add failing test

.pre-commit-config.yaml

@@ -41,14 +41,14 @@ repos:
     - id: ruff
       args: ["--fix", "--show-fixes"]
     - id: ruff-format
-      exclude: ^(docs)|^(tests)|^(examples)
+      exclude: ^(tests/|examples/|docs/)
 
 # Checking static types
 - repo: https://github.com/pre-commit/mirrors-mypy
   rev: "v1.10.0"
   hooks:
     - id: mypy
-      exclude: ^(tests)|^(examples)
+      exclude: ^(tests/|examples/)
       additional_dependencies: [types-setuptools]
 
 # Changes tabs to spaces

examples/hello_world.py

@@ -22,9 +22,5 @@ def LICENSE() -> str:
 
 b = BPF()
 b.load_and_attach()
-if b.is_loaded() and b.is_attached():
-    print("Successfully loaded and attached")
-else:
-    print("Could not load successfully")
 
 # Now cat /sys/kernel/debug/tracing/trace_pipe to see results of the execve syscall.

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 = "0.1.4"
+version = "0.1.3"
 description = "Reduced Python frontend for eBPF"
 authors = [
   { name = "r41k0u", email="pragyanshchaturvedi18@gmail.com" },

pythonbpf/binary_ops.py

@@ -1,66 +1,71 @@
 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"""
-    # TODO: Not worrying about stack overflow for now
-    if isinstance(var.type, ir.PointerType):
+    if var.type == ir.PointerType(ir.PointerType(ir.IntType(64))):
         a = builder.load(var)
         return recursive_dereferencer(a, builder)
-    elif isinstance(var.type, ir.IntType):
+    elif var.type == ir.PointerType(ir.IntType(64)):
+        a = builder.load(var)
+        return recursive_dereferencer(a, builder)
+    elif var.type == ir.IntType(64):
         return var
     else:
         raise TypeError(f"Unsupported type for dereferencing: {var.type}")
 
 
-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):
+def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab, func):
+    print(module)
+    left = rval.left
+    right = rval.right
     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}")
 
-    # 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,
-    }
+    # Handle left operand
+    if isinstance(left, ast.Name):
+        if left.id in local_sym_tab:
+            left = recursive_dereferencer(local_sym_tab[left.id][0], 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")
 
-    if type(op) in op_map:
-        result = op_map[type(op)](left, right)
-        return result
+    if isinstance(right, ast.Name):
+        if right.id in local_sym_tab:
+            right = recursive_dereferencer(local_sym_tab[right.id][0], 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][0])
+    elif isinstance(op, ast.Sub):
+        builder.store(builder.sub(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.Mult):
+        builder.store(builder.mul(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.Div):
+        builder.store(builder.sdiv(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.Mod):
+        builder.store(builder.srem(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.LShift):
+        builder.store(builder.shl(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.RShift):
+        builder.store(builder.lshr(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.BitOr):
+        builder.store(builder.or_(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.BitXor):
+        builder.store(builder.xor(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.BitAnd):
+        builder.store(builder.and_(left, right), local_sym_tab[var_name][0])
+    elif isinstance(op, ast.FloorDiv):
+        builder.store(builder.udiv(left, right), local_sym_tab[var_name][0])
     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

@@ -4,24 +4,16 @@ 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_list_creation,
-    globals_processing,
-    populate_global_symbol_table,
-)
-from .debuginfo import DW_LANG_C11, DwarfBehaviorEnum, DebugInfoGenerator
+from .globals_pass import globals_processing
+from .debuginfo import DW_LANG_C11, DwarfBehaviorEnum
 import os
 import subprocess
 import inspect
 from pathlib import Path
 from pylibbpf import BpfProgram
 import tempfile
-from logging import Logger
-import logging
 
-logger: Logger = logging.getLogger(__name__)
-
-VERSION = "v0.1.4"
+VERSION = "v0.1.3"
 
 
 def find_bpf_chunks(tree):
@@ -38,27 +30,21 @@ def find_bpf_chunks(tree):
 
 def processor(source_code, filename, module):
     tree = ast.parse(source_code, filename)
-    logger.debug(ast.dump(tree, indent=4))
+    print(ast.dump(tree, indent=4))
 
     bpf_chunks = find_bpf_chunks(tree)
     for func_node in bpf_chunks:
-        logger.info(f"Found BPF function/struct: {func_node.name}")
-
-    populate_global_symbol_table(tree, module)
-    license_processing(tree, module)
-    globals_processing(tree, module)
+        print(f"Found BPF function/struct: {func_node.name}")
 
     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)
 
-    globals_list_creation(tree, module)
+    license_processing(tree, module)
+    globals_processing(tree, module)
 
 
-def compile_to_ir(filename: str, output: str, loglevel=logging.WARNING):
-    logging.basicConfig(
-        level=loglevel, format="%(asctime)s [%(levelname)s] %(name)s: %(message)s"
-    )
+def compile_to_ir(filename: str, output: str):
     with open(filename) as f:
         source = f.read()
 
@@ -67,17 +53,33 @@ def compile_to_ir(filename: str, output: str, loglevel=logging.WARNING):
     module.triple = "bpf"
 
     if not hasattr(module, "_debug_compile_unit"):
-        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._file_metadata = module.add_debug_info(
+            "DIFile",
+            {  # type: ignore
+                "filename": filename,
+                "directory": os.path.dirname(filename),
+            },
         )
 
+        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(
@@ -119,7 +121,7 @@ def compile_to_ir(filename: str, output: str, loglevel=logging.WARNING):
 
     module.add_named_metadata("llvm.ident", [f"PythonBPF {VERSION}"])
 
