format chore

Signed-off-by: varun-r-mallya <varunrmallya@gmail.com>

examples/sys_sync.py

@@ -21,17 +21,17 @@ def last() -> HashMap:
 @section("tracepoint/syscalls/sys_enter_sync")
 def do_trace(ctx: c_void_p) -> c_int64:
     key = 0
-    tsp = last().lookup(key)
+    tsp = last.lookup(key)
     if tsp:
         kt = ktime()
         delta = kt - tsp
         if delta < 1000000000:
             time_ms = delta // 1000000
             print(f"sync called within last second, last {time_ms} ms ago")
-        last().delete(key)
+        last.delete(key)
     else:
         kt = ktime()
-        last().update(key, kt)
+        last.update(key, kt)
     return c_int64(0)
 
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pythonbpf"
-version = "0.1.3"
+version = "0.1.4"
 description = "Reduced Python frontend for eBPF"
 authors = [
   { name = "r41k0u", email="pragyanshchaturvedi18@gmail.com" },

pythonbpf/binary_ops.py

@@ -1,71 +1,66 @@
 import ast
 from llvmlite import ir
+from logging import Logger
+import logging
+
+logger: Logger = logging.getLogger(__name__)
 
 
 def recursive_dereferencer(var, builder):
     """dereference until primitive type comes out"""
-    if var.type == ir.PointerType(ir.PointerType(ir.IntType(64))):
+    # TODO: Not worrying about stack overflow for now
+    if isinstance(var.type, ir.PointerType):
         a = builder.load(var)
         return recursive_dereferencer(a, builder)
-    elif var.type == ir.PointerType(ir.IntType(64)):
-        a = builder.load(var)
-        return recursive_dereferencer(a, builder)
-    elif var.type == ir.IntType(64):
+    elif isinstance(var.type, ir.IntType):
         return var
     else:
         raise TypeError(f"Unsupported type for dereferencing: {var.type}")
 
 
-def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab, func):
-    print(module)
-    left = rval.left
-    right = rval.right
+def get_operand_value(operand, module, builder, local_sym_tab):
+    """Extract the value from an operand, handling variables and constants."""
+    if isinstance(operand, ast.Name):
+        if operand.id in local_sym_tab:
+            return recursive_dereferencer(local_sym_tab[operand.id].var, builder)
+        raise ValueError(f"Undefined variable: {operand.id}")
+    elif isinstance(operand, ast.Constant):
+        if isinstance(operand.value, int):
+            return ir.Constant(ir.IntType(64), operand.value)
+        raise TypeError(f"Unsupported constant type: {type(operand.value)}")
+    elif isinstance(operand, ast.BinOp):
+        return handle_binary_op_impl(operand, module, builder, local_sym_tab)
+    raise TypeError(f"Unsupported operand type: {type(operand)}")
+
+
+def handle_binary_op_impl(rval, module, builder, local_sym_tab):
     op = rval.op
+    left = get_operand_value(rval.left, module, builder, local_sym_tab)
+    right = get_operand_value(rval.right, module, builder, local_sym_tab)
+    logger.info(f"left is {left}, right is {right}, op is {op}")
 
-    # Handle left operand
-    if isinstance(left, ast.Name):
-        if left.id in local_sym_tab:
-            left = recursive_dereferencer(local_sym_tab[left.id].var, builder)
-        else:
-            raise SyntaxError(f"Undefined variable: {left.id}")
-    elif isinstance(left, ast.Constant):
-        left = ir.Constant(ir.IntType(64), left.value)
-    else:
-        raise SyntaxError("Unsupported left operand type")
+    # Map AST operation nodes to LLVM IR builder methods
+    op_map = {
+        ast.Add: builder.add,
+        ast.Sub: builder.sub,
+        ast.Mult: builder.mul,
+        ast.Div: builder.sdiv,
+        ast.Mod: builder.srem,
+        ast.LShift: builder.shl,
+        ast.RShift: builder.lshr,
+        ast.BitOr: builder.or_,
+        ast.BitXor: builder.xor,
+        ast.BitAnd: builder.and_,
+        ast.FloorDiv: builder.udiv,
+    }
 
-    if isinstance(right, ast.Name):
-        if right.id in local_sym_tab:
-            right = recursive_dereferencer(local_sym_tab[right.id].var, builder)
-        else:
-            raise SyntaxError(f"Undefined variable: {right.id}")
-    elif isinstance(right, ast.Constant):
-        right = ir.Constant(ir.IntType(64), right.value)
-    else:
-        raise SyntaxError("Unsupported right operand type")
-
-    print(f"left is {left}, right is {right}, op is {op}")
-
-    if isinstance(op, ast.Add):
-        builder.store(builder.add(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.Sub):
-        builder.store(builder.sub(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.Mult):
-        builder.store(builder.mul(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.Div):
-        builder.store(builder.sdiv(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.Mod):
-        builder.store(builder.srem(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.LShift):
-        builder.store(builder.shl(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.RShift):
-        builder.store(builder.lshr(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.BitOr):
-        builder.store(builder.or_(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.BitXor):
-        builder.store(builder.xor(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.BitAnd):
-        builder.store(builder.and_(left, right), local_sym_tab[var_name].var)
-    elif isinstance(op, ast.FloorDiv):
-        builder.store(builder.udiv(left, right), local_sym_tab[var_name].var)
+    if type(op) in op_map:
+        result = op_map[type(op)](left, right)
+        return result
     else:
         raise SyntaxError("Unsupported binary operation")
+
+
+def handle_binary_op(rval, module, builder, var_name, local_sym_tab):
+    result = handle_binary_op_impl(rval, module, builder, local_sym_tab)
+    builder.store(result, local_sym_tab[var_name].var)

pythonbpf/codegen.py

@@ -4,16 +4,24 @@ from .license_pass import license_processing
 from .functions_pass import func_proc
 from .maps import maps_proc
 from .structs import structs_proc
-from .globals_pass import globals_processing
-from .debuginfo import DW_LANG_C11, DwarfBehaviorEnum
+from .globals_pass import (
+    globals_list_creation,
+    globals_processing,
+    populate_global_symbol_table,
+)
+from .debuginfo import DW_LANG_C11, DwarfBehaviorEnum, DebugInfoGenerator
 import os
 import subprocess
 import inspect
 from pathlib import Path
 from pylibbpf import BpfProgram
 import tempfile
+from logging import Logger
+import logging
 
