",
+        ]
         include:
           - os: ubuntu-22.04
             llvm_cache_key: ${{ needs.build_llvm_libraries_on_ubuntu_2204.outputs.cache_key }}
@@ -351,10 +355,16 @@ jobs:
           cmake --build . --config Release --parallel 4
         working-directory: wamr-compiler
 
+      - name: Install dependencies for X86_32
+        if: matrix.build_target == 'X86_32'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y g++-multilib
+
       - name: Build and run unit tests
         run: |
           mkdir build && cd build
-          cmake ..
+          cmake .. -DWAMR_BUILD_TARGET=${{ matrix.build_target }}
           cmake --build . --config Release --parallel 4
           ctest
         working-directory: tests/unit
@@ -427,6 +437,11 @@ jobs:
           ctest --test-dir build --output-on-failure
         working-directory: samples/wasm-c-api
 
+      - name: Build Sample [printversion]
+        run: |
+          ./test.sh
+        working-directory: samples/printversion
+
   build_samples_others:
     needs:
       [
@@ -603,49 +618,6 @@ jobs:
             llvm_cache_key: ${{ needs.build_llvm_libraries_on_ubuntu_2204.outputs.cache_key }}
             running_mode: aot
             test_option: $WAMR_COMPILER_TEST_OPTIONS
-        exclude:
-          # incompatible modes and features
-          # classic-interp doesn't support simd
-          - running_mode: "classic-interp"
-            test_option: $SIMD_TEST_OPTIONS
-          # llvm jit doesn't support multi module
-          - running_mode: "jit"
-            test_option: $MULTI_MODULES_TEST_OPTIONS
-          # fast-jit doesn't support multi module, simd
-          - running_mode: "fast-jit"
-            test_option: $MULTI_MODULES_TEST_OPTIONS
-          - running_mode: "fast-jit"
-            test_option: $SIMD_TEST_OPTIONS
-          # multi-tier-jit doesn't support multi module, simd
-          - running_mode: "multi-tier-jit"
-            test_option: $MULTI_MODULES_TEST_OPTIONS
-          - running_mode: "multi-tier-jit"
-            test_option: $SIMD_TEST_OPTIONS
-          # fast-jit and multi-tier-jit don't support GC
-          - running_mode: "fast-jit"
-            test_option: $GC_TEST_OPTIONS
-          - running_mode: "multi-tier-jit"
-            test_option: $GC_TEST_OPTIONS
-          # fast-interp, fast-jit, llvm-jit, multi-tier-jit don't support Memory64
-          - running_mode: "fast-interp"
-            test_option: $MEMORY64_TEST_OPTIONS
-          - running_mode: "fast-jit"
-            test_option: $MEMORY64_TEST_OPTIONS
-          - running_mode: "jit"
-            test_option: $MEMORY64_TEST_OPTIONS
-          - running_mode: "multi-tier-jit"
-            test_option: $MEMORY64_TEST_OPTIONS
-          # aot, fast-interp, fast-jit, llvm-jit, multi-tier-jit don't support Multi Memory
-          - running_mode: "aot"
-            test_option: $MULTI_MEMORY_TEST_OPTIONS
-          - running_mode: "fast-interp"
-            test_option: $MULTI_MEMORY_TEST_OPTIONS
-          - running_mode: "fast-jit"
-            test_option: $MULTI_MEMORY_TEST_OPTIONS
-          - running_mode: "jit"
-            test_option: $MULTI_MEMORY_TEST_OPTIONS
-          - running_mode: "multi-tier-jit"
-            test_option: $MULTI_MEMORY_TEST_OPTIONS
 
     steps:
       - name: checkout
@@ -667,15 +639,6 @@ jobs:
         with:
           os: ${{ matrix.os }}
 
-      # It is a temporary solution until new wasi-sdk that includes bug fixes is released
-      - name: build wasi-libc from source
-        if: matrix.test_option == '$WASI_TEST_OPTIONS'
-        run: |
-          git clone https://github.com/WebAssembly/wasi-libc
-          cd wasi-libc
-          make -j AR=/opt/wasi-sdk/bin/llvm-ar NM=/opt/wasi-sdk/bin/llvm-nm CC=/opt/wasi-sdk/bin/clang THREAD_MODEL=posix
-          echo "SYSROOT_PATH=$PWD/sysroot" >> $GITHUB_ENV
-
       - name: set env variable(if llvm are used)
         if: matrix.running_mode == 'aot' || matrix.running_mode == 'jit' || matrix.running_mode == 'multi-tier-jit'
         run: echo "USE_LLVM=true" >> $GITHUB_ENV
@@ -712,7 +675,7 @@ jobs:
 
       - name: Build WASI thread tests
         if: matrix.test_option == '$WASI_TEST_OPTIONS'
-        run: bash build.sh --sysroot "$SYSROOT_PATH"
+        run: bash build.sh
         working-directory: ./core/iwasm/libraries/lib-wasi-threads/test/
 
       - name: build socket api tests
@@ -758,123 +721,3 @@ jobs:
           eval $(opam env)
           ./test_wamr.sh ${{ env.X86_32_TARGET_TEST_OPTIONS }} ${{ matrix.test_option }} -t ${{ matrix.running_mode }}
         working-directory: ./tests/wamr-test-suites
-
-  test-wamr-ide:
-    needs:
-      [
-        build_iwasm
-      ]
-    runs-on: ubuntu-22.04
-    env:
-      PYTHON_VERSION: '3.10'
-      PYTHON_UBUNTU_STANDALONE_BUILD: https://github.com/indygreg/python-build-standalone/releases/download/20230507/cpython-3.10.11+20230507-x86_64-unknown-linux-gnu-install_only.tar.gz
-
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: install dependencies
-        run: |
-          rustup target add wasm32-wasip1
-          sudo apt update && sudo apt-get install -y lld ninja-build
-          npm install
-        working-directory: test-tools/wamr-ide/VSCode-Extension
-
-      - name: code style check
-        run: |
-          npm install --save-dev prettier
-          npm run prettier-format-check
-        working-directory: test-tools/wamr-ide/VSCode-Extension
-
-      - name: build iwasm with source debugging feature
-        run: |
-          mkdir build
-          cd build
-          cmake .. -DWAMR_BUILD_DEBUG_INTERP=1 -DWAMR_BUILD_REF_TYPES=1
-          make
-        working-directory: product-mini/platforms/linux
-
-      - name: Cache LLDB
-        id: cache-lldb
-        uses: actions/cache@v4
-        env:
-          cache-name: cache-lldb-vscode
-        with:
-          path: test-tools/wamr-ide/VSCode-Extension/resource/debug/linux
-          key: ${{ env.cache-name }}-${{ hashFiles('build-scripts/lldb_wasm.patch') }}-${{ env.PYTHON_UBUNTU_STANDALONE_BUILD }}
-
-      - if: ${{ steps.cache-lldb.outputs.cache-hit != 'true' }}
-        name: get stand-alone python ubuntu
-        run: |
-          wget ${{ env.PYTHON_UBUNTU_STANDALONE_BUILD }} -O python.tar.gz
-          tar -xvf python.tar.gz
-        working-directory: core/deps
-
-      - if: ${{ steps.cache-lldb.outputs.cache-hit != 'true' }}
-        name: download llvm
-        run: |
-          wget https://github.com/llvm/llvm-project/archive/1f27fe6128769f00197925c3b8f6abb9d0e5cd2e.zip
-          unzip -q 1f27fe6128769f00197925c3b8f6abb9d0e5cd2e.zip
-          mv llvm-project-1f27fe6128769f00197925c3b8f6abb9d0e5cd2e llvm-project
-        working-directory: core/deps
-
-      - if: ${{ steps.cache-lldb.outputs.cache-hit != 'true' }}
-        name: apply wamr patch
-        run: |
-          git init
-          git config user.email "action@github.com"
-          git config user.name "github action"
-          git apply ../../../build-scripts/lldb_wasm.patch
-        working-directory: core/deps/llvm-project
-
-      - if: ${{ steps.cache-lldb.outputs.cache-hit != 'true' }}
-        name: build lldb ubuntu
-        run: |
-          echo "start to build lldb..."
-          mkdir -p wamr-lldb
-          cmake -S ./llvm -B build \
-            -G Ninja \
-            -DCMAKE_INSTALL_PREFIX=../wamr-lldb \
-            -DCMAKE_BUILD_TYPE:STRING="Release" \
-            -DCMAKE_EXPORT_COMPILE_COMMANDS=ON \
-            -DLLVM_ENABLE_PROJECTS="clang;lldb" \
-            -DLLVM_TARGETS_TO_BUILD:STRING="X86;WebAssembly" \
-            -DLLVM_BUILD_BENCHMARKS:BOOL=OFF \
-            -DLLVM_BUILD_DOCS:BOOL=OFF \
-            -DLLVM_BUILD_EXAMPLES:BOOL=OFF \
-            -DLLVM_BUILD_LLVM_DYLIB:BOOL=OFF \
-            -DLLVM_BUILD_TESTS:BOOL=OFF \
-            -DLLVM_INCLUDE_BENCHMARKS:BOOL=OFF \
-            -DLLVM_INCLUDE_DOCS:BOOL=OFF \
-            -DLLVM_INCLUDE_EXAMPLES:BOOL=OFF \
-            -DLLVM_INCLUDE_TESTS:BOOL=OFF \
-            -DLLVM_ENABLE_BINDINGS:BOOL=OFF \
-            -DLLVM_ENABLE_LIBXML2:BOOL=ON \
-            -DLLVM_ENABLE_LLD:BOOL=ON \
-            -DLLDB_ENABLE_PYTHON:BOOL=ON \
-            -DLLDB_EMBED_PYTHON_HOME=ON \
-            -DLLDB_PYTHON_HOME=.. \
-            -DLLDB_PYTHON_RELATIVE_PATH=lib/lldb-python \
-            -DPython3_EXECUTABLE="$(pwd)/../python/bin/python${{ env.PYTHON_VERSION }}"
-          cmake --build build --target lldb install --parallel $(nproc)
-        working-directory: core/deps/llvm-project
-
-      - if: ${{ steps.cache-lldb.outputs.cache-hit != 'true' }}
-        name: copy lldb to extension folder
-        run: |
-          mkdir -p bin
-          mkdir -p lib
-          cp ../../../../../../core/deps/llvm-project/lldb/tools/lldb-vscode/package.json ./
-          cp -r ../../../../../../core/deps/llvm-project/lldb/tools/lldb-vscode/syntaxes/ ./
-          cp ../../../../../../core/deps/llvm-project/build/bin/lldb* bin
-          cp ../../../../../../core/deps/llvm-project/build/lib/liblldb*.so lib
-          cp ../../../../../../core/deps/llvm-project/build/lib/liblldb*.so.* lib
-          cp -R ../../../../../../core/deps/llvm-project/build/lib/lldb-python lib
-          cp -R ../../../../../../core/deps/python/lib/python* lib
-          cp ../../../../../../core/deps/python/lib/libpython${{ env.PYTHON_VERSION }}.so.1.0 lib
-        working-directory: test-tools/wamr-ide/VSCode-Extension/resource/debug/linux
-
-      - name: run tests
-        timeout-minutes: 5
-        run: xvfb-run npm run test
-        working-directory: test-tools/wamr-ide/VSCode-Extension

.github/workflows/compilation_on_macos.yml

@@ -282,6 +282,11 @@ jobs:
           ctest --test-dir build --output-on-failure
         working-directory: samples/wasm-c-api
 
+      - name: Build Sample [printversion]
+        run: |
+          ./test.sh
+        working-directory: samples/printversion
+
   build_samples_others:
     needs: [build_iwasm, build_wamrc, build_llvm_libraries_on_intel_macos, build_llvm_libraries_on_arm_macos]
     runs-on: ${{ matrix.os }}

.github/workflows/compilation_on_sgx.yml

@@ -290,28 +290,6 @@ jobs:
 
       - name: run spec tests
         run: |
-          set +e
           source /opt/intel/sgxsdk/environment
-          attempts=0
-          max_attempts=3
-
-          while [ $attempts -lt $max_attempts ]; do
-            ./test_wamr.sh ${{ matrix.test_option }} -t ${{ matrix.running_mode }}
-            exitcode="$?"
-
-            if [ $exitcode -eq 0 ]; then
-              echo "Spec test passed"
-              exit 0
-            elif [ $exitcode -ne 143 ]; then
-              echo "Spec test failed with error code $exitcode"
-              exit 1
-            fi
-
-            echo "$exitcode is a known GitHub-hosted runner issue"
-            echo "::notice::Re-running the spec test due to error code 143"
-            attempts=$((attempts + 1))
-          done
-
-          echo "::notice::Report an error with code 143 in SGX CI after $max_attempts attempts"
-          exit 143
+          ./test_wamr.sh ${{ matrix.test_option }} -t ${{ matrix.running_mode }}
         working-directory: ./tests/wamr-test-suites

.github/workflows/compilation_on_windows.yml

@@ -57,23 +57,33 @@ permissions:
   contents: read
 
 jobs:
-  build:
+  build_llvm_libraries_on_windows:
+    permissions:
+      contents: read
+      actions: write
+    uses: ./.github/workflows/build_llvm_libraries.yml
+    with:
+      os: "windows-latest"
+      arch: "AArch64 ARM Mips RISCV X86"
+
+  build_iwasm:
     runs-on: windows-latest
     strategy:
       matrix:
-        build_options: [
-          "-DWAMR_BUILD_AOT=1 -DWAMR_BUILD_INTERP=0",
-          "-DWAMR_BUILD_AOT=0",
-          "-DWAMR_BUILD_TAIL_CALL=1",
-          "-DWAMR_BUILD_CUSTOM_NAME_SECTION=1",
-          "-DWAMR_DISABLE_HW_BOUND_CHECK=1",
-          "-DWAMR_BUILD_REF_TYPES=1",
-          "-DWAMR_BUILD_SIMD=1",
-          "-DWAMR_BUILD_DEBUG_INTERP=1",
-          "-DWAMR_BUILD_LIB_PTHREAD=1",
-          "-DWAMR_BUILD_LIB_WASI_THREADS=1",
-          "-DWAMR_BUILD_LIBC_UVWASI=0 -DWAMR_BUILD_LIBC_WASI=1"
-        ]
+        build_options:
+          [
+            "-DWAMR_BUILD_AOT=1 -DWAMR_BUILD_INTERP=0",
+            "-DWAMR_BUILD_AOT=0",
+            "-DWAMR_BUILD_TAIL_CALL=1",
+            "-DWAMR_BUILD_CUSTOM_NAME_SECTION=1",
+            "-DWAMR_DISABLE_HW_BOUND_CHECK=1",
+            "-DWAMR_BUILD_REF_TYPES=1",
+            "-DWAMR_BUILD_SIMD=1",
+            "-DWAMR_BUILD_DEBUG_INTERP=1",
+            "-DWAMR_BUILD_LIB_PTHREAD=1",
+            "-DWAMR_BUILD_LIB_WASI_THREADS=1",
+            "-DWAMR_BUILD_LIBC_UVWASI=0 -DWAMR_BUILD_LIBC_WASI=1",
+          ]
     steps:
       - uses: actions/checkout@v4
 
@@ -89,17 +99,49 @@ jobs:
           cmake .. ${{ matrix.build_options }}
           cmake --build . --config Release --parallel 4
 
+  build_wamrc:
+    needs: [build_llvm_libraries_on_windows]
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        include:
+          - os: windows-latest
+            llvm_cache_key: ${{ needs.build_llvm_libraries_on_windows.outputs.cache_key }}
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      # since jobs.id can't contain the dot character
+      # it is hard to use `format` to assemble the cache key
+      - name: Get LLVM libraries
+        id: retrieve_llvm_libs
+        uses: actions/cache@v4
+        with:
+          path: |
+            ./core/deps/llvm/build/bin
+            ./core/deps/llvm/build/include
+            ./core/deps/llvm/build/lib
+            ./core/deps/llvm/build/libexec
+            ./core/deps/llvm/build/share
+          key: ${{ matrix.llvm_cache_key }}
+
+      - name: Quit if cache miss
+        if: steps.retrieve_llvm_libs.outputs.cache-hit != 'true'
+        run: echo "::error::can not get prebuilt llvm libraries" && exit 1
+
+      - name: Build wamrc
+        run: |
+          cmake -S . -B build
+          cmake --build build --config Release --parallel 4
+        working-directory: wamr-compiler
+
   test:
     runs-on: windows-latest
-    needs: [build]
+    needs: [build_iwasm, build_wamrc]
     strategy:
       fail-fast: false
       matrix:
-        running_mode:
-          [
-            "classic-interp",
-            "fast-interp",
-          ]
+        running_mode: ["classic-interp", "fast-interp"]
         test_option:
           [
             $DEFAULT_TEST_OPTIONS,
@@ -130,6 +172,10 @@ jobs:
         run: ./build.sh
         working-directory: ./core/iwasm/libraries/lib-wasi-threads/test/
 
+      - name: install wget
+        shell: bash
+        run: choco install wget
+
       - name: run tests
         shell: bash
         timeout-minutes: 20

.github/workflows/nightly_run.yml

@@ -36,12 +36,11 @@ env:
   LLVM_EAGER_JIT_BUILD_OPTIONS: "-DWAMR_BUILD_AOT=1 -DWAMR_BUILD_FAST_INTERP=0 -DWAMR_BUILD_INTERP=0 -DWAMR_BUILD_FAST_JIT=0 -DWAMR_BUILD_JIT=1 -DWAMR_BUILD_LAZY_JIT=0"
   MULTI_TIER_JIT_BUILD_OPTIONS: "-DWAMR_BUILD_AOT=1 -DWAMR_BUILD_FAST_INTERP=0 -DWAMR_BUILD_INTERP=1 -DWAMR_BUILD_FAST_JIT=1 -DWAMR_BUILD_JIT=1 -DWAMR_BUILD_LAZY_JIT=1"
   # For Spec Test
-  # FIXME: use binary release(adding -b) instead of building from source after upgrading to 22.04
-  DEFAULT_TEST_OPTIONS: "-s spec -P"
-  MULTI_MODULES_TEST_OPTIONS: "-s spec -M -P"
-  SIMD_TEST_OPTIONS: "-s spec -S -P"
-  THREADS_TEST_OPTIONS: "-s spec -p -P"
-  X86_32_TARGET_TEST_OPTIONS: "-m x86_32 -P"
+  DEFAULT_TEST_OPTIONS: "-s spec -b -P"
+  MULTI_MODULES_TEST_OPTIONS: "-s spec -b -P -M"
+  SIMD_TEST_OPTIONS: "-s spec -b -P -S"
+  THREADS_TEST_OPTIONS: "-s spec -b -P -p"
+  X86_32_TARGET_TEST_OPTIONS: "-m x86_32"
   WASI_TEST_OPTIONS: "-s wasi_certification -w"
 
 permissions:
@@ -617,42 +616,21 @@ jobs:
             sanitizer: tsan
           - running_mode: "multi-tier-jit"
             sanitizer: tsan
-          # classic-interp and fast-interp don't support simd
-          - running_mode: "classic-interp"
-            test_option: $SIMD_TEST_OPTIONS
+          # simd128.h brings ubsan errors
+          # like: negation of XXXcannot be represented in type 'long int';
+          #       cast to an unsigned type to negate this value to itself
           - running_mode: "fast-interp"
-            test_option: $SIMD_TEST_OPTIONS
-          # llvm jit doesn't support multi module
-          - running_mode: "jit"
-            test_option: $MULTI_MODULES_TEST_OPTIONS
-          # fast-jit doesn't support multi module, simd
-          - running_mode: "fast-jit"
-            test_option: $MULTI_MODULES_TEST_OPTIONS
-          - running_mode: "fast-jit"
-            test_option: $SIMD_TEST_OPTIONS
-          # multi-tier-jit doesn't support multi module, simd
-          - running_mode: "multi-tier-jit"
-            test_option: $MULTI_MODULES_TEST_OPTIONS
-          - running_mode: "multi-tier-jit"
-            test_option: $SIMD_TEST_OPTIONS
+            sanitizer: ubsan
     steps:
       - name: checkout
         uses: actions/checkout@v4
 
       - name: install-wasi-sdk-wabt
+        if: matrix.test_option == '$WASI_TEST_OPTIONS'
         uses: ./.github/actions/install-wasi-sdk-wabt
         with:
           os: ${{ matrix.os }}
 
-      # It is a temporary solution until new wasi-sdk that includes bug fixes is released
-      - name: build wasi-libc from source
-        if: matrix.test_option == '$WASI_TEST_OPTIONS'
-        run: |
-          git clone https://github.com/WebAssembly/wasi-libc
-          cd wasi-libc
-          make -j AR=/opt/wasi-sdk/bin/llvm-ar NM=/opt/wasi-sdk/bin/llvm-nm CC=/opt/wasi-sdk/bin/clang THREAD_MODEL=posix
-          echo "SYSROOT_PATH=$PWD/sysroot" >> $GITHUB_ENV
-
       - name: set env variable(if llvm are used)
         if: matrix.running_mode == 'aot' || matrix.running_mode == 'jit' || matrix.running_mode == 'multi-tier-jit'
         run: echo "USE_LLVM=true" >> $GITHUB_ENV
@@ -697,12 +675,12 @@ jobs:
 
       - name: Build WASI thread tests
         if: matrix.test_option == '$WASI_TEST_OPTIONS'
-        run: bash build.sh --sysroot "$SYSROOT_PATH"
+        run: bash build.sh
         working-directory: ./core/iwasm/libraries/lib-wasi-threads/test/
 
       - name: Build WASI thread stress tests
         if: matrix.test_option == '$WASI_TEST_OPTIONS'
-        run: bash build.sh --sysroot "$SYSROOT_PATH"
+        run: bash build.sh
         working-directory: ./core/iwasm/libraries/lib-wasi-threads/stress-test/
 
       - name: build socket api tests

.github/workflows/release_process.yml

@@ -239,3 +239,12 @@ jobs:
       arch: universal
       upload_url: ${{ needs.create_release.outputs.upload_url }}
       ver_num: ${{ needs.create_tag.outputs.new_ver}}
+
+  release_wamr_wasi_extensions:
+    permissions:
+      contents: write # upload release artifact
+    needs: [create_tag, create_release]
+    uses: ./.github/workflows/build_wamr_wasi_extensions.yml
+    with:
+      upload_url: ${{ needs.create_release.outputs.upload_url }}
+      ver_num: ${{ needs.create_tag.outputs.new_ver }}

.github/workflows/supply_chain.yml

@@ -39,7 +39,7 @@ jobs:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/scorecard-action@f49aabe0b5af0936a0987cfb85d86b75731b0186 # v2.4.1
+        uses: ossf/scorecard-action@05b42c624433fc40578a4040d5cf5e36ddca8cde # v2.4.2
         with:
           results_file: results.sarif
           results_format: sarif
@@ -60,6 +60,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@5eb3ed6614230b1931d5c08df9e096e4ba524f21 
+        uses: github/codeql-action/upload-sarif@4c57370d0304fbff638216539f81d9163f77712a 
         with:
           sarif_file: results.sarif

.github/workflows/wamr_wasi_extensions.yml

@@ -0,0 +1,57 @@
+# Copyright (C) 2019 Intel Corporation.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+name: wamr_wasi_extensions
+
+on:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+    paths:
+      - ".github/workflows/wamr_wasi_extensions.yml"
+      - "wamr_wasi_extensios/**"
+      - "core/iwasm/libraries/wasi-nn/include/**"
+      - "core/iwasm/libraries/lib-socket/**"
+  # allow to be triggered manually
+  workflow_dispatch:
+
+# Cancel any in-flight jobs for the same PR/branch so there's only one active
+# at a time
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_wamr_wasi_extensions:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-22.04, macos-13, macos-14]
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: install-wasi-sdk-wabt
+        uses: ./.github/actions/install-wasi-sdk-wabt
+        with:
+          os: ${{ matrix.os }}
+
+      - name: Build wamr-wasi-extensions
+        run: |
+          mkdir dist
+          ./build_libs.sh $(pwd)/dist/wamr-wasi-extensions
+        working-directory: wamr-wasi-extensions
+
+      - name: Build wamr-wasi-extensions samples
+        run: |
+          ./build_samples.sh $(pwd)/dist/wamr-wasi-extensions
+        working-directory: wamr-wasi-extensions
+
+      - name: Upload artifacts
+        if: matrix.os == 'macos-14'
+        uses: actions/upload-artifact@v4
+        with:
+          name: wamr-wasi-extensions
+          path: wamr-wasi-extensions/dist
+          retention-days: 10

CMakeLists.txt

@@ -99,9 +99,9 @@ if (NOT DEFINED WAMR_BUILD_LIB_WASI_THREADS)
   set (WAMR_BUILD_LIB_WASI_THREADS 0)
 endif ()
 
-if (NOT DEFINED WAMR_ENABLE_COPY_CALLSTACK)
+if (NOT DEFINED WAMR_BUILD_COPY_CALL_STACK)
   # Disable copy callstack by default
-  set (WAMR_ENABLE_COPY_CALLSTACK 0)
+  set (WAMR_BUILD_COPY_CALL_STACK 0)
 endif()
 
 if (NOT DEFINED WAMR_BUILD_MINI_LOADER)
@@ -152,15 +152,11 @@ include (${SHARED_DIR}/utils/uncommon/shared_uncommon.cmake)
 set (THREADS_PREFER_PTHREAD_FLAG ON)
 find_package(Threads REQUIRED)
 
-if (MSVC)
-  add_definitions(-DCOMPILING_WASM_RUNTIME_API=1)
-endif ()
-
 add_library (vmlib ${WAMR_RUNTIME_LIB_SOURCE})
 set_target_properties (vmlib PROPERTIES OUTPUT_NAME iwasm)
 target_include_directories(vmlib INTERFACE
   $<BUILD_INTERFACE:${WAMR_ROOT_DIR}/core/iwasm/include>
-  $<INSTALL_INTERFACE:include/iwasm>
+  $<INSTALL_INTERFACE:include>
 )
 
 target_link_libraries (vmlib PUBLIC ${LLVM_AVAILABLE_LIBS} ${UV_A_LIBS} -lm -ldl ${CMAKE_THREAD_LIBS_INIT})
@@ -189,7 +185,7 @@ set_version_info (vmlib)
 install (TARGETS vmlib
   EXPORT iwasmTargets
   LIBRARY DESTINATION lib
-  PUBLIC_HEADER DESTINATION include/iwasm
+  PUBLIC_HEADER DESTINATION include
 )
 
 install_iwasm_package ()

README.md

@@ -21,7 +21,7 @@ WebAssembly Micro Runtime (WAMR) is a lightweight standalone WebAssembly (Wasm)
 
 ### Key features
 - Full compliant to the W3C Wasm MVP
-- Small runtime binary size (core vmlib on cortex-m4f with tail-call/bulk memroy/shared memroy support, text size from bloaty)
+- Small runtime binary size (core vmlib on cortex-m4f with tail-call/bulk memory/shared memory support, text size from bloaty)
   * ~58.9K for fast interpreter
   * ~56.3K for classic interpreter
   * ~29.4K for aot runtime

RELEASE_NOTES.md

@@ -1,3 +1,35 @@
+## WAMR-2.3.1
+
+### Breaking Changes
+
+- Revert the location to install public headers (#4295). This restores compatibility (of installed headers) with WAMR-2.2.0 and earlier.
+
+### New Features
+
+- feat: Add instruction metering for interpreter (#4122)
+
+### Bug Fixes
+
+- updating WASI stdio handle initialization and build options for UVWASI (#4260)
+- Fix SIMD load lane to avoid incompatible pointer types (#4278)
+- Fixed unit tests on X86_32 (#4279)
+- Improve Embedding WAMR guideline (#4284)
+- Fix Compiler Error C2491 (#4286)
+- Enhance type checking for function types in loader and improve error handling (#4294)
+- Dockerfile.vx-delegate build error fix (#4273)
+- Enable runtime API exposure for MSVC builds (#4287)
+
+### Enhancements
+
+- feat(yml): Add ESP32-P4 and ESP32-C5 support (#4270)
+- add a sample to use cmake package (#4291)
+
+### Others
+
+- build(deps): Bump github/codeql-action from 3.28.17 to 3.28.18 (#4285)
+
+---
+
 ## WAMR-2.3.0
 