-    logger.info(f"IR written to {output}")
+    print(f"IR written to {output}")
     with open(output, "w") as f:
         f.write(f'source_filename = "{filename}"\n')
         f.write(str(module))
@@ -128,7 +130,7 @@ def compile_to_ir(filename: str, output: str, loglevel=logging.WARNING):
     return output
 
 
-def compile(loglevel=logging.WARNING) -> bool:
+def compile() -> 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()
@@ -137,9 +139,7 @@ def compile(loglevel=logging.WARNING) -> bool:
     o_file = caller_file.with_suffix(".o")
 
     success = True
-    success = (
-        compile_to_ir(str(caller_file), str(ll_file), loglevel=loglevel) and success
-    )
+    success = compile_to_ir(str(caller_file), str(ll_file)) and success
 
     success = bool(
         subprocess.run(
@@ -157,11 +157,11 @@ def compile(loglevel=logging.WARNING) -> bool:
         and success
     )
 
-    logger.info(f"Object written to {o_file}")
+    print(f"Object written to {o_file}")
     return success
 
 
-def BPF(loglevel=logging.WARNING) -> BpfProgram:
+def BPF() -> BpfProgram:
     caller_frame = inspect.stack()[1]
     src = inspect.getsource(caller_frame.frame)
     with tempfile.NamedTemporaryFile(
@@ -174,7 +174,7 @@ def BPF(loglevel=logging.WARNING) -> BpfProgram:
         f.write(src)
         f.flush()
         source = f.name
-        compile_to_ir(source, str(inter.name), loglevel=loglevel)
+        compile_to_ir(source, str(inter.name))
         subprocess.run(
             [
                 "llc",

pythonbpf/debuginfo/debug_info_generator.py

@@ -12,34 +12,6 @@ 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

@@ -1,91 +1,5 @@
 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(
@@ -96,33 +10,72 @@ def eval_expr(
     local_sym_tab,
     map_sym_tab,
     structs_sym_tab=None,
+    local_var_metadata=None,
 ):
-    logger.info(f"Evaluating expression: {ast.dump(expr)}")
+    print(f"Evaluating expression: {ast.dump(expr)}")
+    print(local_var_metadata)
     if isinstance(expr, ast.Name):
-        return _handle_name_expr(expr, local_sym_tab, builder)
+        if expr.id in local_sym_tab:
+            var = local_sym_tab[expr.id][0]
+            val = builder.load(var)
+            return val, local_sym_tab[expr.id][1]  # return value and type
+        else:
+            print(f"Undefined variable {expr.id}")
+            return None
     elif isinstance(expr, ast.Constant):
-        return _handle_constant_expr(expr)
+        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
     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) and 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):
+            # 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][0]
+                    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][1]
+
+            # 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,
+                    local_var_metadata,
+                )
         elif isinstance(expr.func, ast.Attribute):
-            logger.info(f"Handling method call: {ast.dump(expr.func)}")
+            print(f"Handling method call: {ast.dump(expr.func)}")
             if isinstance(expr.func.value, ast.Call) and isinstance(
                 expr.func.value.func, ast.Name
             ):
@@ -136,6 +89,7 @@ def eval_expr(
                         local_sym_tab,
                         map_sym_tab,
                         structs_sym_tab,
+                        local_var_metadata,
                     )
             elif isinstance(expr.func.value, ast.Name):
                 obj_name = expr.func.value.id
@@ -150,10 +104,25 @@ def eval_expr(
                             local_sym_tab,
                             map_sym_tab,
                             structs_sym_tab,
+                            local_var_metadata,
                         )
     elif isinstance(expr, ast.Attribute):
-        return _handle_attribute_expr(expr, local_sym_tab, structs_sym_tab, builder)
-    logger.info("Unsupported expression evaluation")
+        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 = local_sym_tab[var_name]
+                print(f"Loading attribute " f"{attr_name} from variable {var_name}")
+                print(f"Variable type: {var_type}, Variable ptr: {var_ptr}")
+                print(local_var_metadata)
+                if local_var_metadata and var_name in local_var_metadata:
+                    metadata = structs_sym_tab[local_var_metadata[var_name]]
+                    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 None
 
 
@@ -165,9 +134,11 @@ def handle_expr(
     local_sym_tab,
     map_sym_tab,
     structs_sym_tab,
+    local_var_metadata,
 ):
     """Handle expression statements in the function body."""
-    logger.info(f"Handling expression: {ast.dump(expr)}")
+    print(f"Handling expression: {ast.dump(expr)}")
+    print(local_var_metadata)
     call = expr.value
     if isinstance(call, ast.Call):
         eval_expr(
@@ -178,6 +149,7 @@ def handle_expr(
             local_sym_tab,
             map_sym_tab,
             structs_sym_tab,
+            local_var_metadata,
         )
     else:
-        logger.info("Unsupported expression type")
+        print("Unsupported expression type")

pythonbpf/functions_pass.py

@@ -1,27 +1,13 @@
 from llvmlite import ir
 import ast
-import logging
 from typing import Any
-from dataclasses import dataclass
 
 from .helper import HelperHandlerRegistry, handle_helper_call
 from .type_deducer import ctypes_to_ir
 from .binary_ops import handle_binary_op
 from .expr_pass import eval_expr, handle_expr
 
