Generate jitdump to support linux perf for LLVM JIT (bytecodealliance…

…#2788)

build-scripts/build_llvm.py

@@ -67,8 +67,8 @@ def build_llvm(llvm_dir, platform, backends, projects, use_clang=False, extra_fl
         "-DLLVM_INCLUDE_EXAMPLES:BOOL=OFF",
         "-DLLVM_INCLUDE_UTILS:BOOL=OFF",
         "-DLLVM_INCLUDE_TESTS:BOOL=OFF",
-        "-DLLVM_BUILD_TESTS:BOOL=OFF",
         "-DLLVM_OPTIMIZED_TABLEGEN:BOOL=ON",
+        "-DLLVM_USE_PERF:BOOL=ON",
     ]
 
     # use clang/clang++/lld. but macos doesn't support lld
@@ -255,7 +255,7 @@ def main():
             "branch": "release/15.x",
         },
         "xtensa": {
-            "repo": "https://github.com/espressif/llvm-project.git", 
+            "repo": "https://github.com/espressif/llvm-project.git",
             "repo_ssh": "git@github.com:espressif/llvm-project.git",
             "branch": "xtensa_release_15.x",
         },
@@ -281,13 +281,13 @@ def main():
             commit_hash = query_llvm_version(llvm_info)
             print(commit_hash)
             return commit_hash is not None
-        
+
         repo_addr = llvm_info["repo"]
         if os.environ.get('USE_GIT_SSH') == "true":
             repo_addr = llvm_info["repo_ssh"]
         else:
             print("To use ssh for git clone, run: export USE_GIT_SSH=true")
-        
+
         llvm_dir = clone_llvm(deps_dir, repo_addr, llvm_info["branch"])
         if (
             build_llvm(

core/iwasm/common/wasm_runtime_common.c

@@ -158,7 +158,7 @@ static JitCompOptions jit_options = { 0 };
 #endif
 
 #if WASM_ENABLE_JIT != 0
-static LLVMJITOptions llvm_jit_options = { 3, 3, 0 };
+static LLVMJITOptions llvm_jit_options = { 3, 3, 0, false };
 #endif
 
 static RunningMode runtime_running_mode = Mode_Default;
@@ -662,9 +662,14 @@ wasm_runtime_full_init(RuntimeInitArgs *init_args)
 #endif
 
 #if WASM_ENABLE_JIT != 0
+    LOG_DEBUG("Start LLVM_JIT, opt_sz=%u, opt_lvl=%u, segue=%s, linux_perf=%s",
+              init_args->llvm_jit_size_level, init_args->llvm_jit_opt_level,
+              init_args->segue_flags ? "Yes" : "No",
+              init_args->linux_perf_support ? "Yes" : "No");
     llvm_jit_options.size_level = init_args->llvm_jit_size_level;
     llvm_jit_options.opt_level = init_args->llvm_jit_opt_level;
     llvm_jit_options.segue_flags = init_args->segue_flags;
+    llvm_jit_options.linux_perf_support = init_args->linux_perf_support;
 #endif
 
     if (!wasm_runtime_env_init()) {

core/iwasm/common/wasm_runtime_common.h

@@ -430,6 +430,7 @@ typedef struct LLVMJITOptions {
     uint32 opt_level;
     uint32 size_level;
     uint32 segue_flags;
+    bool linux_perf_support;
 } LLVMJITOptions;
 #endif
 

core/iwasm/compilation/aot_llvm.c

@@ -653,6 +653,19 @@ aot_add_llvm_func(AOTCompContext *comp_ctx, LLVMModuleRef module,
                                 attr_no_jump_tables);
     }
 
+    /* spread fp.all to every function */
+    if (comp_ctx->emit_frame_pointer) {
+        const char *key = "frame-pointer";
+        const char *val = "all";
+        LLVMAttributeRef no_omit_fp = LLVMCreateStringAttribute(
+            comp_ctx->context, key, strlen(key), val, strlen(val));
+        if (!no_omit_fp) {
+            aot_set_last_error("create LLVM attribute (frame-pointer) failed.");
+            goto fail;
+        }
+        LLVMAddAttributeAtIndex(func, LLVMAttributeFunctionIndex, no_omit_fp);
+    }
+
     if (need_precheck) {
         if (!comp_ctx->is_jit_mode)
             LLVMSetLinkage(func, LLVMInternalLinkage);
@@ -2160,7 +2173,7 @@ jit_stack_size_callback(void *user_data, const char *name, size_t namelen,
 }
 
 static bool
-orc_jit_create(AOTCompContext *comp_ctx)
+orc_jit_create(AOTCompContext *comp_ctx, bool linux_perf_support)
 {
     LLVMErrorRef err;
     LLVMOrcLLLazyJITRef orc_jit = NULL;
@@ -2200,6 +2213,14 @@ orc_jit_create(AOTCompContext *comp_ctx)
     /* Ownership transfer: LLVMOrcLLJITBuilderRef -> LLVMOrcLLJITRef */
     builder = NULL;
 