-VERSION = "v0.1.3"
+logger: Logger = logging.getLogger(__name__)
+
+VERSION = "v0.1.4"
 
 
 def find_bpf_chunks(tree):
@@ -30,21 +38,27 @@ def find_bpf_chunks(tree):
 
 def processor(source_code, filename, module):
     tree = ast.parse(source_code, filename)
-    print(ast.dump(tree, indent=4))
+    logger.debug(ast.dump(tree, indent=4))
 
     bpf_chunks = find_bpf_chunks(tree)
     for func_node in bpf_chunks:
-        print(f"Found BPF function/struct: {func_node.name}")
+        logger.info(f"Found BPF function/struct: {func_node.name}")
+
+    populate_global_symbol_table(tree, module)
+    license_processing(tree, module)
+    globals_processing(tree, module)
 
     structs_sym_tab = structs_proc(tree, module, bpf_chunks)
     map_sym_tab = maps_proc(tree, module, bpf_chunks)
     func_proc(tree, module, bpf_chunks, map_sym_tab, structs_sym_tab)
 
-    license_processing(tree, module)
-    globals_processing(tree, module)
+    globals_list_creation(tree, module)
 
 
-def compile_to_ir(filename: str, output: str):
+def compile_to_ir(filename: str, output: str, loglevel=logging.WARNING):
+    logging.basicConfig(
+        level=loglevel, format="%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+    )
     with open(filename) as f:
         source = f.read()
 
@@ -53,33 +67,17 @@ def compile_to_ir(filename: str, output: str):
     module.triple = "bpf"
 
     if not hasattr(module, "_debug_compile_unit"):
-        module._file_metadata = module.add_debug_info(
-            "DIFile",
-            {  # type: ignore
-                "filename": filename,
-                "directory": os.path.dirname(filename),
-            },
+        debug_generator = DebugInfoGenerator(module)
+        debug_generator.generate_file_metadata(filename, os.path.dirname(filename))
+        debug_generator.generate_debug_cu(
+            DW_LANG_C11,
+            f"PythonBPF {VERSION}",
+            True,  # TODO: This is probably not true
+            # TODO: add a global field here that keeps track of all the globals. Works without it, but I think it might
+            # be required for kprobes.
+            True,
         )
 
-        module._debug_compile_unit = module.add_debug_info(
-            "DICompileUnit",
-            {  # type: ignore
-                "language": DW_LANG_C11,
-                "file": module._file_metadata,  # type: ignore
-                "producer": f"PythonBPF {VERSION}",
-                "isOptimized": True,  # TODO: This is probably not true
-                # TODO: add a global field here that keeps track of all the globals. Works without it, but I think it might
-                # be required for kprobes.
-                "runtimeVersion": 0,
-                "emissionKind": 1,
-                "splitDebugInlining": False,
-                "nameTableKind": 0,
-            },
-            is_distinct=True,
-        )
-
-        module.add_named_metadata("llvm.dbg.cu", module._debug_compile_unit)  # type: ignore
-
     processor(source, filename, module)
 
     wchar_size = module.add_metadata(
@@ -121,7 +119,7 @@ def compile_to_ir(filename: str, output: str):
 
     module.add_named_metadata("llvm.ident", [f"PythonBPF {VERSION}"])
 
-    print(f"IR written to {output}")
+    logger.info(f"IR written to {output}")
     with open(output, "w") as f:
         f.write(f'source_filename = "{filename}"\n')
         f.write(str(module))
@@ -130,7 +128,7 @@ def compile_to_ir(filename: str, output: str):
     return output
 
 
-def compile() -> bool:
+def compile(loglevel=logging.WARNING) -> bool:
     # Look one level up the stack to the caller of this function
     caller_frame = inspect.stack()[1]
     caller_file = Path(caller_frame.filename).resolve()
@@ -139,7 +137,9 @@ def compile() -> bool:
     o_file = caller_file.with_suffix(".o")
 
     success = True
-    success = compile_to_ir(str(caller_file), str(ll_file)) and success
+    success = (
+        compile_to_ir(str(caller_file), str(ll_file), loglevel=loglevel) and success
+    )
 
     success = bool(
         subprocess.run(
@@ -157,11 +157,11 @@ def compile() -> bool:
         and success
     )
 
-    print(f"Object written to {o_file}")
+    logger.info(f"Object written to {o_file}")
     return success
 
 
-def BPF() -> BpfProgram:
+def BPF(loglevel=logging.WARNING) -> BpfProgram:
     caller_frame = inspect.stack()[1]
     src = inspect.getsource(caller_frame.frame)
     with tempfile.NamedTemporaryFile(
@@ -174,7 +174,7 @@ def BPF() -> BpfProgram:
         f.write(src)
         f.flush()
         source = f.name
-        compile_to_ir(source, str(inter.name))
+        compile_to_ir(source, str(inter.name), loglevel=loglevel)
         subprocess.run(
             [
                 "llc",

pythonbpf/debuginfo/debug_info_generator.py

@@ -12,6 +12,34 @@ class DebugInfoGenerator:
         self.module = module
         self._type_cache = {}  # Cache for common debug types
 