 ### Breaking changes
@@ -465,7 +497,7 @@
 - wasm loader: Fix handling if block without op else (#3404)
 - ref-types: Correct default value for function local variables (#3397)
 - aot compiler: Fix the length type passed to aot_memmove/aot_memset (#3378)
-- Fix loader and mini-loader select potiential error (#3374)
+- Fix loader and mini-loader select potential error (#3374)
 - Fix aot debugger compilation error on windows (#3370)
 - A few native stack detection fixes for macOS/arm64 (#3368)
 - Fix ESP32-S3 compiling error (#3359)

build-scripts/config_common.cmake

@@ -334,15 +334,10 @@ if (WAMR_BUILD_SHARED_HEAP EQUAL 1)
   add_definitions (-DWASM_ENABLE_SHARED_HEAP=1)
   message ("     Shared heap enabled")
 endif()
-
-if (WAMR_ENABLE_COPY_CALLSTACK EQUAL 1)
-  add_definitions (-DWAMR_ENABLE_COPY_CALLSTACK=1)
+if (WAMR_BUILD_COPY_CALL_STACK EQUAL 1)
+  add_definitions (-DWASM_ENABLE_COPY_CALL_STACK=1)
   message("     Copy callstack enabled")
-else ()
-  add_definitions (-DWAMR_ENABLE_COPY_CALLSTACK=0)
-  message("     Copy callstack disabled")
 endif()
-
 if (WAMR_BUILD_MEMORY64 EQUAL 1)
   # if native is 32-bit or cross-compiled to 32-bit
   if (NOT WAMR_BUILD_TARGET MATCHES ".*64.*")
@@ -539,6 +534,9 @@ if (WAMR_BUILD_WASI_NN EQUAL 1)
   if (DEFINED WAMR_BUILD_WASI_NN_EXTERNAL_DELEGATE_PATH)
       add_definitions (-DWASM_WASI_NN_EXTERNAL_DELEGATE_PATH="${WAMR_BUILD_WASI_NN_EXTERNAL_DELEGATE_PATH}")
   endif ()
+  if (NOT DEFINED WAMR_BUILD_WASI_EPHEMERAL_NN)
+      set(WAMR_BUILD_WASI_EPHEMERAL_NN 1)
+  endif()
   if (WAMR_BUILD_WASI_EPHEMERAL_NN EQUAL 1)
       message ("     WASI-NN: use 'wasi_ephemeral_nn' instead of 'wasi-nn'")
       add_definitions (-DWASM_ENABLE_WASI_EPHEMERAL_NN=1)
@@ -671,6 +669,10 @@ if (WAMR_BUILD_AOT_VALIDATOR EQUAL 1)
   message ("     AOT validator enabled")
   add_definitions (-DWASM_ENABLE_AOT_VALIDATOR=1)
 endif ()
+if (WAMR_BUILD_INSTRUCTION_METERING EQUAL 1)
+  message ("     Instruction metering enabled")
+  add_definitions (-DWASM_ENABLE_INSTRUCTION_METERING=1)
+endif ()
 
 ########################################
 # Show Phase4 Wasm proposals status.

build-scripts/esp-idf/wamr/CMakeLists.txt

@@ -5,11 +5,15 @@
 if (NOT CMAKE_BUILD_EARLY_EXPANSION)
 
   if (CONFIG_IDF_TARGET_ARCH_RISCV)
-      set (WAMR_BUILD_TARGET "RISCV32")
+    if (CONFIG_IDF_TARGET_ESP32P4)
+      set (WAMR_BUILD_TARGET "RISCV32_ILP32F")
+    else ()
+      set (WAMR_BUILD_TARGET "RISCV32_ILP32")
+    endif ()
   elseif (CONFIG_IDF_TARGET_ARCH_XTENSA)
-      set (WAMR_BUILD_TARGET "XTENSA")
+    set (WAMR_BUILD_TARGET "XTENSA")
   else ()
-      message (FATAL_ERROR "Arch ${CONFIG_IDF_TARGET_ARCH} is not supported")
+    message (FATAL_ERROR "Arch ${CONFIG_IDF_TARGET_ARCH} is not supported")
   endif ()
 
   set (WAMR_BUILD_PLATFORM "esp-idf")
@@ -41,31 +45,31 @@ if (NOT CMAKE_BUILD_EARLY_EXPANSION)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_MULTI_MODULE)
-      set (WAMR_BUILD_MULTI_MODULE 1)
+    set (WAMR_BUILD_MULTI_MODULE 1)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_SHARED_MEMORY)
-      set (WAMR_BUILD_SHARED_MEMORY 1)
+    set (WAMR_BUILD_SHARED_MEMORY 1)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_MEMORY_PROFILING)
-      set (WAMR_BUILD_MEMORY_PROFILING 1)
+    set (WAMR_BUILD_MEMORY_PROFILING 1)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_PERF_PROFILING)
-      set (WAMR_BUILD_PERF_PROFILING 1)
+    set (WAMR_BUILD_PERF_PROFILING 1)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_REF_TYPES)
-      set (WAMR_BUILD_REF_TYPES 1)
+    set (WAMR_BUILD_REF_TYPES 1)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_LIBC_WASI)
-      set (WAMR_BUILD_LIBC_WASI 1)
+    set (WAMR_BUILD_LIBC_WASI 1)
   endif ()
 
   if (CONFIG_WAMR_ENABLE_LIB_PTHREAD)
-      set (WAMR_BUILD_LIB_PTHREAD 1)
+    set (WAMR_BUILD_LIB_PTHREAD 1)
   endif ()
 
   set (WAMR_ROOT_DIR ${CMAKE_CURRENT_LIST_DIR}/../../..)
@@ -89,7 +93,11 @@ idf_component_register(SRCS ${srcs}
 target_compile_options(${COMPONENT_LIB} PRIVATE "-Wno-format")
 
 if (CONFIG_IDF_TARGET_ARCH_RISCV)
-  target_compile_definitions(${COMPONENT_LIB} PUBLIC -DBUILD_TARGET_RISCV32_ILP32=1)
+  if (CONFIG_IDF_TARGET_ESP32P4)
+    target_compile_definitions(${COMPONENT_LIB} PUBLIC -DBUILD_TARGET_RISCV32_ILP32F=1)
+  else ()
+    target_compile_definitions(${COMPONENT_LIB} PUBLIC -DBUILD_TARGET_RISCV32_ILP32=1)
+  endif ()
 elseif (CONFIG_IDF_TARGET_ARCH_XTENSA)
   target_compile_definitions(${COMPONENT_LIB} PUBLIC -DBUILD_TARGET_XTENSA=1)
 endif ()

build-scripts/requirements.txt

@@ -1 +1 @@
-requests==2.32.3
+requests==2.32.4

build-scripts/runtime_lib.cmake

@@ -106,6 +106,7 @@ endif ()
 
 if (WAMR_BUILD_WASI_NN EQUAL 1)
     include (${IWASM_DIR}/libraries/wasi-nn/cmake/wasi_nn.cmake)
+    set (WAMR_BUILD_MODULE_INST_CONTEXT 1)
 endif ()
 
 if (WAMR_BUILD_LIB_PTHREAD EQUAL 1)
@@ -193,6 +194,13 @@ else()
     enable_language (ASM)
 endif()
 
+# it will expose the runtime APIs.
+# you'll use the following command to check the exported APIs
+# dumpbin.exe /EXPORTS xxx
+if (MSVC)
+    add_compile_definitions(COMPILING_WASM_RUNTIME_API=1)
+endif ()
+
 include (${SHARED_PLATFORM_CONFIG})
 include (${SHARED_DIR}/mem-alloc/mem_alloc.cmake)
 include (${IWASM_DIR}/common/iwasm_common.cmake)

build-scripts/version.cmake

@@ -8,7 +8,7 @@ endif()
 
 set(WAMR_VERSION_MAJOR 2)
 set(WAMR_VERSION_MINOR 3)
-set(WAMR_VERSION_PATCH 0)
+set(WAMR_VERSION_PATCH 1)
 
 message("-- WAMR version: ${WAMR_VERSION_MAJOR}.${WAMR_VERSION_MINOR}.${WAMR_VERSION_PATCH}")
 

ci/coding_guidelines_check.py

@@ -4,7 +4,6 @@
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 #
 import argparse
-import re
 from pathlib import Path
 import re
 import shlex
@@ -39,7 +38,7 @@ INVALID_FILE_NAME_SEGMENT = r"([a-zA-Z0-9]+\-[a-zA-Z0-9]+)"
 
 def locate_command(command: str) -> bool:
     if not shutil.which(command):
-        print(f"Command '{command}'' not found")
+        print(f"Command '{command}' not found")
         return False
 
     return True

core/config.h

@@ -193,8 +193,8 @@
 #error "Heap aux stack allocation must be enabled for WASI threads"
 #endif
 
-#ifndef WAMR_ENABLE_COPY_CALLSTACK
-#define WAMR_ENABLE_COPY_CALLSTACK 0
+#ifndef WASM_ENABLE_COPY_CALL_STACK
+#define WASM_ENABLE_COPY_CALL_STACK 0
 #endif
 
 #ifndef WASM_ENABLE_BASE_LIB
@@ -716,4 +716,8 @@ unless used elsewhere */
 #define WASM_ENABLE_AOT_VALIDATOR 0
 #endif
 
+#ifndef WASM_ENABLE_INSTRUCTION_METERING
+#define WASM_ENABLE_INSTRUCTION_METERING 0
+#endif
+
 #endif /* end of _CONFIG_H_ */

core/iwasm/aot/aot_loader.c

@@ -1309,6 +1309,13 @@ load_init_expr(const uint8 **p_buf, const uint8 *buf_end, AOTModule *module,
             read_uint32(buf, buf_end, type_idx);
             read_uint32(buf, buf_end, length);
 
+            if (type_idx >= module->type_count
+                || !wasm_type_is_array_type(module->types[type_idx])) {
+                set_error_buf(error_buf, error_buf_size,
+                              "invalid or non-array type index.");
+                goto fail;
+            }
+
             if (init_expr_type == INIT_EXPR_TYPE_ARRAY_NEW_DEFAULT) {
                 expr->u.array_new_default.type_index = type_idx;
                 expr->u.array_new_default.length = length;
@@ -1723,6 +1730,12 @@ load_types(const uint8 **p_buf, const uint8 *buf_end, AOTModule *module,
             (void)u8;
 
             read_uint32(buf, buf_end, j);
+#if WASM_ENABLE_AOT_VALIDATOR != 0
+            if (j >= module->type_count) {
+                set_error_buf(error_buf, error_buf_size, "invalid type index");
+                goto fail;
+            }
+#endif
             if (module->types[j]->ref_count == UINT16_MAX) {
                 set_error_buf(error_buf, error_buf_size,
                               "wasm type's ref count too large");
@@ -1986,6 +1999,13 @@ load_types(const uint8 **p_buf, const uint8 *buf_end, AOTModule *module,
                 AOTType *cur_type = module->types[j];
                 parent_type_idx = cur_type->parent_type_idx;
                 if (parent_type_idx != (uint32)-1) { /* has parent */
+#if WASM_ENABLE_AOT_VALIDATOR != 0
+                    if (parent_type_idx >= module->type_count) {
+                        set_error_buf(error_buf, error_buf_size,
+                                      "invalid parent type index");
+                        goto fail;
+                    }
+#endif
                     AOTType *parent_type = module->types[parent_type_idx];
 
                     module->types[j]->parent_type = parent_type;
@@ -2009,6 +2029,13 @@ load_types(const uint8 **p_buf, const uint8 *buf_end, AOTModule *module,
                 AOTType *cur_type = module->types[j];
                 parent_type_idx = cur_type->parent_type_idx;
                 if (parent_type_idx != (uint32)-1) { /* has parent */
+#if WASM_ENABLE_AOT_VALIDATOR != 0
+                    if (parent_type_idx >= module->type_count) {
+                        set_error_buf(error_buf, error_buf_size,
+                                      "invalid parent type index");
+                        goto fail;
+                    }
+#endif
                     AOTType *parent_type = module->types[parent_type_idx];
                     /* subtyping has been checked during compilation */
                     bh_assert(wasm_type_is_subtype_of(
@@ -3323,7 +3350,7 @@ do_data_relocation(AOTModule *module, AOTRelocationGroup *group,
     uint8 *data_addr;
     uint32 data_size = 0, i;
     AOTRelocation *relocation = group->relocations;
-    void *symbol_addr;
+    void *symbol_addr = NULL;
     char *symbol, *data_section_name;
 
     if (!strncmp(group->section_name, ".rela.", 6)) {
@@ -4128,10 +4155,16 @@ create_module(char *name, char *error_buf, uint32 error_buf_size)
 #endif
 
 #if WASM_ENABLE_LIBC_WASI != 0
+#if WASM_ENABLE_UVWASI == 0
     module->wasi_args.stdio[0] = os_invalid_raw_handle();
     module->wasi_args.stdio[1] = os_invalid_raw_handle();
     module->wasi_args.stdio[2] = os_invalid_raw_handle();
-#endif
+#else
+    module->wasi_args.stdio[0] = os_get_invalid_handle();
+    module->wasi_args.stdio[1] = os_get_invalid_handle();
+    module->wasi_args.stdio[2] = os_get_invalid_handle();
+#endif /* WASM_ENABLE_UVWASI == 0 */
+#endif /* WASM_ENABLE_LIBC_WASI != 0 */
 
     return module;
 #if WASM_ENABLE_GC != 0

core/iwasm/aot/aot_runtime.c

@@ -3639,7 +3639,7 @@ aot_get_module_inst_mem_consumption(const AOTModuleInstance *module_inst,
     for (i = 0; i < module_inst->memory_count; i++) {
         AOTMemoryInstance *mem_inst = module_inst->memories[i];
         mem_conspn->memories_size +=
-            mem_inst->num_bytes_per_page * mem_inst->cur_page_count;
+            (uint64)mem_inst->num_bytes_per_page * mem_inst->cur_page_count;
         mem_conspn->app_heap_size =
             mem_inst->heap_data_end - mem_inst->heap_data;
         /* size of app heap structure */
@@ -4137,9 +4137,9 @@ aot_frame_update_profile_info(WASMExecEnv *exec_env, bool alloc_frame)
 }
 #endif /* end of WASM_ENABLE_AOT_STACK_FRAME != 0 */
 
-#if WAMR_ENABLE_COPY_CALLSTACK != 0
+#if WASM_ENABLE_COPY_CALL_STACK != 0
 uint32
-aot_copy_callstack_tiny_frame(WASMExecEnv *exec_env, wasm_frame_t *buffer,
+aot_copy_callstack_tiny_frame(WASMExecEnv *exec_env, WASMCApiFrame *buffer,
                               const uint32 length, const uint32 skip_n,
                               char *error_buf, uint32 error_buf_size)
 {
@@ -4193,7 +4193,7 @@ aot_copy_callstack_tiny_frame(WASMExecEnv *exec_env, wasm_frame_t *buffer,
 }
 
 uint32
-aot_copy_callstack_standard_frame(WASMExecEnv *exec_env, wasm_frame_t *buffer,
+aot_copy_callstack_standard_frame(WASMExecEnv *exec_env, WASMCApiFrame *buffer,
                                   const uint32 length, const uint32 skip_n,
                                   char *error_buf, uint32_t error_buf_size)
 {
@@ -4243,7 +4243,7 @@ aot_copy_callstack_standard_frame(WASMExecEnv *exec_env, wasm_frame_t *buffer,
 }
 
 uint32
-aot_copy_callstack(WASMExecEnv *exec_env, wasm_frame_t *buffer,
+aot_copy_callstack(WASMExecEnv *exec_env, WASMCApiFrame *buffer,
                    const uint32 length, const uint32 skip_n, char *error_buf,
                    uint32_t error_buf_size)
 {
@@ -4265,7 +4265,7 @@ aot_copy_callstack(WASMExecEnv *exec_env, wasm_frame_t *buffer,
                                              error_buf, error_buf_size);
     }
 }
-#endif // WAMR_ENABLE_COPY_CALLSTACK
+#endif // WASM_ENABLE_COPY_CALL_STACK
 
 #if WASM_ENABLE_DUMP_CALL_STACK != 0
 bool
@@ -4877,8 +4877,8 @@ aot_dump_pgo_prof_data_to_buf(AOTModuleInstance *module_inst, char *buf,
     }
 
     prof_header.magic = 0xFF6C70726F667281LL;
-    /* Version 8 */
-    prof_header.version = 0x0000000000000008LL;
+    /* Version 9 */
+    prof_header.version = 0x0000000000000009LL;
     /* with VARIANT_MASK_IR_PROF (IR Instrumentation) */
     prof_header.version |= 0x1ULL << 56;
     /* with VARIANT_MASK_MEMPROF (Memory Profile) */
@@ -4887,14 +4887,19 @@ aot_dump_pgo_prof_data_to_buf(AOTModuleInstance *module_inst, char *buf,
     prof_header.num_prof_counters = num_prof_counters;
     prof_header.names_size = prof_names_size;
     prof_header.value_kind_last = 1;
+    /* __llvm_prf_bits won't be used in PGO, set dummy value here */
+    prof_header.num_prof_bitmaps = 0;
+    prof_header.bitmap_delta = 0;
 
     if (!is_little_endian()) {
         aot_exchange_uint64((uint8 *)&prof_header.magic);
         aot_exchange_uint64((uint8 *)&prof_header.version);
         aot_exchange_uint64((uint8 *)&prof_header.num_prof_data);
         aot_exchange_uint64((uint8 *)&prof_header.num_prof_counters);
+        aot_exchange_uint64((uint8 *)&prof_header.num_prof_bitmaps);
         aot_exchange_uint64((uint8 *)&prof_header.names_size);
         aot_exchange_uint64((uint8 *)&prof_header.counters_delta);
+        aot_exchange_uint64((uint8 *)&prof_header.bitmap_delta);
         aot_exchange_uint64((uint8 *)&prof_header.value_kind_last);
     }
 
@@ -4912,19 +4917,23 @@ aot_dump_pgo_prof_data_to_buf(AOTModuleInstance *module_inst, char *buf,
             prof_data_64->func_md5 = prof_data->func_md5;
             prof_data_64->func_hash = prof_data->func_hash;
             prof_data_64->offset_counters = prof_data->offset_counters;
+            prof_data_64->offset_bitmaps = prof_data->offset_bitmaps;
             prof_data_64->func_ptr = prof_data->func_ptr;
             prof_data_64->values = (uint64)(uintptr_t)prof_data->values;
             prof_data_64->num_counters = prof_data->num_counters;
+            /* __llvm_prf_bits won't be used in PGO, set dummy value here */
+            prof_data_64->num_bitmaps = 0;
             prof_data_64->num_value_sites[0] = prof_data->num_value_sites[0];
             prof_data_64->num_value_sites[1] = prof_data->num_value_sites[1];
 
             if (!is_little_endian()) {
                 aot_exchange_uint64((uint8 *)&prof_data_64->func_hash);
                 aot_exchange_uint64((uint8 *)&prof_data_64->offset_counters);
-                aot_exchange_uint64((uint8 *)&prof_data_64->offset_counters);
+                aot_exchange_uint64((uint8 *)&prof_data_64->offset_bitmaps);
                 aot_exchange_uint64((uint8 *)&prof_data_64->func_ptr);
                 aot_exchange_uint64((uint8 *)&prof_data_64->values);
                 aot_exchange_uint32((uint8 *)&prof_data_64->num_counters);
+                aot_exchange_uint32((uint8 *)&prof_data_64->num_bitmaps);
                 aot_exchange_uint16((uint8 *)&prof_data_64->num_value_sites[0]);
                 aot_exchange_uint16((uint8 *)&prof_data_64->num_value_sites[1]);
             }

core/iwasm/aot/aot_runtime.h

@@ -437,6 +437,9 @@ typedef struct AOTFrame {
 } AOTFrame;
 
 #if WASM_ENABLE_STATIC_PGO != 0
+/* The bitmaps fields in LLVMProfileRawHeader, LLVMProfileData,
+ * LLVMProfileData_64 all dummy fields, it's used in MC/DC code coverage
+ * instead of PGO. See https://llvm.org/docs/InstrProfileFormat.html#bitmap */
 typedef struct LLVMProfileRawHeader {
     uint64 magic;
     uint64 version;
@@ -445,8 +448,11 @@ typedef struct LLVMProfileRawHeader {
     uint64 padding_bytes_before_counters;
     uint64 num_prof_counters;
     uint64 padding_bytes_after_counters;
+    uint64 num_prof_bitmaps;
+    uint64 padding_bytes_after_bitmaps;
     uint64 names_size;
     uint64 counters_delta;
+    uint64 bitmap_delta;
     uint64 names_delta;
     uint64 value_kind_last;
 } LLVMProfileRawHeader;
@@ -464,10 +470,12 @@ typedef struct LLVMProfileData {
     uint64 func_md5;
     uint64 func_hash;
     uint64 offset_counters;
+    uint64 offset_bitmaps;
     uintptr_t func_ptr;
     ValueProfNode **values;
     uint32 num_counters;
     uint16 num_value_sites[2];
+    uint32 num_bitmaps;
 } LLVMProfileData;
 
 /* The profiling data for writing to the output file, the width of
@@ -477,10 +485,12 @@ typedef struct LLVMProfileData_64 {
     uint64 func_md5;
     uint64 func_hash;
     uint64 offset_counters;
+    uint64 offset_bitmaps;
     uint64 func_ptr;
     uint64 values;
     uint32 num_counters;
     uint16 num_value_sites[2];
+    uint32 num_bitmaps;
 } LLVMProfileData_64;
 #endif /* end of WASM_ENABLE_STATIC_PGO != 0 */
 
@@ -777,12 +787,12 @@ aot_frame_update_profile_info(WASMExecEnv *exec_env, bool alloc_frame);
 bool
 aot_create_call_stack(struct WASMExecEnv *exec_env);
 
-#if WAMR_ENABLE_COPY_CALLSTACK != 0
+#if WASM_ENABLE_COPY_CALL_STACK != 0
 uint32
-aot_copy_callstack(WASMExecEnv *exec_env, wasm_frame_t *buffer,
+aot_copy_callstack(WASMExecEnv *exec_env, WASMCApiFrame *buffer,
                    const uint32 length, const uint32 skip_n, char *error_buf,
                    uint32_t error_buf_size);
-#endif // WAMR_ENABLE_COPY_CALLSTACK
+#endif // WASM_ENABLE_COPY_CALL_STACK
 
 /**
  * @brief Dump wasm call stack or get the size

core/iwasm/common/gc/gc_type.c

@@ -1145,7 +1145,7 @@ wasm_reftype_is_subtype_of(uint8 type1, const WASMRefType *ref_type1,
                 return true;
             else {
                 int32 heap_type = ref_type1->ref_ht_common.heap_type;
-                // We dont care whether type2 is nullable or not. So
+                // We don't care whether type2 is nullable or not. So
                 // we normalize it into its related one-byte type.
                 if (type2 == REF_TYPE_HT_NULLABLE
                     || type2 == REF_TYPE_HT_NON_NULLABLE) {

core/iwasm/common/wasm_exec_env.c

@@ -85,6 +85,10 @@ wasm_exec_env_create_internal(struct WASMModuleInstanceCommon *module_inst,
     wasm_runtime_dump_exec_env_mem_consumption(exec_env);
 #endif
 
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+    exec_env->instructions_to_execute = -1;
+#endif
+
     return exec_env;
 
 #ifdef OS_ENABLE_HW_BOUND_CHECK

core/iwasm/common/wasm_exec_env.h

@@ -87,6 +87,11 @@ typedef struct WASMExecEnv {
         uint8 *bottom;
     } wasm_stack;
 
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+    /* instructions to execute */
+    int instructions_to_execute;
+#endif
+
 #if WASM_ENABLE_FAST_JIT != 0
     /**
      * Cache for

core/iwasm/common/wasm_runtime_common.c

@@ -1504,7 +1504,7 @@ wasm_runtime_load_ex(uint8 *buf, uint32 size, const LoadArgs *args,
                                           error_buf_size);
 }
 
-WASM_RUNTIME_API_EXTERN bool
+bool
 wasm_runtime_resolve_symbols(WASMModuleCommon *module)
 {
 #if WASM_ENABLE_INTERP != 0
@@ -1743,9 +1743,9 @@ wasm_runtime_destroy_exec_env(WASMExecEnv *exec_env)
     wasm_exec_env_destroy(exec_env);
 }
 
-#if WAMR_ENABLE_COPY_CALLSTACK != 0
+#if WASM_ENABLE_COPY_CALL_STACK != 0
 uint32
-wasm_copy_callstack(const wasm_exec_env_t exec_env, wasm_frame_t *buffer,
+wasm_copy_callstack(const wasm_exec_env_t exec_env, WASMCApiFrame *buffer,
                     const uint32 length, const uint32 skip_n, char *error_buf,
                     uint32_t error_buf_size)
 {
@@ -1780,7 +1780,7 @@ wasm_copy_callstack(const wasm_exec_env_t exec_env, wasm_frame_t *buffer,
     strncpy(error_buf, err_msg, error_buf_size);
     return 0;
 }
-#endif // WAMR_ENABLE_COPY_CALLSTACK
+#endif // WASM_ENABLE_COPY_CALL_STACK
 
 bool
 wasm_runtime_init_thread_env(void)
@@ -2285,6 +2285,15 @@ wasm_runtime_access_exce_check_guard_page()
 }
 #endif
 
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+void
+wasm_runtime_set_instruction_count_limit(WASMExecEnv *exec_env,
+                                         int instructions_to_execute)
+{
+    exec_env->instructions_to_execute = instructions_to_execute;
+}
+#endif
+
 WASMFuncType *
 wasm_runtime_get_function_type(const WASMFunctionInstanceCommon *function,
                                uint32 module_type)
@@ -3877,11 +3886,15 @@ wasm_runtime_init_wasi(WASMModuleInstanceCommon *module_inst,
     init_options.allocator = &uvwasi_allocator;
     init_options.argc = argc;
     init_options.argv = (const char **)argv;
-    init_options.in = (stdinfd != -1) ? (uvwasi_fd_t)stdinfd : init_options.in;
-    init_options.out =
-        (stdoutfd != -1) ? (uvwasi_fd_t)stdoutfd : init_options.out;
-    init_options.err =
-        (stderrfd != -1) ? (uvwasi_fd_t)stderrfd : init_options.err;
+    init_options.in = (stdinfd != os_get_invalid_handle())
+                          ? (uvwasi_fd_t)stdinfd
+                          : init_options.in;
+    init_options.out = (stdoutfd != os_get_invalid_handle())
+                           ? (uvwasi_fd_t)stdoutfd
+                           : init_options.out;
+    init_options.err = (stderrfd != os_get_invalid_handle())
+                           ? (uvwasi_fd_t)stderrfd
+                           : init_options.err;
 
     if (dir_count > 0) {
         init_options.preopenc = dir_count;
@@ -7836,7 +7849,7 @@ wasm_runtime_detect_native_stack_overflow_size(WASMExecEnv *exec_env,
     return true;
 }
 
-WASM_RUNTIME_API_EXTERN bool
+bool
 wasm_runtime_is_underlying_binary_freeable(WASMModuleCommon *const module)
 {
 #if WASM_ENABLE_INTERP != 0

core/iwasm/common/wasm_runtime_common.h

@@ -758,12 +758,12 @@ wasm_runtime_create_exec_env(WASMModuleInstanceCommon *module_inst,
 WASM_RUNTIME_API_EXTERN void
 wasm_runtime_destroy_exec_env(WASMExecEnv *exec_env);
 
-#if WAMR_ENABLE_COPY_CALLSTACK != 0
+#if WASM_ENABLE_COPY_CALL_STACK != 0
 WASM_RUNTIME_API_EXTERN uint32_t
-wasm_copy_callstack(const wasm_exec_env_t exec_env, wasm_frame_t *buffer,
+wasm_copy_callstack(const wasm_exec_env_t exec_env, WASMCApiFrame *buffer,
                     const uint32 length, const uint32 skip_n, char *error_buf,
                     uint32 error_buf_size);
-#endif // WAMR_ENABLE_COPY_CALLSTACK
+#endif // WASM_ENABLE_COPY_CALL_STACK
 
 /* See wasm_export.h for description */
 WASM_RUNTIME_API_EXTERN WASMModuleInstanceCommon *
@@ -791,9 +791,17 @@ WASM_RUNTIME_API_EXTERN void
 wasm_runtime_set_native_stack_boundary(WASMExecEnv *exec_env,
                                        uint8 *native_stack_boundary);
 
-#if WASM_CONFIGURABLE_BOUNDS_CHECKS != 0
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
 /* See wasm_export.h for description */
 WASM_RUNTIME_API_EXTERN void
+wasm_runtime_set_instruction_count_limit(WASMExecEnv *exec_env,
+                                         int instructions_to_execute);
+#endif
+
+#if WASM_CONFIGURABLE_BOUNDS_CHECKS != 0
+/* See wasm_export.h for description */
+WASM_RUNTIME_API_EXTERN
+void
 wasm_runtime_set_bounds_checks(WASMModuleInstanceCommon *module_inst,
                                bool enable);
 

core/iwasm/compilation/aot_emit_aot_file.c

@@ -48,7 +48,7 @@ typedef struct AOTSymbolList {
 } AOTSymbolList;
 
 /* AOT object data */
-typedef struct AOTObjectData {
+struct AOTObjectData {
     AOTCompContext *comp_ctx;
 
     LLVMMemoryBufferRef mem_buf;
@@ -82,7 +82,7 @@ typedef struct AOTObjectData {
     const char *stack_sizes_section_name;
     uint32 stack_sizes_offset;
     uint32 *stack_sizes;
-} AOTObjectData;
+};
 