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class LocalSymbol:
-    var: ir.AllocaInstr
-    ir_type: ir.Type
-    metadata: Any = None
-
-    def __iter__(self):
-        yield self.var
-        yield self.ir_type
-        yield self.metadata
+local_var_metadata: dict[str | Any, Any] = {}
 
 
 def get_probe_string(func_node):
@@ -46,27 +32,28 @@ def handle_assign(
 ):
     """Handle assignment statements in the function body."""
     if len(stmt.targets) != 1:
-        logger.info("Unsupported multiassignment")
+        print("Unsupported multiassignment")
         return
 
     num_types = ("c_int32", "c_int64", "c_uint32", "c_uint64")
 
     target = stmt.targets[0]
-    logger.info(f"Handling assignment to {ast.dump(target)}")
+    print(f"Handling assignment to {ast.dump(target)}")
     if not isinstance(target, ast.Name) and not isinstance(target, ast.Attribute):
-        logger.info("Unsupported assignment target")
+        print("Unsupported assignment target")
         return
     var_name = target.id if isinstance(target, ast.Name) else target.value.id
     rval = stmt.value
     if isinstance(target, ast.Attribute):
         # struct field assignment
         field_name = target.attr
-        if var_name in local_sym_tab:
-            struct_type = local_sym_tab[var_name].metadata
+        if var_name in local_sym_tab and var_name in local_var_metadata:
+            struct_type = local_var_metadata[var_name]
             struct_info = structs_sym_tab[struct_type]
+
             if field_name in struct_info.fields:
                 field_ptr = struct_info.gep(
-                    builder, local_sym_tab[var_name].var, field_name
+                    builder, local_sym_tab[var_name][0], field_name
                 )
                 val = eval_expr(
                     func,
@@ -87,31 +74,28 @@ def handle_assign(
                     # print(f"Assigned to struct field {var_name}.{field_name}")
                     pass
                 if val is None:
-                    logger.info("Failed to evaluate struct field assignment")
+                    print("Failed to evaluate struct field assignment")
                     return
-                logger.info(field_ptr)
+                print(field_ptr)
                 builder.store(val[0], field_ptr)
-                logger.info(f"Assigned to struct field {var_name}.{field_name}")
+                print(f"Assigned to struct field {var_name}.{field_name}")
                 return
     elif isinstance(rval, ast.Constant):
         if isinstance(rval.value, bool):
             if rval.value:
-                builder.store(
-                    ir.Constant(ir.IntType(1), 1), local_sym_tab[var_name].var
-                )
+                builder.store(ir.Constant(ir.IntType(1), 1), local_sym_tab[var_name][0])
             else:
-                builder.store(
-                    ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name].var
-                )
-            logger.info(f"Assigned constant {rval.value} to {var_name}")
+                builder.store(ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name][0])
+            print(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)
             # var.align = 8
             builder.store(
-                ir.Constant(ir.IntType(64), rval.value), local_sym_tab[var_name].var
+                ir.Constant(ir.IntType(64), rval.value), local_sym_tab[var_name][0]
             )
-            logger.info(f"Assigned constant {rval.value} to {var_name}")
+            # local_sym_tab[var_name] = var
+            print(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(
@@ -124,14 +108,14 @@ def handle_assign(
             global_str.global_constant = True
             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)
-            logger.info(f"Assigned string constant '{rval.value}' to {var_name}")
+            builder.store(str_ptr, local_sym_tab[var_name][0])
+            print(f"Assigned string constant '{rval.value}' to {var_name}")
         else:
-            logger.info("Unsupported constant type")
+            print("Unsupported constant type")
     elif isinstance(rval, ast.Call):
         if isinstance(rval.func, ast.Name):
             call_type = rval.func.id
-            logger.info(f"Assignment call type: {call_type}")
+            print(f"Assignment call type: {call_type}")
             if (
                 call_type in num_types
                 and len(rval.args) == 1
@@ -142,13 +126,13 @@ def handle_assign(
                 # var = builder.alloca(ir_type, name=var_name)
                 # var.align = ir_type.width // 8
                 builder.store(
-                    ir.Constant(ir_type, rval.args[0].value),
-                    local_sym_tab[var_name].var,
+                    ir.Constant(ir_type, rval.args[0].value), local_sym_tab[var_name][0]
                 )
-                logger.info(
+                print(
                     f"Assigned {call_type} constant "
                     f"{rval.args[0].value} to {var_name}"
                 )
+                # local_sym_tab[var_name] = var
             elif HelperHandlerRegistry.has_handler(call_type):
                 # var = builder.alloca(ir.IntType(64), name=var_name)
                 # var.align = 8
@@ -160,11 +144,13 @@ def handle_assign(
                     local_sym_tab,
                     map_sym_tab,
                     structs_sym_tab,
+                    local_var_metadata,
                 )
-                builder.store(val[0], local_sym_tab[var_name].var)
-                logger.info(f"Assigned constant {rval.func.id} to {var_name}")
+                builder.store(val[0], local_sym_tab[var_name][0])
+                # local_sym_tab[var_name] = var
+                print(f"Assigned constant {rval.func.id} to {var_name}")
             elif call_type == "deref" and len(rval.args) == 1:
-                logger.info(f"Handling deref assignment {ast.dump(rval)}")
+                print(f"Handling deref assignment {ast.dump(rval)}")
                 val = eval_expr(
                     func,
                     module,
@@ -175,40 +161,28 @@ def handle_assign(
                     structs_sym_tab,
                 )
                 if val is None:
-                    logger.info("Failed to evaluate deref argument")
+                    print("Failed to evaluate deref argument")
                     return
-                logger.info(f"Dereferenced value: {val}, storing in {var_name}")
-                builder.store(val[0], local_sym_tab[var_name].var)
-                logger.info(f"Dereferenced and assigned to {var_name}")
+                print(f"Dereferenced value: {val}, storing in {var_name}")
+                builder.store(val[0], local_sym_tab[var_name][0])
+                # local_sym_tab[var_name] = var
+                print(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)
-                logger.info(f"Assigned struct {call_type} to {var_name}")
+                builder.store(ir.Constant(ir_type, None), local_sym_tab[var_name][0])
+                local_var_metadata[var_name] = call_type
+                print(f"Assigned struct {call_type} to {var_name}")
+                # local_sym_tab[var_name] = var
             else:
-                logger.info(f"Unsupported assignment call type: {call_type}")
+                print(f"Unsupported assignment call type: {call_type}")
         elif isinstance(rval.func, ast.Attribute):
-            logger.info(f"Assignment call attribute: {ast.dump(rval.func)}")
+            print(f"Assignment call attribute: {ast.dump(rval.func)}")
             if isinstance(rval.func.value, ast.Name):
-                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)}")
+                # TODO: probably a struct access
+                print(f"TODO STRUCT ACCESS {ast.dump(rval)}")
             elif isinstance(rval.func.value, ast.Call) and isinstance(
                 rval.func.value.func, ast.Name
             ):
@@ -224,18 +198,22 @@ def handle_assign(
                             local_sym_tab,
                             map_sym_tab,
                             structs_sym_tab,
+                            local_var_metadata,
                         )
                         # var = builder.alloca(ir.IntType(64), name=var_name)
                         # var.align = 8
-                        builder.store(val[0], local_sym_tab[var_name].var)
+                        builder.store(val[0], local_sym_tab[var_name][0])
+                        # local_sym_tab[var_name] = var
             else:
-                logger.info("Unsupported assignment call structure")
+                print("Unsupported assignment call structure")
         else:
-            logger.info("Unsupported assignment call function type")
+            print("Unsupported assignment call function type")
     elif isinstance(rval, ast.BinOp):
-        handle_binary_op(rval, module, builder, var_name, local_sym_tab)
+        handle_binary_op(
+            rval, module, builder, var_name, local_sym_tab, map_sym_tab, func
+        )
     else:
-        logger.info("Unsupported assignment value type")
+        print("Unsupported assignment value type")
 