+    def generate_file_metadata(self, filename, dirname):
+        self.module._file_metadata = self.module.add_debug_info(
+            "DIFile",
+            {  # type: ignore
+                "filename": filename,
+                "directory": dirname,
+            },
+        )
+
+    def generate_debug_cu(
+        self, language, producer: str, is_optimized: bool, is_distinct: bool
+    ):
+        self.module._debug_compile_unit = self.module.add_debug_info(
+            "DICompileUnit",
+            {  # type: ignore
+                "language": language,
+                "file": self.module._file_metadata,  # type: ignore
+                "producer": producer,
+                "isOptimized": is_optimized,
+                "runtimeVersion": 0,
+                "emissionKind": 1,
+                "splitDebugInlining": False,
+                "nameTableKind": 0,
+            },
+            is_distinct=is_distinct,
+        )
+        self.module.add_named_metadata("llvm.dbg.cu", self.module._debug_compile_unit)  # type: ignore
+
     def get_basic_type(self, name: str, size: int, encoding: int) -> Any:
         """Get or create a basic type with caching"""
         key = (name, size, encoding)

pythonbpf/expr_pass.py

@@ -1,5 +1,91 @@
 import ast
 from llvmlite import ir
+from logging import Logger
+import logging
+from typing import Dict
+
+logger: Logger = logging.getLogger(__name__)
+
+
+def _handle_name_expr(expr: ast.Name, local_sym_tab: Dict, builder: ir.IRBuilder):
+    """Handle ast.Name expressions."""
+    if expr.id in local_sym_tab:
+        var = local_sym_tab[expr.id].var
+        val = builder.load(var)
+        return val, local_sym_tab[expr.id].ir_type
+    else:
+        logger.info(f"Undefined variable {expr.id}")
+        return None
+
+
+def _handle_constant_expr(expr: ast.Constant):
+    """Handle ast.Constant expressions."""
+    if isinstance(expr.value, int):
+        return ir.Constant(ir.IntType(64), expr.value), ir.IntType(64)
+    elif isinstance(expr.value, bool):
+        return ir.Constant(ir.IntType(1), int(expr.value)), ir.IntType(1)
+    else:
+        logger.info("Unsupported constant type")
+        return None
+
+
+def _handle_attribute_expr(
+    expr: ast.Attribute,
+    local_sym_tab: Dict,
+    structs_sym_tab: Dict,
+    builder: ir.IRBuilder,
+):
+    """Handle ast.Attribute expressions for struct field access."""
+    if isinstance(expr.value, ast.Name):
+        var_name = expr.value.id
+        attr_name = expr.attr
+        if var_name in local_sym_tab:
+            var_ptr, var_type, var_metadata = local_sym_tab[var_name]
+            logger.info(f"Loading attribute {attr_name} from variable {var_name}")
+            logger.info(f"Variable type: {var_type}, Variable ptr: {var_ptr}")
+
+            metadata = structs_sym_tab[var_metadata]
+            if attr_name in metadata.fields:
+                gep = metadata.gep(builder, var_ptr, attr_name)
+                val = builder.load(gep)
+                field_type = metadata.field_type(attr_name)
+                return val, field_type
+    return None
+
+
+def _handle_deref_call(expr: ast.Call, local_sym_tab: Dict, builder: ir.IRBuilder):
+    """Handle deref function calls."""
+    logger.info(f"Handling deref {ast.dump(expr)}")
+    if len(expr.args) != 1:
+        logger.info("deref takes exactly one argument")
+        return None
+
+    arg = expr.args[0]
+    if (
+        isinstance(arg, ast.Call)
+        and isinstance(arg.func, ast.Name)
+        and arg.func.id == "deref"
+    ):
+        logger.info("Multiple deref not supported")
+        return None
+
+    if isinstance(arg, ast.Name):
+        if arg.id in local_sym_tab:
+            arg_ptr = local_sym_tab[arg.id].var
+        else:
+            logger.info(f"Undefined variable {arg.id}")
+            return None
+    else:
+        logger.info("Unsupported argument type for deref")
+        return None
+
+    if arg_ptr is None:
+        logger.info("Failed to evaluate deref argument")
+        return None
+
+    # Load the value from pointer
+    val = builder.load(arg_ptr)
+    return val, local_sym_tab[arg.id].ir_type
 
 
 def eval_expr(
@@ -11,68 +97,32 @@ def eval_expr(
     map_sym_tab,
     structs_sym_tab=None,
 ):
-    print(f"Evaluating expression: {ast.dump(expr)}")
+    logger.info(f"Evaluating expression: {ast.dump(expr)}")
     if isinstance(expr, ast.Name):
-        if expr.id in local_sym_tab:
-            var = local_sym_tab[expr.id].var
-            val = builder.load(var)
-            return val, local_sym_tab[expr.id].ir_type  # return value and type
-        else:
-            print(f"Undefined variable {expr.id}")
-            return None
+        return _handle_name_expr(expr, local_sym_tab, builder)
     elif isinstance(expr, ast.Constant):
-        if isinstance(expr.value, int):
-            return ir.Constant(ir.IntType(64), expr.value), ir.IntType(64)
-        elif isinstance(expr.value, bool):
-            return ir.Constant(ir.IntType(1), int(expr.value)), ir.IntType(1)
-        else:
-            print("Unsupported constant type")
-            return None
+        return _handle_constant_expr(expr)
     elif isinstance(expr, ast.Call):
+        if isinstance(expr.func, ast.Name) and expr.func.id == "deref":
+            return _handle_deref_call(expr, local_sym_tab, builder)
+
         # delayed import to avoid circular dependency
         from pythonbpf.helper import HelperHandlerRegistry, handle_helper_call
 