 #if 0
 static void dump_buf(uint8 *buf, uint32 size, char *title)
@@ -302,8 +302,8 @@ get_init_expr_size(const AOTCompContext *comp_ctx, const AOTCompData *comp_data,
 
             /* array_elem_type + type_index + len + elems */
             size += sizeof(uint32) * 3
-                    + wasm_value_type_size_internal(array_type->elem_type,
-                                                    comp_ctx->pointer_size)
+                    + (uint64)wasm_value_type_size_internal(
+                          array_type->elem_type, comp_ctx->pointer_size)
                           * value_count;
             break;
         }
@@ -3378,6 +3378,12 @@ aot_resolve_object_data_sections(AOTObjectData *obj_data)
                     bh_memcpy_s(data_section->name, size, buf, size);
                     data_section->is_name_allocated = true;
                 }
+                else if (obj_data->comp_ctx->enable_llvm_pgo
+                         && !strcmp(name, "__llvm_prf_bits")) {
+                    LOG_WARNING("__llvm_prf_bits section is not supported and "
+                                "shouldn't be used in PGO.");
+                    return false;
+                }
 
                 if (obj_data->comp_ctx->enable_llvm_pgo
                     && !strcmp(name, "__llvm_prf_names")) {

core/iwasm/compilation/aot_emit_function.c

@@ -347,7 +347,8 @@ call_aot_invoke_c_api_native(AOTCompContext *comp_ctx, AOTFuncContext *func_ctx,
 
     /* Get &c_api_func_imports[func_idx], note size of CApiFuncImport
        is pointer_size * 3 */
-    offset = I32_CONST((comp_ctx->pointer_size * 3) * import_func_idx);
+    offset = I32_CONST((unsigned long long)comp_ctx->pointer_size * 3
+                       * import_func_idx);
     CHECK_LLVM_CONST(offset);
     c_api_func_import =
         LLVMBuildInBoundsGEP2(comp_ctx->builder, INT8_TYPE, c_api_func_imports,

core/iwasm/compilation/aot_llvm.c

@@ -3204,6 +3204,21 @@ aot_create_comp_context(const AOTCompData *comp_data, aot_comp_option_t option)
 
 #if WASM_ENABLE_WAMR_COMPILER != 0
     WASMModule *wasm_module = (WASMModule *)comp_data->wasm_module;
+    bool is_memory64 = false;
+
+    /* TODO: multi-memories for now assuming the memory64 flag of a memory is
+     * consistent across multi-memories */
+    if (wasm_module->import_memory_count > 0)
+        is_memory64 = !!(wasm_module->import_memories[0].u.memory.mem_type.flags
+                         & MEMORY64_FLAG);
+    else if (wasm_module->memory_count > 0)
+        is_memory64 = !!(wasm_module->memories[0].flags & MEMORY64_FLAG);
+
+    if (!(option->bounds_checks == 1 || option->bounds_checks == 0)
+        && is_memory64) {
+        /* For memory64, the boundary check default value is true */
+        comp_ctx->enable_bound_check = true;
+    }
 
     /* Return error if SIMD is disabled by command line but SIMD instructions
      * are used */
@@ -3984,7 +3999,7 @@ aot_get_func_from_table(const AOTCompContext *comp_ctx, LLVMValueRef base,
 
     if (!(func =
               LLVMBuildBitCast(comp_ctx->builder, func, func_type, "func"))) {
-        aot_set_last_error("cast function fialed.");
+        aot_set_last_error("cast function failed.");
         goto fail;
     }
 
@@ -4053,7 +4068,7 @@ aot_load_const_from_table(AOTCompContext *comp_ctx, LLVMValueRef base,
 
     if (!(const_addr = LLVMBuildBitCast(comp_ctx->builder, const_addr,
                                         const_ptr_type, "const_addr"))) {
-        aot_set_last_error("cast const fialed.");
+        aot_set_last_error("cast const failed.");
         return NULL;
     }
 

core/iwasm/include/wasm_export.h

@@ -139,8 +139,6 @@ typedef struct wasm_frame_t {
     uint32_t *lp;
 } WASMCApiFrame;
 
-typedef WASMCApiFrame wasm_frame_t;
-
 /* WASM section */
 typedef struct wasm_section_t {
     struct wasm_section_t *next;
@@ -904,7 +902,7 @@ wasm_runtime_destroy_exec_env(wasm_exec_env_t exec_env);
  * @return number of copied frames
  */
 WASM_RUNTIME_API_EXTERN uint32_t
-wasm_copy_callstack(const wasm_exec_env_t exec_env, wasm_frame_t *buffer,
+wasm_copy_callstack(const wasm_exec_env_t exec_env, WASMCApiFrame *buffer,
                     const uint32_t length, const uint32_t skip_n,
                     char *error_buf, uint32_t error_buf_size);
 
@@ -1821,6 +1819,20 @@ WASM_RUNTIME_API_EXTERN void
 wasm_runtime_set_native_stack_boundary(wasm_exec_env_t exec_env,
                                        uint8_t *native_stack_boundary);
 
+/**
+ * Set the instruction count limit to the execution environment.
+ * By default the instruction count limit is -1, which means no limit.
+ * However, if the instruction count limit is set to a positive value,
+ * the execution will be terminated when the instruction count reaches
+ * the limit.
+ *
+ * @param exec_env the execution environment
+ * @param instruction_count the instruction count limit
+ */
+WASM_RUNTIME_API_EXTERN void
+wasm_runtime_set_instruction_count_limit(wasm_exec_env_t exec_env,
+                                         int instruction_count);
+
 /**
  * Dump runtime memory consumption, including:
  *     Exec env memory consumption

core/iwasm/interpreter/wasm.h

@@ -1243,7 +1243,7 @@ wasm_value_type_size_internal(uint8 value_type, uint8 pointer_size)
         return sizeof(int16);
 #endif
     else {
-        bh_assert(0);
+        bh_assert(0 && "Unknown value type. It should be handled ahead.");
     }
 #if WASM_ENABLE_GC == 0
     (void)pointer_size;

core/iwasm/interpreter/wasm_interp_classic.c

@@ -1516,10 +1516,13 @@ wasm_interp_call_func_import(WASMModuleInstance *module_inst,
             }                                                                 \
             os_mutex_unlock(&exec_env->wait_lock);                            \
         }                                                                     \
+        CHECK_INSTRUCTION_LIMIT();                                            \
         goto *handle_table[*frame_ip++];                                      \
     } while (0)
 #else
-#define HANDLE_OP_END() FETCH_OPCODE_AND_DISPATCH()
+#define HANDLE_OP_END()        \
+    CHECK_INSTRUCTION_LIMIT(); \
+    FETCH_OPCODE_AND_DISPATCH()
 #endif
 
 #else /* else of WASM_ENABLE_LABELS_AS_VALUES */
@@ -1542,9 +1545,12 @@ wasm_interp_call_func_import(WASMModuleInstance *module_inst,
         }                                                                 \
         os_mutex_unlock(&exec_env->wait_lock);                            \
     }                                                                     \
+    CHECK_INSTRUCTION_LIMIT();                                            \
     continue;
 #else
-#define HANDLE_OP_END() continue
+#define HANDLE_OP_END()        \
+    CHECK_INSTRUCTION_LIMIT(); \
+    continue;
 #endif
 
 #endif /* end of WASM_ENABLE_LABELS_AS_VALUES */
@@ -1562,6 +1568,18 @@ get_global_addr(uint8 *global_data, WASMGlobalInstance *global)
 #endif
 }
 
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+#define CHECK_INSTRUCTION_LIMIT()                                 \
+    if (instructions_left == 0) {                                 \
+        wasm_set_exception(module, "instruction limit exceeded"); \
+        goto got_exception;                                       \
+    }                                                             \
+    else if (instructions_left > 0)                               \
+        instructions_left--;
+#else
+#define CHECK_INSTRUCTION_LIMIT() (void)0
+#endif
+
 static void
 wasm_interp_call_func_bytecode(WASMModuleInstance *module,
                                WASMExecEnv *exec_env,
@@ -1605,6 +1623,14 @@ wasm_interp_call_func_bytecode(WASMModuleInstance *module,
     uint32 local_idx, local_offset, global_idx;
     uint8 local_type, *global_addr;
     uint32 cache_index, type_index, param_cell_num, cell_num;
+
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+    int instructions_left = -1;
+    if (exec_env) {
+        instructions_left = exec_env->instructions_to_execute;
+    }
+#endif
+
 #if WASM_ENABLE_EXCE_HANDLING != 0
     int32_t exception_tag_index;
 #endif
@@ -4062,7 +4088,7 @@ wasm_interp_call_func_bytecode(WASMModuleInstance *module,
                     case WASM_OP_STRING_ENCODE_LOSSY_UTF8_ARRAY:
                     case WASM_OP_STRING_ENCODE_WTF8_ARRAY:
                     {
-                        uint32 start, array_len, count;
+                        uint32 start, array_len;
                         int32 bytes_written;
                         EncodingFlag flag = WTF8;
                         WASMArrayType *array_type;

core/iwasm/interpreter/wasm_interp_fast.c

@@ -105,6 +105,19 @@ typedef float64 CellType_F64;
             goto unaligned_atomic;                 \
     } while (0)
 
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+#define CHECK_INSTRUCTION_LIMIT()                                 \
+    if (instructions_left == 0) {                                 \
+        wasm_set_exception(module, "instruction limit exceeded"); \
+        goto got_exception;                                       \
+    }                                                             \
+    else if (instructions_left > 0)                               \
+        instructions_left--;
+
+#else
+#define CHECK_INSTRUCTION_LIMIT() (void)0
+#endif
+
 static inline uint32
 rotl32(uint32 n, uint32 c)
 {
@@ -1441,6 +1454,7 @@ wasm_interp_dump_op_count()
     do {                                               \
         const void *p_label_addr = *(void **)frame_ip; \
         frame_ip += sizeof(void *);                    \
+        CHECK_INSTRUCTION_LIMIT();                     \
         goto *p_label_addr;                            \
     } while (0)
 #else
@@ -1452,6 +1466,7 @@ wasm_interp_dump_op_count()
         /* int32 relative offset was emitted in 64-bit target */          \
         p_label_addr = label_base + (int32)LOAD_U32_WITH_2U16S(frame_ip); \
         frame_ip += sizeof(int32);                                        \
+        CHECK_INSTRUCTION_LIMIT();                                        \
         goto *p_label_addr;                                               \
     } while (0)
 #else
@@ -1462,6 +1477,7 @@ wasm_interp_dump_op_count()
         /* uint32 label address was emitted in 32-bit target */          \
         p_label_addr = (void *)(uintptr_t)LOAD_U32_WITH_2U16S(frame_ip); \
         frame_ip += sizeof(int32);                                       \
+        CHECK_INSTRUCTION_LIMIT();                                       \
         goto *p_label_addr;                                              \
     } while (0)
 #endif
@@ -1538,6 +1554,13 @@ wasm_interp_call_func_bytecode(WASMModuleInstance *module,
     uint8 *maddr = NULL;
     uint32 local_idx, local_offset, global_idx;
     uint8 opcode = 0, local_type, *global_addr;
+
+#if WASM_ENABLE_INSTRUCTION_METERING != 0
+    int instructions_left = -1;
+    if (exec_env) {
+        instructions_left = exec_env->instructions_to_execute;
+    }
+#endif
 #if !defined(OS_ENABLE_HW_BOUND_CHECK) \
     || WASM_CPU_SUPPORTS_UNALIGNED_ADDR_ACCESS == 0
 #if WASM_CONFIGURABLE_BOUNDS_CHECKS != 0
@@ -6101,8 +6124,9 @@ wasm_interp_call_func_bytecode(WASMModuleInstance *module,
 #if WASM_CPU_SUPPORTS_UNALIGNED_ADDR_ACCESS != 0
 #define SIMD_LANE_HANDLE_UNALIGNED_ACCESS()
 #else
-#define SIMD_LANE_HANDLE_UNALIGNED_ACCESS() *frame_ip++;
-#endif
+#define SIMD_LANE_HANDLE_UNALIGNED_ACCESS() (void)*frame_ip++
+#endif /* WASM_CPU_SUPPORTS_UNALIGNED_ADDR_ACCESS != 0 */
+
 #define SIMD_EXTRACT_LANE_OP(register, return_type, push_elem) \
     do {                                                       \
         uint8 lane = *frame_ip++;                              \
@@ -6514,17 +6538,17 @@ wasm_interp_call_func_bytecode(WASMModuleInstance *module,
                         break;
                     }
 
-#define SIMD_LOAD_LANE_COMMON(vec, register, lane, width)  \
-    do {                                                   \
-        addr_ret = GET_OFFSET();                           \
-        CHECK_MEMORY_OVERFLOW(width / 8);                  \
-        if (width == 64) {                                 \
-            vec.register[lane] = GET_I64_FROM_ADDR(maddr); \
-        }                                                  \
-        else {                                             \
-            vec.register[lane] = *(uint##width *)(maddr);  \
-        }                                                  \
-        PUT_V128_TO_ADDR(frame_lp + addr_ret, vec);        \
+#define SIMD_LOAD_LANE_COMMON(vec, register, lane, width)            \
+    do {                                                             \
+        addr_ret = GET_OFFSET();                                     \
+        CHECK_MEMORY_OVERFLOW(width / 8);                            \
+        if (width == 64) {                                           \
+            vec.register[lane] = GET_I64_FROM_ADDR((uint32 *)maddr); \
+        }                                                            \
+        else {                                                       \
+            vec.register[lane] = *(uint##width *)(maddr);            \
+        }                                                            \
+        PUT_V128_TO_ADDR(frame_lp + addr_ret, vec);                  \
     } while (0)
 
 #define SIMD_LOAD_LANE_OP(register, width)                 \

core/iwasm/interpreter/wasm_loader.c

@@ -379,7 +379,6 @@ memory_realloc(void *mem_old, uint32 size_old, uint32 size_new, char *error_buf,
         mem = mem_new;                                                     \
     } while (0)
 
-#if WASM_ENABLE_GC != 0
 static bool
 check_type_index(const WASMModule *module, uint32 type_count, uint32 type_index,
                  char *error_buf, uint32 error_buf_size)
@@ -392,6 +391,7 @@ check_type_index(const WASMModule *module, uint32 type_count, uint32 type_index,
     return true;
 }
 
+#if WASM_ENABLE_GC != 0
 static bool
 check_array_type(const WASMModule *module, uint32 type_index, char *error_buf,
                  uint32 error_buf_size)
@@ -409,6 +409,29 @@ check_array_type(const WASMModule *module, uint32 type_index, char *error_buf,
 }
 #endif
 
+/*
+ * if no GC is enabled, an valid type is always a function type.
+ * but if GC is enabled, we need to check the type flag
+ */
+static bool
+check_function_type(const WASMModule *module, uint32 type_index,
+                    char *error_buf, uint32 error_buf_size)
+{
+    if (!check_type_index(module, module->type_count, type_index, error_buf,
+                          error_buf_size)) {
+        return false;
+    }
+
+#if WASM_ENABLE_GC != 0
+    if (module->types[type_index]->type_flag != WASM_TYPE_FUNC) {
+        set_error_buf(error_buf, error_buf_size, "unknown function type");
+        return false;
+    }
+#endif
+
+    return true;
+}
+
 static bool
 check_function_index(const WASMModule *module, uint32 function_index,
                      char *error_buf, uint32 error_buf_size)
@@ -808,19 +831,24 @@ load_init_expr(WASMModule *module, const uint8 **p_buf, const uint8 *buf_end,
             {
                 uint8 type1;
 
+#if WASM_ENABLE_GC == 0
                 CHECK_BUF(p, p_end, 1);
                 type1 = read_uint8(p);
 
-#if WASM_ENABLE_GC == 0
                 cur_value.ref_index = NULL_REF;
                 if (!push_const_expr_stack(&const_expr_ctx, flag, type1,
                                            &cur_value, error_buf,
                                            error_buf_size))
                     goto fail;
 #else
+                int32 heap_type;
+                read_leb_int32(p, p_end, heap_type);
+                type1 = (uint8)((int32)0x80 + heap_type);
+
                 cur_value.gc_obj = NULL_REF;
 
                 if (!is_byte_a_type(type1)
+                    || !wasm_is_valid_heap_type(heap_type)
                     || wasm_is_type_multi_byte_type(type1)) {
                     p--;
                     read_leb_uint32(p, p_end, type_idx);
@@ -2014,9 +2042,9 @@ load_type_section(const uint8 *buf, const uint8 *buf_end, WASMModule *module,
                                       "recursive type count too large");
                         return false;
                     }
-                    module->type_count += rec_count - 1;
                     new_total_size =
-                        sizeof(WASMFuncType *) * (uint64)module->type_count;
+                        sizeof(WASMFuncType *)
+                        * (uint64)(module->type_count + rec_count - 1);
                     if (new_total_size > UINT32_MAX) {
                         set_error_buf(error_buf, error_buf_size,
                                       "allocate memory failed");
@@ -2024,6 +2052,7 @@ load_type_section(const uint8 *buf, const uint8 *buf_end, WASMModule *module,
                     }
                     MEM_REALLOC(module->types, (uint32)total_size,
                                 (uint32)new_total_size);
+                    module->type_count += rec_count - 1;
                     total_size = new_total_size;
                 }
 
@@ -2479,8 +2508,8 @@ load_function_import(const uint8 **p_buf, const uint8 *buf_end,
     read_leb_uint32(p, p_end, declare_type_index);
     *p_buf = p;
 
-    if (declare_type_index >= parent_module->type_count) {
-        set_error_buf(error_buf, error_buf_size, "unknown type");
+    if (!check_function_type(parent_module, declare_type_index, error_buf,
+                             error_buf_size)) {
         return false;
     }
 
@@ -2560,7 +2589,8 @@ load_table_import(const uint8 **p_buf, const uint8 *buf_end,
                             error_buf_size)) {
         return false;
     }
-    if (wasm_is_reftype_htref_non_nullable(ref_type.ref_type)) {
+    if (!wasm_is_type_reftype(ref_type.ref_type)
+        || wasm_is_reftype_htref_non_nullable(ref_type.ref_type)) {
         set_error_buf(error_buf, error_buf_size, "type mismatch");
         return false;
     }
@@ -2893,8 +2923,8 @@ load_tag_import(const uint8 **p_buf, const uint8 *buf_end,
     /* get type */
     read_leb_uint32(p, p_end, declare_type_index);
     /* compare against module->types */
-    if (declare_type_index >= parent_module->type_count) {
-        set_error_buf(error_buf, error_buf_size, "unknown tag type");
+    if (!check_function_type(parent_module, declare_type_index, error_buf,
+                             error_buf_size)) {
         goto fail;
     }
 
@@ -3086,6 +3116,15 @@ load_table(const uint8 **p_buf, const uint8 *buf_end, WASMModule *module,
                             error_buf_size)) {
         return false;
     }
+    /*
+     * TODO: add this validator
+     *   `wasm_is_reftype_htref_non_nullable(ref_type.ref_type)`
+     * after sync up with the latest GC spec
+     */
+    if (!wasm_is_type_reftype(ref_type.ref_type)) {
+        set_error_buf(error_buf, error_buf_size, "type mismatch");
+        return false;
+    }
     table->table_type.elem_type = ref_type.ref_type;
     if (need_ref_type_map) {
         if (!(table->table_type.elem_ref_type =
@@ -3259,6 +3298,13 @@ load_import_section(const uint8 *buf, const uint8 *buf_end, WASMModule *module,
                     CHECK_BUF(p, p_end, 1);
                     /* 0x70 */
                     u8 = read_uint8(p);
+#if WASM_ENABLE_GC != 0
+                    if (wasm_is_reftype_htref_nullable(u8)) {
+                        int32 heap_type;
+                        read_leb_int32(p, p_end, heap_type);
+                        (void)heap_type;
+                    }
+#endif
                     read_leb_uint32(p, p_end, flags);
                     read_leb_uint32(p, p_end, u32);
                     if (flags & 1)
@@ -3306,7 +3352,8 @@ load_import_section(const uint8 *buf, const uint8 *buf_end, WASMModule *module,
                     /* valtype */
                     CHECK_BUF(p, p_end, 1);
                     global_type = read_uint8(p);
-                    if (wasm_is_type_multi_byte_type(global_type)) {
+                    if (wasm_is_reftype_htref_nullable(global_type)
+                        || wasm_is_reftype_htref_non_nullable(global_type)) {
                         int32 heap_type;
                         read_leb_int32(p, p_end, heap_type);
                         (void)heap_type;
@@ -3563,8 +3610,9 @@ load_function_section(const uint8 *buf, const uint8 *buf_end,
         for (i = 0; i < func_count; i++) {
             /* Resolve function type */
             read_leb_uint32(p, p_end, type_index);
-            if (type_index >= module->type_count) {
-                set_error_buf(error_buf, error_buf_size, "unknown type");
+
+            if (!check_function_type(module, type_index, error_buf,
+                                     error_buf_size)) {
                 return false;
             }
 
@@ -3666,7 +3714,7 @@ load_function_section(const uint8 *buf, const uint8 *buf_end,
              * we shall make a copy of code body [p_code, p_code + code_size]
              * when we are worrying about inappropriate releasing behaviour.
              * all code bodies are actually in a buffer which user allocates in
-             * his embedding environment and we don't have power on them.
+             * their embedding environment and we don't have power over them.
              * it will be like:
              * code_body_cp = malloc(code_size);
              * memcpy(code_body_cp, p_code, code_size);
@@ -4970,8 +5018,8 @@ load_tag_section(const uint8 *buf, const uint8 *buf_end, const uint8 *buf_code,
             /* get type */
             read_leb_uint32(p, p_end, tag_type);
             /* compare against module->types */
-            if (tag_type >= module->type_count) {
-                set_error_buf(error_buf, error_buf_size, "unknown type");
+            if (!check_function_type(module, tag_type, error_buf,
+                                     error_buf_size)) {
                 return false;
             }
 
@@ -6380,10 +6428,16 @@ create_module(char *name, char *error_buf, uint32 error_buf_size)
 #endif
 
 #if WASM_ENABLE_LIBC_WASI != 0
+#if WASM_ENABLE_UVWASI == 0
     module->wasi_args.stdio[0] = os_invalid_raw_handle();
     module->wasi_args.stdio[1] = os_invalid_raw_handle();
     module->wasi_args.stdio[2] = os_invalid_raw_handle();
-#endif
+#else
+    module->wasi_args.stdio[0] = os_get_invalid_handle();
+    module->wasi_args.stdio[1] = os_get_invalid_handle();
+    module->wasi_args.stdio[2] = os_get_invalid_handle();
+#endif /* WASM_ENABLE_UVWASI == 0 */
+#endif /* WASM_ENABLE_LIBC_WASI != 0 */
 
     (void)ret;
     return module;
@@ -10477,7 +10531,7 @@ wasm_loader_check_br(WASMLoaderContext *loader_ctx, uint32 depth, uint8 opcode,
      * match block type. */
     if (cur_block->is_stack_polymorphic) {
 #if WASM_ENABLE_GC != 0
-        int32 j = reftype_map_count - 1;
+        int32 j = (int32)reftype_map_count - 1;
 #endif
         for (i = (int32)arity - 1; i >= 0; i--) {
 #if WASM_ENABLE_GC != 0
@@ -10780,7 +10834,7 @@ check_block_stack(WASMLoaderContext *loader_ctx, BranchBlock *block,
      * match block type. */
     if (block->is_stack_polymorphic) {
 #if WASM_ENABLE_GC != 0
-        int32 j = return_reftype_map_count - 1;
+        int32 j = (int32)return_reftype_map_count - 1;
 #endif
         for (i = (int32)return_count - 1; i >= 0; i--) {
 #if WASM_ENABLE_GC != 0
@@ -11549,15 +11603,17 @@ re_scan:
                 }
                 else {
                     int32 type_index;
+
                     /* Resolve the leb128 encoded type index as block type */
                     p--;
                     p_org = p - 1;
                     pb_read_leb_int32(p, p_end, type_index);
-                    if ((uint32)type_index >= module->type_count) {
-                        set_error_buf(error_buf, error_buf_size,
-                                      "unknown type");
+
+                    if (!check_function_type(module, type_index, error_buf,
+                                             error_buf_size)) {
                         goto fail;
                     }
+
                     block_type.is_value_type = false;
                     block_type.u.type =
                         (WASMFuncType *)module->types[type_index];
@@ -12607,8 +12663,8 @@ re_scan:
                 /* skip elem idx */
                 POP_TBL_ELEM_IDX();
 
-                if (type_idx >= module->type_count) {
-                    set_error_buf(error_buf, error_buf_size, "unknown type");
+                if (!check_function_type(module, type_idx, error_buf,
+                                         error_buf_size)) {
                     goto fail;
                 }
 
@@ -14969,8 +15025,6 @@ re_scan:
                     case WASM_OP_STRING_NEW_LOSSY_UTF8:
                     case WASM_OP_STRING_NEW_WTF8:
                     {
-                        uint32 memidx;
-
 #if WASM_ENABLE_JIT != 0 || WASM_ENABLE_WAMR_COMPILER != 0
                         func->has_memory_operations = true;
 #endif
@@ -14982,7 +15036,6 @@ re_scan:
                         POP_I32();
                         POP_I32();
                         PUSH_REF(REF_TYPE_STRINGREF);
-                        (void)memidx;
                         break;
                     }
                     case WASM_OP_STRING_CONST:
@@ -15010,8 +15063,6 @@ re_scan:
                     case WASM_OP_STRING_ENCODE_LOSSY_UTF8:
                     case WASM_OP_STRING_ENCODE_WTF8:
                     {
-                        uint32 memidx;
-
 #if WASM_ENABLE_JIT != 0 || WASM_ENABLE_WAMR_COMPILER != 0
                         func->has_memory_operations = true;
 #endif
@@ -15023,7 +15074,6 @@ re_scan:
                         POP_I32();
                         POP_STRINGREF();
                         PUSH_I32();
-                        (void)memidx;
                         break;
                     }
                     case WASM_OP_STRING_CONCAT:
@@ -15064,8 +15114,6 @@ re_scan:
                     case WASM_OP_STRINGVIEW_WTF8_ENCODE_LOSSY_UTF8:
                     case WASM_OP_STRINGVIEW_WTF8_ENCODE_WTF8:
                     {
-                        uint32 memidx;
-
 #if WASM_ENABLE_JIT != 0 || WASM_ENABLE_WAMR_COMPILER != 0
                         func->has_memory_operations = true;
 #endif
@@ -15080,7 +15128,6 @@ re_scan:
                         POP_REF(REF_TYPE_STRINGVIEWWTF8);
                         PUSH_I32();
                         PUSH_I32();
-                        (void)memidx;
                         break;
                     }
                     case WASM_OP_STRINGVIEW_WTF8_SLICE:
@@ -15112,8 +15159,6 @@ re_scan:
                     }
                     case WASM_OP_STRINGVIEW_WTF16_ENCODE:
                     {
-                        uint32 memidx;
-
 #if WASM_ENABLE_JIT != 0 || WASM_ENABLE_WAMR_COMPILER != 0
                         func->has_memory_operations = true;
 #endif
@@ -15127,7 +15172,6 @@ re_scan:
                         POP_I32();
                         POP_REF(REF_TYPE_STRINGVIEWWTF16);
                         PUSH_I32();
-                        (void)memidx;
                         break;
                     }
                     case WASM_OP_STRINGVIEW_WTF16_SLICE:

core/iwasm/interpreter/wasm_mini_loader.c

@@ -1226,7 +1226,7 @@ load_function_section(const uint8 *buf, const uint8 *buf_end,
              * we shall make a copy of code body [p_code, p_code + code_size]
              * when we are worrying about inappropriate releasing behaviour.
              * all code bodies are actually in a buffer which user allocates in
-             * his embedding environment and we don't have power on them.
+             * their embedding environment and we don't have power over them.
              * it will be like:
              * code_body_cp = malloc(code_size);
              * memcpy(code_body_cp, p_code, code_size);
@@ -3140,10 +3140,16 @@ create_module(char *name, char *error_buf, uint32 error_buf_size)
 #endif
 
 #if WASM_ENABLE_LIBC_WASI != 0
+#if WASM_ENABLE_LIBC_UVWASI == 0
     module->wasi_args.stdio[0] = os_invalid_raw_handle();
     module->wasi_args.stdio[1] = os_invalid_raw_handle();
     module->wasi_args.stdio[2] = os_invalid_raw_handle();
-#endif
+#else
+    module->wasi_args.stdio[0] = os_get_invalid_handle();
+    module->wasi_args.stdio[1] = os_get_invalid_handle();
+    module->wasi_args.stdio[2] = os_get_invalid_handle();
+#endif /* WASM_ENABLE_UVWASI == 0 */
+#endif /* WASM_ENABLE_LIBC_WASI != 0 */
 