+    if (linux_perf_support) {
+        LOG_DEBUG("Enable linux perf support");
+        LLVMOrcObjectLayerRef obj_linking_layer =
+            (LLVMOrcObjectLayerRef)LLVMOrcLLLazyJITGetObjLinkingLayer(orc_jit);
+        LLVMOrcRTDyldObjectLinkingLayerRegisterJITEventListener(
+            obj_linking_layer, LLVMCreatePerfJITEventListener());
+    }
+
     /* Ownership transfer: local -> AOTCompContext */
     comp_ctx->orc_jit = orc_jit;
     orc_jit = NULL;
@@ -2298,6 +2319,17 @@ aot_create_comp_context(const AOTCompData *comp_data, aot_comp_option_t option)
         goto fail;
     }
 
+    if (option->linux_perf_support) {
+        /* FramePointerKind.All */
+        LLVMMetadataRef val =
+            LLVMValueAsMetadata(LLVMConstInt(LLVMInt32Type(), 2, false));
+        const char *key = "frame-pointer";
+        LLVMAddModuleFlag(comp_ctx->module, LLVMModuleFlagBehaviorWarning, key,
+                          strlen(key), val);
+
+        comp_ctx->emit_frame_pointer = true;
+    }
+
     if (BH_LIST_ERROR == bh_list_init(&comp_ctx->native_symbols)) {
         goto fail;
     }
@@ -2401,7 +2433,7 @@ aot_create_comp_context(const AOTCompData *comp_data, aot_comp_option_t option)
             goto fail;
 
         /* Create LLJIT Instance */
-        if (!orc_jit_create(comp_ctx))
+        if (!orc_jit_create(comp_ctx, option->linux_perf_support))
             goto fail;
     }
     else {

core/iwasm/compilation/aot_llvm.h

@@ -12,6 +12,7 @@
 #include "llvm-c/Target.h"
 #include "llvm-c/Core.h"
 #include "llvm-c/Object.h"
+#include "llvm-c/OrcEE.h"
 #include "llvm-c/ExecutionEngine.h"
 #include "llvm-c/Analysis.h"
 #include "llvm-c/BitWriter.h"
@@ -422,6 +423,8 @@ typedef struct AOTCompContext {
     char stack_usage_temp_file[64];
     const char *llvm_passes;
     const char *builtin_intrinsics;
+
+    bool emit_frame_pointer;
 } AOTCompContext;
 
 enum {
@@ -431,6 +434,7 @@ enum {
     AOT_LLVMIR_OPT_FILE,
 };
 
+/* always sync it with AOTCompOption in aot_export.h */
 typedef struct AOTCompOption {
     bool is_jit_mode;
     bool is_indirect_mode;
@@ -457,6 +461,7 @@ typedef struct AOTCompOption {
     uint32 bounds_checks;
     uint32 stack_bounds_checks;
     uint32 segue_flags;
+    bool linux_perf_support;
     char **custom_sections;
     uint32 custom_sections_count;
     const char *stack_usage_file;

core/iwasm/compilation/aot_orc_extra.cpp

@@ -12,11 +12,13 @@
 #include "llvm/ADT/None.h"
 #include "llvm/ADT/Optional.h"
 #endif
+#include "llvm/ExecutionEngine/JITEventListener.h"
+#include "llvm/ExecutionEngine/Orc/CompileOnDemandLayer.h"
 #include "llvm/ExecutionEngine/Orc/JITTargetMachineBuilder.h"
 #include "llvm/ExecutionEngine/Orc/LLJIT.h"
+#include "llvm/ExecutionEngine/Orc/ObjectLinkingLayer.h"
 #include "llvm/ExecutionEngine/Orc/ObjectTransformLayer.h"
 #include "llvm/ExecutionEngine/Orc/RTDyldObjectLinkingLayer.h"
-#include "llvm/ExecutionEngine/Orc/CompileOnDemandLayer.h"
 #include "llvm/ExecutionEngine/SectionMemoryManager.h"
 #include "llvm/Support/CBindingWrapping.h"
 
@@ -108,6 +110,7 @@ DEFINE_SIMPLE_CONVERSION_FUNCTIONS(ObjectTransformLayer,
                                    LLVMOrcObjectTransformLayerRef)
 DEFINE_SIMPLE_CONVERSION_FUNCTIONS(OrcV2CAPIHelper::PoolEntry,
                                    LLVMOrcSymbolStringPoolEntryRef)
+DEFINE_SIMPLE_CONVERSION_FUNCTIONS(ObjectLayer, LLVMOrcObjectLayerRef)
 DEFINE_SIMPLE_CONVERSION_FUNCTIONS(SymbolStringPool, LLVMOrcSymbolStringPoolRef)
 DEFINE_SIMPLE_CONVERSION_FUNCTIONS(ThreadSafeModule, LLVMOrcThreadSafeModuleRef)
 