-        if isinstance(expr.func, ast.Name):
-            # check deref
-            if expr.func.id == "deref":
-                print(f"Handling deref {ast.dump(expr)}")
-                if len(expr.args) != 1:
-                    print("deref takes exactly one argument")
-                    return None
-                arg = expr.args[0]
-                if (
-                    isinstance(arg, ast.Call)
-                    and isinstance(arg.func, ast.Name)
-                    and arg.func.id == "deref"
-                ):
-                    print("Multiple deref not supported")
-                    return None
-                if isinstance(arg, ast.Name):
-                    if arg.id in local_sym_tab:
-                        arg = local_sym_tab[arg.id].var
-                    else:
-                        print(f"Undefined variable {arg.id}")
-                        return None
-                if arg is None:
-                    print("Failed to evaluate deref argument")
-                    return None
-                # Since we are handling only name case, directly take type from sym tab
-                val = builder.load(arg)
-                return val, local_sym_tab[expr.args[0].id].ir_type
-
-            # check for helpers
-            if HelperHandlerRegistry.has_handler(expr.func.id):
-                return handle_helper_call(
-                    expr,
-                    module,
-                    builder,
-                    func,
-                    local_sym_tab,
-                    map_sym_tab,
-                    structs_sym_tab,
-                )
+        if isinstance(expr.func, ast.Name) and HelperHandlerRegistry.has_handler(
+            expr.func.id
+        ):
+            return handle_helper_call(
+                expr,
+                module,
+                builder,
+                func,
+                local_sym_tab,
+                map_sym_tab,
+                structs_sym_tab,
+            )
         elif isinstance(expr.func, ast.Attribute):
-            print(f"Handling method call: {ast.dump(expr.func)}")
+            logger.info(f"Handling method call: {ast.dump(expr.func)}")
             if isinstance(expr.func.value, ast.Call) and isinstance(
                 expr.func.value.func, ast.Name
             ):
@@ -102,20 +152,8 @@ def eval_expr(
                             structs_sym_tab,
                         )
     elif isinstance(expr, ast.Attribute):
-        if isinstance(expr.value, ast.Name):
-            var_name = expr.value.id
-            attr_name = expr.attr
-            if var_name in local_sym_tab:
-                var_ptr, var_type, var_metadata = local_sym_tab[var_name]
-                print(f"Loading attribute {attr_name} from variable {var_name}")
-                print(f"Variable type: {var_type}, Variable ptr: {var_ptr}")
-                metadata = structs_sym_tab[var_metadata]
-                if attr_name in metadata.fields:
-                    gep = metadata.gep(builder, var_ptr, attr_name)
-                    val = builder.load(gep)
-                    field_type = metadata.field_type(attr_name)
-                    return val, field_type
-    print("Unsupported expression evaluation")
+        return _handle_attribute_expr(expr, local_sym_tab, structs_sym_tab, builder)
+    logger.info("Unsupported expression evaluation")
     return None
 
 
@@ -129,7 +167,7 @@ def handle_expr(
     structs_sym_tab,
 ):
     """Handle expression statements in the function body."""
-    print(f"Handling expression: {ast.dump(expr)}")
+    logger.info(f"Handling expression: {ast.dump(expr)}")
     call = expr.value
     if isinstance(call, ast.Call):
         eval_expr(
@@ -142,4 +180,4 @@ def handle_expr(
             structs_sym_tab,
         )
     else:
-        print("Unsupported expression type")
+        logger.info("Unsupported expression type")

pythonbpf/functions_pass.py

@@ -46,15 +46,15 @@ def handle_assign(
 ):
     """Handle assignment statements in the function body."""
     if len(stmt.targets) != 1:
-        print("Unsupported multiassignment")
+        logger.info("Unsupported multiassignment")
         return
 
     num_types = ("c_int32", "c_int64", "c_uint32", "c_uint64")
 
     target = stmt.targets[0]
-    print(f"Handling assignment to {ast.dump(target)}")
+    logger.info(f"Handling assignment to {ast.dump(target)}")
     if not isinstance(target, ast.Name) and not isinstance(target, ast.Attribute):
-        print("Unsupported assignment target")
+        logger.info("Unsupported assignment target")
         return
     var_name = target.id if isinstance(target, ast.Name) else target.value.id
     rval = stmt.value
@@ -87,11 +87,11 @@ def handle_assign(
                     # print(f"Assigned to struct field {var_name}.{field_name}")
                     pass
                 if val is None:
-                    print("Failed to evaluate struct field assignment")
+                    logger.info("Failed to evaluate struct field assignment")
                     return
-                print(field_ptr)
+                logger.info(field_ptr)
                 builder.store(val[0], field_ptr)
-                print(f"Assigned to struct field {var_name}.{field_name}")
+                logger.info(f"Assigned to struct field {var_name}.{field_name}")
                 return
     elif isinstance(rval, ast.Constant):
         if isinstance(rval.value, bool):
@@ -103,7 +103,7 @@ def handle_assign(
                 builder.store(
                     ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name].var
                 )
-            print(f"Assigned constant {rval.value} to {var_name}")
+            logger.info(f"Assigned constant {rval.value} to {var_name}")
         elif isinstance(rval.value, int):
             # Assume c_int64 for now
             # var = builder.alloca(ir.IntType(64), name=var_name)
@@ -111,7 +111,7 @@ def handle_assign(
             builder.store(
                 ir.Constant(ir.IntType(64), rval.value), local_sym_tab[var_name].var
             )
-            print(f"Assigned constant {rval.value} to {var_name}")
+            logger.info(f"Assigned constant {rval.value} to {var_name}")
         elif isinstance(rval.value, str):
             str_val = rval.value.encode("utf-8") + b"\x00"
             str_const = ir.Constant(
@@ -125,13 +125,13 @@ def handle_assign(
             global_str.initializer = str_const
             str_ptr = builder.bitcast(global_str, ir.PointerType(ir.IntType(8)))
             builder.store(str_ptr, local_sym_tab[var_name].var)
-            print(f"Assigned string constant '{rval.value}' to {var_name}")
+            logger.info(f"Assigned string constant '{rval.value}' to {var_name}")
         else:
-            print("Unsupported constant type")
+            logger.info("Unsupported constant type")
     elif isinstance(rval, ast.Call):
         if isinstance(rval.func, ast.Name):
             call_type = rval.func.id
-            print(f"Assignment call type: {call_type}")
+            logger.info(f"Assignment call type: {call_type}")
             if (
                 call_type in num_types
                 and len(rval.args) == 1
@@ -145,7 +145,7 @@ def handle_assign(
                     ir.Constant(ir_type, rval.args[0].value),
                     local_sym_tab[var_name].var,
                 )
-                print(
+                logger.info(
                     f"Assigned {call_type} constant "
                     f"{rval.args[0].value} to {var_name}"
                 )
@@ -162,9 +162,9 @@ def handle_assign(
                     structs_sym_tab,
                 )
                 builder.store(val[0], local_sym_tab[var_name].var)
-                print(f"Assigned constant {rval.func.id} to {var_name}")
+                logger.info(f"Assigned constant {rval.func.id} to {var_name}")
             elif call_type == "deref" and len(rval.args) == 1:
-                print(f"Handling deref assignment {ast.dump(rval)}")
+                logger.info(f"Handling deref assignment {ast.dump(rval)}")
                 val = eval_expr(
                     func,
                     module,
@@ -175,25 +175,40 @@ def handle_assign(
                     structs_sym_tab,
                 )
                 if val is None:
-                    print("Failed to evaluate deref argument")
+                    logger.info("Failed to evaluate deref argument")
                     return
-                print(f"Dereferenced value: {val}, storing in {var_name}")
+                logger.info(f"Dereferenced value: {val}, storing in {var_name}")
                 builder.store(val[0], local_sym_tab[var_name].var)
-                print(f"Dereferenced and assigned to {var_name}")
+                logger.info(f"Dereferenced and assigned to {var_name}")
             elif call_type in structs_sym_tab and len(rval.args) == 0:
                 struct_info = structs_sym_tab[call_type]
                 ir_type = struct_info.ir_type
                 # var = builder.alloca(ir_type, name=var_name)
                 # Null init
                 builder.store(ir.Constant(ir_type, None), local_sym_tab[var_name].var)
-                print(f"Assigned struct {call_type} to {var_name}")
+                logger.info(f"Assigned struct {call_type} to {var_name}")
             else:
-                print(f"Unsupported assignment call type: {call_type}")
+                logger.info(f"Unsupported assignment call type: {call_type}")
         elif isinstance(rval.func, ast.Attribute):
-            print(f"Assignment call attribute: {ast.dump(rval.func)}")
+            logger.info(f"Assignment call attribute: {ast.dump(rval.func)}")
             if isinstance(rval.func.value, ast.Name):
-                # TODO: probably a struct access
-                print(f"TODO STRUCT ACCESS {ast.dump(rval)}")
+                if rval.func.value.id in map_sym_tab:
+                    map_name = rval.func.value.id
+                    method_name = rval.func.attr
+                    if HelperHandlerRegistry.has_handler(method_name):
+                        val = handle_helper_call(
+                            rval,
+                            module,
+                            builder,
+                            func,
+                            local_sym_tab,
+                            map_sym_tab,
+                            structs_sym_tab,
+                        )
+                        builder.store(val[0], local_sym_tab[var_name].var)
+                else:
+                    # TODO: probably a struct access
+                    logger.info(f"TODO STRUCT ACCESS {ast.dump(rval)}")
             elif isinstance(rval.func.value, ast.Call) and isinstance(
                 rval.func.value.func, ast.Name
             ):
@@ -214,15 +229,13 @@ def handle_assign(
                         # var.align = 8
                         builder.store(val[0], local_sym_tab[var_name].var)
             else:
-                print("Unsupported assignment call structure")
+                logger.info("Unsupported assignment call structure")
         else:
-            print("Unsupported assignment call function type")
+            logger.info("Unsupported assignment call function type")
     elif isinstance(rval, ast.BinOp):
-        handle_binary_op(
-            rval, module, builder, var_name, local_sym_tab, map_sym_tab, func
-        )
+        handle_binary_op(rval, module, builder, var_name, local_sym_tab)
     else:
-        print("Unsupported assignment value type")
+        logger.info("Unsupported assignment value type")
 