 
 def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
@@ -245,11 +223,11 @@ 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:
-            logger.info("Unsupported constant type in condition")
+            print("Unsupported constant type in condition")
             return None
     elif isinstance(cond, ast.Name):
         if cond.id in local_sym_tab:
-            var = local_sym_tab[cond.id].var
+            var = local_sym_tab[cond.id][0]
             val = builder.load(var)
             if val.type != ir.IntType(1):
                 # Convert nonzero values to true, zero to false
@@ -262,12 +240,12 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
                 val = builder.icmp_signed("!=", val, zero)
             return val
         else:
-            logger.info(f"Undefined variable {cond.id} in condition")
+            print(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:
-            logger.info("Unsupported complex comparison")
+            print("Unsupported complex comparison")
             return None
         rhs = eval_expr(
             func, module, builder, cond.comparators[0], local_sym_tab, map_sym_tab
@@ -282,7 +260,7 @@ 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:
-                logger.info("Type mismatch in comparison")
+                print("Type mismatch in comparison")
                 return None
 
         if isinstance(op, ast.Eq):
@@ -298,10 +276,10 @@ 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:
-            logger.info("Unsupported comparison operator")
+            print("Unsupported comparison operator")
             return None
     else:
-        logger.info("Unsupported condition expression")
+        print("Unsupported condition expression")
         return None
 
 
@@ -309,7 +287,7 @@ def handle_if(
     func, module, builder, stmt, map_sym_tab, local_sym_tab, structs_sym_tab=None
 ):
     """Handle if statements in the function body."""
-    logger.info("Handling if statement")
+    print("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")
@@ -362,8 +340,9 @@ def process_stmt(
     did_return,
     ret_type=ir.IntType(64),
 ):
-    logger.info(f"Processing statement: {ast.dump(stmt)}")
+    print(f"Processing statement: {ast.dump(stmt)}")
     if isinstance(stmt, ast.Expr):
+        print(local_var_metadata)
         handle_expr(
             func,
             module,
@@ -372,6 +351,7 @@ def process_stmt(
             local_sym_tab,
             map_sym_tab,
             structs_sym_tab,
+            local_var_metadata,
         )
     elif isinstance(stmt, ast.Assign):
         handle_assign(
@@ -421,7 +401,6 @@ def allocate_mem(
     module, builder, body, func, ret_type, map_sym_tab, local_sym_tab, structs_sym_tab
 ):
     for stmt in body:
-        has_metadata = False
         if isinstance(stmt, ast.If):
             if stmt.body:
                 local_sym_tab = allocate_mem(
@@ -447,11 +426,11 @@ def allocate_mem(
                 )
         elif isinstance(stmt, ast.Assign):
             if len(stmt.targets) != 1:
-                logger.info("Unsupported multiassignment")
+                print("Unsupported multiassignment")
                 continue
             target = stmt.targets[0]
             if not isinstance(target, ast.Name):
-                logger.info("Unsupported assignment target")
+                print("Unsupported assignment target")
                 continue
             var_name = target.id
             rval = stmt.value
@@ -462,27 +441,25 @@ def allocate_mem(
                         ir_type = ctypes_to_ir(call_type)
                         var = builder.alloca(ir_type, name=var_name)
                         var.align = ir_type.width // 8
-                        logger.info(
-                            f"Pre-allocated variable {var_name} of type {call_type}"
-                        )
+                        print(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
-                        logger.info(f"Pre-allocated variable {var_name} for helper")
+                        print(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
-                        logger.info(f"Pre-allocated variable {var_name} for deref")
+                        print(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
-                        logger.info(
+                        local_var_metadata[var_name] = call_type
+                        print(
                             f"Pre-allocated variable {var_name} "
                             f"for struct {call_type}"
                         )
@@ -490,44 +467,40 @@ def allocate_mem(
                     ir_type = ir.PointerType(ir.IntType(64))
                     var = builder.alloca(ir_type, name=var_name)
                     # var.align = ir_type.width // 8
-                    logger.info(f"Pre-allocated variable {var_name} for map")
+                    print(f"Pre-allocated variable {var_name} for map")
                 else:
-                    logger.info("Unsupported assignment call function type")
+                    print("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
-                    logger.info(f"Pre-allocated variable {var_name} of type c_bool")
+                    print(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
-                    logger.info(f"Pre-allocated variable {var_name} of type c_int64")
+                    print(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
-                    logger.info(f"Pre-allocated variable {var_name} of type string")
+                    print(f"Pre-allocated variable {var_name} of type string")
                 else:
-                    logger.info("Unsupported constant type")
+                    print("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
-                logger.info(f"Pre-allocated variable {var_name} of type c_int64")
+                print(f"Pre-allocated variable {var_name} of type c_int64")
             else:
-                logger.info("Unsupported assignment value type")
+                print("Unsupported assignment value type")
                 continue
-
-            if has_metadata:
-                local_sym_tab[var_name] = LocalSymbol(var, ir_type, call_type)
-            else:
-                local_sym_tab[var_name] = LocalSymbol(var, ir_type)
+            local_sym_tab[var_name] = (var, ir_type)
     return local_sym_tab
 
