3 Commits

58 changed files with 697 additions and 1678 deletions

View File

@ -21,7 +21,7 @@ ci:
repos:
# Standard hooks
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v6.0.0
rev: v4.6.0
hooks:
- id: check-added-large-files
- id: check-case-conflict
@ -36,19 +36,19 @@ repos:
- id: trailing-whitespace
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: "v0.13.2"
rev: "v0.4.2"
hooks:
- 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: "v1.18.2"
rev: "v1.10.0"
hooks:
- id: mypy
exclude: ^(tests)|^(examples)
exclude: ^(tests/|examples/)
additional_dependencies: [types-setuptools]
# Changes tabs to spaces

View File

@ -1,6 +1,7 @@
## Short term
- Implement enough functionality to port the BCC tutorial examples in PythonBPF
- Static Typing
- Add all maps
- XDP support in pylibbpf
- ringbuf support

View File

@ -12,7 +12,7 @@
"from pythonbpf import bpf, map, section, bpfglobal, BPF\n",
"from pythonbpf.helper import pid\n",
"from pythonbpf.maps import HashMap\n",
"from pylibbpf import BpfMap\n",
"from pylibbpf import *\n",
"from ctypes import c_void_p, c_int64, c_uint64, c_int32\n",
"import matplotlib.pyplot as plt"
]

View File

@ -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.

View File

@ -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)

View File

@ -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" },

View File

@ -1,72 +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
logger.info(f"Dereferencing {var}, type is {var.type}")
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, 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, builder, local_sym_tab)
raise TypeError(f"Unsupported operand type: {type(operand)}")
def handle_binary_op_impl(rval, 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, builder, local_sym_tab)
right = get_operand_value(rval.right, 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, builder, var_name, local_sym_tab):
result = handle_binary_op_impl(rval, builder, local_sym_tab)
if var_name and var_name in local_sym_tab:
logger.info(
f"Storing result {result} into variable {local_sym_tab[var_name].var}"
)
builder.store(result, local_sym_tab[var_name].var)
return result, result.type

View File

@ -1,23 +1,19 @@
import ast
from llvmlite import ir
from .license_pass import license_processing
from .functions import func_proc
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, DebugInfoGenerator
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):
@ -34,11 +30,11 @@ 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}")
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)
@ -48,10 +44,7 @@ def processor(source_code, filename, module):
globals_processing(tree, module)
def compile_to_ir(filename: str, output: str, loglevel=logging.INFO):
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()
@ -60,17 +53,33 @@ def compile_to_ir(filename: str, output: str, loglevel=logging.INFO):
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(
@ -112,7 +121,7 @@ def compile_to_ir(filename: str, output: str, loglevel=logging.INFO):
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))
@ -121,7 +130,7 @@ def compile_to_ir(filename: str, output: str, loglevel=logging.INFO):
return output
def compile(loglevel=logging.INFO) -> 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()
@ -130,9 +139,7 @@ def compile(loglevel=logging.INFO) -> 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(
@ -150,11 +157,11 @@ def compile(loglevel=logging.INFO) -> bool:
and success
)
logger.info(f"Object written to {o_file}")
print(f"Object written to {o_file}")
return success
def BPF(loglevel=logging.INFO) -> BpfProgram:
def BPF() -> BpfProgram:
caller_frame = inspect.stack()[1]
src = inspect.getsource(caller_frame.frame)
with tempfile.NamedTemporaryFile(
@ -167,7 +174,7 @@ def BPF(loglevel=logging.INFO) -> 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",

View File

@ -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)

View File

@ -1,4 +0,0 @@
from .expr_pass import eval_expr, handle_expr
from .type_normalization import convert_to_bool
__all__ = ["eval_expr", "handle_expr", "convert_to_bool"]