     (void)ret;
     return module;

core/iwasm/interpreter/wasm_runtime.c

@@ -2668,7 +2668,7 @@ wasm_instantiate(WASMModule *module, WASMModuleInstance *parent,
                         }
                         STORE_PTR((void **)global_data, func_obj);
                         global_data += sizeof(void *);
-                        /* Also update the inital_value since other globals may
+                        /* Also update the initial_value since other globals may
                          * refer to this */
                         global->initial_value.gc_obj = (wasm_obj_t)func_obj;
                         break;
@@ -4161,7 +4161,7 @@ wasm_get_module_inst_mem_consumption(const WASMModuleInstance *module_inst,
         sizeof(WASMMemoryInstance *) * module_inst->memory_count;
     for (i = 0; i < module_inst->memory_count; i++) {
         WASMMemoryInstance *memory = module_inst->memories[i];
-        size = memory->num_bytes_per_page * memory->cur_page_count;
+        size = (uint64)memory->num_bytes_per_page * memory->cur_page_count;
         mem_conspn->memories_size += size;
         mem_conspn->app_heap_size += memory->heap_data_end - memory->heap_data;
         /* size of app heap structure */
@@ -4195,9 +4195,9 @@ wasm_get_module_inst_mem_consumption(const WASMModuleInstance *module_inst,
 #endif /* end of (WASM_ENABLE_MEMORY_PROFILING != 0) \
                  || (WASM_ENABLE_MEMORY_TRACING != 0) */
 
-#if WAMR_ENABLE_COPY_CALLSTACK != 0
+#if WASM_ENABLE_COPY_CALL_STACK != 0
 uint32
-wasm_interp_copy_callstack(WASMExecEnv *exec_env, wasm_frame_t *buffer,
+wasm_interp_copy_callstack(WASMExecEnv *exec_env, WASMCApiFrame *buffer,
                            uint32 length, uint32 skip_n, char *error_buf,
                            uint32_t error_buf_size)
 {
@@ -4242,7 +4242,7 @@ wasm_interp_copy_callstack(WASMExecEnv *exec_env, wasm_frame_t *buffer,
     }
     return count >= skip_n ? count - skip_n : 0;
 }
-#endif // WAMR_ENABLE_COPY_CALLSTACK
+#endif // WASM_ENABLE_COPY_CALL_STACK
 
 #if WASM_ENABLE_DUMP_CALL_STACK != 0
 bool

core/iwasm/interpreter/wasm_runtime.h

@@ -731,12 +731,12 @@ wasm_get_table_inst(const WASMModuleInstance *module_inst, uint32 tbl_idx)
 
 #if WASM_ENABLE_DUMP_CALL_STACK != 0
 
-#if WAMR_ENABLE_COPY_CALLSTACK != 0
+#if WASM_ENABLE_COPY_CALL_STACK != 0
 uint32
-wasm_interp_copy_callstack(WASMExecEnv *exec_env, wasm_frame_t *buffer,
+wasm_interp_copy_callstack(WASMExecEnv *exec_env, WASMCApiFrame *buffer,
                            uint32 length, uint32 skip_n, char *error_buf,
                            uint32_t error_buf_size);
-#endif // WAMR_ENABLE_COPY_CALLSTACK
+#endif // WASM_ENABLE_COPY_CALL_STACK
 
 bool
 wasm_interp_create_call_stack(struct WASMExecEnv *exec_env);

core/iwasm/libraries/debug-engine/debug_engine.c

@@ -743,7 +743,7 @@ wasm_debug_instance_get_obj_mem(WASMDebugInstance *instance, uint64 offset,
     module_inst = (WASMModuleInstance *)exec_env->module_inst;
 
     if (offset + *size > module_inst->module->load_size) {
-        LOG_VERBOSE("wasm_debug_instance_get_data_mem size over flow!\n");
+        LOG_VERBOSE("wasm_debug_instance_get_data_mem size overflow!\n");
         *size = module_inst->module->load_size >= offset
                     ? module_inst->module->load_size - offset
                     : 0;
@@ -797,7 +797,7 @@ wasm_debug_instance_get_linear_mem(WASMDebugInstance *instance, uint64 offset,
         num_bytes_per_page = memory->num_bytes_per_page;
         linear_mem_size = num_bytes_per_page * memory->cur_page_count;
         if (offset + *size > linear_mem_size) {
-            LOG_VERBOSE("wasm_debug_instance_get_linear_mem size over flow!\n");
+            LOG_VERBOSE("wasm_debug_instance_get_linear_mem size overflow!\n");
             *size = linear_mem_size >= offset ? linear_mem_size - offset : 0;
         }
         bh_memcpy_s(buf, (uint32)*size, memory->memory_data + offset,
@@ -830,7 +830,7 @@ wasm_debug_instance_set_linear_mem(WASMDebugInstance *instance, uint64 offset,
         num_bytes_per_page = memory->num_bytes_per_page;
         linear_mem_size = num_bytes_per_page * memory->cur_page_count;
         if (offset + *size > linear_mem_size) {
-            LOG_VERBOSE("wasm_debug_instance_get_linear_mem size over flow!\n");
+            LOG_VERBOSE("wasm_debug_instance_get_linear_mem size overflow!\n");
             *size = linear_mem_size >= offset ? linear_mem_size - offset : 0;
         }
         bh_memcpy_s(memory->memory_data + offset, (uint32)*size, buf,

core/iwasm/libraries/debug-engine/handler.c

@@ -175,6 +175,19 @@ process_wasm_global(WASMGDBServer *server, char *args)
     os_mutex_unlock(&tmpbuf_lock);
 }
 
+/* TODO: let server send an empty/error reply.
+   Original issue: 4265
+   Not tested yet, but it should work.
+ */
+static void
+send_reply(WASMGDBServer *server, const char *err)
+{
+    if (!err || !*err)
+        write_packet(server, "");
+    else
+        write_packet(server, err);
+}
+
 void
 handle_general_query(WASMGDBServer *server, char *payload)
 {
@@ -214,6 +227,7 @@ handle_general_query(WASMGDBServer *server, char *payload)
 
         if (!args) {
             LOG_ERROR("payload parse error during handle_general_query");
+            send_reply(server, "");
             return;
         }
 
@@ -384,7 +398,7 @@ send_thread_stop_status(WASMGDBServer *server, uint32 status, korp_tid tid)
     if (status == 0) {
         os_mutex_lock(&tmpbuf_lock);
         (void)snprintf(tmpbuf, MAX_PACKET_SIZE, "W%02" PRIx32, status);
-        write_packet(server, tmpbuf);
+        send_reply(server, tmpbuf);
         os_mutex_unlock(&tmpbuf_lock);
         return;
     }
@@ -403,6 +417,7 @@ send_thread_stop_status(WASMGDBServer *server, uint32 status, korp_tid tid)
                    "T%02" PRIx32 "thread:%" PRIx64 ";name:%s;", gdb_status,
                    (uint64)(uintptr_t)tid, "nobody");
     if (len < 0 || len >= MAX_PACKET_SIZE) {
+        send_reply(server, "E01");
         os_mutex_unlock(&tmpbuf_lock);
         return;
     }
@@ -410,6 +425,7 @@ send_thread_stop_status(WASMGDBServer *server, uint32 status, korp_tid tid)
     if (tids_count > 0) {
         int n = snprintf(tmpbuf + len, MAX_PACKET_SIZE - len, "threads:");
         if (n < 0 || n >= MAX_PACKET_SIZE - len) {
+            send_reply(server, "E01");
             os_mutex_unlock(&tmpbuf_lock);
             return;
         }
@@ -426,6 +442,7 @@ send_thread_stop_status(WASMGDBServer *server, uint32 status, korp_tid tid)
             }
 
             if (n < 0 || n >= MAX_PACKET_SIZE - len) {
+                send_reply(server, "E01");
                 os_mutex_unlock(&tmpbuf_lock);
                 return;
             }
@@ -452,6 +469,7 @@ send_thread_stop_status(WASMGDBServer *server, uint32 status, korp_tid tid)
                      "thread-pcs:%" PRIx64 ";00:%s;reason:%s;description:", pc,
                      pc_string, "exception");
         if (n < 0 || n >= MAX_PACKET_SIZE - len) {
+            send_reply(server, "E01");
             os_mutex_unlock(&tmpbuf_lock);
             return;
         }
@@ -462,6 +480,7 @@ send_thread_stop_status(WASMGDBServer *server, uint32 status, korp_tid tid)
             n = snprintf(tmpbuf + len, MAX_PACKET_SIZE - len, "%02x",
                          exception[i]);
             if (n < 0 || n >= MAX_PACKET_SIZE - len) {
+                send_reply(server, "E01");
                 os_mutex_unlock(&tmpbuf_lock);
                 return;
             }
@@ -592,7 +611,7 @@ handle_get_register(WASMGDBServer *server, char *payload)
     int32 i = strtol(payload, NULL, 16);
 
     if (i != 0) {
-        write_packet(server, "E01");
+        send_reply(server, "E01");
         return;
     }
     regdata = wasm_debug_instance_get_pc(
@@ -748,7 +767,7 @@ handle_add_break(WASMGDBServer *server, char *payload)
     if ((arg_c = sscanf(payload, "%zx,%" SCNx64 ",%zx", &type, &addr, &length))
         != 3) {
         LOG_ERROR("Unsupported number of add break arguments %d", arg_c);
-        write_packet(server, "");
+        send_reply(server, "");
         return;
     }
 
@@ -783,7 +802,7 @@ handle_remove_break(WASMGDBServer *server, char *payload)
     if ((arg_c = sscanf(payload, "%zx,%" SCNx64 ",%zx", &type, &addr, &length))
         != 3) {
         LOG_ERROR("Unsupported number of remove break arguments %d", arg_c);
-        write_packet(server, "");
+        send_reply(server, "");
         return;
     }
 
@@ -835,6 +854,7 @@ handle_malloc(WASMGDBServer *server, char *payload)
     }
     else {
         LOG_ERROR("Payload parse error during handle malloc");
+        send_reply(server, "");
         return;
     }
 

core/iwasm/libraries/lib-socket/src/wasi/wasi_socket_ext.c

@@ -12,6 +12,26 @@
 #include <wasi/api.h>
 #include <wasi_socket_ext.h>
 
+/*
+ * Avoid direct TLS access to allow a single library to be
+ * linked to both of threaded and non-threaded applications.
+ *
+ * wasi-libc's errno is a TLS variable, exposed directly via
+ * errno.h. if we use it here, LLVM may lower it differently,
+ * depending on enabled features like atomcs and bulk-memory.
+ * we tweak the way to access errno here in order to make us
+ * compatible with both of threaded and non-threaded applications.
+ * __errno_location() should be reasonably stable because
+ * it was introduced as an alternative ABI for non-C software.
+ * https://github.com/WebAssembly/wasi-libc/pull/347
+ */
+#if defined(errno)
+#undef errno
+#endif
+int *
+__errno_location(void);
+#define errno (*__errno_location())
+
 #define HANDLE_ERROR(error)              \
     if (error != __WASI_ERRNO_SUCCESS) { \
         errno = error;                   \

core/iwasm/libraries/libc-uvwasi/libc_uvwasi.cmake

@@ -43,7 +43,7 @@ else()
     FetchContent_Declare(
         uvwasi
         GIT_REPOSITORY https://github.com/nodejs/uvwasi.git
-        GIT_TAG v0.0.21
+        GIT_TAG 392e1f1c1c8a2d2102c9f2e0b9f35959a149d133
     )
     FetchContent_MakeAvailable(uvwasi)
     include_directories("${uvwasi_SOURCE_DIR}/include")

core/iwasm/libraries/libc-uvwasi/libc_uvwasi_wrapper.c

@@ -890,24 +890,6 @@ wasi_path_symlink(wasm_exec_env_t exec_env, const char *old_path,
     if (!uvwasi)
         return (wasi_errno_t)-1;
 
-    /*
-     * check if old_path is valid.
-     * if it is a symlink, follow it.
-     *
-     * this is a workaround for the fact that
-     * uvwasi_path_symlink does not check if the old_path is valid
-     *
-     * the goal is trigger uvwasi__resolve_path() to check
-     */
-    {
-        uvwasi_filestat_t filestat = { 0 };
-        wasi_errno_t err =
-            uvwasi_path_filestat_get(uvwasi, fd, UVWASI_LOOKUP_SYMLINK_FOLLOW,
-                                     old_path, old_path_len, &filestat);
-        if (err)
-            return err;
-    }
-
     return uvwasi_path_symlink(uvwasi, old_path, old_path_len, fd, new_path,
                                new_path_len);
 }

core/iwasm/libraries/thread-mgr/thread_manager.c

@@ -301,7 +301,8 @@ wasm_cluster_create(WASMExecEnv *exec_env)
         aux_stack_start -= cluster->stack_size;
 
         for (i = 0; i < cluster_max_thread_num; i++) {
-            cluster->stack_tops[i] = aux_stack_start - cluster->stack_size * i;
+            cluster->stack_tops[i] =
+                aux_stack_start - (uint64)cluster->stack_size * i;
         }
     }
 #endif