 
@@ -552,7 +525,7 @@ def process_func_body(
         structs_sym_tab,
     )
 
-    logger.info(f"Local symbol table: {local_sym_tab.keys()}")
+    print(f"Local symbol table: {local_sym_tab.keys()}")
 
     for stmt in func_node.body:
         did_return = process_stmt(
@@ -624,7 +597,7 @@ def func_proc(tree, module, chunks, map_sym_tab, structs_sym_tab):
         if is_global:
             continue
         func_type = get_probe_string(func_node)
-        logger.info(f"Found probe_string of {func_node.name}: {func_type}")
+        print(f"Found probe_string of {func_node.name}: {func_type}")
 
         process_bpf_chunk(
             func_node,
@@ -689,7 +662,7 @@ def infer_return_type(func_node: ast.FunctionDef):
             if found_type is None:
                 found_type = t
             elif found_type != t:
-                raise ValueError(f"Conflicting return types: {found_type} vs {t}")
+                raise ValueError("Conflicting return types:" f"{found_type} vs {t}")
     return found_type or "None"
 
 

pythonbpf/globals_pass.py

@@ -1,121 +1,8 @@
 from llvmlite import ir
 import ast
 
-from logging import Logger
-import logging
-from .type_deducer import ctypes_to_ir
 
-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]):
+def emit_globals(module: ir.Module, names: list[str]):
     """
     Emit the @llvm.compiler.used global given a list of function/global names.
     """
@@ -137,7 +24,7 @@ def emit_llvm_compiler_used(module: ir.Module, names: list[str]):
     gv.section = "llvm.metadata"
 
 
-def globals_list_creation(tree, module: ir.Module):
+def globals_processing(tree, module: ir.Module):
     collected = ["LICENSE"]
 
     for node in tree.body:
@@ -153,11 +40,10 @@ def globals_list_creation(tree, module: ir.Module):
                 ):
                     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 == "bpfglobal":
+                    collected.append(node.name)
 
                 elif isinstance(dec, ast.Name) and dec.id == "map":
                     collected.append(node.name)
 
-    emit_llvm_compiler_used(module, collected)
+    emit_globals(module, collected)

pythonbpf/helper/bpf_helper_handler.py

@@ -9,10 +9,6 @@ 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):
@@ -23,6 +19,8 @@ class BPFHelperID(Enum):
     BPF_PRINTK = 6
     BPF_GET_CURRENT_PID_TGID = 14
     BPF_PERF_EVENT_OUTPUT = 25
+    BPF_RINGBUF_RESERVE = 131
+    BPF_RINGBUF_SUBMIT = 132
 
 
 @HelperHandlerRegistry.register("ktime")
@@ -34,6 +32,7 @@ def bpf_ktime_get_ns_emitter(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """
     Emit LLVM IR for bpf_ktime_get_ns helper function call.
@@ -56,6 +55,7 @@ def bpf_map_lookup_elem_emitter(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """
     Emit LLVM IR for bpf_map_lookup_elem helper function call.
@@ -91,6 +91,7 @@ def bpf_printk_emitter(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """Emit LLVM IR for bpf_printk helper function call."""
     if not hasattr(func, "_fmt_counter"):
@@ -108,6 +109,7 @@ def bpf_printk_emitter(
             func,
             local_sym_tab,
             struct_sym_tab,
+            local_var_metadata,
         )
     elif isinstance(call.args[0], ast.Constant) and isinstance(call.args[0].value, str):
         # TODO: We are only supporting single arguments for now.
@@ -138,6 +140,7 @@ def bpf_map_update_elem_emitter(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """
     Emit LLVM IR for bpf_map_update_elem helper function call.
@@ -179,6 +182,114 @@ def bpf_map_update_elem_emitter(
 