View File

@ -1,445 +0,0 @@
import ast
from llvmlite import ir
from logging import Logger
import logging
from typing import Dict
from pythonbpf.type_deducer import ctypes_to_ir, is_ctypes
from .type_normalization import convert_to_bool, handle_comparator
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) or isinstance(expr.value, bool):
return ir.Constant(ir.IntType(64), int(expr.value)), ir.IntType(64)
else:
logger.error("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 _handle_ctypes_call(
func,
module,
builder,
expr,
local_sym_tab,
map_sym_tab,
structs_sym_tab=None,
):
"""Handle ctypes type constructor calls."""
if len(expr.args) != 1:
logger.info("ctypes constructor takes exactly one argument")
return None
arg = expr.args[0]
val = eval_expr(
func,
module,
builder,
arg,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
if val is None:
logger.info("Failed to evaluate argument to ctypes constructor")
return None
call_type = expr.func.id
expected_type = ctypes_to_ir(call_type)
if val[1] != expected_type:
# NOTE: We are only considering casting to and from int types for now
if isinstance(val[1], ir.IntType) and isinstance(expected_type, ir.IntType):
if val[1].width < expected_type.width:
val = (builder.sext(val[0], expected_type), expected_type)
else:
val = (builder.trunc(val[0], expected_type), expected_type)
else:
raise ValueError(f"Type mismatch: expected {expected_type}, got {val[1]}")
return val
def _handle_compare(
func, module, builder, cond, local_sym_tab, map_sym_tab, structs_sym_tab=None
):
"""Handle ast.Compare expressions."""
if len(cond.ops) != 1 or len(cond.comparators) != 1:
logger.error("Only single comparisons are supported")
return None
lhs = eval_expr(
func,
module,
builder,
cond.left,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
rhs = eval_expr(
func,
module,
builder,
cond.comparators[0],
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
if lhs is None or rhs is None:
logger.error("Failed to evaluate comparison operands")
return None
lhs, _ = lhs
rhs, _ = rhs
return handle_comparator(func, builder, cond.ops[0], lhs, rhs)
def _handle_unary_op(
func,
module,
builder,
expr: ast.UnaryOp,
local_sym_tab,
map_sym_tab,
structs_sym_tab=None,
):
"""Handle ast.UnaryOp expressions."""
if not isinstance(expr.op, ast.Not):
logger.error("Only 'not' unary operator is supported")
return None
operand = eval_expr(
func, module, builder, expr.operand, local_sym_tab, map_sym_tab, structs_sym_tab
)
if operand is None:
logger.error("Failed to evaluate operand for unary operation")
return None
operand_val, operand_type = operand
true_const = ir.Constant(ir.IntType(1), 1)
result = builder.xor(convert_to_bool(builder, operand_val), true_const)
return result, ir.IntType(1)
def _handle_and_op(func, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab):
"""Handle `and` boolean operations."""
logger.debug(f"Handling 'and' operator with {len(expr.values)} operands")
merge_block = func.append_basic_block(name="and.merge")
false_block = func.append_basic_block(name="and.false")
incoming_values = []
for i, value in enumerate(expr.values):
is_last = i == len(expr.values) - 1
# Evaluate current operand
operand_result = eval_expr(
func, None, builder, value, local_sym_tab, map_sym_tab, structs_sym_tab
)
if operand_result is None:
logger.error(f"Failed to evaluate operand {i} in 'and' expression")
return None
operand_val, operand_type = operand_result
# Convert to boolean if needed
operand_bool = convert_to_bool(builder, operand_val)
current_block = builder.block
if is_last:
# Last operand: result is this value
builder.branch(merge_block)
incoming_values.append((operand_bool, current_block))
else:
# Not last: check if true, continue or short-circuit
next_check = func.append_basic_block(name=f"and.check_{i + 1}")
builder.cbranch(operand_bool, next_check, false_block)
builder.position_at_end(next_check)
# False block: short-circuit with false
builder.position_at_end(false_block)
builder.branch(merge_block)
false_value = ir.Constant(ir.IntType(1), 0)
incoming_values.append((false_value, false_block))
# Merge block: phi node
builder.position_at_end(merge_block)
phi = builder.phi(ir.IntType(1), name="and.result")
for val, block in incoming_values:
phi.add_incoming(val, block)
logger.debug(f"Generated 'and' with {len(incoming_values)} incoming values")
return phi, ir.IntType(1)
def _handle_or_op(func, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab):
"""Handle `or` boolean operations."""
logger.debug(f"Handling 'or' operator with {len(expr.values)} operands")