core/iwasm/libraries/wasi-nn/README.md

@@ -37,7 +37,7 @@ There is a big difference between the two sets of functions, `tensor_type`.
 
 ```c
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
-typedef enum { fp16 = 0, fp32, fp64, bf16, u8, i32, i64 } tensor_type;
+typedef enum { fp16 = 0, fp32, fp64, u8, i32, i64 } tensor_type;
 #else
 typedef enum { fp16 = 0, fp32, up8, ip32 } tensor_type;
 #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */

core/iwasm/libraries/wasi-nn/include/wasi_ephemeral_nn.h

@@ -0,0 +1,12 @@
+/*
+ * Copyright (C) 2025 Midokura Japan KK.  All rights reserved.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ */
+
+#define WASM_ENABLE_WASI_EPHEMERAL_NN 1
+#define WASI_NN_NAME(name) wasi_ephemeral_nn_##name
+
+#include "wasi_nn.h"
+
+#undef WASM_ENABLE_WASI_EPHEMERAL_NN
+#undef WASI_NN_NAME

core/iwasm/libraries/wasi-nn/include/wasi_nn.h

@@ -15,23 +15,43 @@
 #include <stdint.h>
 #include "wasi_nn_types.h"
 
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+#define WASI_NN_IMPORT(name) \
+    __attribute__((import_module("wasi_ephemeral_nn"), import_name(name)))
+#else
+#define WASI_NN_IMPORT(name) \
+    __attribute__((import_module("wasi_nn"), import_name(name)))
+#warning You are using "wasi_nn", which is a legacy WAMR-specific ABI. It's deperecated and will likely be removed in future versions of WAMR. Please use "wasi_ephemeral_nn" instead. (For a WASM module, use the wasi_ephemeral_nn.h header instead. For the runtime configurations, enable WASM_ENABLE_WASI_EPHEMERAL_NN/WAMR_BUILD_WASI_EPHEMERAL_NN.)
+#endif
+
 /**
  * @brief Load an opaque sequence of bytes to use for inference.
  *
  * @param builder   Model builder.
+ * @param builder_len The size of model builder.
  * @param encoding  Model encoding.
  * @param target    Execution target.
  * @param g         Graph.
  * @return wasi_nn_error    Execution status.
  */
-wasi_nn_error
-load(graph_builder_array *builder, graph_encoding encoding,
-     execution_target target, graph *g)
-    __attribute__((import_module("wasi_nn")));
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(load)
+(WASI_NN_NAME(graph_builder) * builder, uint32_t builder_len,
+ WASI_NN_NAME(graph_encoding) encoding, WASI_NN_NAME(execution_target) target,
+ WASI_NN_NAME(graph) * g) WASI_NN_IMPORT("load");
+#else
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(load)
+(WASI_NN_NAME(graph_builder_array) * builder,
+ WASI_NN_NAME(graph_encoding) encoding, WASI_NN_NAME(execution_target) target,
+ WASI_NN_NAME(graph) * g) WASI_NN_IMPORT("load");
+#endif
 
-wasi_nn_error
-load_by_name(const char *name, graph *g)
-    __attribute__((import_module("wasi_nn")));
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(load_by_name)
+(const char *name, uint32_t name_len, WASI_NN_NAME(graph) * g)
+    WASI_NN_IMPORT("load_by_name");
 
 /**
  * INFERENCE
@@ -45,9 +65,10 @@ load_by_name(const char *name, graph *g)
  * @param ctx       Execution context.
  * @return wasi_nn_error    Execution status.
  */
-wasi_nn_error
-init_execution_context(graph g, graph_execution_context *ctx)
-    __attribute__((import_module("wasi_nn")));
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(init_execution_context)
+(WASI_NN_NAME(graph) g, WASI_NN_NAME(graph_execution_context) * ctx)
+    WASI_NN_IMPORT("init_execution_context");
 
 /**
  * @brief Define the inputs to use for inference.
@@ -57,9 +78,10 @@ init_execution_context(graph g, graph_execution_context *ctx)
  * @param tensor    Input tensor.
  * @return wasi_nn_error    Execution status.
  */
-wasi_nn_error
-set_input(graph_execution_context ctx, uint32_t index, tensor *tensor)
-    __attribute__((import_module("wasi_nn")));
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(set_input)
+(WASI_NN_NAME(graph_execution_context) ctx, uint32_t index,
+ WASI_NN_NAME(tensor) * tensor) WASI_NN_IMPORT("set_input");
 
 /**
  * @brief Compute the inference on the given inputs.
@@ -67,8 +89,9 @@ set_input(graph_execution_context ctx, uint32_t index, tensor *tensor)
  * @param ctx       Execution context.
  * @return wasi_nn_error    Execution status.
  */
-wasi_nn_error
-compute(graph_execution_context ctx) __attribute__((import_module("wasi_nn")));
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(compute)
+(WASI_NN_NAME(graph_execution_context) ctx) WASI_NN_IMPORT("compute");
 
 /**
  * @brief Extract the outputs after inference.
@@ -82,9 +105,17 @@ compute(graph_execution_context ctx) __attribute__((import_module("wasi_nn")));
  * copied number of bytes.
  * @return wasi_nn_error                Execution status.
  */
-wasi_nn_error
-get_output(graph_execution_context ctx, uint32_t index,
-           tensor_data output_tensor, uint32_t *output_tensor_size)
-    __attribute__((import_module("wasi_nn")));
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(get_output)
+(WASI_NN_NAME(graph_execution_context) ctx, uint32_t index,
+ uint8_t *output_tensor, uint32_t output_tensor_max_size,
+ uint32_t *output_tensor_size) WASI_NN_IMPORT("get_output");
+#else
+WASI_NN_ERROR_TYPE
+WASI_NN_NAME(get_output)
+(graph_execution_context ctx, uint32_t index, uint8_t *output_tensor,
+ uint32_t *output_tensor_size) WASI_NN_IMPORT("get_output");
+#endif
 
 #endif

core/iwasm/libraries/wasi-nn/include/wasi_nn_types.h

@@ -13,42 +13,48 @@
 extern "C" {
 #endif
 
+/* our host logic doesn't use any prefix. neither legacy wasi_nn.h does. */
+
+#if !defined(__wasm__) || !defined(WASI_NN_NAME)
+#define WASI_NN_NAME(name) name
+#define WASI_NN_ERROR_NAME(name) name
+#define WASI_NN_TYPE_NAME(name) name
+#define WASI_NN_ENCODING_NAME(name) name
+#define WASI_NN_TARGET_NAME(name) name
+#define WASI_NN_ERROR_TYPE wasi_nn_error
+#else
+#define WASI_NN_ERROR_NAME(name) WASI_NN_NAME(error_##name)
+#define WASI_NN_TYPE_NAME(name) WASI_NN_NAME(type_##name)
+#define WASI_NN_ENCODING_NAME(name) WASI_NN_NAME(encoding_##name)
+#define WASI_NN_TARGET_NAME(name) WASI_NN_NAME(target_##name)
+#define WASI_NN_ERROR_TYPE WASI_NN_NAME(error);
+#endif
+
 /**
  * ERRORS
  *
  */
 
 // sync up with
-// https://github.com/WebAssembly/wasi-nn/blob/main/wit/wasi-nn.wit#L136 Error
-// codes returned by functions in this API.
+// https://github.com/WebAssembly/wasi-nn/blob/71320d95b8c6d43f9af7f44e18b1839db85d89b4/wasi-nn.witx#L5-L17
+// Error codes returned by functions in this API.
 typedef enum {
-    // No error occurred.
-    success = 0,
-    // Caller module passed an invalid argument.
-    invalid_argument,
-    // Invalid encoding.
-    invalid_encoding,
-    // The operation timed out.
-    timeout,
-    // Runtime Error.
-    runtime_error,
-    // Unsupported operation.
-    unsupported_operation,
-    // Graph is too large.
-    too_large,
-    // Graph not found.
-    not_found,
-    // The operation is insecure or has insufficient privilege to be performed.
-    // e.g., cannot access a hardware feature requested
-    security,
-    // The operation failed for an unspecified reason.
-    unknown,
+    WASI_NN_ERROR_NAME(success) = 0,
+    WASI_NN_ERROR_NAME(invalid_argument),
+    WASI_NN_ERROR_NAME(invalid_encoding),
+    WASI_NN_ERROR_NAME(missing_memory),
+    WASI_NN_ERROR_NAME(busy),
+    WASI_NN_ERROR_NAME(runtime_error),
+    WASI_NN_ERROR_NAME(unsupported_operation),
+    WASI_NN_ERROR_NAME(too_large),
+    WASI_NN_ERROR_NAME(not_found),
+
     // for WasmEdge-wasi-nn
-    end_of_sequence = 100,  // End of Sequence Found.
-    context_full = 101,     // Context Full.
-    prompt_tool_long = 102, // Prompt Too Long.
-    model_not_found = 103,  // Model Not Found.
-} wasi_nn_error;
+    WASI_NN_ERROR_NAME(end_of_sequence) = 100,  // End of Sequence Found.
+    WASI_NN_ERROR_NAME(context_full) = 101,     // Context Full.
+    WASI_NN_ERROR_NAME(prompt_tool_long) = 102, // Prompt Too Long.
+    WASI_NN_ERROR_NAME(model_not_found) = 103,  // Model Not Found.
+} WASI_NN_ERROR_TYPE;
 
 /**
  * TENSOR
@@ -62,15 +68,27 @@ typedef enum {
 typedef struct {
     uint32_t *buf;
     uint32_t size;
-} tensor_dimensions;
+} WASI_NN_NAME(tensor_dimensions);
 
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
 // sync up with
-// https://github.com/WebAssembly/wasi-nn/blob/main/wit/wasi-nn.wit#L27
+// https://github.com/WebAssembly/wasi-nn/blob/71320d95b8c6d43f9af7f44e18b1839db85d89b4/wasi-nn.witx#L19-L28
 // The type of the elements in a tensor.
-typedef enum { fp16 = 0, fp32, fp64, bf16, u8, i32, i64 } tensor_type;
+typedef enum {
+    WASI_NN_TYPE_NAME(fp16) = 0,
+    WASI_NN_TYPE_NAME(fp32),
+    WASI_NN_TYPE_NAME(fp64),
+    WASI_NN_TYPE_NAME(u8),
+    WASI_NN_TYPE_NAME(i32),
+    WASI_NN_TYPE_NAME(i64),
+} WASI_NN_NAME(tensor_type);
 #else
-typedef enum { fp16 = 0, fp32, up8, ip32 } tensor_type;
+typedef enum {
+    WASI_NN_TYPE_NAME(fp16) = 0,
+    WASI_NN_TYPE_NAME(fp32),
+    WASI_NN_TYPE_NAME(up8),
+    WASI_NN_TYPE_NAME(ip32),
+} WASI_NN_NAME(tensor_type);
 #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */
 
 // The tensor data.
@@ -81,19 +99,31 @@ typedef enum { fp16 = 0, fp32, up8, ip32 } tensor_type;
 // 4-byte f32 elements would have a data array of length 16). Naturally, this
 // representation requires some knowledge of how to lay out data in
 // memory--e.g., using row-major ordering--and could perhaps be improved.
-typedef uint8_t *tensor_data;
+#if !defined(__wasm__) || WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+typedef struct {
+    uint8_t *buf;
+    uint32_t size;
+} WASI_NN_NAME(tensor_data);
+#else
+typedef uint8_t *WASI_NN_NAME(tensor_data);
+#endif
 
 // A tensor.
 typedef struct {
     // Describe the size of the tensor (e.g., 2x2x2x2 -> [2, 2, 2, 2]). To
     // represent a tensor containing a single value, use `[1]` for the tensor
     // dimensions.
-    tensor_dimensions *dimensions;
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0 && defined(__wasm__)
+    WASI_NN_NAME(tensor_dimensions) dimensions;
+#else
+    WASI_NN_NAME(tensor_dimensions) * dimensions;
+#endif
     // Describe the type of element in the tensor (e.g., f32).
-    tensor_type type;
+    uint8_t type;
+    uint8_t _pad[3];
     // Contains the tensor data.
-    tensor_data data;
-} tensor;
+    WASI_NN_NAME(tensor_data) data;
+} WASI_NN_NAME(tensor);
 
 /**
  * GRAPH
@@ -108,15 +138,15 @@ typedef struct {
 typedef struct {
     uint8_t *buf;
     uint32_t size;
-} graph_builder;
+} WASI_NN_NAME(graph_builder);
 
 typedef struct {
-    graph_builder *buf;
+    WASI_NN_NAME(graph_builder) * buf;
     uint32_t size;
-} graph_builder_array;
+} WASI_NN_NAME(graph_builder_array);
 
 // An execution graph for performing inference (i.e., a model).
-typedef uint32_t graph;
+typedef uint32_t WASI_NN_NAME(graph);
 
 // sync up with
 // https://github.com/WebAssembly/wasi-nn/blob/main/wit/wasi-nn.wit#L75
@@ -124,56 +154,25 @@ typedef uint32_t graph;
 // various backends that encode (i.e., serialize) their graph IR with different
 // formats.
 typedef enum {
-    openvino = 0,
-    onnx,
-    tensorflow,
-    pytorch,
-    tensorflowlite,
-    ggml,
-    autodetect,
-    unknown_backend,
-} graph_encoding;
+    WASI_NN_ENCODING_NAME(openvino) = 0,
+    WASI_NN_ENCODING_NAME(onnx),
+    WASI_NN_ENCODING_NAME(tensorflow),
+    WASI_NN_ENCODING_NAME(pytorch),
+    WASI_NN_ENCODING_NAME(tensorflowlite),
+    WASI_NN_ENCODING_NAME(ggml),
+    WASI_NN_ENCODING_NAME(autodetect),
+    WASI_NN_ENCODING_NAME(unknown_backend),
+} WASI_NN_NAME(graph_encoding);
 
 // Define where the graph should be executed.
-typedef enum execution_target { cpu = 0, gpu, tpu } execution_target;
+typedef enum WASI_NN_NAME(execution_target) {
+    WASI_NN_TARGET_NAME(cpu) = 0,
+    WASI_NN_TARGET_NAME(gpu),
+    WASI_NN_TARGET_NAME(tpu),
+} WASI_NN_NAME(execution_target);
 
 // Bind a `graph` to the input and output tensors for an inference.
-typedef uint32_t graph_execution_context;
-
-/* Definition of 'wasi_nn.h' structs in WASM app format (using offset) */
-
-typedef wasi_nn_error (*LOAD)(void *, graph_builder_array *, graph_encoding,
-                              execution_target, graph *);
-typedef wasi_nn_error (*LOAD_BY_NAME)(void *, const char *, uint32_t, graph *);
-typedef wasi_nn_error (*LOAD_BY_NAME_WITH_CONFIG)(void *, const char *,
-                                                  uint32_t, void *, uint32_t,
-                                                  graph *);
-typedef wasi_nn_error (*INIT_EXECUTION_CONTEXT)(void *, graph,
-                                                graph_execution_context *);
-typedef wasi_nn_error (*SET_INPUT)(void *, graph_execution_context, uint32_t,
-                                   tensor *);
-typedef wasi_nn_error (*COMPUTE)(void *, graph_execution_context);
-typedef wasi_nn_error (*GET_OUTPUT)(void *, graph_execution_context, uint32_t,
-                                    tensor_data, uint32_t *);
-/* wasi-nn general APIs */
-typedef wasi_nn_error (*BACKEND_INITIALIZE)(void **);
-typedef wasi_nn_error (*BACKEND_DEINITIALIZE)(void *);
-
-typedef struct {
-    LOAD load;
-    LOAD_BY_NAME load_by_name;
-    LOAD_BY_NAME_WITH_CONFIG load_by_name_with_config;
-    INIT_EXECUTION_CONTEXT init_execution_context;
-    SET_INPUT set_input;
-    COMPUTE compute;
-    GET_OUTPUT get_output;
-    BACKEND_INITIALIZE init;
-    BACKEND_DEINITIALIZE deinit;
-} api_function;
-
-void
-wasi_nn_dump_tensor_dimension(tensor_dimensions *dim, int32_t output_len,
-                              char *output);
+typedef uint32_t WASI_NN_NAME(graph_execution_context);
 
 #ifdef __cplusplus
 }

core/iwasm/libraries/wasi-nn/src/utils/wasi_nn_app_native.c

@@ -99,7 +99,8 @@ graph_builder_array_app_native(wasm_module_inst_t instance,
 
 static wasi_nn_error
 tensor_data_app_native(wasm_module_inst_t instance, uint32_t total_elements,
-                       tensor_wasm *input_tensor_wasm, tensor_data *data)
+                       tensor_wasm *input_tensor_wasm, void **data,
+                       uint32_t *size)
 {
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
 #define data_size input_tensor_wasm->data_size
@@ -113,8 +114,9 @@ tensor_data_app_native(wasm_module_inst_t instance, uint32_t total_elements,
         NN_ERR_PRINTF("input_tensor_wasm->data_offset is invalid");
         return invalid_argument;
     }
-    *data = (tensor_data)wasm_runtime_addr_app_to_native(
+    *data = wasm_runtime_addr_app_to_native(
         instance, (uint64)input_tensor_wasm->data_offset);
+    *size = data_size;
     return success;
 #undef data_size
 }
@@ -188,16 +190,19 @@ tensor_app_native(wasm_module_inst_t instance, tensor_wasm *input_tensor_wasm,
     NN_DBG_PRINTF("Tensor type: %d", input_tensor_wasm->type);
     NN_DBG_PRINTF("Total number of elements: %d", total_elements);
 
-    tensor_data data = NULL;
+    void *data = NULL;
+    uint32_t datasize;
     if (success
-        != (res = tensor_data_app_native(instance, total_elements,
-                                         input_tensor_wasm, &data))) {
+        != (res =
+                tensor_data_app_native(instance, total_elements,
+                                       input_tensor_wasm, &data, &datasize))) {
         wasm_runtime_free(dimensions);
         return res;
     }
 
     input_tensor->type = input_tensor_wasm->type;
     input_tensor->dimensions = dimensions;
-    input_tensor->data = data;
+    input_tensor->data.buf = data;
+    input_tensor->data.size = datasize;
     return success;
 }

core/iwasm/libraries/wasi-nn/src/wasi_nn.c

@@ -20,12 +20,29 @@
 #include "wasi_nn_types.h"
 #include "wasm_export.h"
 
+#if WASM_ENABLE_WASI_EPHEMERAL_NN == 0
+#warning You are using "wasi_nn", which is a legacy WAMR-specific ABI. It's deperecated and will likely be removed in future versions of WAMR. Please use "wasi_ephemeral_nn" instead. (For a WASM module, use the wasi_ephemeral_nn.h header instead. For the runtime configurations, enable WASM_ENABLE_WASI_EPHEMERAL_NN/WAMR_BUILD_WASI_EPHEMERAL_NN.)
+#endif
+
 #define HASHMAP_INITIAL_SIZE 20
-#define TFLITE_BACKEND_LIB "libwasi_nn_tflite.so"
-#define OPENVINO_BACKEND_LIB "libwasi_nn_openvino.so"
-#define LLAMACPP_BACKEND_LIB "libwasi_nn_llamacpp.so"
+#if defined(__APPLE__)
+#define LIB_EXTENTION ".dylib"
+#else
+#define LIB_EXTENTION ".so"
+#endif
+#define TFLITE_BACKEND_LIB "libwasi_nn_tflite" LIB_EXTENTION
+#define OPENVINO_BACKEND_LIB "libwasi_nn_openvino" LIB_EXTENTION
+#define LLAMACPP_BACKEND_LIB "libwasi_nn_llamacpp" LIB_EXTENTION
 
 /* Global variables */
+static korp_mutex wasi_nn_lock;
+/*
+ * the "lookup" table is protected by wasi_nn_lock.
+ *
+ * an exception: during wasm_runtime_destroy, wasi_nn_destroy tears down
+ * the table without acquiring the lock. it's ok because there should be
+ * no other threads using the runtime at this point.
+ */
 struct backends_api_functions {
     void *backend_handle;
     api_function functions;
@@ -38,65 +55,36 @@ struct backends_api_functions {
             NN_ERR_PRINTF("Error %s() -> %d", #func, wasi_error);          \
     } while (0)
 
-/* HashMap utils */
-static HashMap *hashmap;
-
-static uint32
-hash_func(const void *key)
-{
-    // fnv1a_hash
-    const uint32 FNV_PRIME = 16777619;
-    const uint32 FNV_OFFSET_BASIS = 2166136261U;
-
-    uint32 hash = FNV_OFFSET_BASIS;
-    const unsigned char *bytes = (const unsigned char *)key;
-
-    for (size_t i = 0; i < sizeof(uintptr_t); ++i) {
-        hash ^= bytes[i];
-        hash *= FNV_PRIME;
-    }
-
-    return hash;
-}
-
-static bool
-key_equal_func(void *key1, void *key2)
-{
-    return key1 == key2;
-}
-
-static void
-key_destroy_func(void *key1)
-{
-    /* key type is wasm_module_inst_t*. do nothing */
-}
+static void *wasi_nn_key;
 
 static void
 wasi_nn_ctx_destroy(WASINNContext *wasi_nn_ctx)
 {
-    NN_DBG_PRINTF("[WASI NN] DEINIT...");
-
     if (wasi_nn_ctx == NULL) {
-        NN_ERR_PRINTF(
-            "Error when deallocating memory. WASI-NN context is NULL");
         return;
     }
+    NN_DBG_PRINTF("[WASI NN] DEINIT...");
     NN_DBG_PRINTF("Freeing wasi-nn");
     NN_DBG_PRINTF("-> is_model_loaded: %d", wasi_nn_ctx->is_model_loaded);
     NN_DBG_PRINTF("-> current_encoding: %d", wasi_nn_ctx->backend);
 
-    /* deinit() the backend */
-    wasi_nn_error res;
-    call_wasi_nn_func(wasi_nn_ctx->backend, deinit, res,
-                      wasi_nn_ctx->backend_ctx);
+    bh_assert(!wasi_nn_ctx->busy);
 
+    /* deinit() the backend */
+    if (wasi_nn_ctx->is_backend_ctx_initialized) {
+        wasi_nn_error res;
+        call_wasi_nn_func(wasi_nn_ctx->backend, deinit, res,
+                          wasi_nn_ctx->backend_ctx);
+    }
+
+    os_mutex_destroy(&wasi_nn_ctx->lock);
     wasm_runtime_free(wasi_nn_ctx);
 }
 
 static void
-value_destroy_func(void *value)
+dtor(wasm_module_inst_t inst, void *ctx)
 {
-    wasi_nn_ctx_destroy((WASINNContext *)value);
+    wasi_nn_ctx_destroy(ctx);
 }
 
 bool
@@ -104,12 +92,15 @@ wasi_nn_initialize()
 {
     NN_DBG_PRINTF("[WASI NN General] Initializing wasi-nn");
 
-    // hashmap { instance: wasi_nn_ctx }
-    hashmap = bh_hash_map_create(HASHMAP_INITIAL_SIZE, true, hash_func,
-                                 key_equal_func, key_destroy_func,
-                                 value_destroy_func);
-    if (hashmap == NULL) {
-        NN_ERR_PRINTF("Error while initializing hashmap");
+    if (os_mutex_init(&wasi_nn_lock)) {
+        NN_ERR_PRINTF("Error while initializing global lock");
+        return false;
+    }
+
+    wasi_nn_key = wasm_runtime_create_context_key(dtor);
+    if (wasi_nn_key == NULL) {
+        NN_ERR_PRINTF("Failed to create context key");
+        os_mutex_destroy(&wasi_nn_lock);
         return false;
     }
 
@@ -129,6 +120,11 @@ wasi_nn_initialize_context()
     }
 
     memset(wasi_nn_ctx, 0, sizeof(WASINNContext));
+    if (os_mutex_init(&wasi_nn_ctx->lock)) {
+        NN_ERR_PRINTF("Error when initializing a lock for WASI-NN context");
+        wasm_runtime_free(wasi_nn_ctx);
+        return NULL;
+    }
     return wasi_nn_ctx;
 }
 
@@ -137,29 +133,59 @@ static WASINNContext *
 wasm_runtime_get_wasi_nn_ctx(wasm_module_inst_t instance)
 {
     WASINNContext *wasi_nn_ctx =
-        (WASINNContext *)bh_hash_map_find(hashmap, (void *)instance);
+        wasm_runtime_get_context(instance, wasi_nn_key);
     if (wasi_nn_ctx == NULL) {
-        wasi_nn_ctx = wasi_nn_initialize_context();
-        if (wasi_nn_ctx == NULL)
-            return NULL;
-
-        bool ok =
-            bh_hash_map_insert(hashmap, (void *)instance, (void *)wasi_nn_ctx);
-        if (!ok) {
-            NN_ERR_PRINTF("Error while storing context");
-            wasi_nn_ctx_destroy(wasi_nn_ctx);
+        WASINNContext *newctx = wasi_nn_initialize_context();
+        if (newctx == NULL)
             return NULL;
+        os_mutex_lock(&wasi_nn_lock);
+        wasi_nn_ctx = wasm_runtime_get_context(instance, wasi_nn_key);
+        if (wasi_nn_ctx == NULL) {
+            wasm_runtime_set_context_spread(instance, wasi_nn_key, newctx);
+            wasi_nn_ctx = newctx;
+            newctx = NULL;
+        }
+        os_mutex_unlock(&wasi_nn_lock);
+        if (newctx != NULL) {
+            wasi_nn_ctx_destroy(newctx);
         }
     }
-
     return wasi_nn_ctx;
 }
 
+static WASINNContext *
+lock_ctx(wasm_module_inst_t instance)
+{
+    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        return NULL;
+    }
+    os_mutex_lock(&wasi_nn_ctx->lock);
+    if (wasi_nn_ctx->busy) {
+        os_mutex_unlock(&wasi_nn_ctx->lock);
+        return NULL;
+    }
+    wasi_nn_ctx->busy = true;
+    os_mutex_unlock(&wasi_nn_ctx->lock);
+    return wasi_nn_ctx;
+}
+
+static void
+unlock_ctx(WASINNContext *wasi_nn_ctx)
+{
+    if (wasi_nn_ctx == NULL) {
+        return;
+    }
+    os_mutex_lock(&wasi_nn_ctx->lock);
+    bh_assert(wasi_nn_ctx->busy);
+    wasi_nn_ctx->busy = false;
+    os_mutex_unlock(&wasi_nn_ctx->lock);
+}
+
 void
 wasi_nn_destroy()
 {
-    // destroy hashmap will destroy keys and values
-    bh_hash_map_destroy(hashmap);
+    wasm_runtime_destroy_context_key(wasi_nn_key);
 
     // close backends' libraries and registered functions
     for (unsigned i = 0; i < sizeof(lookup) / sizeof(lookup[0]); i++) {
@@ -170,6 +196,8 @@ wasi_nn_destroy()
 
         memset(&lookup[i].functions, 0, sizeof(api_function));
     }
+
+    os_mutex_destroy(&wasi_nn_lock);
 }
 
 /* Utils */
@@ -342,9 +370,10 @@ graph_encoding_to_backend_lib_name(graph_encoding encoding)
 
 static bool
 detect_and_load_backend(graph_encoding backend_hint,
-                        struct backends_api_functions *backends,
                         graph_encoding *loaded_backend)
 {
+    bool ret;
+
     if (backend_hint > autodetect)
         return false;
 
@@ -356,16 +385,58 @@ detect_and_load_backend(graph_encoding backend_hint,
 
     *loaded_backend = backend_hint;
 
+    os_mutex_lock(&wasi_nn_lock);
     /* if already loaded */
-    if (lookup[backend_hint].backend_handle)
+    if (lookup[backend_hint].backend_handle) {
+        os_mutex_unlock(&wasi_nn_lock);
         return true;
+    }
 
     const char *backend_lib_name =
         graph_encoding_to_backend_lib_name(backend_hint);
-    if (!backend_lib_name)
+    if (!backend_lib_name) {
+        os_mutex_unlock(&wasi_nn_lock);
         return false;
+    }
 
-    return prepare_backend(backend_lib_name, backends + backend_hint);
+    ret = prepare_backend(backend_lib_name, lookup + backend_hint);
+    os_mutex_unlock(&wasi_nn_lock);
+    return ret;
+}
+
+static wasi_nn_error
+ensure_backend(wasm_module_inst_t instance, graph_encoding encoding,
+               WASINNContext *wasi_nn_ctx)
+{
+    wasi_nn_error res;
+
+    graph_encoding loaded_backend = autodetect;
+    if (!detect_and_load_backend(encoding, &loaded_backend)) {
+        res = invalid_encoding;
+        NN_ERR_PRINTF("load backend failed");
+        goto fail;
+    }
+
+    if (wasi_nn_ctx->is_backend_ctx_initialized) {
+        if (wasi_nn_ctx->backend != loaded_backend) {
+            res = unsupported_operation;
+            goto fail;
+        }
+    }
+    else {
+        wasi_nn_ctx->backend = loaded_backend;
+
+        /* init() the backend */
+        call_wasi_nn_func(wasi_nn_ctx->backend, init, res,
+                          &wasi_nn_ctx->backend_ctx);
+        if (res != success)
+            goto fail;
+
+        wasi_nn_ctx->is_backend_ctx_initialized = true;
+    }
+    return success;
+fail:
+    return res;
 }
 
 /* WASI-NN implementation */
@@ -381,6 +452,8 @@ wasi_nn_load(wasm_exec_env_t exec_env, graph_builder_array_wasm *builder,
              graph_encoding encoding, execution_target target, graph *g)
 #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */
 {
+    wasi_nn_error res;
+
     NN_DBG_PRINTF("[WASI NN] LOAD [encoding=%d, target=%d]...", encoding,
                   target);
 
@@ -388,18 +461,23 @@ wasi_nn_load(wasm_exec_env_t exec_env, graph_builder_array_wasm *builder,
     if (!instance)
         return runtime_error;
 
-    wasi_nn_error res;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
+    }
+
     graph_builder_array builder_native = { 0 };
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
     if (success
         != (res = graph_builder_array_app_native(
                 instance, builder, builder_wasm_size, &builder_native)))
-        return res;
+        goto fail;
 #else  /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
     if (success
         != (res = graph_builder_array_app_native(instance, builder,
                                                  &builder_native)))
-        return res;
+        goto fail;
 #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */
 
     if (!wasm_runtime_validate_native_addr(instance, g,
@@ -409,19 +487,7 @@ wasi_nn_load(wasm_exec_env_t exec_env, graph_builder_array_wasm *builder,
         goto fail;
     }
 
-    graph_encoding loaded_backend = autodetect;
-    if (!detect_and_load_backend(encoding, lookup, &loaded_backend)) {
-        res = invalid_encoding;
-        NN_ERR_PRINTF("load backend failed");
-        goto fail;
-    }
-
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-    wasi_nn_ctx->backend = loaded_backend;
-
-    /* init() the backend */
-    call_wasi_nn_func(wasi_nn_ctx->backend, init, res,
-                      &wasi_nn_ctx->backend_ctx);
+    res = ensure_backend(instance, encoding, wasi_nn_ctx);
     if (res != success)
         goto fail;
 
@@ -436,6 +502,7 @@ fail:
     // XXX: Free intermediate structure pointers
     if (builder_native.buf)
         wasm_runtime_free(builder_native.buf);
+    unlock_ctx(wasi_nn_ctx);
 
     return res;
 }
@@ -444,6 +511,8 @@ wasi_nn_error
 wasi_nn_load_by_name(wasm_exec_env_t exec_env, char *name, uint32_t name_len,
                      graph *g)
 {
+    wasi_nn_error res;
+
     wasm_module_inst_t instance = wasm_runtime_get_module_inst(exec_env);
     if (!instance) {
         return runtime_error;
@@ -467,30 +536,26 @@ wasi_nn_load_by_name(wasm_exec_env_t exec_env, char *name, uint32_t name_len,
 
     NN_DBG_PRINTF("[WASI NN] LOAD_BY_NAME %s...", name);
 
-    graph_encoding loaded_backend = autodetect;
-    if (!detect_and_load_backend(autodetect, lookup, &loaded_backend)) {
-        NN_ERR_PRINTF("load backend failed");
-        return invalid_encoding;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
     }
 
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-    wasi_nn_ctx->backend = loaded_backend;
-
-    wasi_nn_error res;
-    /* init() the backend */
-    call_wasi_nn_func(wasi_nn_ctx->backend, init, res,
-                      &wasi_nn_ctx->backend_ctx);
+    res = ensure_backend(instance, autodetect, wasi_nn_ctx);
     if (res != success)
-        return res;
+        goto fail;
 
     call_wasi_nn_func(wasi_nn_ctx->backend, load_by_name, res,
                       wasi_nn_ctx->backend_ctx, name, name_len, g);
     if (res != success)
-        return res;
+        goto fail;
 
-    wasi_nn_ctx->backend = loaded_backend;
     wasi_nn_ctx->is_model_loaded = true;
-    return success;
+    res = success;
+fail:
+    unlock_ctx(wasi_nn_ctx);
+    return res;
 }
 
 wasi_nn_error
@@ -498,6 +563,8 @@ wasi_nn_load_by_name_with_config(wasm_exec_env_t exec_env, char *name,
                                  int32_t name_len, char *config,
                                  int32_t config_len, graph *g)
 {
+    wasi_nn_error res;
+
     wasm_module_inst_t instance = wasm_runtime_get_module_inst(exec_env);
     if (!instance) {
         return runtime_error;
@@ -526,31 +593,28 @@ wasi_nn_load_by_name_with_config(wasm_exec_env_t exec_env, char *name,
 
     NN_DBG_PRINTF("[WASI NN] LOAD_BY_NAME_WITH_CONFIG %s %s...", name, config);
 
-    graph_encoding loaded_backend = autodetect;
-    if (!detect_and_load_backend(autodetect, lookup, &loaded_backend)) {
-        NN_ERR_PRINTF("load backend failed");
-        return invalid_encoding;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
     }
 
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-    wasi_nn_ctx->backend = loaded_backend;
-
-    wasi_nn_error res;
-    /* init() the backend */
-    call_wasi_nn_func(wasi_nn_ctx->backend, init, res,
-                      &wasi_nn_ctx->backend_ctx);
+    res = ensure_backend(instance, autodetect, wasi_nn_ctx);
     if (res != success)
-        return res;
+        goto fail;
+    ;
 
     call_wasi_nn_func(wasi_nn_ctx->backend, load_by_name_with_config, res,
                       wasi_nn_ctx->backend_ctx, name, name_len, config,
                       config_len, g);
     if (res != success)
-        return res;
+        goto fail;
 
-    wasi_nn_ctx->backend = loaded_backend;
     wasi_nn_ctx->is_model_loaded = true;
-    return success;
+    res = success;
+fail:
+    unlock_ctx(wasi_nn_ctx);
+    return res;
 }
 
 wasi_nn_error
@@ -564,20 +628,27 @@ wasi_nn_init_execution_context(wasm_exec_env_t exec_env, graph g,
         return runtime_error;
     }
 
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-
     wasi_nn_error res;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
+    }
+
     if (success != (res = is_model_initialized(wasi_nn_ctx)))
-        return res;
+        goto fail;
 
     if (!wasm_runtime_validate_native_addr(
             instance, ctx, (uint64)sizeof(graph_execution_context))) {
         NN_ERR_PRINTF("ctx is invalid");
-        return invalid_argument;
+        res = invalid_argument;
+        goto fail;
     }
 
     call_wasi_nn_func(wasi_nn_ctx->backend, init_execution_context, res,
                       wasi_nn_ctx->backend_ctx, g, ctx);
+fail:
+    unlock_ctx(wasi_nn_ctx);
     return res;
 }
 
@@ -592,17 +663,21 @@ wasi_nn_set_input(wasm_exec_env_t exec_env, graph_execution_context ctx,
         return runtime_error;
     }
 
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-
     wasi_nn_error res;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
+    }
+
     if (success != (res = is_model_initialized(wasi_nn_ctx)))
-        return res;
+        goto fail;
 
     tensor input_tensor_native = { 0 };
     if (success
         != (res = tensor_app_native(instance, input_tensor,
                                     &input_tensor_native)))
-        return res;
+        goto fail;
 
     call_wasi_nn_func(wasi_nn_ctx->backend, set_input, res,
                       wasi_nn_ctx->backend_ctx, ctx, index,
@@ -610,7 +685,8 @@ wasi_nn_set_input(wasm_exec_env_t exec_env, graph_execution_context ctx,
     // XXX: Free intermediate structure pointers
     if (input_tensor_native.dimensions)
         wasm_runtime_free(input_tensor_native.dimensions);
-
+fail:
+    unlock_ctx(wasi_nn_ctx);
     return res;
 }
 
@@ -624,26 +700,32 @@ wasi_nn_compute(wasm_exec_env_t exec_env, graph_execution_context ctx)
         return runtime_error;
     }
 
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-
     wasi_nn_error res;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
+    }
+
     if (success != (res = is_model_initialized(wasi_nn_ctx)))
-        return res;
+        goto fail;
 
     call_wasi_nn_func(wasi_nn_ctx->backend, compute, res,
                       wasi_nn_ctx->backend_ctx, ctx);
+fail:
+    unlock_ctx(wasi_nn_ctx);
     return res;
 }
 
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
 wasi_nn_error
 wasi_nn_get_output(wasm_exec_env_t exec_env, graph_execution_context ctx,
-                   uint32_t index, tensor_data output_tensor,
+                   uint32_t index, void *output_tensor,
                    uint32_t output_tensor_len, uint32_t *output_tensor_size)
 #else  /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
 wasi_nn_error
 wasi_nn_get_output(wasm_exec_env_t exec_env, graph_execution_context ctx,
-                   uint32_t index, tensor_data output_tensor,
+                   uint32_t index, void *output_tensor,
                    uint32_t *output_tensor_size)
 #endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */
 {
@@ -654,28 +736,36 @@ wasi_nn_get_output(wasm_exec_env_t exec_env, graph_execution_context ctx,
         return runtime_error;
     }
 
-    WASINNContext *wasi_nn_ctx = wasm_runtime_get_wasi_nn_ctx(instance);
-
     wasi_nn_error res;
+    WASINNContext *wasi_nn_ctx = lock_ctx(instance);
+    if (wasi_nn_ctx == NULL) {
+        res = busy;
+        goto fail;
+    }
+
     if (success != (res = is_model_initialized(wasi_nn_ctx)))
-        return res;
+        goto fail;
 
     if (!wasm_runtime_validate_native_addr(instance, output_tensor_size,
                                            (uint64)sizeof(uint32_t))) {
         NN_ERR_PRINTF("output_tensor_size is invalid");
-        return invalid_argument;
+        res = invalid_argument;
+        goto fail;
     }
 
+    tensor_data tensor = {
+        .buf = output_tensor,
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+        .size = output_tensor_len,
+#else
+        .size = *output_tensor_size,
+#endif
+    };
     call_wasi_nn_func(wasi_nn_ctx->backend, get_output, res,
-                      wasi_nn_ctx->backend_ctx, ctx, index, output_tensor,
-                      &output_tensor_len);
-    *output_tensor_size = output_tensor_len;
-#else  /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
-    call_wasi_nn_func(wasi_nn_ctx->backend, get_output, res,
-                      wasi_nn_ctx->backend_ctx, ctx, index, output_tensor,
+                      wasi_nn_ctx->backend_ctx, ctx, index, &tensor,
                       output_tensor_size);
-#endif /* WASM_ENABLE_WASI_EPHEMERAL_NN != 0 */
+fail:
+    unlock_ctx(wasi_nn_ctx);
     return res;
 }
 
@@ -697,6 +787,7 @@ static NativeSymbol native_symbols_wasi_nn[] = {
     REG_NATIVE_FUNC(get_output, "(ii*i*)i"),
 #else  /* WASM_ENABLE_WASI_EPHEMERAL_NN == 0 */
     REG_NATIVE_FUNC(load, "(*ii*)i"),
+    REG_NATIVE_FUNC(load_by_name, "(*i*)i"),
     REG_NATIVE_FUNC(init_execution_context, "(i*)i"),
     REG_NATIVE_FUNC(set_input, "(ii*)i"),
     REG_NATIVE_FUNC(compute, "(i)i"),

core/iwasm/libraries/wasi-nn/src/wasi_nn_backend.h

@@ -3,15 +3,26 @@
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  */
 
-#ifndef WASI_NN_OPENVINO_HPP
-#define WASI_NN_OPENVINO_HPP
+#ifndef WASI_NN_BACKEND_H
+#define WASI_NN_BACKEND_H
 
 #include "wasi_nn_types.h"
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 __attribute__((visibility("default"))) wasi_nn_error
 load(void *ctx, graph_builder_array *builder, graph_encoding encoding,
      execution_target target, graph *g);
 
+__attribute__((visibility("default"))) wasi_nn_error
+load_by_name(void *tflite_ctx, const char *name, uint32_t namelen, graph *g);
+
+__attribute__((visibility("default"))) wasi_nn_error
+load_by_name_with_config(void *ctx, const char *name, uint32_t namelen,
+                         const char *config, uint32_t config_len, graph *g);
+
 __attribute__((visibility("default"))) wasi_nn_error
 init_execution_context(void *ctx, graph g, graph_execution_context *exec_ctx);
 
@@ -24,7 +35,7 @@ compute(void *ctx, graph_execution_context exec_ctx);
 
 __attribute__((visibility("default"))) wasi_nn_error
 get_output(void *ctx, graph_execution_context exec_ctx, uint32_t index,
-           tensor_data output_tensor, uint32_t *output_tensor_size);
+           tensor_data *output_tensor, uint32_t *output_tensor_size);
 
 __attribute__((visibility("default"))) wasi_nn_error
 init_backend(void **ctx);
@@ -32,4 +43,8 @@ init_backend(void **ctx);
 __attribute__((visibility("default"))) wasi_nn_error
 deinit_backend(void *ctx);
 
-#endif /* WASI_NN_OPENVINO_HPP */
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* WASI_NN_BACKEND_H */

core/iwasm/libraries/wasi-nn/src/wasi_nn_llamacpp.c

@@ -2,7 +2,10 @@
  * Copyright (C) 2019 Intel Corporation.  All rights reserved.
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  */
-#include "wasi_nn_types.h"
+
+#include <stdlib.h>
+
+#include "wasi_nn_backend.h"
 #include "utils/logger.h"
 #include "llama.h"
 #include "ggml.h"
@@ -286,7 +289,7 @@ deinit_backend(void *ctx)
 
     llama_backend_free();
 
-    os_free(backend_ctx);
+    free(backend_ctx);
     return success;
 }
 
@@ -302,6 +305,11 @@ __load_by_name_with_configuration(void *ctx, const char *filename, graph *g)
 {
     struct LlamaContext *backend_ctx = (struct LlamaContext *)ctx;
 
+    if (backend_ctx->model != NULL) {
+        // we only implement a single graph
+        return unsupported_operation;
+    }
+
     // make sure backend_ctx->config is initialized
 
     struct llama_model_params model_params =
@@ -320,6 +328,7 @@ __load_by_name_with_configuration(void *ctx, const char *filename, graph *g)
 #endif
 
     backend_ctx->model = model;
+    *g = 0;
 
     return success;
 }
@@ -360,6 +369,16 @@ init_execution_context(void *ctx, graph g, graph_execution_context *exec_ctx)
 {
     struct LlamaContext *backend_ctx = (struct LlamaContext *)ctx;
 
+    if (g != 0 || backend_ctx->model == NULL) {
+        // we only implement a single graph
+        return runtime_error;
+    }
+
+    if (backend_ctx->ctx != NULL) {
+        // we only implement a single context
+        return unsupported_operation;
+    }
+
     struct llama_context_params ctx_params =
         llama_context_params_from_wasi_nn_llama_config(&backend_ctx->config);
     struct llama_context *llama_ctx =
@@ -370,6 +389,7 @@ init_execution_context(void *ctx, graph g, graph_execution_context *exec_ctx)
     }
 
     backend_ctx->ctx = llama_ctx;
+    *exec_ctx = 0;
 
     NN_INFO_PRINTF("n_predict = %d, n_ctx = %d", backend_ctx->config.n_predict,
                    llama_n_ctx(backend_ctx->ctx));
@@ -381,18 +401,36 @@ set_input(void *ctx, graph_execution_context exec_ctx, uint32_t index,
           tensor *wasi_nn_tensor)
 {
     struct LlamaContext *backend_ctx = (struct LlamaContext *)ctx;
-    // tensor->data is the prompt string. ends with \0
-    char *prompt_text = (char *)wasi_nn_tensor->data;
+
+    if (exec_ctx != 0 || backend_ctx->ctx == NULL) {
+        // we only implement a single context
+        return runtime_error;
+    }
+
+    // tensor->data is the prompt string.
+    char *prompt_text = (char *)wasi_nn_tensor->data.buf;
+    uint32_t prompt_text_len = wasi_nn_tensor->data.size;
+
+    // note: buf[0] == 1 is a workaround for
+    // https://github.com/second-state/WasmEdge-WASINN-examples/issues/196.
+    // we may remove it in future.
+    if (wasi_nn_tensor->type != u8 || wasi_nn_tensor->dimensions->size != 1
+        || !(wasi_nn_tensor->dimensions->buf[0] == 1
+             || wasi_nn_tensor->dimensions->buf[0] == prompt_text_len)) {
+        return invalid_argument;
+    }
+    if (wasi_nn_tensor->dimensions->buf[0] == 1 && prompt_text_len != 1) {
+        NN_WARN_PRINTF("Ignoring seemingly wrong input tensor dimensions.");
+    }
 
 #ifndef NDEBUG
     NN_DBG_PRINTF("--------------------------------------------------");
-    NN_DBG_PRINTF("prompt_text: %s", prompt_text);
+    NN_DBG_PRINTF("prompt_text: %.*s", (int)prompt_text_len, prompt_text);
     NN_DBG_PRINTF("--------------------------------------------------");
 #endif
 
     // tokenize the prompt
     uint32_t n_token_max = llama_n_ctx(backend_ctx->ctx);
-    uint32_t prompt_text_len = strlen(prompt_text);
 
     if (backend_ctx->prompt == NULL) {
         backend_ctx->prompt = calloc(n_token_max, sizeof(llama_token));
@@ -430,6 +468,11 @@ compute(void *ctx, graph_execution_context exec_ctx)
     struct LlamaContext *backend_ctx = (struct LlamaContext *)ctx;
     wasi_nn_error ret = runtime_error;
 
+    if (exec_ctx != 0 || backend_ctx->ctx == NULL) {
+        // we only implement a single context
+        return runtime_error;
+    }
+
     // reset the generation buffer
     if (backend_ctx->generation == NULL) {
         backend_ctx->generation =
@@ -477,7 +520,6 @@ compute(void *ctx, graph_execution_context exec_ctx)
 
     // main loop
     int32_t n_cur = batch.n_tokens;
-    int n_decode = 0;
     int32_t n_vocab = llama_n_vocab(backend_ctx->model);
     llama_token_data *candidates = NULL;
 
@@ -528,7 +570,6 @@ compute(void *ctx, graph_execution_context exec_ctx)
         // push this new token for next evaluation
         llama_batch_add(&batch, new_token_id, n_cur, seq_ids,
                         sizeof(seq_ids) / sizeof(seq_ids[0]), true);
-        n_decode++;
         n_cur++;
 
         if (llama_decode(backend_ctx->ctx, batch) != 0) {
@@ -549,10 +590,15 @@ fail:
 
 __attribute__((visibility("default"))) wasi_nn_error
 get_output(void *ctx, graph_execution_context exec_ctx, uint32_t index,
-           tensor_data output_tensor, uint32_t *output_tensor_size)
+           tensor_data *output_tensor, uint32_t *output_tensor_size)
 {
     struct LlamaContext *backend_ctx = (struct LlamaContext *)ctx;
 
+    if (exec_ctx != 0 || backend_ctx->ctx == NULL) {
+        // we only implement a single context
+        return runtime_error;
+    }
+
     // Compatibility with WasmEdge
     if (index > 1) {
         NN_ERR_PRINTF("Invalid output index %d", index);
@@ -568,7 +614,7 @@ get_output(void *ctx, graph_execution_context exec_ctx, uint32_t index,
             printf("%s\n", output_metadata);
         }
 
-        memcpy(output_tensor, output_metadata, strlen(output_metadata));
+        memcpy(output_tensor->buf, output_metadata, strlen(output_metadata));
         *output_tensor_size = strlen(output_metadata);
         return success;
     }
@@ -588,7 +634,7 @@ get_output(void *ctx, graph_execution_context exec_ctx, uint32_t index,
             printf("%s", buf);
         }
 
-        memcpy(output_tensor + end_pos, buf, strlen(buf));
+        memcpy(output_tensor->buf + end_pos, buf, strlen(buf));
         end_pos += strlen(buf);
     }
 

core/iwasm/libraries/wasi-nn/src/wasi_nn_openvino.c

@@ -3,8 +3,7 @@
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  */
 
-#include "wasi_nn_types.h"
-#include "wasi_nn_openvino.h"
+#include "wasi_nn_backend.h"
 #include "utils/logger.h"
 #include "bh_platform.h"
 
@@ -26,17 +25,25 @@
  * from 4. to 6. is the Inference Loop
  */
 
+/* these limits are arbitrary. */
+#define MAX_GRAPHS 4
+#define MAX_EXECUTION_CONTEXTS 4
+
 typedef struct {
     ov_core_t *core;
     /* keep input model files */
-    void *weight_data;
-    ov_tensor_t *weights_tensor;
-    ov_model_t *model;
-    /* add prepostprocess */
-    ov_model_t *new_model;
-    ov_compiled_model_t *compiled_model;
-    ov_infer_request_t *infer_request;
-    ov_tensor_t *input_tensor;
+    struct OpenVINOGraph {
+        void *weight_data;
+        ov_tensor_t *weights_tensor;
+        ov_model_t *model;
+        ov_compiled_model_t *compiled_model;
+    } graphs[MAX_GRAPHS];
+    struct OpenVINOExecutionContext {
+        struct OpenVINOGraph *graph;
+        ov_infer_request_t *infer_request;
+    } execution_contexts[MAX_EXECUTION_CONTEXTS];
+    unsigned int n_graphs;
+    unsigned int n_execution_contexts;
 } OpenVINOContext;
 
 /*
@@ -58,7 +65,7 @@ dump_ov_shape_t(const ov_shape_t *shape, int32_t output_len, char *output)
 {
     int ret = 0;
 
-    ret = snprintf(output, output_len, "%ld,[", shape->rank);
+    ret = snprintf(output, output_len, "%" PRId64 ",[", shape->rank);
     if (!ret)
         return;
 
@@ -66,7 +73,7 @@ dump_ov_shape_t(const ov_shape_t *shape, int32_t output_len, char *output)
     output += ret;
 
     for (unsigned i = 0; i < shape->rank && output_len; i++) {
-        ret = snprintf(output, output_len, " %ld", shape->dims[i]);
+        ret = snprintf(output, output_len, " %" PRId64, shape->dims[i]);
         if (!ret)
             return;
 
@@ -136,7 +143,7 @@ print_model_input_output_info(ov_model_t *model)
         output_port = NULL;
     }
 
-    ov_error = ov_error;
+    (void)ov_error;
 fail:
     if (friendly_name)
         ov_free(friendly_name);
@@ -161,8 +168,6 @@ wasi_nn_tensor_type_to_openvino_element_type(tensor_type wasi_nn_type)
 #if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
         case fp64:
             return F64;
-        case bf16:
-            return BF16;
         case i64:
             return I64;
         case u8:
@@ -183,6 +188,29 @@ wasi_nn_tensor_type_to_openvino_element_type(tensor_type wasi_nn_type)
     return UNDEFINED;
 }
 
+static void
+free_graph(struct OpenVINOGraph *graph)
+{
+    if (graph->weight_data)
+        os_free(graph->weight_data);
+
+    if (graph->weights_tensor)
+        ov_tensor_free(graph->weights_tensor);
+
+    if (graph->model)
+        ov_model_free(graph->model);
+
+    if (graph->compiled_model)
+        ov_compiled_model_free(graph->compiled_model);
+}
+
+static void
+free_execution_context(struct OpenVINOExecutionContext *c)
+{
+    if (c->infer_request)
+        ov_infer_request_free(c->infer_request);
+}
+
 static wasi_nn_error
 uint32_array_to_int64_array(uint32_t array_size, uint32_t *src, int64_t **dst)
 {
@@ -202,6 +230,8 @@ load(void *ctx, graph_builder_array *builder, graph_encoding encoding,
      execution_target target, graph *g)
 {
     OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    struct OpenVINOGraph *graph;
+    unsigned int graph_idx;
     wasi_nn_error ret = unsupported_operation;
 
     if (encoding != openvino) {
@@ -227,39 +257,47 @@ load(void *ctx, graph_builder_array *builder, graph_encoding encoding,
     graph_builder xml = builder->buf[0];
     graph_builder weight = builder->buf[1];
 
-    /* if xml is a String with a model in IR */
-    if (!(xml.buf[xml.size] == '\0' && xml.buf[xml.size - 1] != '\0')) {
-        NN_ERR_PRINTF("Invalid xml string.");
-        return invalid_argument;
+    graph_idx = ov_ctx->n_graphs;
+    if (graph_idx >= MAX_GRAPHS) {
+        return runtime_error;
     }
+    graph = &ov_ctx->graphs[graph_idx];
+    memset(graph, 0, sizeof(*graph));
 
     /* transfer weight to an ov tensor */
     {
-        ov_ctx->weight_data = os_malloc(weight.size);
-        if (!ov_ctx->weight_data)
+        graph->weight_data = os_malloc(weight.size);
+        if (!graph->weight_data)
             goto fail;
-        memcpy(ov_ctx->weight_data, weight.buf, weight.size);
+        memcpy(graph->weight_data, weight.buf, weight.size);
 
         ov_element_type_e type = U8;
         int64_t dims[1] = { weight.size };
         ov_shape_t shape = { 1, dims };
         CHECK_OV_STATUS(ov_tensor_create_from_host_ptr(type, shape,
-                                                       ov_ctx->weight_data,
-                                                       &ov_ctx->weights_tensor),
+                                                       graph->weight_data,
+                                                       &graph->weights_tensor),
                         ret);
     }
 
     /* load model from buffer */
     CHECK_OV_STATUS(ov_core_read_model_from_memory_buffer(
                         ov_ctx->core, (char *)xml.buf, xml.size,
-                        ov_ctx->weights_tensor, &ov_ctx->model),
+                        graph->weights_tensor, &graph->model),
                     ret);
 #ifndef NDEBUG
-    print_model_input_output_info(ov_ctx->model);
+    print_model_input_output_info(graph->model);
 #endif
 
-    ret = success;
+    CHECK_OV_STATUS(ov_core_compile_model(ov_ctx->core, graph->model, "CPU", 0,
+                                          &graph->compiled_model),
+                    ret);
+
+    *g = graph_idx;
+    ov_ctx->n_graphs++;
+    return success;
 fail:
+    free_graph(graph);
     return ret;
 }
 
@@ -267,20 +305,62 @@ __attribute__((visibility("default"))) wasi_nn_error
 load_by_name(void *ctx, const char *filename, uint32_t filename_len, graph *g)
 {
     OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    struct OpenVINOGraph *graph;
+    unsigned int graph_idx;
     wasi_nn_error ret = unsupported_operation;
 
-    CHECK_OV_STATUS(
-        ov_core_read_model(ov_ctx->core, filename, NULL, &ov_ctx->model), ret);
+    graph_idx = ov_ctx->n_graphs;
+    if (graph_idx >= MAX_GRAPHS) {
+        return runtime_error;
+    }
+    graph = &ov_ctx->graphs[graph_idx];
 
-    ret = success;
+    memset(graph, 0, sizeof(*graph));
+    CHECK_OV_STATUS(
+        ov_core_read_model(ov_ctx->core, filename, NULL, &graph->model), ret);
+
+    CHECK_OV_STATUS(ov_core_compile_model(ov_ctx->core, graph->model, "CPU", 0,
+                                          &graph->compiled_model),
+                    ret);
+
+    *g = graph_idx;
+    ov_ctx->n_graphs++;
+    return success;
 fail:
+    free_graph(graph);
     return ret;
 }
 
 __attribute__((visibility("default"))) wasi_nn_error
 init_execution_context(void *ctx, graph g, graph_execution_context *exec_ctx)
 {
+    OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    struct OpenVINOGraph *graph;
+    struct OpenVINOExecutionContext *exec;
+    unsigned int exec_idx;
+    wasi_nn_error ret;
+
+    if (g >= ov_ctx->n_graphs)
+        return runtime_error;
+    graph = &ov_ctx->graphs[g];
+
+    exec_idx = ov_ctx->n_execution_contexts;
+    if (exec_idx >= MAX_EXECUTION_CONTEXTS)
+        return runtime_error;
+    exec = &ov_ctx->execution_contexts[exec_idx];
+
+    memset(exec, 0, sizeof(*exec));
+    exec->graph = graph;
+
+    CHECK_OV_STATUS(ov_compiled_model_create_infer_request(
+                        graph->compiled_model, &exec->infer_request),
+                    ret);
+
+    *exec_ctx = exec_idx;
+    ov_ctx->n_execution_contexts++;
     return success;
+fail:
+    return ret;
 }
 
 __attribute__((visibility("default"))) wasi_nn_error
@@ -288,19 +368,15 @@ set_input(void *ctx, graph_execution_context exec_ctx, uint32_t index,
           tensor *wasi_nn_tensor)
 {
     OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    struct OpenVINOExecutionContext *exec;
     wasi_nn_error ret = unsupported_operation;
     ov_shape_t input_shape = { 0 };
+    ov_tensor_t *input_tensor = NULL;
     int64_t *ov_dims = NULL;
 
-    ov_preprocess_prepostprocessor_t *ppp = NULL;
-    ov_preprocess_input_info_t *input_info = NULL;
-    ov_preprocess_input_tensor_info_t *input_tensor_info = NULL;
-    ov_layout_t *input_layout = NULL;
-    ov_preprocess_preprocess_steps_t *input_process = NULL;
-    ov_preprocess_input_model_info_t *p_input_model = NULL;
-    ov_layout_t *model_layout = NULL;
-    ov_preprocess_output_info_t *output_info = NULL;
-    ov_preprocess_output_tensor_info_t *output_tensor_info = NULL;
+    if (exec_ctx >= ov_ctx->n_execution_contexts)
+        return runtime_error;
+    exec = &ov_ctx->execution_contexts[exec_ctx];
 
     /* wasi_nn_tensor -> ov_tensor */
     {
@@ -310,17 +386,6 @@ set_input(void *ctx, graph_execution_context exec_ctx, uint32_t index,
         if (ret != success)
             goto fail;
 
-        /* NCHW -> NHWC */
-        if (wasi_nn_tensor->dimensions->size == 4 || ov_dims[1] == 3) {
-            /* N */
-            /* H */
-            ov_dims[1] = ov_dims[2];
-            /* W */
-            ov_dims[2] = ov_dims[3];
-            /* C */
-            ov_dims[3] = 3;
-        }
-
         CHECK_OV_STATUS(ov_shape_create(wasi_nn_tensor->dimensions->size,
                                         ov_dims, &input_shape),
                         ret);
@@ -336,101 +401,22 @@ set_input(void *ctx, graph_execution_context exec_ctx, uint32_t index,
                       shape_info);
 
         CHECK_OV_STATUS(ov_tensor_create_from_host_ptr(input_type, input_shape,
-                                                       wasi_nn_tensor->data,
-                                                       &ov_ctx->input_tensor),
+                                                       wasi_nn_tensor->data.buf,
+                                                       &input_tensor),
                         ret);
     }
 
-    /* set preprocess based on wasi_nn_tensor */
-    {
-        CHECK_OV_STATUS(
-            ov_preprocess_prepostprocessor_create(ov_ctx->model, &ppp), ret);
-
-        /* reuse user' created tensor's info */
-        CHECK_OV_STATUS(ov_preprocess_prepostprocessor_get_input_info_by_index(
-                            ppp, index, &input_info),
-                        ret);
-        CHECK_OV_STATUS(ov_preprocess_input_info_get_tensor_info(
-                            input_info, &input_tensor_info),
-                        ret);
-        CHECK_OV_STATUS(ov_preprocess_input_tensor_info_set_from(
-                            input_tensor_info, ov_ctx->input_tensor),
-                        ret);
-        /* ! HAS TO BE NHWC. Match previous layout conversion */
-        CHECK_OV_STATUS(ov_layout_create("NHWC", &input_layout), ret);
-        CHECK_OV_STATUS(ov_preprocess_input_tensor_info_set_layout(
-                            input_tensor_info, input_layout),
-                        ret);
-
-        /* add RESIZE */
-        CHECK_OV_STATUS(ov_preprocess_input_info_get_preprocess_steps(
-                            input_info, &input_process),
-                        ret);
-        CHECK_OV_STATUS(
-            ov_preprocess_preprocess_steps_resize(input_process, RESIZE_LINEAR),
-            ret);
-
-        /* input model */
-        CHECK_OV_STATUS(
-            ov_preprocess_input_info_get_model_info(input_info, &p_input_model),
-            ret);
-        // TODO: what if not?
-        CHECK_OV_STATUS(ov_layout_create("NCHW", &model_layout), ret);
-        CHECK_OV_STATUS(ov_preprocess_input_model_info_set_layout(p_input_model,
-                                                                  model_layout),
-                        ret);
-
-        /* output -> F32(possibility) */
-        CHECK_OV_STATUS(ov_preprocess_prepostprocessor_get_output_info_by_index(
-                            ppp, index, &output_info),
-                        ret);
-        CHECK_OV_STATUS(ov_preprocess_output_info_get_tensor_info(
-                            output_info, &output_tensor_info),
-                        ret);
-        CHECK_OV_STATUS(
-            ov_preprocess_output_set_element_type(output_tensor_info, F32),
-            ret);
-
-        CHECK_OV_STATUS(
-            ov_preprocess_prepostprocessor_build(ppp, &ov_ctx->new_model), ret);
-    }
-
-    CHECK_OV_STATUS(ov_core_compile_model(ov_ctx->core, ov_ctx->new_model,
-                                          "CPU", 0, &ov_ctx->compiled_model),
-                    ret);
-
-    CHECK_OV_STATUS(ov_compiled_model_create_infer_request(
-                        ov_ctx->compiled_model, &ov_ctx->infer_request),
-                    ret);
-
     /* install ov_tensor -> infer_request */
     CHECK_OV_STATUS(ov_infer_request_set_input_tensor_by_index(
-                        ov_ctx->infer_request, index, ov_ctx->input_tensor),
+                        exec->infer_request, index, input_tensor),
                     ret);
     ret = success;
-
 fail:
     if (ov_dims)
         os_free(ov_dims);
+    if (input_tensor)
+        ov_tensor_free(input_tensor);
     ov_shape_free(&input_shape);
-    if (ppp)
-        ov_preprocess_prepostprocessor_free(ppp);
-    if (input_info)
-        ov_preprocess_input_info_free(input_info);
-    if (input_tensor_info)
-        ov_preprocess_input_tensor_info_free(input_tensor_info);
-    if (input_layout)
-        ov_layout_free(input_layout);
-    if (input_process)
-        ov_preprocess_preprocess_steps_free(input_process);
-    if (p_input_model)
-        ov_preprocess_input_model_info_free(p_input_model);
-    if (model_layout)
-        ov_layout_free(model_layout);
-    if (output_info)
-        ov_preprocess_output_info_free(output_info);
-    if (output_tensor_info)
-        ov_preprocess_output_tensor_info_free(output_tensor_info);
 
     return ret;
 }
@@ -439,9 +425,14 @@ __attribute__((visibility("default"))) wasi_nn_error
 compute(void *ctx, graph_execution_context exec_ctx)
 {
     OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    struct OpenVINOExecutionContext *exec;
     wasi_nn_error ret = unsupported_operation;
 
-    CHECK_OV_STATUS(ov_infer_request_infer(ov_ctx->infer_request), ret);
+    if (exec_ctx >= ov_ctx->n_execution_contexts)
+        return runtime_error;
+    exec = &ov_ctx->execution_contexts[exec_ctx];
+
+    CHECK_OV_STATUS(ov_infer_request_infer(exec->infer_request), ret);
     ret = success;
 fail:
     return ret;
@@ -449,23 +440,33 @@ fail:
 
 __attribute__((visibility("default"))) wasi_nn_error
 get_output(void *ctx, graph_execution_context exec_ctx, uint32_t index,
-           tensor_data output_tensor, uint32_t *output_tensor_size)
+           tensor_data *output_tensor, uint32_t *output_tensor_size)
 {
     OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    struct OpenVINOExecutionContext *exec;
     wasi_nn_error ret = unsupported_operation;
     ov_tensor_t *ov_tensor = NULL;
     void *data = NULL;
     size_t byte_size = 0;
 
+    if (exec_ctx >= ov_ctx->n_execution_contexts)
+        return runtime_error;
+    exec = &ov_ctx->execution_contexts[exec_ctx];
+
     CHECK_OV_STATUS(ov_infer_request_get_output_tensor_by_index(
-                        ov_ctx->infer_request, index, &ov_tensor),
+                        exec->infer_request, index, &ov_tensor),
                     ret);
 
     CHECK_OV_STATUS(ov_tensor_get_byte_size(ov_tensor, &byte_size), ret);
 
+    if (byte_size > output_tensor->size) {
+        ret = too_large;
+        goto fail;
+    }
+
     CHECK_OV_STATUS(ov_tensor_data(ov_tensor, &data), ret);
 
-    memcpy(output_tensor, data, byte_size);
+    memcpy(output_tensor->buf, data, byte_size);
 
     *output_tensor_size = (uint32_t)byte_size;
 
@@ -511,7 +512,7 @@ init_backend(void **ctx)
     *ctx = (void *)ov_ctx;
     return success;
 fail:
-    openvino_destroy((void *)ov_ctx);
+    os_free(ov_ctx);
     return ret;
 }
 
@@ -519,27 +520,16 @@ __attribute__((visibility("default"))) wasi_nn_error
 deinit_backend(void *ctx)
 {
     OpenVINOContext *ov_ctx = (OpenVINOContext *)ctx;
+    unsigned int i;
 
     if (!ov_ctx)
         return invalid_argument;
 
-    if (ov_ctx->weight_data)
-        os_free(ov_ctx->weight_data);
+    for (i = 0; i < ov_ctx->n_execution_contexts; i++)
+        free_execution_context(&ov_ctx->execution_contexts[i]);
 
-    if (ov_ctx->weights_tensor)
-        ov_tensor_free(ov_ctx->weights_tensor);
-
-    if (ov_ctx->input_tensor)
-        ov_tensor_free(ov_ctx->input_tensor);
-
-    if (ov_ctx->infer_request)
-        ov_infer_request_free(ov_ctx->infer_request);
-
-    if (ov_ctx->compiled_model)
-        ov_compiled_model_free(ov_ctx->compiled_model);
-
-    if (ov_ctx->model)
-        ov_model_free(ov_ctx->model);
+    for (i = 0; i < ov_ctx->n_graphs; i++)
+        free_graph(&ov_ctx->graphs[i]);
 
     if (ov_ctx->core)
         ov_core_free(ov_ctx->core);

core/iwasm/libraries/wasi-nn/src/wasi_nn_private.h

@@ -9,10 +9,44 @@
 #include "wasi_nn_types.h"
 #include "wasm_export.h"
 
+#include "bh_platform.h"
+
 typedef struct {
+    korp_mutex lock;
+    bool busy;
+    bool is_backend_ctx_initialized;
     bool is_model_loaded;
     graph_encoding backend;
     void *backend_ctx;
 } WASINNContext;
 
+typedef wasi_nn_error (*LOAD)(void *, graph_builder_array *, graph_encoding,
+                              execution_target, graph *);
+typedef wasi_nn_error (*LOAD_BY_NAME)(void *, const char *, uint32_t, graph *);
+typedef wasi_nn_error (*LOAD_BY_NAME_WITH_CONFIG)(void *, const char *,
+                                                  uint32_t, void *, uint32_t,
+                                                  graph *);
+typedef wasi_nn_error (*INIT_EXECUTION_CONTEXT)(void *, graph,
+                                                graph_execution_context *);
+typedef wasi_nn_error (*SET_INPUT)(void *, graph_execution_context, uint32_t,
+                                   tensor *);
+typedef wasi_nn_error (*COMPUTE)(void *, graph_execution_context);
+typedef wasi_nn_error (*GET_OUTPUT)(void *, graph_execution_context, uint32_t,
+                                    tensor_data *, uint32_t *);
+/* wasi-nn general APIs */
+typedef wasi_nn_error (*BACKEND_INITIALIZE)(void **);
+typedef wasi_nn_error (*BACKEND_DEINITIALIZE)(void *);
+
+typedef struct {
+    LOAD load;
+    LOAD_BY_NAME load_by_name;
+    LOAD_BY_NAME_WITH_CONFIG load_by_name_with_config;
+    INIT_EXECUTION_CONTEXT init_execution_context;
+    SET_INPUT set_input;
+    COMPUTE compute;
+    GET_OUTPUT get_output;
+    BACKEND_INITIALIZE init;
+    BACKEND_DEINITIALIZE deinit;
+} api_function;
+
 #endif

core/iwasm/libraries/wasi-nn/src/wasi_nn_tensorflowlite.cpp

@@ -3,11 +3,10 @@
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  */
 
-#include "wasi_nn_tensorflowlite.hpp"
 #include "utils/logger.h"
 
 #include "bh_platform.h"
-#include "wasi_nn_types.h"
+#include "wasi_nn_backend.h"
 #include "wasm_export.h"
 
 #include <tensorflow/lite/interpreter.h>
@@ -85,12 +84,8 @@ is_valid_graph(TFLiteContext *tfl_ctx, graph g)
         NN_ERR_PRINTF("Invalid graph: %d >= %d.", g, MAX_GRAPHS_PER_INST);
         return runtime_error;
     }
-    if (tfl_ctx->models[g].model_pointer == NULL) {
-        NN_ERR_PRINTF("Context (model) non-initialized.");
-        return runtime_error;
-    }
     if (tfl_ctx->models[g].model == NULL) {
-        NN_ERR_PRINTF("Context (tflite model) non-initialized.");
+        NN_ERR_PRINTF("Context (model) non-initialized.");
         return runtime_error;
     }
     return success;
@@ -285,6 +280,11 @@ set_input(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
 {
     TFLiteContext *tfl_ctx = (TFLiteContext *)tflite_ctx;
 
+    if (input_tensor->type != fp32) {
+        NN_ERR_PRINTF("unsupported input tensor type %u", input_tensor->type);
+        return runtime_error;
+    }
+
     wasi_nn_error res;
     if (success != (res = is_valid_graph_execution_context(tfl_ctx, ctx)))
         return res;
@@ -323,7 +323,7 @@ set_input(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
                 index);
 
         int size = model_tensor_size * sizeof(float);
-        bh_memcpy_s(it, size, input_tensor->data, size);
+        bh_memcpy_s(it, size, input_tensor->data.buf, size);
     }
     else { // TODO: Assuming uint8 quantized networks.
         TfLiteAffineQuantization *quant_info =
@@ -341,7 +341,7 @@ set_input(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
         NN_DBG_PRINTF("input tensor: (scale, offset) = (%f, %f)", scale,
                       zero_point);
 
-        float *input_tensor_f = (float *)input_tensor->data;
+        float *input_tensor_f = (float *)input_tensor->data.buf;
         for (uint32_t i = 0; i < model_tensor_size; ++i) {
             it[i] = (uint8_t)(input_tensor_f[i] / scale + zero_point);
         }
@@ -365,7 +365,7 @@ compute(void *tflite_ctx, graph_execution_context ctx)
 
 __attribute__((visibility("default"))) wasi_nn_error
 get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
-           tensor_data output_tensor, uint32_t *output_tensor_size)
+           tensor_data *output_tensor, uint32_t *output_tensor_size)
 {
     TFLiteContext *tfl_ctx = (TFLiteContext *)tflite_ctx;
 
@@ -388,23 +388,34 @@ get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
         return too_large;
     }
 
-    uint32_t model_tensor_size = 1;
-    for (int i = 0; i < (int)tensor->dims->size; ++i)
-        model_tensor_size *= (uint32_t)tensor->dims->data[i];
-
-    if (*output_tensor_size < model_tensor_size) {
-        NN_ERR_PRINTF("Insufficient memory to copy tensor %d", index);
-        return too_large;
-    }
-
     if (tensor->quantization.type == kTfLiteNoQuantization) {
         NN_DBG_PRINTF("No quantization information");
-        float *ot =
-            tfl_ctx->interpreters[ctx].interpreter->typed_output_tensor<float>(
-                index);
-
-        int size = model_tensor_size * sizeof(float);
-        bh_memcpy_s(output_tensor, size, ot, size);
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+        if (output_tensor->size < tensor->bytes) {
+            NN_ERR_PRINTF("Insufficient memory to copy tensor %d", index);
+            return too_large;
+        }
+#else
+        /*
+         * for now, maintain the bug-to-bug compatibility with the old abi,
+         * where the size here is the number of fp32, not bytes.
+         */
+        if (output_tensor->size < tensor->bytes / sizeof(float)) {
+            NN_ERR_PRINTF("Insufficient memory to copy tensor %d", index);
+            return too_large;
+        }
+#endif
+        bh_memcpy_s(output_tensor->buf, output_tensor->size, tensor->data.data,
+                    tensor->bytes);
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+        *output_tensor_size = tensor->bytes;
+#else
+        /*
+         * for now, maintain the bug-to-bug compatibility with the old abi,
+         * where the size here is the number of fp32, not bytes.
+         */
+        *output_tensor_size = tensor->bytes / sizeof(float);
+#endif
     }
     else { // TODO: Assuming uint8 quantized networks.
         TfLiteAffineQuantization *quant_info =
@@ -413,6 +424,27 @@ get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
             NN_ERR_PRINTF("Quantization per channel is not supported");
             return runtime_error;
         }
+
+        uint32_t model_tensor_size = 1;
+        for (int i = 0; i < (int)tensor->dims->size; ++i)
+            model_tensor_size *= (uint32_t)tensor->dims->data[i];
+
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+        if (output_tensor->size / sizeof(float) < model_tensor_size) {
+            NN_ERR_PRINTF("Insufficient memory to copy tensor %d", index);
+            return too_large;
+        }
+#else
+        /*
+         * for now, maintain the bug-to-bug compatibility with the old abi,
+         * where the size here is the number of fp32, not bytes.
+         */
+        if (output_tensor->size < model_tensor_size) {
+            NN_ERR_PRINTF("Insufficient memory to copy tensor %d", index);
+            return too_large;
+        }
+#endif
+
         uint8_t *ot = tfl_ctx->interpreters[ctx]
                           .interpreter->typed_output_tensor<uint8_t>(index);
 
@@ -421,13 +453,22 @@ get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
         NN_DBG_PRINTF("output tensor: (scale, offset) = (%f, %f)", scale,
                       zero_point);
 
-        float *output_tensor_f = (float *)output_tensor;
+        float *output_tensor_f = (float *)output_tensor->buf;
         for (uint32_t i = 0; i < model_tensor_size; ++i) {
             output_tensor_f[i] = (ot[i] - zero_point) * scale;
         }
+
+#if WASM_ENABLE_WASI_EPHEMERAL_NN != 0
+        *output_tensor_size = model_tensor_size * sizeof(float);
+#else
+        /*
+         * for now, maintain the bug-to-bug compatibility with the old abi,
+         * where the size here is the number of fp32, not bytes.
+         */
+        *output_tensor_size = model_tensor_size;
+#endif
     }
 
-    *output_tensor_size = model_tensor_size;
     return success;
 }
 
@@ -472,32 +513,31 @@ deinit_backend(void *tflite_ctx)
     NN_DBG_PRINTF("Freeing memory.");
     for (int i = 0; i < MAX_GRAPHS_PER_INST; ++i) {
         tfl_ctx->models[i].model.reset();
-        if (tfl_ctx->models[i].model_pointer) {
-            if (tfl_ctx->delegate) {
-                switch (tfl_ctx->models[i].target) {
-                    case gpu:
-                    {
+        if (tfl_ctx->delegate) {
+            switch (tfl_ctx->models[i].target) {
+                case gpu:
+                {
 #if WASM_ENABLE_WASI_NN_GPU != 0
-                        TfLiteGpuDelegateV2Delete(tfl_ctx->delegate);
+                    TfLiteGpuDelegateV2Delete(tfl_ctx->delegate);
 #else
-                        NN_ERR_PRINTF("GPU delegate delete but not enabled.");
+                    NN_ERR_PRINTF("GPU delegate delete but not enabled.");
 #endif
-                        break;
-                    }
-                    case tpu:
-                    {
-#if WASM_ENABLE_WASI_NN_EXTERNAL_DELEGATE != 0
-                        TfLiteExternalDelegateDelete(tfl_ctx->delegate);
-#else
-                        NN_ERR_PRINTF(
-                            "External delegate delete but not enabled.");
-#endif
-                        break;
-                    }
-                    default:
-                        break;
+                    break;
                 }
+                case tpu:
+                {
+#if WASM_ENABLE_WASI_NN_EXTERNAL_DELEGATE != 0
+                    TfLiteExternalDelegateDelete(tfl_ctx->delegate);
+#else
+                    NN_ERR_PRINTF("External delegate delete but not enabled.");
+#endif
+                    break;
+                }
+                default:
+                    break;
             }
+        }
+        if (tfl_ctx->models[i].model_pointer) {
             wasm_runtime_free(tfl_ctx->models[i].model_pointer);
         }
         tfl_ctx->models[i].model_pointer = NULL;

core/iwasm/libraries/wasi-nn/src/wasi_nn_tensorflowlite.hpp

@@ -1,47 +0,0 @@
-/*
- * Copyright (C) 2019 Intel Corporation.  All rights reserved.
- * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
- */
-
-#ifndef WASI_NN_TENSORFLOWLITE_HPP
-#define WASI_NN_TENSORFLOWLITE_HPP
-
-#include "wasi_nn_types.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-__attribute__((visibility("default"))) wasi_nn_error
-load(void *tflite_ctx, graph_builder_array *builder, graph_encoding encoding,
-     execution_target target, graph *g);
-
-__attribute__((visibility("default"))) wasi_nn_error
-load_by_name(void *tflite_ctx, const char *filename, uint32_t filename_len,
-             graph *g);
-
-__attribute__((visibility("default"))) wasi_nn_error
-init_execution_context(void *tflite_ctx, graph g, graph_execution_context *ctx);
-
-__attribute__((visibility("default"))) wasi_nn_error
-set_input(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
-          tensor *input_tensor);
-
-__attribute__((visibility("default"))) wasi_nn_error
-compute(void *tflite_ctx, graph_execution_context ctx);
-
-__attribute__((visibility("default"))) wasi_nn_error
-get_output(void *tflite_ctx, graph_execution_context ctx, uint32_t index,
-           tensor_data output_tensor, uint32_t *output_tensor_size);
-
-__attribute__((visibility("default"))) wasi_nn_error
-init_backend(void **tflite_ctx);
-
-__attribute__((visibility("default"))) wasi_nn_error
-deinit_backend(void *tflite_ctx);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif

core/iwasm/libraries/wasi-nn/test/Dockerfile.vx-delegate

@@ -37,7 +37,10 @@ RUN wget https://github.com/Kitware/CMake/releases/download/v${CMAKE_VER}/cmake-
 WORKDIR /tmp
 RUN git clone https://github.com/VeriSilicon/TIM-VX.git tim-vx \
     && git clone https://github.com/VeriSilicon/tflite-vx-delegate.git \
-    && git clone https://github.com/tensorflow/tensorflow.git
+    && git clone https://github.com/tensorflow/tensorflow.git --branch v2.12.0 
+
+WORKDIR /tmp/tensorflow
+RUN git cherry-pick -n 5115fa96d7c5b41451674892317be43e30b7c389
 
 
 # Build TIM-VX
@@ -99,28 +102,24 @@ RUN cp --parents \
 ENV VIVANTE_SDK_DIR=/tmp/tim-vx/prebuilt-sdk/x86_64_linux/
 ENV VSIMULATOR_CONFIG=czl
 
-ENV LD_LIBRARY_PATH=/tmp/tim-vx/prebuilt-sdk/x86_64_linux/lib:/usr/local/lib:/lib/x86_64-linux-gnu/:/lib64/:/usr/lib:$LD_LIBRARY_PATH 
-
 # Build WASI-NN
 WORKDIR /home/wamr
 
 COPY . .
 
-WORKDIR /home/wamr/core/iwasm/libraries/wasi-nn/test/build
+WORKDIR /home/wamr/product-mini/platforms/linux
 
-# hadolint ignore=SC2086
-RUN cmake \
-    -DCMAKE_LIBRARY_PATH=${CMAKE_LIBRARY_PATH}:/usr/local/lib/ \
-    -DCMAKE_INCLUDE_PATH=${CMAKE_INCLUDE_PATH}:/usr/local/include/ \
+RUN rm -rf build \
+  && cmake -S . -B build\
+    -DCMAKE_LIBRARY_PATH="/usr/local/lib/" \
+    -DCMAKE_INCLUDE_PATH="/usr/local/include/" \
     -DWAMR_BUILD_WASI_NN=1 \
     -DWAMR_BUILD_WASI_NN_TFLITE=1\
     -DWAMR_BUILD_WASI_NN_ENABLE_EXT=1 \
     -DWASI_NN_EXT_DELEGATE_PATH="/usr/lib/libvx_delegate.so" \
-    ..
+  && cmake --build build -j "$(grep -c ^processor /proc/cpuinfo)"
 
-RUN make -j "$(grep -c ^processor /proc/cpuinfo)"
-
-RUN cp /home/wamr/core/iwasm/libraries/wasi-nn/test/build/iwasm /run/iwasm \
+RUN cp /home/wamr/product-mini/platforms/linux/build/iwasm /run/iwasm \
   && cp /home/wamr/product-mini/platforms/linux/build/lib*.so /usr/lib
 
 ENTRYPOINT [ "/run/iwasm" ]

core/iwasm/libraries/wasi-nn/test/build.sh

@@ -3,6 +3,17 @@
 # Copyright (C) 2019 Intel Corporation.  All rights reserved.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
+# on intel mac, this ends up with a lot of the following error.
+#
+#  AttributeError: 'Sequential' object has no attribute '_get_save_spec'.
+#
+# * "pip install tensorflow" installs tensorflow 2.16.2 on intel mac.
+#   (because it's the last version before tf deprecated the target.)
+# * keras 3 support in the version seems incomplete (thus the error)
+# * a workaround: use keras 2 as mentioned in:
+#   https://github.com/tensorflow/tensorflow/releases/tag/v2.16.1
+#   https://blog.tensorflow.org/2024/03/whats-new-in-tensorflow-216.html
+
 CURR_PATH=$(cd $(dirname $0) && pwd -P)
 
 # WASM application that uses WASI-NN

core/iwasm/libraries/wasi-nn/test/models/mult_outputs.py

@@ -3,7 +3,7 @@
 
 import tensorflow as tf
 import numpy as np
-from keras.layers import AveragePooling2D, Conv2D
+from tensorflow.keras.layers import AveragePooling2D, Conv2D
 
 from tensorflow.keras import Input, Model
 

core/iwasm/libraries/wasi-nn/test/utils.c

@@ -58,7 +58,7 @@ wasm_load(char *model_name, graph *g, execution_target target)
 wasi_nn_error
 wasm_load_by_name(const char *model_name, graph *g)
 {
-    wasi_nn_error res = load_by_name(model_name, g);
+    wasi_nn_error res = load_by_name(model_name, strlen(model_name), g);
     return res;
 }
 
@@ -108,7 +108,8 @@ run_inference(execution_target target, float *input, uint32_t *input_size,
               uint32_t num_output_tensors)
 {
     graph graph;
-    if (wasm_load(model_name, &graph, target) != success) {
+
+    if (wasm_load_by_name(model_name, &graph) != success) {
         NN_ERR_PRINTF("Error when loading model.");
         exit(1);
     }

core/shared/platform/esp-idf/espidf_platform.c

@@ -201,10 +201,20 @@ openat(int fd, const char *pathname, int flags, ...)
     int ret;
     char dir_path[DIR_PATH_LEN];
     char *full_path;
+    mode_t mode = 0;
+    bool has_mode = false;
+
+    if (flags & O_CREAT) {
+        va_list ap;
+        va_start(ap, flags);
+        mode = (mode_t)va_arg(ap, int);
+        va_end(ap);
+        has_mode = true;
+    }
 
     ret = fcntl(fd, F_GETPATH, dir_path);
     if (ret != 0) {
-        errno = -EINVAL;
+        errno = EINVAL;
         return -1;
     }
 
@@ -214,7 +224,7 @@ openat(int fd, const char *pathname, int flags, ...)
         return -1;
     }
 
-    new_fd = open(full_path, flags);
+    new_fd = has_mode ? open(full_path, flags, mode) : open(full_path, flags);
     free(full_path);
 
     return new_fd;

core/shared/utils/bh_vector.c

@@ -35,8 +35,8 @@ extend_vector(Vector *vector, size_t length)
     if (length <= vector->max_elems)
         return true;
 
-    if (length < vector->size_elem * 3 / 2)
-        length = vector->size_elem * 3 / 2;
+    if (length < vector->max_elems * 3 / 2)
+        length = vector->max_elems * 3 / 2;
 
     if (!(data = alloc_vector_data(length, vector->size_elem))) {
         return false;
@@ -194,12 +194,12 @@ bh_vector_append(Vector *vector, const void *elem_buf)
         goto just_return;
     }
 
-    /* make sure one more slot is used by the thread who allocas it */
+    /* make sure one more slot is used by the thread who allocates it */
     if (vector->lock)
         os_mutex_lock(vector->lock);
 
     if (!extend_vector(vector, vector->num_elems + 1)) {
-        LOG_ERROR("Append ector elem failed: extend vector failed.\n");
+        LOG_ERROR("Append vector elem failed: extend vector failed.\n");
         goto unlock_return;
     }
 

core/version.h

@@ -18,7 +18,7 @@
 /* clang-format off */
 #define WAMR_VERSION_MAJOR 2
 #define WAMR_VERSION_MINOR 3
-#define WAMR_VERSION_PATCH 0
+#define WAMR_VERSION_PATCH 1
 /* clang-format on */
 
 #endif

doc/build_wamr.md

@@ -102,6 +102,7 @@ cmake -DWAMR_BUILD_PLATFORM=linux -DWAMR_BUILD_TARGET=ARM
 
 ### **Enable lib wasi-nn**
 - **WAMR_BUILD_WASI_NN**=1/0, default to disable if not set
+> Note: WAMR_BUILD_WASI_NN without WAMR_BUILD_WASI_EPHEMERAL_NN is deprecated and will likely be removed in future versions of WAMR. Please consider to enable WAMR_BUILD_WASI_EPHEMERAL_NN as well.
 > Note: See [WASI-NN](../core/iwasm/libraries/wasi-nn) for more details.
 
 ### **Enable lib wasi-nn GPU mode**
@@ -113,7 +114,7 @@ cmake -DWAMR_BUILD_PLATFORM=linux -DWAMR_BUILD_TARGET=ARM
 - **WAMR_BUILD_WASI_NN_EXTERNAL_DELEGATE_PATH**=Path to the external delegate shared library (e.g. `libedgetpu.so.1.0` for Coral USB)
 
 ### **Enable lib wasi-nn with `wasi_ephemeral_nn` module support**
-- **WAMR_BUILD_WASI_EPHEMERAL_NN**=1/0, default to disable if not set
+- **WAMR_BUILD_WASI_EPHEMERAL_NN**=1/0, default to enable if not set
 
 ### **Disable boundary check with hardware trap**
 - **WAMR_DISABLE_HW_BOUND_CHECK**=1/0, default to enable if not set and supported by platform
@@ -327,6 +328,10 @@ And the wasm app can calls below APIs to allocate/free memory from/to the shared
 - **WAMR_BUILD_SHRUNK_MEMORY**=1/0, default to enable if not set
 > Note: When enabled, this feature will reduce memory usage by decreasing the size of the linear memory, particularly when the `memory.grow` opcode is not used and memory usage is somewhat predictable.
 
+## **Instruction metering**
+- **WAMR_BUILD_INSTRUCTION_METERING**=1/0, default to disable if not set
+> Note: Enabling this feature allows limiting the number of instructions a wasm module instance can execute. Use the `wasm_runtime_set_instruction_count_limit(...)` API before calling `wasm_runtime_call_*(...)` APIs to enforce this limit.
+
 ## **Combination of configurations:**
 
 We can combine the configurations. For example, if we want to disable interpreter, enable AOT and WASI, we can run command:

doc/embed_wamr.md

@@ -22,7 +22,12 @@ set (WAMR_ROOT_DIR path/to/wamr/root)
 include (${WAMR_ROOT_DIR}/build-scripts/runtime_lib.cmake)
 add_library(vmlib ${WAMR_RUNTIME_LIB_SOURCE})
 
-target_link_libraries (your_project vmlib)
+# include bh_read_file.h
+include (${SHARED_DIR}/utils/uncommon/shared_uncommon.cmake)
+
+add_executable (your_project main.c ${UNCOMMON_SHARED_SOURCE})
+
+target_link_libraries (your_project vmlib -lm)
 ```
 Examples can be found in [CMakeLists.txt of linux platform](../product-mini/platforms/linux/CMakeLists.txt) and [other platforms](../product-mini/platforms). The available features to configure can be found in [Build WAMR vmcore](./build_wamr.md#wamr-vmcore-cmake-building-configurations).
 