     return result, None
 
+@HelperHandlerRegistry.register("submit")
+def bpf_ringbuf_submit_emitter(
+    call,
+    map_ptr,
+    module,
+    builder,
+    func,
+    local_sym_tab=None,
+    struct_sym_tab=None,
+    local_var_metadata=None,
+):
+    """
+    Emit LLVM IR for bpf_ringbuf_submit helper function call.
+    Expected call signature: ringbuf.submit(data, flags=0)
+    """
+    if not call.args or len(call.args) < 1 or len(call.args) > 2:
+        raise ValueError(
+            "Ringbuf submit expects 1 or 2 args (data, flags), "
+            f"got {len(call.args)}"
+        )
+
+    data_arg = call.args[0]
+    data_ptr = get_or_create_ptr_from_arg(data_arg, builder, local_sym_tab)
+
+    # Get flags argument (default to 0)
+    flags_arg = call.args[1] if len(call.args) > 1 else None
+    flags_val = get_flags_val(flags_arg, builder, local_sym_tab)
+
+    # Returns: void
+    # Args: (void* data, u64 flags)
+    fn_type = ir.FunctionType(
+        ir.VoidType(),
+        [ir.PointerType(), ir.IntType(64)],
+        var_arg=False,
+    )
+    fn_ptr_type = ir.PointerType(fn_type)
+
+    fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_RINGBUF_SUBMIT.value)
+    fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
+
+    if isinstance(flags_val, int):
+        flags_const = ir.Constant(ir.IntType(64), flags_val)
+    else:
+        flags_const = flags_val
+
+    builder.call(fn_ptr, [data_ptr, flags_const], tail=True)
+
+    return None
+
+@HelperHandlerRegistry.register("reserve")
+def bpf_ringbuf_reserve_emitter(
+    call,
+    map_ptr,
+    module,
+    builder,
+    func,
+    local_sym_tab=None,
+    struct_sym_tab=None,
+    local_var_metadata=None,
+):
+    """
+    Emit LLVM IR for bpf_ringbuf_reserve helper function call.
+    Expected call signature: ringbuf.reserve(size, flags=0)
+    """
+    if not call.args or len(call.args) < 1 or len(call.args) > 2:
+        raise ValueError(
+            "Ringbuf reserve expects 1 or 2 args (size, flags), "
+            f"got {len(call.args)}"
+        )
+
+    # TODO: here, getting length of stuff does not actually work. need to fix this.
+    size_arg = call.args[0]
+    if isinstance(size_arg, ast.Constant):
+        size_val = ir.Constant(ir.IntType(64), size_arg.value)
+    elif isinstance(size_arg, ast.Name):
+        if size_arg.id not in local_sym_tab:
+            raise ValueError(
+                f"Variable '{size_arg.id}' not found in local symbol table"
+            )
+        size_val = builder.load(local_sym_tab[size_arg.id])
+    else:
+        raise NotImplementedError(f"Unsupported size argument type: {type(size_arg)}")
+
+    flags_arg = call.args[1] if len(call.args) > 1 else None
+    flags_val = get_flags_val(flags_arg, builder, local_sym_tab)
+
+    map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
+
+    # Args: (void* ringbuf, u64 size, u64 flags)
+    fn_type = ir.FunctionType(
+        ir.PointerType(),
+        [ir.PointerType(), ir.IntType(64), ir.IntType(64)],
+        var_arg=False,
+    )
+    fn_ptr_type = ir.PointerType(fn_type)
+
+    fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_RINGBUF_RESERVE.value)
+    fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
+
+    if isinstance(flags_val, int):
+        flags_const = ir.Constant(ir.IntType(64), flags_val)
+    else:
+        flags_const = flags_val
+
+    result = builder.call(fn_ptr, [map_void_ptr, size_val, flags_const], tail=True)
+
+    return result, ir.PointerType()
+
 
 @HelperHandlerRegistry.register("delete")
 def bpf_map_delete_elem_emitter(
@@ -189,6 +300,7 @@ def bpf_map_delete_elem_emitter(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """
     Emit LLVM IR for bpf_map_delete_elem helper function call.
@@ -226,6 +338,7 @@ def bpf_get_current_pid_tgid_emitter(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """
     Emit LLVM IR for bpf_get_current_pid_tgid helper function call.
@@ -252,6 +365,7 @@ def bpf_perf_event_output_handler(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     if len(call.args) != 1:
         raise ValueError(
@@ -260,7 +374,9 @@ def bpf_perf_event_output_handler(
     data_arg = call.args[0]
     ctx_ptr = func.args[0]  # First argument to the function is ctx
 
-    data_ptr, size_val = get_data_ptr_and_size(data_arg, local_sym_tab, struct_sym_tab)
+    data_ptr, size_val = get_data_ptr_and_size(
+        data_arg, local_sym_tab, struct_sym_tab, local_var_metadata
+    )
 
     # BPF_F_CURRENT_CPU is -1 in 32 bit
     flags_val = ir.Constant(ir.IntType(64), 0xFFFFFFFF)
@@ -298,6 +414,7 @@ def handle_helper_call(
     local_sym_tab=None,
     map_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """Process a BPF helper function call and emit the appropriate LLVM IR."""
 
@@ -316,6 +433,7 @@ def handle_helper_call(
             func,
             local_sym_tab,
             struct_sym_tab,
+            local_var_metadata,
         )
 
     # Handle direct function calls (e.g., print(), ktime())
@@ -326,7 +444,7 @@ def handle_helper_call(
     elif isinstance(call.func, ast.Attribute):
         method_name = call.func.attr
         value = call.func.value
-        logger.info(f"Handling method call: {ast.dump(call.func)}")
+        print(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/helper/helper_utils.py

@@ -37,7 +37,7 @@ class HelperHandlerRegistry:
 def get_var_ptr_from_name(var_name, local_sym_tab):
     """Get a pointer to a variable from the symbol table."""
     if local_sym_tab and var_name in local_sym_tab:
-        return local_sym_tab[var_name].var
+        return local_sym_tab[var_name][0]
     raise ValueError(f"Variable '{var_name}' not found in local symbol table")
 