@@ -322,3 +325,9 @@ LLVMOrcLLLazyJITGetObjTransformLayer(LLVMOrcLLLazyJITRef J)
 {
     return wrap(&unwrap(J)->getObjTransformLayer());
 }
+
+LLVMOrcObjectLayerRef
+LLVMOrcLLLazyJITGetObjLinkingLayer(LLVMOrcLLLazyJITRef J)
+{
+    return wrap(&unwrap(J)->getObjLinkingLayer());
+}

core/iwasm/compilation/aot_orc_extra.h

@@ -76,5 +76,8 @@ LLVMOrcLLJITBuilderSetCompileFuncitonCreatorWithStackSizesCallback(
     LLVMOrcLLLazyJITBuilderRef Builder,
     void (*cb)(void *, const char *, size_t, size_t), void *cb_data);
 
+LLVMOrcObjectLayerRef
+LLVMOrcLLLazyJITGetObjLinkingLayer(LLVMOrcLLLazyJITRef J);
+
 LLVM_C_EXTERN_C_END
 #endif

core/iwasm/fast-jit/jit_compiler.h

@@ -70,6 +70,7 @@ typedef struct JitInterpSwitchInfo {
 typedef struct JitCompOptions {
     uint32 code_cache_size;
     uint32 opt_level;
+    bool linux_perf_support;
 } JitCompOptions;
 
 bool

core/iwasm/include/aot_export.h

@@ -38,6 +38,7 @@ enum {
     AOT_LLVMIR_OPT_FILE,
 };
 
+/* always sync it with AOTCompOption in compilation/aot_llvm.h */
 typedef struct AOTCompOption {
     bool is_jit_mode;
     bool is_indirect_mode;
@@ -64,6 +65,7 @@ typedef struct AOTCompOption {
     uint32_t bounds_checks;
     uint32_t stack_bounds_checks;
     uint32_t segue_flags;
+    bool linux_perf_support;
     char **custom_sections;
     uint32_t custom_sections_count;
     const char *stack_usage_file;

core/iwasm/include/wasm_export.h

@@ -169,6 +169,15 @@ typedef struct RuntimeInitArgs {
     uint32_t llvm_jit_size_level;
     /* Segue optimization flags for LLVM JIT */
     uint32_t segue_flags;
+    /**
+     * If enabled
+     * - llvm-jit will output a jitdump file for `perf inject`
+     * - aot. TBD
+     * - fast-jit. TBD
+     * - multi-tier-jit. TBD
+     * - interpreter. TBD
+     */
+    bool linux_perf_support;
 } RuntimeInitArgs;
 
 #ifndef WASM_VALKIND_T_DEFINED
@@ -945,7 +954,7 @@ wasm_runtime_get_custom_data(wasm_module_inst_t module_inst);
 
 /**
  * Set the memory bounds checks flag of a WASM module instance.
- * 
+ *
  * @param module_inst the WASM module instance
  * @param enable the flag to enable/disable the memory bounds checks
  */
@@ -954,9 +963,8 @@ wasm_runtime_set_bounds_checks(wasm_module_inst_t module_inst,
                                bool enable);
 /**
  * Check if the memory bounds checks flag is enabled for a WASM module instance.
- * 
- * @param module_inst the WASM module instance
  *
+ * @param module_inst the WASM module instance
  * @return true if the memory bounds checks flag is enabled, false otherwise
  */
 WASM_RUNTIME_API_EXTERN bool

core/iwasm/interpreter/wasm_loader.c

@@ -2878,6 +2878,7 @@ init_llvm_jit_functions_stage1(WASMModule *module, char *error_buf,
     option.opt_level = llvm_jit_options.opt_level;
     option.size_level = llvm_jit_options.size_level;
     option.segue_flags = llvm_jit_options.segue_flags;
+    option.linux_perf_support = llvm_jit_options.linux_perf_support;
 
 #if WASM_ENABLE_BULK_MEMORY != 0
     option.enable_bulk_memory = true;

core/iwasm/interpreter/wasm_mini_loader.c

@@ -1877,6 +1877,7 @@ init_llvm_jit_functions_stage1(WASMModule *module, char *error_buf,
     option.opt_level = llvm_jit_options.opt_level;
     option.size_level = llvm_jit_options.size_level;
     option.segue_flags = llvm_jit_options.segue_flags;
+    option.linux_perf_support = llvm_jit_options.linux_perf_support;
 
 #if WASM_ENABLE_BULK_MEMORY != 0
     option.enable_bulk_memory = true;