@@ -31,6 +36,10 @@ Developer can also use Makefile to embed WAMR, by defining macros and including
 ## The runtime initialization
 
 ``` C
+  #include "bh_platform.h"
+  #include "bh_read_file.h"
+  #include "wasm_export.h"
+
   char *buffer, error_buf[128];
   wasm_module_t module;
   wasm_module_inst_t module_inst;
@@ -42,7 +51,7 @@ Developer can also use Makefile to embed WAMR, by defining macros and including
   wasm_runtime_init();
 
   /* read WASM file into a memory buffer */
-  buffer = read_wasm_binary_to_buffer(…, &size);
+  buffer = bh_read_file_to_buffer(…, &size);
 
   /* add line below if we want to export native functions to WASM app */
   wasm_runtime_register_natives(...);

doc/ref_types.md

@@ -4,6 +4,6 @@ WebAssembly [reference-types](https://github.com/WebAssembly/reference-types) pr
 
 WAMR has implemented the reference-types proposal. WAMR allows a native method to pass a host object to a WASM application as an `externref` parameter or receives a host object from a WASM application as an `externref` result. Internally, WAMR won't try to parse or dereference `externref`. It is an opaque type.
 
-The restriction of using `externref` in a native method is the host object has to be the value of a `unintptr_t` variable. In other words, it takes **8 bytes** on 64-bit machine and **4 bytes** on 32-bit machines. Please keep that in mind especially when calling `wasm_runtime_call_wasm`.
+The restriction of using `externref` in a native method is the host object has to be the value of a `uintptr_t` variable. In other words, it takes **8 bytes** on 64-bit machine and **4 bytes** on 32-bit machines. Please keep that in mind especially when calling `wasm_runtime_call_wasm`.
 
 Please ref to the [sample](../samples/ref-types) for more details.

idf_component.yml

@@ -1,4 +1,4 @@
-version: "2.0.0"
+version: "2.2.0~3"
 description: WebAssembly Micro Runtime - A lightweight standalone WebAssembly (Wasm) runtime with small footprint, high performance and highly configurable features
 url: https://bytecodealliance.org/
 repository: https://github.com/bytecodealliance/wasm-micro-runtime.git
@@ -11,5 +11,7 @@ targets:
   - esp32s3
   - esp32c3
   - esp32c6
+  - esp32p4
+  - esp32c5
 examples:
   - path: product-mini/platforms/esp-idf

language-bindings/python/src/wamr/wasmcapi/ffi.py

@@ -112,12 +112,12 @@ def wasm_vec_to_list(vec):
         wasm_frame_vec_t,
         wasm_extern_vec_t,
     ]
-    known_vec_pointer_type = [POINTER(type) for type in known_vec_type]
+    known_vec_pointer_type = [POINTER(vec_type) for vec_type in known_vec_type]
 
-    if any([isinstance(vec, type) for type in known_vec_pointer_type]):
+    if any([isinstance(vec, pointer_type) for pointer_type in known_vec_pointer_type]):
         vec = dereference(vec)
         return [vec.data[i] for i in range(vec.num_elems)]
-    elif any([isinstance(vec, type) for type in known_vec_type]):
+    elif any([isinstance(vec, vec_type) for vec_type in known_vec_type]):
         return [vec.data[i] for i in range(vec.num_elems)]
     else:
         raise RuntimeError("not a known vector type")
@@ -405,7 +405,7 @@ def __compare_wasm_val_t(self, other):
     elif WASM_F32 == self.kind:
         return self.of.f32 == other.of.f32
     elif WASM_F64 == self.kind:
-        return self.of.f64 == other.of.f63
+        return self.of.f64 == other.of.f64
     elif WASM_EXTERNREF == self.kind:
         raise RuntimeError("FIXME")
     else:

language-bindings/python/wamr-api/README.md

@@ -6,7 +6,7 @@
 
 ### Pre-requisites
 #### Install requirements
-Before proceeding it is necessary to make sure your Python environment is correctly configured. To do ths open a terminal session in this directory and perfom the following:
+Before proceeding it is necessary to make sure your Python environment is correctly configured. To do this open a terminal session in this directory and perform the following:
 
 
 ```shell