 
 def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
@@ -232,7 +245,7 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
         elif isinstance(cond.value, int):
             return ir.Constant(ir.IntType(1), int(bool(cond.value)))
         else:
-            print("Unsupported constant type in condition")
+            logger.info("Unsupported constant type in condition")
             return None
     elif isinstance(cond, ast.Name):
         if cond.id in local_sym_tab:
@@ -249,12 +262,12 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
                 val = builder.icmp_signed("!=", val, zero)
             return val
         else:
-            print(f"Undefined variable {cond.id} in condition")
+            logger.info(f"Undefined variable {cond.id} in condition")
             return None
     elif isinstance(cond, ast.Compare):
         lhs = eval_expr(func, module, builder, cond.left, local_sym_tab, map_sym_tab)[0]
         if len(cond.ops) != 1 or len(cond.comparators) != 1:
-            print("Unsupported complex comparison")
+            logger.info("Unsupported complex comparison")
             return None
         rhs = eval_expr(
             func, module, builder, cond.comparators[0], local_sym_tab, map_sym_tab
@@ -269,7 +282,7 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
                 elif lhs.type.width > rhs.type.width:
                     rhs = builder.sext(rhs, lhs.type)
             else:
-                print("Type mismatch in comparison")
+                logger.info("Type mismatch in comparison")
                 return None
 
         if isinstance(op, ast.Eq):
@@ -285,10 +298,10 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
         elif isinstance(op, ast.GtE):
             return builder.icmp_signed(">=", lhs, rhs)
         else:
-            print("Unsupported comparison operator")
+            logger.info("Unsupported comparison operator")
             return None
     else:
-        print("Unsupported condition expression")
+        logger.info("Unsupported condition expression")
         return None
 