 
@@ -72,7 +72,7 @@ def get_flags_val(arg, builder, local_sym_tab):
 
     if isinstance(arg, ast.Name):
         if local_sym_tab and arg.id in local_sym_tab:
-            flags_ptr = local_sym_tab[arg.id].var
+            flags_ptr = local_sym_tab[arg.id][0]
             return builder.load(flags_ptr)
         else:
             raise ValueError(f"Variable '{arg.id}' not found in local symbol table")
@@ -100,6 +100,7 @@ def handle_fstring_print(
     func,
     local_sym_tab=None,
     struct_sym_tab=None,
+    local_var_metadata=None,
 ):
     """Handle f-string formatting for bpf_printk emitter."""
     fmt_parts = []
@@ -117,6 +118,7 @@ def handle_fstring_print(
                 exprs,
                 local_sym_tab,
                 struct_sym_tab,
+                local_var_metadata,
             )
         else:
             raise NotImplementedError(f"Unsupported f-string value type: {type(value)}")
@@ -136,6 +138,7 @@ def handle_fstring_print(
             builder,
             local_sym_tab,
             struct_sym_tab,
+            local_var_metadata,
         )
         args.append(arg_value)
 
@@ -155,7 +158,9 @@ def _process_constant_in_fstring(cst, fmt_parts, exprs):
         )
 
 
-def _process_fval(fval, fmt_parts, exprs, local_sym_tab, struct_sym_tab):
+def _process_fval(
+    fval, fmt_parts, exprs, local_sym_tab, struct_sym_tab, local_var_metadata
+):
     """Process formatted values in f-string."""
     logger.debug(f"Processing formatted value: {ast.dump(fval)}")
 
@@ -168,6 +173,7 @@ def _process_fval(fval, fmt_parts, exprs, local_sym_tab, struct_sym_tab):
             exprs,
             local_sym_tab,
             struct_sym_tab,
+            local_var_metadata,
         )
     else:
         raise NotImplementedError(
@@ -178,11 +184,13 @@ def _process_fval(fval, fmt_parts, exprs, local_sym_tab, struct_sym_tab):
 def _process_name_in_fval(name_node, fmt_parts, exprs, local_sym_tab):
     """Process name nodes in formatted values."""
     if local_sym_tab and name_node.id in local_sym_tab:
-        _, var_type, tmp = local_sym_tab[name_node.id]
+        _, var_type = local_sym_tab[name_node.id]
         _populate_fval(var_type, name_node, fmt_parts, exprs)
 
 
-def _process_attr_in_fval(attr_node, fmt_parts, exprs, local_sym_tab, struct_sym_tab):
+def _process_attr_in_fval(
+    attr_node, fmt_parts, exprs, local_sym_tab, struct_sym_tab, local_var_metadata
+):
     """Process attribute nodes in formatted values."""
     if (
         isinstance(attr_node.value, ast.Name)
@@ -192,7 +200,12 @@ def _process_attr_in_fval(attr_node, fmt_parts, exprs, local_sym_tab, struct_sym
         var_name = attr_node.value.id
         field_name = attr_node.attr
 
-        var_type = local_sym_tab[var_name].metadata
+        if not local_var_metadata or var_name not in local_var_metadata:
+            raise ValueError(
+                f"Metadata for '{var_name}' not found in local var metadata"
+            )
+
+        var_type = local_var_metadata[var_name]
         if var_type not in struct_sym_tab:
             raise ValueError(
                 f"Struct '{var_type}' for '{var_name}' not in symbol table"
@@ -250,7 +263,9 @@ def _create_format_string_global(fmt_str, func, module, builder):
     return builder.bitcast(fmt_gvar, ir.PointerType())
 
 
-def _prepare_expr_args(expr, func, module, builder, local_sym_tab, struct_sym_tab):
+def _prepare_expr_args(
+    expr, func, module, builder, local_sym_tab, struct_sym_tab, local_var_metadata
+):
     """Evaluate and prepare an expression to use as an arg for bpf_printk."""
     val, _ = eval_expr(
         func,
@@ -260,6 +275,7 @@ def _prepare_expr_args(expr, func, module, builder, local_sym_tab, struct_sym_ta
         local_sym_tab,
         None,
         struct_sym_tab,
+        local_var_metadata,
     )
 
     if val:
@@ -282,26 +298,34 @@ def _prepare_expr_args(expr, func, module, builder, local_sym_tab, struct_sym_ta
         return ir.Constant(ir.IntType(64), 0)
 
 
-def get_data_ptr_and_size(data_arg, local_sym_tab, struct_sym_tab):
+def get_data_ptr_and_size(data_arg, local_sym_tab, struct_sym_tab, local_var_metadata):
     """Extract data pointer and size information for perf event output."""
     if isinstance(data_arg, ast.Name):
         data_name = data_arg.id
         if local_sym_tab and data_name in local_sym_tab:
-            data_ptr = local_sym_tab[data_name].var
+            data_ptr = local_sym_tab[data_name][0]
         else:
             raise ValueError(
                 f"Data variable {data_name} not found in local symbol table."
             )
 