language-bindings/python/wasm-c-api/docs/design.md

@@ -353,12 +353,12 @@ writable and needs to be copied into a ctype array.
 
 #### variable arguments
 
-A function with _variable arugments_ makes it hard to specify the required
+A function with _variable arguments_ makes it hard to specify the required
 argument types for the function prototype. It leaves us one way to call it
 directly without any arguments type checking.
 
 ```python
-libc.printf(b"Hello, an int %d, a float %f, a string %s\n", c_int(1), c_doulbe(3.14), "World!")
+libc.printf(b"Hello, an int %d, a float %f, a string %s\n", c_int(1), c_double(3.14), "World!")
 ```
 
 #### Use `c_bool` to represent `wasm_mutability_t `
@@ -373,7 +373,7 @@ libc.printf(b"Hello, an int %d, a float %f, a string %s\n", c_int(1), c_doulbe(3
 
 ### bindgen.py
 
-`bindge.py` is a tool to create WAMR python binding automatically. `binding.py`
+`bindgen.py` is a tool to create WAMR python binding automatically. `binding.py`
 is generated. We should avoid modification on it. Additional helpers should go
 to `ffi.py`.
 

product-mini/README.md

@@ -111,7 +111,7 @@ The Fast JIT is a lightweight JIT engine with quick startup, small footprint and
 (6) To enable the `Multi-tier JIT` mode:
 ``` Bash
 mkdir build && cd build
-cmake .. -DWAMR_BUILD_FAST_JTI=1 -DWAMR_BUILD_JIT=1
+cmake .. -DWAMR_BUILD_FAST_JIT=1 -DWAMR_BUILD_JIT=1
 make
 ```
 The Multi-tier JIT is a two level JIT tier-up engine, which launches Fast JIT to run the wasm module as soon as possible and creates backend threads to compile the LLVM JIT functions at the same time, and when the LLVM JIT functions are compiled, the runtime will switch the extecution from the Fast JIT jitted code to LLVM JIT jitted code gradually, so as to gain the best performance.

product-mini/platforms/darwin/CMakeLists.txt

@@ -114,6 +114,12 @@ set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS}")
 
 set (CMAKE_MACOSX_RPATH True)
 
+# if enable wasi-nn, both wasi-nn-backends and iwasm
+# need to use same WAMR (dynamic) libraries
+if (WAMR_BUILD_WASI_NN EQUAL 1)
+  set (BUILD_SHARED_LIBS ON)
+endif ()
+
 set (WAMR_ROOT_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../../..)
 
 include (${WAMR_ROOT_DIR}/build-scripts/runtime_lib.cmake)
@@ -132,7 +138,7 @@ add_library (vmlib ${WAMR_RUNTIME_LIB_SOURCE})
 set_version_info (vmlib)
 
 target_include_directories(vmlib INTERFACE
-  $<INSTALL_INTERFACE:include/iwasm>
+  $<INSTALL_INTERFACE:include>
 )
 
 set (WAMR_PUBLIC_HEADERS
@@ -151,7 +157,7 @@ target_link_libraries (vmlib ${LLVM_AVAILABLE_LIBS} ${UV_A_LIBS} -lm -ldl -lpthr
 install (TARGETS vmlib
   EXPORT iwasmTargets
   DESTINATION lib
-  PUBLIC_HEADER DESTINATION include/iwasm
+  PUBLIC_HEADER DESTINATION include
 )
 
 install_iwasm_package ()

product-mini/platforms/esp-idf/README.md

@@ -0,0 +1,91 @@
+# How to Use WAMR with ESP-IDF
+
+ESP-IDF is the official development framework for Espressif SoCs, supporting Windows, Linux, and macOS. WAMR (WebAssembly Micro Runtime) can be integrated as a standard [ESP-IDF](https://github.com/espressif/esp-idf) component.
+
+## 1. Setup the ESP-IDF Development Environment
+
+This example demonstrates how to use WAMR with ESP-IDF. Before proceeding, ensure you have the ESP-IDF development environment installed. For the relevant process, please refer to ESP-IDF [documents](https://docs.espressif.com/projects/esp-idf/en/latest/esp32/get-started/index.html).
+
+### Prerequisites
+
+#### Software Requirements
+
+* ESP-IDF v4.4.0 and above.
+
+#### Hardware Requirements
+
+* A development board with one of the following SoCs:
+
+  - ESP32
+
+  - ESP32-C3
+
+  - ESP32-S3
+
+  - ESP32-C6
+
+  - ESP32-P4
+
+  - ESP32-C5
+
+* See [Development Boards](https://www.espressif.com/en/products/devkits) for more information about it.
+
+> Note: Different chips require different ESP-IDF versions, please check [ESP-IDF Release and SoC Compatibility](https://github.com/espressif/esp-idf?tab=readme-ov-file#esp-idf-release-and-soc-compatibility) before proceeding.
+
+### Installation Steps
+
+1. Navigate to the ESP-IDF root directory.
+
+2. Run the installation script based on your OS:
+
+  - Linux/MacOS
+
+    ```
+    ./install.sh
+    ```
+
+  - Windows
+
+    ```
+    ./install.bat
+    ```
+
+3. If successful, you should see:
+
+    ```
+    All done! You can now run:
+
+      . ./export.sh
+    ```
+
+## 2. Compiling and Running the Project
+
+### Set the Target Chip
+
+Switch to the project directory and specify the target chip:
+
+```bash
+idf.py set-target <chip_name>
+```
+
+### Configure the project
+
+Open the configuration menu: 
+
+```bash
+idf.py menuconfig
+```
+
+To modify WAMR settings, navigate to: `Component config -> WASM Micro Runtime`
+
+### Build and Flash
+
+Run the following command to compile, flash, and monitor the application:
+
+```bash
+idf.py -p PORT flash monitor
+```
+
+(To exit the serial monitor, type ``Ctrl-]``.)
+
+See the [Getting Started Guide](https://idf.espressif.com/) for full steps to configure and use ESP-IDF to build projects.

product-mini/platforms/esp-idf/build_and_run.sh

@@ -7,16 +7,20 @@ ESP32_TARGET="esp32"
 ESP32C3_TARGET="esp32c3"
 ESP32S3_TARGET="esp32s3"
 ESP32C6_TARGET="esp32c6"
+ESP32P4_TARGET="esp32p4"
+ESP32C5_TARGET="esp32c5"
 
 usage ()
 {
         echo "USAGE:"
-        echo "$0 $ESP32_TARGET|$ESP32C3_TARGET|$ESP32S3_TARGET"
+        echo "$0 $ESP32_TARGET|$ESP32C3_TARGET|$ESP32S3_TARGET|$ESP32C6_TARGET|$ESP32P4_TARGET|$ESP32C5_TARGET"
         echo "Example:"
         echo "        $0 $ESP32_TARGET"
         echo "        $0 $ESP32C3_TARGET"
         echo "        $0 $ESP32S3_TARGET"
         echo "        $0 $ESP32C6_TARGET"
+        echo "        $0 $ESP32P4_TARGET"
+        echo "        $0 $ESP32C5_TARGET"
         exit 1
 }
 
@@ -26,12 +30,18 @@ fi
 
 TARGET=$1
 
+if [ "$TARGET" = "$ESP32C5_TARGET" ]; then
+        IDF_ST_CMD="idf.py --preview set-target $TARGET"
+else
+        IDF_ST_CMD="idf.py set-target $TARGET"
+fi
+
 if [[ -z "${WAMR_PATH}" ]]; then
         export WAMR_PATH=$PWD/../../..
 fi
 
 rm -rf build
-idf.py set-target $TARGET
+$IDF_ST_CMD
 idf.py build
 idf.py flash
 

product-mini/platforms/linux-sgx/enclave-sample/App/pal_api.h

@@ -79,7 +79,7 @@ struct wamr_pal_create_process_args {
     // Untrusted environment variable array pass to new process.
     //
     // The untrusted env vars to the command. And the last element of the array
-    // must be NULL to indicate the length of array.
+    // must be NULL to indicate the end of the array.
     //
     // Optional field.
     const char **env;

product-mini/platforms/linux/CMakeLists.txt

@@ -177,7 +177,7 @@ add_library (vmlib ${WAMR_RUNTIME_LIB_SOURCE})
 set_version_info (vmlib)
 
 target_include_directories(vmlib INTERFACE
-  $<INSTALL_INTERFACE:include/iwasm>
+  $<INSTALL_INTERFACE:include>
 )
 
 set (WAMR_PUBLIC_HEADERS
@@ -197,7 +197,7 @@ target_link_libraries (vmlib ${LLVM_AVAILABLE_LIBS} ${UV_A_LIBS} -lm -ldl -lpthr
 install (TARGETS vmlib
   EXPORT iwasmTargets
   DESTINATION lib
-  PUBLIC_HEADER DESTINATION include/iwasm
+  PUBLIC_HEADER DESTINATION include
 )
 
 install_iwasm_package ()

product-mini/platforms/windows/CMakeLists.txt

@@ -16,8 +16,6 @@ set (CMAKE_SHARED_LIBRARY_LINK_CXX_FLAGS "")
 
 set(CMAKE_CXX_STANDARD 17)
 