 
@@ -296,7 +309,7 @@ def handle_if(
     func, module, builder, stmt, map_sym_tab, local_sym_tab, structs_sym_tab=None
 ):
     """Handle if statements in the function body."""
-    print("Handling if statement")
+    logger.info("Handling if statement")
     # start = builder.block.parent
     then_block = func.append_basic_block(name="if.then")
     merge_block = func.append_basic_block(name="if.end")
@@ -349,7 +362,7 @@ def process_stmt(
     did_return,
     ret_type=ir.IntType(64),
 ):
-    print(f"Processing statement: {ast.dump(stmt)}")
+    logger.info(f"Processing statement: {ast.dump(stmt)}")
     if isinstance(stmt, ast.Expr):
         handle_expr(
             func,
@@ -434,11 +447,11 @@ def allocate_mem(
                 )
         elif isinstance(stmt, ast.Assign):
             if len(stmt.targets) != 1:
-                print("Unsupported multiassignment")
+                logger.info("Unsupported multiassignment")
                 continue
             target = stmt.targets[0]
             if not isinstance(target, ast.Name):
-                print("Unsupported assignment target")
+                logger.info("Unsupported assignment target")
                 continue
             var_name = target.id
             rval = stmt.value
@@ -449,25 +462,27 @@ def allocate_mem(
                         ir_type = ctypes_to_ir(call_type)
                         var = builder.alloca(ir_type, name=var_name)
                         var.align = ir_type.width // 8
-                        print(f"Pre-allocated variable {var_name} of type {call_type}")
+                        logger.info(
+                            f"Pre-allocated variable {var_name} of type {call_type}"
+                        )
                     elif HelperHandlerRegistry.has_handler(call_type):
                         # Assume return type is int64 for now
                         ir_type = ir.IntType(64)
                         var = builder.alloca(ir_type, name=var_name)
                         var.align = ir_type.width // 8
-                        print(f"Pre-allocated variable {var_name} for helper")
+                        logger.info(f"Pre-allocated variable {var_name} for helper")
                     elif call_type == "deref" and len(rval.args) == 1:
                         # Assume return type is int64 for now
                         ir_type = ir.IntType(64)
                         var = builder.alloca(ir_type, name=var_name)
                         var.align = ir_type.width // 8
-                        print(f"Pre-allocated variable {var_name} for deref")
+                        logger.info(f"Pre-allocated variable {var_name} for deref")
                     elif call_type in structs_sym_tab:
                         struct_info = structs_sym_tab[call_type]
                         ir_type = struct_info.ir_type
                         var = builder.alloca(ir_type, name=var_name)
                         has_metadata = True
-                        print(
+                        logger.info(
                             f"Pre-allocated variable {var_name} "
                             f"for struct {call_type}"
                         )
@@ -475,38 +490,38 @@ def allocate_mem(
                     ir_type = ir.PointerType(ir.IntType(64))
                     var = builder.alloca(ir_type, name=var_name)
                     # var.align = ir_type.width // 8
-                    print(f"Pre-allocated variable {var_name} for map")
+                    logger.info(f"Pre-allocated variable {var_name} for map")
                 else:
-                    print("Unsupported assignment call function type")
+                    logger.info("Unsupported assignment call function type")
                     continue
             elif isinstance(rval, ast.Constant):
                 if isinstance(rval.value, bool):
                     ir_type = ir.IntType(1)
                     var = builder.alloca(ir_type, name=var_name)
                     var.align = 1
-                    print(f"Pre-allocated variable {var_name} of type c_bool")
+                    logger.info(f"Pre-allocated variable {var_name} of type c_bool")
                 elif isinstance(rval.value, int):
                     # Assume c_int64 for now
                     ir_type = ir.IntType(64)
                     var = builder.alloca(ir_type, name=var_name)
                     var.align = ir_type.width // 8
-                    print(f"Pre-allocated variable {var_name} of type c_int64")
+                    logger.info(f"Pre-allocated variable {var_name} of type c_int64")
                 elif isinstance(rval.value, str):
                     ir_type = ir.PointerType(ir.IntType(8))
                     var = builder.alloca(ir_type, name=var_name)
                     var.align = 8
-                    print(f"Pre-allocated variable {var_name} of type string")
+                    logger.info(f"Pre-allocated variable {var_name} of type string")
                 else:
-                    print("Unsupported constant type")
+                    logger.info("Unsupported constant type")
                     continue
             elif isinstance(rval, ast.BinOp):
                 # Assume c_int64 for now
                 ir_type = ir.IntType(64)
                 var = builder.alloca(ir_type, name=var_name)
                 var.align = ir_type.width // 8
-                print(f"Pre-allocated variable {var_name} of type c_int64")
+                logger.info(f"Pre-allocated variable {var_name} of type c_int64")
             else:
-                print("Unsupported assignment value type")
+                logger.info("Unsupported assignment value type")
                 continue
 
             if has_metadata:
@@ -537,7 +552,7 @@ def process_func_body(
         structs_sym_tab,
     )
 
-    print(f"Local symbol table: {local_sym_tab.keys()}")
+    logger.info(f"Local symbol table: {local_sym_tab.keys()}")
 
     for stmt in func_node.body:
         did_return = process_stmt(
@@ -609,7 +624,7 @@ def func_proc(tree, module, chunks, map_sym_tab, structs_sym_tab):
         if is_global:
             continue
         func_type = get_probe_string(func_node)
-        print(f"Found probe_string of {func_node.name}: {func_type}")
+        logger.info(f"Found probe_string of {func_node.name}: {func_type}")
 
         process_bpf_chunk(
             func_node,

pythonbpf/globals_pass.py

@@ -1,8 +1,121 @@
 from llvmlite import ir
 import ast
 
+from logging import Logger
+import logging
+from .type_deducer import ctypes_to_ir
 