         # Check if data_name is a struct
-        data_type = local_sym_tab[data_name].metadata
-        if data_type in struct_sym_tab:
-            struct_info = struct_sym_tab[data_type]
-            size_val = ir.Constant(ir.IntType(64), struct_info.size)
-            return data_ptr, size_val
+        if local_var_metadata and data_name in local_var_metadata:
+            data_type = local_var_metadata[data_name]
+            if data_type in struct_sym_tab:
+                struct_info = struct_sym_tab[data_type]
+                size_val = ir.Constant(ir.IntType(64), struct_info.size)
+                return data_ptr, size_val
+            else:
+                raise ValueError(
+                    f"Struct {data_type} for {data_name} not in symbol table."
+                )
         else:
-            raise ValueError(f"Struct {data_type} for {data_name} not in symbol table.")
+            raise ValueError(
+                f"Metadata for variable {data_name} "
+                "not found in local variable metadata."
+            )
     else:
         raise NotImplementedError(
-            "Only simple object names are supported as data in perf event output."
+            "Only simple object names are supported " "as data in perf event output."
         )

pythonbpf/license_pass.py

@@ -1,9 +1,5 @@
 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):
@@ -45,9 +41,9 @@ def license_processing(tree, module):
                         emit_license(module, node.body[0].value.value)
                         return "LICENSE"
                     else:
-                        logger.info("ERROR: LICENSE() must return a string literal")
+                        print("ERROR: LICENSE() must return a string literal")
                         return None
                 else:
-                    logger.info("ERROR: LICENSE already defined")
+                    print("ERROR: LICENSE already defined")
                     return None
     return None

pythonbpf/maps/maps_pass.py

@@ -85,7 +85,7 @@ def create_bpf_map(module, map_name, map_params):
 
 
 def create_map_debug_info(module, map_global, map_name, map_params):
-    """Generate debug info metadata for BPF maps HASH and PERF_EVENT_ARRAY"""
+    """Generate debug information metadata for BPF maps HASH and PERF_EVENT_ARRAY"""
     generator = DebugInfoGenerator(module)
 
     uint_type = generator.get_uint32_type()

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):
-            logger.info(f"Found BPF struct: {cls_node.name}")
+            print(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

@@ -1,27 +0,0 @@
-// 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/c-form/ringbuf.bpf.c

@@ -22,27 +22,29 @@ struct {
 SEC("tracepoint/syscalls/sys_enter_execve")
 int trace_execve(void *ctx)
 {
-    struct event *e;
-    __u64 pid_tgid;
-    __u64 uid_gid;
-
+//    struct event *e;
+//    __u64 pid_tgid;
+//    __u64 uid_gid;
+    __u32 *e;
     // Reserve space in the ringbuffer
     e = bpf_ringbuf_reserve(&events, sizeof(*e), 0);
     if (!e)
         return 0;
+//
+//    // Fill the struct with data
+//    pid_tgid = bpf_get_current_pid_tgid();
+//    e->pid = pid_tgid >> 32;
+//
+//    uid_gid = bpf_get_current_uid_gid();
+//    e->uid = uid_gid & 0xFFFFFFFF;
+//
+//    e->timestamp = bpf_ktime_get_ns();
 
-    // Fill the struct with data
-    pid_tgid = bpf_get_current_pid_tgid();
-    e->pid = pid_tgid >> 32;
-
-    uid_gid = bpf_get_current_uid_gid();
-    e->uid = uid_gid & 0xFFFFFFFF;
-
-    e->timestamp = bpf_ktime_get_ns();
-
-    bpf_get_current_comm(&e->comm, sizeof(e->comm));
-
-    // Submit the event to ringbuffer
+//    bpf_get_current_comm(&e->comm, sizeof(e->comm));
+//
+//    // Submit the event to ringbuffer
+    __u32 temp = 32;
+    e = &temp;
     bpf_ringbuf_submit(e, 0);
 
     return 0;

tests/failing_tests/binops.py

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

tests/failing_tests/binops1.py

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

tests/failing_tests/condition_issue.py

@@ -0,0 +1,33 @@
+from pythonbpf import bpf, map, bpfglobal, section, compile, compile_to_ir, BPF
+from pythonbpf.maps import RingBuf
+from ctypes import c_int32, c_void_p
+
+
+# Define a map
+@bpf
+@map
+def mymap() -> RingBuf:
+    return RingBuf(max_entries=(1024))
+
+@bpf
+@section("tracepoint/syscalls/sys_enter_clone")
+def random_section(ctx: c_void_p) -> c_int32:
+    e: c_int32 = mymap().reserve(64)
+    if e == 0:  # here is the issue i think
+        return c_int32(0)
+    mymap().submit(e)
+    return c_int32(0)
+
+
+@bpf
+@bpfglobal
+def LICENSE() -> str:
+    return "GPL"
+
+
+compile_to_ir("ringbuf.py", "ringbuf.ll")
+compile()
+b = BPF()
+b.load_and_attach()
+while True:
+    print("running")

tests/failing_tests/globals.py

@@ -1,101 +0,0 @@
-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

@@ -1,21 +0,0 @@
-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/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()
 

tests/passing_tests/ringbuf.py

@@ -1,5 +1,5 @@
-from pythonbpf import bpf, BPF, map, bpfglobal, section, compile, compile_to_ir
-from pythonbpf.maps import RingBuf, HashMap
+from pythonbpf import bpf, map, bpfglobal, section, compile, compile_to_ir, BPF
+from pythonbpf.maps import RingBuf
 from ctypes import c_int32, c_void_p
 
 
@@ -9,17 +9,13 @@ from ctypes import c_int32, c_void_p
 def mymap() -> RingBuf:
     return RingBuf(max_entries=(1024))
 
-
-@bpf
-@map
-def mymap2() -> HashMap:
-    return HashMap(key=c_int32, value=c_int32, max_entries=1024)
-
-
 @bpf
 @section("tracepoint/syscalls/sys_enter_clone")
 def random_section(ctx: c_void_p) -> c_int32:
     print("Hello")
+    e = mymap().reserve(6)
+    if e:
+        mymap().submit(e)
     return c_int32(0)
 
 
@@ -33,3 +29,5 @@ compile_to_ir("ringbuf.py", "ringbuf.ll")
 compile()
 b = BPF()
 b.load_and_attach()
+while True:
+    print("running")