-add_definitions(-DCOMPILING_WASM_RUNTIME_API=1)
-
 # Set WAMR_BUILD_TARGET, currently values supported:
 # "X86_64", "AMD_64", "X86_32", "AARCH64[sub]", "ARM[sub]", "THUMB[sub]", "MIPS", "XTENSA"
 if (NOT DEFINED WAMR_BUILD_TARGET)
@@ -147,7 +145,7 @@ add_library (vmlib ${WAMR_RUNTIME_LIB_SOURCE})
 set_version_info (vmlib)
 
 target_include_directories(vmlib INTERFACE
-  $<INSTALL_INTERFACE:include/iwasm>
+  $<INSTALL_INTERFACE:include>
 )
 
 set (WAMR_PUBLIC_HEADERS
@@ -174,7 +172,7 @@ endif()
 install (TARGETS vmlib
   EXPORT iwasmTargets
   DESTINATION lib
-  PUBLIC_HEADER DESTINATION include/iwasm
+  PUBLIC_HEADER DESTINATION include
 )
 
 install_iwasm_package ()

product-mini/platforms/zephyr/simple/Dockerfile

@@ -1,9 +1,15 @@
 # Copyright (C) 2019 Intel Corporation.  All rights reserved.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+# Refer to https://docs.zephyrproject.org/3.7.0/develop/getting_started/index.html
+# for more information on how to set up the Zephyr development environment.
 FROM ubuntu:22.04
 
 ARG DEBIAN_FRONTEND=noninteractive
 ENV TZ=Asian/Shanghai
+ARG ZEPHYR_SDK_VERSION=0.16.9
+# In west_lite.yml, the Zephyr version is set to v3.7.0
+#ARG ZEPHYR_VERSION=3.7.0
 
 # Install dependencies for Zephyr
 # hadolint ignore=DL3008
@@ -16,28 +22,34 @@ RUN apt-get update && apt-get install -y --no-install-recommends git cmake ninja
 # Install the Zephyr Software Development Kit (SDK)
 WORKDIR /opt
 # hadolint ignore=DL4006
-RUN wget --progress=dot:giga https://github.com/zephyrproject-rtos/sdk-ng/releases/download/v0.16.3/zephyr-sdk-0.16.3_linux-x86_64.tar.xz \
-    && wget --progress=dot:giga -O - https://github.com/zephyrproject-rtos/sdk-ng/releases/download/v0.16.3/sha256.sum | shasum --check --ignore-missing \
-    && tar xvf zephyr-sdk-0.16.3_linux-x86_64.tar.xz && rm zephyr-sdk-0.16.3_linux-x86_64.tar.xz
+RUN wget --progress=dot:giga https://github.com/zephyrproject-rtos/sdk-ng/releases/download/v${ZEPHYR_SDK_VERSION}/zephyr-sdk-${ZEPHYR_SDK_VERSION}_linux-x86_64.tar.xz \
+    && wget --progress=dot:giga -O - https://github.com/zephyrproject-rtos/sdk-ng/releases/download/v${ZEPHYR_SDK_VERSION}/sha256.sum | shasum --check --ignore-missing \
+    && tar xf zephyr-sdk-${ZEPHYR_SDK_VERSION}_linux-x86_64.tar.xz && rm zephyr-sdk-${ZEPHYR_SDK_VERSION}_linux-x86_64.tar.xz
 
-WORKDIR /opt/zephyr-sdk-0.16.3
+WORKDIR /opt/zephyr-sdk-${ZEPHYR_SDK_VERSION}
 # hadolint ignore=DL4006
-RUN yes | ./setup.sh
+# Install host tools and Register Zephyr SDK CMake package
+RUN ./setup.sh -h -c
 
 # Get Zephyr 
+WORKDIR /root/zephyrproject/smoke-test
+
 # hadolint ignore=DL3013
-RUN pip3 install --no-cache-dir west && west init -m https://github.com/zephyrproject-rtos/zephyr --mr v3.5.0 /root/zephyrproject
+RUN pip3 install --no-cache-dir west
+COPY ./west_lite.yml ./west.yml
+
+# init the west workspace with a minimal manifest
+RUN west init -l
 
 WORKDIR /root/zephyrproject
-RUN west update 
+RUN west update --stats
 
-WORKDIR /root/zephyrproject/zephyr
-RUN west zephyr-export && pip install --no-cache-dir -r ~/zephyrproject/zephyr/scripts/requirements.txt
+WORKDIR /root/zephyrproject/modules/zephyr
+RUN west zephyr-export && pip install --no-cache-dir -r ./scripts/requirements.txt
+
+ENV ZEPHYR_BASE="/root/zephyrproject/modules/zephyr"
 
 # Git clone wamr
-WORKDIR /root
-RUN git clone https://github.com/bytecodealliance/wasm-micro-runtime.git
-
-WORKDIR /root/wasm-micro-runtime/product-mini/platforms/zephyr/simple
-
-ENV ZEPHYR_BASE="/root/zephyrproject/zephyr"
+WORKDIR /root/zephyrproject/modules/
+RUN git clone https://github.com/bytecodealliance/wasm-micro-runtime.git wasm-micro-runtime
+WORKDIR /root/zephyrproject/modules/wasm-micro-runtime/product-mini/platforms/zephyr

product-mini/platforms/zephyr/simple/README.md

@@ -87,6 +87,12 @@ is a 64-bit ARM target for emulating the Cortex-A53 platform.
 west build . -b qemu_cortex_a53 -p always -- -DWAMR_BUILD_TARGET=AARCH64 
 ```
 
+[ARC QEMU](https://docs.zephyrproject.org/latest/boards/qemu/arc/doc/index.html)
+is a 32-bit ARC target for emulating the ARC platform.
+
+```shell
+west build . -b qemu_arc/qemu_arc_em  -p always -- -DWAMR_BUILD_TARGET=ARC
+```
 
 ## Flashing or Running Image
 

product-mini/platforms/zephyr/simple/west_lite.yml

@@ -0,0 +1,15 @@
+# The west manifest file for WAMR on Zephyr smoke test.
+#
+manifest:
+  #
+  # Please add items below based on alphabetical order
+  projects:
+    - name: zephyr
+      url: https://github.com/zephyrproject-rtos/zephyr
+      revision: v3.7.0
+      clone-depth: 1
+      path: modules/zephyr
+      west-commands: scripts/west-commands.yml
+
+  self:
+    path: smoke-test

samples/basic/src/free_buffer_early.c

@@ -5,6 +5,7 @@
 
 #include "wasm_export.h"
 #include "bh_read_file.h"
+#include "bh_getopt.h"
 
 void
 my_log(uint32 log_level, const char *file, int line, const char *fmt, ...)

samples/printversion/CMakeLists.txt

@@ -0,0 +1,10 @@
+# Copyright (C) 2025 Midokura Japan KK.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+cmake_minimum_required(VERSION 3.16)
+
+project(printversion LANGUAGES C)
+
+add_executable(printversion printversion.c)
+find_package(iwasm REQUIRED)
+target_link_libraries(printversion iwasm::vmlib)

samples/printversion/printversion.c

@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2025 Midokura Japan KK.  All rights reserved.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ */
+
+#include <inttypes.h>
+#include <stdint.h>
+#include <stdio.h>
+
+#include <wasm_export.h>
+
+int
+main(int argc, char **argv)
+{
+    uint32_t major;
+    uint32_t minor;
+    uint32_t patch;
+    wasm_runtime_get_version(&major, &minor, &patch);
+    printf("wasm-micro-runtime %" PRIu32 ".%" PRIu32 ".%" PRIu32 "\n", major,
+           minor, patch);
+}

samples/printversion/test.sh

@@ -0,0 +1,24 @@
+#! /bin/sh
+
+# Copyright (C) 2025 Midokura Japan KK.  All rights reserved.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+set -e
+
+DIST=$(mktemp -d)
+
+# WAMR_BUILD_SIMD=0 to avoid fetching simde, which is
+# not relevant to this particular test.
+cmake -B build-wamr \
+-D CMAKE_INSTALL_PREFIX=${DIST} \
+-D WAMR_BUILD_SIMD=0 \
+../..
+cmake --build build-wamr -t install
+
+cmake -B build-app \
+-D CMAKE_PREFIX_PATH=${DIST} \
+-D CMAKE_INSTALL_PREFIX=${DIST} \
+.
+cmake --build build-app
+
+./build-app/printversion

samples/socket-api/sample_test_run.py

@@ -121,7 +121,6 @@ def main():
         print("\n================================")
         print("Test address resolving")
         cmd = "./iwasm --allow-resolve=*.com addr_resolve.wasm github.com"
-        cmd = "./multicast_server FF02:113D:6FDD:2C17:A643:FFE2:1BD1:3CD2"
         run_cmd(cmd, args.working_directory)
 
         # wait for a second

tests/benchmarks/README.md

@@ -8,6 +8,8 @@ Refer to the `README.md` under each folder for how to build and run the benchmar
 
 ## Install `llvm-profdata`
 
+> PS: the `llvm-profdata` vesion needs to be the same major version with llvm libraries used to build wamrc.
+
 The tool `llvm-profdata` is used when running the `test_pgo.sh` script under the benchmark folder. There are two ways to install it:
 
 1. Refer to https://apt.llvm.org/, e.g. in Ubuntu 20.04, add lines below to /etc/apt/source.list
@@ -18,19 +20,22 @@ deb-src http://apt.llvm.org/focal/ llvm-toolchain-focal main
 # 15
 deb http://apt.llvm.org/focal/ llvm-toolchain-focal-15 main
 deb-src http://apt.llvm.org/focal/ llvm-toolchain-focal-15 main
+# 18
+deb http://apt.llvm.org/focal/ llvm-toolchain-focal-18 main
+deb-src http://apt.llvm.org/focal/ llvm-toolchain-focal-18 main
 ```
 
 Then run `sudo apt update`, `sudo apt install llvm`. And after installing:
 
 ```bash
 cd /usr/bin
-sudo ln -s llvm-profdata-15 llvm-profdata
+sudo ln -s llvm-profdata-18 llvm-profdata
 ```
 
 2. Build manually
 
 ```bash
-git clone --depth 1 --branch release/15.x https://github.com/llvm/llvm-project.git
+git clone --depth 1 --branch release/18.x https://github.com/llvm/llvm-project.git
 cd llvm-project
 mkdir build && cd build
 cmake ../llvm \

tests/benchmarks/coremark/run.sh

@@ -2,6 +2,7 @@
 
 # Copyright (C) 2019 Intel Corporation.  All rights reserved.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+set -e
 
 PLATFORM=$(uname -s | tr A-Z a-z)
 

tests/benchmarks/coremark/test_pgo.sh

@@ -2,6 +2,7 @@
 
 # Copyright (C) 2019 Intel Corporation.  All rights reserved.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+set -e
 
 PLATFORM=$(uname -s | tr A-Z a-z)
 

tests/fuzz/wasm-mutator-fuzz/CMakeLists.txt

@@ -181,7 +181,12 @@ add_link_options(-fsanitize=fuzzer -fno-sanitize=vptr)
 
 # Enable sanitizers if not in oss-fuzz environment
 set(CFLAGS_ENV $ENV{CFLAGS})
-string(FIND "${CFLAGS_ENV}" "-DFUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION" IN_OSS_FUZZ)
+string(FIND "${CFLAGS_ENV}" "-DFUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION" FUZZ_POS)
+if (FUZZ_POS GREATER -1)
+  set(IN_OSS_FUZZ 1)
+else()
+  set(IN_OSS_FUZZ 0)
+endif()
 
 add_subdirectory(aot-compiler)
 add_subdirectory(wasm-mutator)

tests/fuzz/wasm-mutator-fuzz/aot-compiler/CMakeLists.txt

@@ -68,7 +68,7 @@ target_link_directories(aotclib PUBLIC ${LLVM_LIBRARY_DIR})
 target_link_libraries(aotclib PUBLIC ${REQUIRED_LLVM_LIBS})
 
 if(NOT IN_OSS_FUZZ)
-  message(STATUS "Enable ASan and UBSan in non-oss-fuzz environment")
+  message(STATUS "Enable ASan and UBSan in non-oss-fuzz environment for aotclib")
   target_compile_options(aotclib PUBLIC
     -fprofile-instr-generate -fcoverage-mapping
     -fno-sanitize-recover=all

tests/fuzz/wasm-mutator-fuzz/server/app/main.py

@@ -72,7 +72,7 @@ def to_json(inst, cls):
 
 
 class Fuzzing(db.Model):
-    __tablename__ = 'fazzing_task'
+    __tablename__ = 'fuzzing_task'
     id = db.Column(db.Integer, autoincrement=True,
                    primary_key=True, nullable=False)
     repo = db.Column(db.String(200), nullable=False, default='')
@@ -96,7 +96,7 @@ class TaskError(db.Model):
     __tablename__ = 'task_error'
     id = db.Column(db.Integer, autoincrement=True,
                    primary_key=True, nullable=False)
-    fazzing_id = db.Column(db.Integer, db.ForeignKey("fazzing_task.id"))
+    fuzzing_id = db.Column(db.Integer, db.ForeignKey("fuzzing_task.id"))
     name = db.Column(db.String(200), nullable=False, default='')
     std_out = db.Column(db.Text, default='')
     data = db.Column(db.JSON)
@@ -119,9 +119,9 @@ def to_data(data):
 
 def error_count(data):
     error = len(TaskError.query.filter(
-        TaskError.fazzing_id == data.get('id'), TaskError.status.in_([1, 2])).all())
+        TaskError.fuzzing_id == data.get('id'), TaskError.status.in_([1, 2])).all())
     end_error = len(TaskError.query.filter(
-        TaskError.fazzing_id == data.get('id'), TaskError.status == 0).all())
+        TaskError.fuzzing_id == data.get('id'), TaskError.status == 0).all())
     data['error'] = error
     data['end_error'] = end_error
     return data
@@ -159,11 +159,11 @@ def show_fuzz_list():
     id = data.get('id')
     if id:
         all_error = TaskError.query.filter(
-            TaskError.fazzing_id == id).with_entities(TaskError.id, TaskError.fazzing_id,
+            TaskError.fuzzing_id == id).with_entities(TaskError.id, TaskError.fuzzing_id,
                                                       TaskError.create_time, TaskError.data,
                                                       TaskError.name, TaskError.status,
                                                       TaskError.update_time, TaskError.comment).order_by(TaskError.status.desc(), TaskError.update_time.desc(), TaskError.id.desc()).all()
-        data_message = [{'id': error['id'], "fuzzing_id": error['fazzing_id'],
+        data_message = [{'id': error['id'], "fuzzing_id": error['fuzzing_id'],
                          "name": error['name'], "data": error['data'],
                          'create_time': error['create_time'].strftime('%Y-%m-%d %H:%M:%S'),
                          'update_time': error['update_time'].strftime('%Y-%m-%d %H:%M:%S'),
@@ -204,7 +204,7 @@ def New_fuzzing():
         # curd.set_error_status_to(list(map(lambda x: x.id, error_list)), db)
         # Fuzzing.query.filter_by(id=fuzz.id).delete()
         fuzz.data = {'error': "Clone repo Error"}
-        db.commit()
+        db.session.commit()
         return jsonify({"status": 0, "result": "", "msg": "Clone repo Error"})
 
     wamr_path_parent = fuzz_dir.parent.parent
@@ -277,7 +277,7 @@ def scheduler_run_task():
 
     for fuzz in fuzz_query:
         all_error = TaskError.query.filter(
-            TaskError.fazzing_id == fuzz.id).with_entities(TaskError.name).all()
+            TaskError.fuzzing_id == fuzz.id).with_entities(TaskError.name).all()
         fuzz_cmd = wasm_mutator_dir / \
             'workspace' / f'build_{fuzz.id}'
         dir_list = filter(lambda x: x.startswith(
@@ -287,7 +287,7 @@ def scheduler_run_task():
         for dir in dir_list:
             cmd = f'cd {fuzz_cmd} && ./wasm_mutator_fuzz {dir}'
             status, resp = getstatusoutput(cmd)
-            task_error = TaskError(name=dir, std_out=resp, fazzing_id=fuzz.id,
+            task_error = TaskError(name=dir, std_out=resp, fuzzing_id=fuzz.id,
                                    create_time=datetime.utcnow() + timedelta(hours=8))
             db.session.add(task_error)
             db.session.commit()
@@ -312,7 +312,7 @@ def get_error_txt():
         return jsonify({"status": 0, "results": [], 'msg': "Error"})
     error = TaskError.query.get(id)
     fuzz_cmd = wasm_mutator_dir / \
-        'workspace' / f'build_{error.fazzing_id}'
+        'workspace' / f'build_{error.fuzzing_id}'
     file_cmd = fuzz_cmd / error.name
 
     response = send_file(file_cmd, as_attachment=True,
@@ -351,7 +351,7 @@ def get_cases_zip():
     with ZipFile(memory_file, "w", ZIP_DEFLATED) as zf:
         for task_error in task_query:
             fuzz_cmd = wasm_mutator_dir / \
-                'workspace' / f'build_{task_error.fazzing_id}'
+                'workspace' / f'build_{task_error.fuzzing_id}'
             file_cmd = fuzz_cmd / task_error.name
             zf.write(str(file_cmd), arcname=task_error.name)
     memory_file.seek(0)
@@ -399,7 +399,7 @@ def error_restart():
     if run_status:
         return jsonify({"status": 0, "results": [], 'msg': "There are already tasks in progress"})
     task_query = TaskError.query.filter(TaskError.id.in_(id_list)).all()
-    fuzzing_id = task_query[0].fazzing_id
+    fuzzing_id = task_query[0].fuzzing_id
     fuzz_cmd = wasm_mutator_dir / \
         'workspace' / f'build_{fuzzing_id}'
     restart_cmd = wasm_mutator_dir / \
@@ -412,7 +412,7 @@ def error_restart():
     if not Path(restart_cmd / 'wamr').exists():
         print('------ error: clone repo not folder exists ------')
         # fuzz.data = {'error': "Clone repo Error"}
-        db.commit()
+        db.session.commit()
         return jsonify({"status": 0, "result": "", "msg": "Clone repo Error"})
     wamr_path_parent = fuzz_dir.parent.parent
     wamr_path = wamr_path_parent / 'wamr'

tests/fuzz/wasm-mutator-fuzz/wasm-mutator/CMakeLists.txt

@@ -58,7 +58,7 @@ add_executable(wasm_mutator_fuzz wasm_mutator_fuzz.cc)
 target_link_libraries(wasm_mutator_fuzz PRIVATE vmlib m)
 
 if(NOT IN_OSS_FUZZ)
-  message(STATUS "Enable ASan and UBSan in non-oss-fuzz environment")
+  message(STATUS "Enable ASan and UBSan in non-oss-fuzz environment for vmlib")
   target_compile_options(vmlib PUBLIC
     -fprofile-instr-generate -fcoverage-mapping
     -fno-sanitize-recover=all

tests/regression/ba-issues/README.md

@@ -218,22 +218,57 @@ simply run `run.py`
 ./run.py
 ```
 
+Specify a specific issue with option `--issues`/`-i`
+
+```shell
+./run.py --issues 2833         # test 1 issue #2833
+./run.py -i 2833,2834,2835     # test 3 issues #2833 #2834 #2835
+```
+
 If everything went well, you should see similarly output in your command line output
 
 ```shell
-Finish testing, 22/22 of test cases passed, no more issues should further test
+==== Test results ====
+   Total: 22
+  Passed: 22
+  Failed: 0
+  Left issues in folder: no more
+  Cases in JSON but not found in folder: no more
 ```
 
 If you add the test case under directory `issues` but forget to add the running config in json file, the output can be something like
 
 ```shell
-Finish testing, 21/21 of test cases passed, {2945} issue(s) should further test
+==== Test results ====
+   Total: 21
+  Passed: 21
+  Failed: 0
+  missed: 0
+  Left issues in folder: #3022
+  Cases in JSON but not found in folder: no more
+```
+
+If you add the test case in `running_config.json` but used the wrong id or forget to add the test case under directory `issues`, the output can be someting like
+
+```shell
+==== Test results ====
+   Total: 21
+  Passed: 21
+  Failed: 0
+  missed: 0
+  Left issues in folder: #2855
+  Cases in JSON but not found in folder: #12345
 ```
 
 If some test case are failing, then it will be something like
 
 ```shell
-Finish testing, 21/22 of test cases passed, no more issue(s) should further test
+==== Test results ====
+   Total: 22
+  Passed: 21
+  Failed: 1
+  Left issues in folder: no more
+  Cases in JSON but not found in folder: no more
 ```
 
 And a log file named `issues_tests.log` will be generated and inside it will display the details of the failing cases, for example:

tests/regression/ba-issues/run.py

@@ -10,7 +10,9 @@ import os
 import subprocess
 import glob
 import re
-from typing import Dict
+import argparse
+
+from typing import Dict, Optional, List
 
 WORK_DIR = os.getcwd()
 TEST_WASM_COMMAND = (
@@ -45,7 +47,12 @@ def dump_error_log(failing_issue_id, command_lists, exit_code_cmp, stdout_cmp):
         )
 
 
-def get_issue_ids_should_test():
+def get_issue_ids_should_test(selected_ids: Optional[List[int]] = None):
+    """Find all issue IDs that should be tested in folder issues."""
+    # If specific issue IDs are provided, return them as a set
+    if selected_ids:
+        return set(selected_ids)
+
     # Define the path pattern
     path_pattern = "issues/issue-*"
 
@@ -60,8 +67,8 @@ def get_issue_ids_should_test():
         # Extract the issue number using regular expression
         match = re.search(pattern, dir_path)
         if match:
-            issue_number = match.group(1)
-            issue_numbers.add(int(issue_number))
+            issue_number = int(match.group(1))
+            issue_numbers.add(issue_number)
 
     # Print the set of issue numbers
     return issue_numbers
@@ -77,10 +84,10 @@ def get_and_check(d, key, default=None, nullable=False):
 
 
 def run_and_compare_results(
-    passed_ids, failed_ids, issue_id, cmd, description, ret_code, stdout_content
-):
+    issue_id, cmd, description, ret_code, stdout_content
+) -> bool:
     print(f"####################################")
-    print(f"test BA issue #{issue_id} `{description}`: {cmd}")
+    print(f"test BA issue #{issue_id} `{description}`...")
     command_list = cmd.split()
     result = subprocess.run(
         command_list,
@@ -95,19 +102,21 @@ def run_and_compare_results(
 
     exit_code_cmp = f"exit code (actual, expected) : {actual_exit_code, ret_code}"
     stdout_cmp = f"stdout (actual, expected) : {actual_output, stdout_content}"
-    print(exit_code_cmp)
-    print(stdout_cmp)
 
     if actual_exit_code == ret_code and (
         actual_output == stdout_content
-        or (stdout_content == "Compile success"
-            and actual_output.find(stdout_content) != -1)
+        or (
+            stdout_content == "Compile success"
+            and actual_output.find(stdout_content) != -1
+        )
         or (len(stdout_content) > 30 and actual_output.find(stdout_content) != -1)
     ):
-        passed_ids.add(issue_id)
         print("== PASS ==")
+        return True
     else:
-        failed_ids.add(issue_id)
+        print(cmd)
+        print(exit_code_cmp)
+        print(stdout_cmp)
         print(f"== FAILED: {issue_id} ==")
         dump_error_log(
             issue_id,
@@ -115,15 +124,11 @@ def run_and_compare_results(
             exit_code_cmp,
             stdout_cmp,
         )
-
-    print("")
+        return False
 
 
-def run_issue_test_wamrc(
-    passed_ids, failed_ids, issue_id, compile_options, stdout_only_cmp_last_line=False
-):
+def run_issue_test_wamrc(issue_id, compile_options):
     compiler = get_and_check(compile_options, "compiler")
-    only_compile = get_and_check(compile_options, "only compile")
     in_file = get_and_check(compile_options, "in file")
     out_file = get_and_check(compile_options, "out file")
     options = get_and_check(compile_options, "options")
@@ -145,14 +150,10 @@ def run_issue_test_wamrc(
         compiler=compiler, options=options, out_file=out_file_path, in_file=in_file_path
     )
 
-    run_and_compare_results(
-        passed_ids, failed_ids, issue_id, cmd, description, ret_code, stdout_content
-    )
-
-    return only_compile
+    return run_and_compare_results(issue_id, cmd, description, ret_code, stdout_content)
 
 
-def run_issue_test_iwasm(passed_ids, failed_ids, issue_id, test_case):
+def run_issue_test_iwasm(issue_id, test_case) -> bool:
     runtime = get_and_check(test_case, "runtime")
     mode = get_and_check(test_case, "mode")
     file = get_and_check(test_case, "file")
@@ -194,17 +195,19 @@ def run_issue_test_iwasm(passed_ids, failed_ids, issue_id, test_case):
             argument=argument,
         )
 
-    run_and_compare_results(
-        passed_ids, failed_ids, issue_id, cmd, description, ret_code, stdout_content
-    )
+    return run_and_compare_results(issue_id, cmd, description, ret_code, stdout_content)
 
 
-def process_and_run_test_cases(data: Dict[str, Dict]):
-    issue_ids_should_test = get_issue_ids_should_test()
+def process_and_run_test_cases(
+    data: Dict[str, Dict], selected_ids: Optional[List[int]] = None
+):
+    issue_ids_should_test = get_issue_ids_should_test(selected_ids)
 
     passed_ids = set()
     failed_ids = set()
+    json_only_ids = set()
 
+    # Iterate through each test case in the json data
     for test_case in data.get("test cases", []):
         is_deprecated = get_and_check(test_case, "deprecated")
         issue_ids = get_and_check(test_case, "ids", default=[])
@@ -214,33 +217,79 @@ def process_and_run_test_cases(data: Dict[str, Dict]):
             continue
 
         compile_options = get_and_check(test_case, "compile_options", nullable=True)
-        for issue_id in issue_ids:
-            only_compile = False
-            # if this issue needs to test wamrc to compile the test case first
-            if compile_options:
-                only_compile = compile_options["only compile"]
-                run_issue_test_wamrc(passed_ids, failed_ids, issue_id, compile_options)
 
-            # if this issue requires to test iwasm to run the test case
-            if not only_compile:
-                run_issue_test_iwasm(passed_ids, failed_ids, issue_id, test_case)
+        for issue_id in issue_ids:
+            if issue_id not in issue_ids_should_test:
+                json_only_ids.add(issue_id)
+                continue
 
             # cross out the this issue_id in the should test set
             issue_ids_should_test.remove(issue_id)
 
+            only_compile = False
+
+            # if this issue needs to test wamrc to compile the test case first
+            if compile_options:
+                only_compile = compile_options["only compile"]
+                compile_res = run_issue_test_wamrc(issue_id, compile_options)
+                if only_compile:
+                    if compile_res:
+                        passed_ids.add(issue_id)
+                    else:
+                        failed_ids.add(issue_id)
+                    continue
+                else:
+                    # if compile success, then continue to test iwasm
+                    if not compile_res:
+                        failed_ids.add(issue_id)
+                        continue
+
+            # if this issue requires to test iwasm to run the test case
+            if not only_compile:
+                if run_issue_test_iwasm(issue_id, test_case):
+                    passed_ids.add(issue_id)
+                else:
+                    failed_ids.add(issue_id)
+
     total = len(passed_ids) + len(failed_ids)
     passed = len(passed_ids)
     failed = len(failed_ids)
-    issue_ids_should_test = (
-        issue_ids_should_test if issue_ids_should_test else "no more"
+
+    format_issue_ids_should_test = (
+        " ".join(f"#{x}" for x in issue_ids_should_test)
+        if issue_ids_should_test
+        else "no more"
     )
+    format_json_only_ids = (
+        " ".join(f"#{x}" for x in json_only_ids) if json_only_ids else "no more"
+    )
+
+    print(f"####################################")
     print(f"==== Test results ====")
-    print(f"  Total: {total}")
+    print(f"   Total: {total}")
     print(f"  Passed: {passed}")
     print(f"  Failed: {failed}")
+    if not selected_ids:
+        print(f"  Left issues in folder: {format_issue_ids_should_test}")
+        print(f"  Cases in JSON but not found in folder: {format_json_only_ids}")
+    else:
+        print(f"  Issues not found in folder: {format_issue_ids_should_test}")
 
 
 def main():
+    parser = argparse.ArgumentParser(description="Run BA issue tests.")
+    parser.add_argument(
+        "-i",
+        "--issues",
+        type=str,
+        help="Comma separated list of issue ids to run, e.g. 1,2,3. Default: all.",
+    )
+    args = parser.parse_args()
+
+    selected_ids = None
+    if args.issues:
+        selected_ids = [int(x) for x in args.issues.split(",") if x.strip().isdigit()]
+
     # Path to the JSON file
     file_path = "running_config.json"
 
@@ -256,7 +305,7 @@ def main():
         os.remove(LOG_FILE)
 
     # Process the data
-    process_and_run_test_cases(data)
+    process_and_run_test_cases(data, selected_ids)
 
 
 if __name__ == "__main__":