-def emit_globals(module: ir.Module, names: list[str]):
+logger: Logger = logging.getLogger(__name__)
+
+# TODO: this is going to be a huge fuck of a headache in the future.
+global_sym_tab = []
+
+
+def populate_global_symbol_table(tree, module: ir.Module):
+    for node in tree.body:
+        if isinstance(node, ast.FunctionDef):
+            for dec in node.decorator_list:
+                if (
+                    isinstance(dec, ast.Call)
+                    and isinstance(dec.func, ast.Name)
+                    and dec.func.id == "section"
+                    and len(dec.args) == 1
+                    and isinstance(dec.args[0], ast.Constant)
+                    and isinstance(dec.args[0].value, str)
+                ):
+                    global_sym_tab.append(node)
+                elif isinstance(dec, ast.Name) and dec.id == "bpfglobal":
+                    global_sym_tab.append(node)
+
+                elif isinstance(dec, ast.Name) and dec.id == "map":
+                    global_sym_tab.append(node)
+    return False
+
+
+def emit_global(module: ir.Module, node, name):
+    logger.info(f"global identifier {name} processing")
+    # deduce LLVM type from the annotated return
+    if not isinstance(node.returns, ast.Name):
+        raise ValueError(f"Unsupported return annotation {ast.dump(node.returns)}")
+    ty = ctypes_to_ir(node.returns.id)
+
+    # extract the return expression
+    # TODO: turn this return extractor into a generic function I can use everywhere.
+    ret_stmt = node.body[0]
+    if not isinstance(ret_stmt, ast.Return) or ret_stmt.value is None:
+        raise ValueError(f"Global '{name}' has no valid return")
+
+    init_val = ret_stmt.value
+
+    # simple constant like "return 0"
+    if isinstance(init_val, ast.Constant):
+        llvm_init = ir.Constant(ty, init_val.value)
+
+    # variable reference like "return SOME_CONST"
+    elif isinstance(init_val, ast.Name):
+        # need symbol resolution here, stub as 0 for now
+        raise ValueError(f"Name reference {init_val.id} not yet supported")
+
+    # constructor call like "return c_int64(0)" or dataclass(...)
+    elif isinstance(init_val, ast.Call):
+        if len(init_val.args) >= 1 and isinstance(init_val.args[0], ast.Constant):
+            llvm_init = ir.Constant(ty, init_val.args[0].value)
+        else:
+            logger.info("Defaulting to zero as no constant argument found")
+            llvm_init = ir.Constant(ty, 0)
+    else:
+        raise ValueError(f"Unsupported return expr {ast.dump(init_val)}")
+
+    gvar = ir.GlobalVariable(module, ty, name=name)
+    gvar.initializer = llvm_init
+    gvar.align = 8
+    gvar.linkage = "dso_local"
+    gvar.global_constant = False
+    return gvar
+
+
+def globals_processing(tree, module):
+    """Process stuff decorated with @bpf and @bpfglobal except license and return the section name"""
+    globals_sym_tab = []
+
+    for node in tree.body:
+        # Skip non-assignment and non-function nodes
+        if not (isinstance(node, ast.FunctionDef)):
+            continue
+
+        # Get the name based on node type
+        if isinstance(node, ast.FunctionDef):
+            name = node.name
+        else:
+            continue
+
+        # Check for duplicate names
+        if name in globals_sym_tab:
+            raise SyntaxError(f"ERROR: Global name '{name}' previously defined")
+        else:
+            globals_sym_tab.append(name)
+
+        if isinstance(node, ast.FunctionDef) and node.name != "LICENSE":
+            decorators = [
+                dec.id for dec in node.decorator_list if isinstance(dec, ast.Name)
+            ]
+            if "bpf" in decorators and "bpfglobal" in decorators:
+                if (
+                    len(node.body) == 1
+                    and isinstance(node.body[0], ast.Return)
+                    and node.body[0].value is not None
+                    and isinstance(
+                        node.body[0].value, (ast.Constant, ast.Name, ast.Call)
+                    )
+                ):
+                    emit_global(module, node, name)
+                else:
+                    raise SyntaxError(f"ERROR: Invalid syntax for {name} global")
+
+    return None
+
+
+def emit_llvm_compiler_used(module: ir.Module, names: list[str]):
     """
     Emit the @llvm.compiler.used global given a list of function/global names.
     """
@@ -24,7 +137,7 @@ def emit_globals(module: ir.Module, names: list[str]):
     gv.section = "llvm.metadata"
 
 
-def globals_processing(tree, module: ir.Module):
+def globals_list_creation(tree, module: ir.Module):
     collected = ["LICENSE"]
 
     for node in tree.body:
@@ -40,10 +153,11 @@ def globals_processing(tree, module: ir.Module):
                 ):
                     collected.append(node.name)
 
-                elif isinstance(dec, ast.Name) and dec.id == "bpfglobal":
-                    collected.append(node.name)
+                # NOTE: all globals other than
+                # elif isinstance(dec, ast.Name) and dec.id == "bpfglobal":
+                #     collected.append(node.name)
 
                 elif isinstance(dec, ast.Name) and dec.id == "map":
                     collected.append(node.name)
 
-    emit_globals(module, collected)
+    emit_llvm_compiler_used(module, collected)

pythonbpf/helper/bpf_helper_handler.py

@@ -9,6 +9,10 @@ from .helper_utils import (
     simple_string_print,
     get_data_ptr_and_size,
 )
+from logging import Logger
+import logging
+
+logger: Logger = logging.getLogger(__name__)
 
 
 class BPFHelperID(Enum):
@@ -322,7 +326,7 @@ def handle_helper_call(
     elif isinstance(call.func, ast.Attribute):
         method_name = call.func.attr
         value = call.func.value
-        print(f"Handling method call: {ast.dump(call.func)}")
+        logger.info(f"Handling method call: {ast.dump(call.func)}")
         # Get map pointer from different styles of map access
         if isinstance(value, ast.Call) and isinstance(value.func, ast.Name):
             # Func style: my_map().lookup(key)

pythonbpf/license_pass.py

@@ -1,5 +1,9 @@
 from llvmlite import ir
 import ast
+from logging import Logger
+import logging
+
+logger: Logger = logging.getLogger(__name__)
 
 
 def emit_license(module: ir.Module, license_str: str):
@@ -41,9 +45,9 @@ def license_processing(tree, module):
                         emit_license(module, node.body[0].value.value)
                         return "LICENSE"
                     else:
-                        print("ERROR: LICENSE() must return a string literal")
+                        logger.info("ERROR: LICENSE() must return a string literal")
                         return None
                 else:
-                    print("ERROR: LICENSE already defined")
+                    logger.info("ERROR: LICENSE already defined")
                     return None
     return None

pythonbpf/maps/maps_pass.py

@@ -158,8 +158,7 @@ def create_ringbuf_debug_info(module, map_global, map_name, map_params):
     type_ptr = generator.create_pointer_type(type_array, 64)
     type_member = generator.create_struct_member("type", type_ptr, 0)
 
-    max_entries_array = generator.create_array_type(
-        int_type, map_params["max_entries"])
+    max_entries_array = generator.create_array_type(int_type, map_params["max_entries"])
     max_entries_ptr = generator.create_pointer_type(max_entries_array, 64)
     max_entries_member = generator.create_struct_member(
         "max_entries", max_entries_ptr, 64
@@ -167,8 +166,7 @@ def create_ringbuf_debug_info(module, map_global, map_name, map_params):
 
     elements_arr = [type_member, max_entries_member]
 
-    struct_type = generator.create_struct_type(
-        elements_arr, 128, is_distinct=True)
+    struct_type = generator.create_struct_type(elements_arr, 128, is_distinct=True)
 
     global_var = generator.create_global_var_debug_info(
         map_name, struct_type, is_local=False

pythonbpf/structs/structs_pass.py

@@ -19,7 +19,7 @@ def structs_proc(tree, module, chunks):
     structs_sym_tab = {}
     for cls_node in chunks:
         if is_bpf_struct(cls_node):
-            print(f"Found BPF struct: {cls_node.name}")
+            logger.info(f"Found BPF struct: {cls_node.name}")
             struct_info = process_bpf_struct(cls_node, module)
             structs_sym_tab[cls_node.name] = struct_info
     return structs_sym_tab

tests/c-form/globals.bpf.c

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/types.h>
+
+struct test_struct {
+    __u64 a;
+    __u64 b;
+};
+
+struct test_struct w = {};
+volatile __u64 prev_time = 0;
+
+SEC("tracepoint/syscalls/sys_enter_execve")
+int trace_execve(void *ctx)
+{
+    bpf_printk("previous %ul now %ul", w.b, w.a);
+    __u64 ts = bpf_ktime_get_ns();
+    bpf_printk("prev %ul now %ul", prev_time, ts);
+    w.a = ts;
+    w.b = prev_time;
+    prev_time = ts;
+    return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";

tests/failing_tests/globals.py

@@ -0,0 +1,101 @@
+import logging
+
+from pythonbpf import compile, bpf, section, bpfglobal, compile_to_ir
+from ctypes import c_void_p, c_int64, c_int32
+
+@bpf
+@bpfglobal
+def somevalue() -> c_int32:
+    return c_int32(42)
+
+@bpf
+@bpfglobal
+def somevalue2() -> c_int64:
+    return c_int64(69)
+
+@bpf
+@bpfglobal
+def somevalue1() -> c_int32:
+    return c_int32(42)
+
+
+# --- Passing examples ---
+
+# Simple constant return
+@bpf
+@bpfglobal
+def g1() -> c_int64:
+    return c_int64(42)
+
+# Constructor with one constant argument
+@bpf
+@bpfglobal
+def g2() -> c_int64:
+    return c_int64(69)
+
+
+# --- Failing examples ---
+
+# No return annotation
+# @bpf
+# @bpfglobal
+# def g3():
+#     return 42
+
+# Return annotation is complex
+# @bpf
+# @bpfglobal
+# def g4() -> List[int]:
+#     return []
+
+# # Return is missing
+# @bpf
+# @bpfglobal
+# def g5() -> c_int64:
+#     pass
+
+# # Return is a variable reference
+# #TODO: maybe fix this sometime later. It defaults to 0
+# CONST = 5
+# @bpf
+# @bpfglobal
+# def g6() -> c_int64:
+#     return c_int64(CONST)
+
+# Constructor with multiple args
+#TODO: this is not working. should it work ?
+@bpf
+@bpfglobal
+def g7() -> c_int64:
+    return c_int64(1)
+
+# Dataclass call
+#TODO: fails with dataclass
+# @dataclass
+# class Point:
+#     x: c_int64
+#     y: c_int64
+
+# @bpf
+# @bpfglobal
+# def g8() -> Point:
+#     return Point(1, 2)
+
+
+@bpf
+@section("tracepoint/syscalls/sys_enter_execve")
+def sometag(ctx: c_void_p) -> c_int64:
+    print("test")
+    global somevalue
+    somevalue = 2
+    print(f"{somevalue}")
+    return c_int64(1)
+
+@bpf
+@bpfglobal
+def LICENSE() -> str:
+    return "GPL"
+
+
+compile_to_ir("globals.py", "globals.ll", loglevel=logging.INFO)
+compile()

tests/failing_tests/undeclared_values.py

@@ -0,0 +1,21 @@
+import logging
+
+from pythonbpf import compile, bpf, section, bpfglobal, compile_to_ir
+from ctypes import c_void_p, c_int64
+
+# This should not pass as somevalue is not declared at all.
+@bpf
+@section("tracepoint/syscalls/sys_enter_execve")
+def sometag(ctx: c_void_p) -> c_int64:
+    print("test")
+    print(f"{somevalue}")  # noqa: F821
+    return c_int64(1)
+
+@bpf
+@bpfglobal
+def LICENSE() -> str:
+    return "GPL"
+
+
+compile_to_ir("globals.py", "globals.ll", loglevel=logging.INFO)
+compile()

tests/passing_tests/binops.py

@@ -3,9 +3,9 @@ from ctypes import c_void_p, c_int64
 
 
 @bpf
-@section("sometag1")
+@section("tracepoint/syscalls/sys_enter_sync")
 def sometag(ctx: c_void_p) -> c_int64:
-    a = 1 + 2 + 1
+    a = 1 + 2 + 1 + 12 + 13
     print(f"{a}")
     return c_int64(0)
 

tests/passing_tests/binops1.py

@@ -3,11 +3,12 @@ from ctypes import c_void_p, c_int64
 
 
 @bpf
-@section("sometag1")
+@section("tracepoint/syscalls/sys_enter_sync")
 def sometag(ctx: c_void_p) -> c_int64:
     b = 1 + 2
     a = 1 + b
-    return c_int64(a)
+    print(f"{a}")
+    return c_int64(0)
 
 
 @bpf

tests/passing_tests/perf_buffer_map.py

@@ -1,7 +1,7 @@
 from pythonbpf import bpf, map, struct, section, bpfglobal, compile, compile_to_ir, BPF
 from pythonbpf.helper import ktime, pid
 from pythonbpf.maps import PerfEventArray
-
+import logging
 from ctypes import c_void_p, c_int32, c_uint64
 
 
@@ -42,8 +42,8 @@ def LICENSE() -> str:
     return "GPL"
 
 
-compile()
 compile_to_ir("perf_buffer_map.py", "perf_buffer_map.ll")
+compile(loglevel=logging.INFO)
 b = BPF()
 b.load_and_attach()