merge_block = func.append_basic_block(name="or.merge")
true_block = func.append_basic_block(name="or.true")
incoming_values = []
for i, value in enumerate(expr.values):
is_last = i == len(expr.values) - 1
# Evaluate current operand
operand_result = eval_expr(
func, None, builder, value, local_sym_tab, map_sym_tab, structs_sym_tab
)
if operand_result is None:
logger.error(f"Failed to evaluate operand {i} in 'or' expression")
return None
operand_val, operand_type = operand_result
# Convert to boolean if needed
operand_bool = convert_to_bool(builder, operand_val)
current_block = builder.block
if is_last:
# Last operand: result is this value
builder.branch(merge_block)
incoming_values.append((operand_bool, current_block))
else:
# Not last: check if false, continue or short-circuit
next_check = func.append_basic_block(name=f"or.check_{i + 1}")
builder.cbranch(operand_bool, true_block, next_check)
builder.position_at_end(next_check)
# True block: short-circuit with true
builder.position_at_end(true_block)
builder.branch(merge_block)
true_value = ir.Constant(ir.IntType(1), 1)
incoming_values.append((true_value, true_block))
# Merge block: phi node
builder.position_at_end(merge_block)
phi = builder.phi(ir.IntType(1), name="or.result")
for val, block in incoming_values:
phi.add_incoming(val, block)
logger.debug(f"Generated 'or' with {len(incoming_values)} incoming values")
return phi, ir.IntType(1)
def _handle_boolean_op(
func,
module,
builder,
expr: ast.BoolOp,
local_sym_tab,
map_sym_tab,
structs_sym_tab=None,
):
"""Handle `and` and `or` boolean operations."""
if isinstance(expr.op, ast.And):
return _handle_and_op(
func, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab
)
elif isinstance(expr.op, ast.Or):
return _handle_or_op(
func, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab
)
else:
logger.error(f"Unsupported boolean operator: {type(expr.op).__name__}")
return None
def eval_expr(
func,
module,
builder,
expr,
local_sym_tab,
map_sym_tab,
structs_sym_tab=None,
):
logger.info(f"Evaluating expression: {ast.dump(expr)}")
if isinstance(expr, ast.Name):
return _handle_name_expr(expr, local_sym_tab, builder)
elif isinstance(expr, ast.Constant):
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)
if isinstance(expr.func, ast.Name) and is_ctypes(expr.func.id):
return _handle_ctypes_call(
func,
module,
builder,
expr,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
# 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,
)
elif isinstance(expr.func, ast.Attribute):
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
):
method_name = expr.func.attr
if HelperHandlerRegistry.has_handler(method_name):
return handle_helper_call(
expr,
module,
builder,
func,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
elif isinstance(expr.func.value, ast.Name):
obj_name = expr.func.value.id
method_name = expr.func.attr
if obj_name in map_sym_tab:
if HelperHandlerRegistry.has_handler(method_name):
return handle_helper_call(
expr,
module,
builder,
func,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
elif isinstance(expr, ast.Attribute):
return _handle_attribute_expr(expr, local_sym_tab, structs_sym_tab, builder)
elif isinstance(expr, ast.BinOp):
from pythonbpf.binary_ops import handle_binary_op
return handle_binary_op(expr, builder, None, local_sym_tab)
elif isinstance(expr, ast.Compare):
return _handle_compare(
func, module, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab
)
elif isinstance(expr, ast.UnaryOp):
return _handle_unary_op(
func, module, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab
)
elif isinstance(expr, ast.BoolOp):
return _handle_boolean_op(
func, module, builder, expr, local_sym_tab, map_sym_tab, structs_sym_tab
)
logger.info("Unsupported expression evaluation")
return None
def handle_expr(
func,
module,
builder,
expr,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
):
"""Handle expression statements in the function body."""
logger.info(f"Handling expression: {ast.dump(expr)}")
call = expr.value
if isinstance(call, ast.Call):
eval_expr(
func,
module,
builder,
call,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
)
else:
logger.info("Unsupported expression type")

View File

@ -1,128 +0,0 @@
from llvmlite import ir
import logging
import ast
logger = logging.getLogger(__name__)
COMPARISON_OPS = {
ast.Eq: "==",
ast.NotEq: "!=",
ast.Lt: "<",
ast.LtE: "<=",
ast.Gt: ">",
ast.GtE: ">=",
ast.Is: "==",
ast.IsNot: "!=",
}
def _get_base_type_and_depth(ir_type):
"""Get the base type for pointer types."""
cur_type = ir_type
depth = 0
while isinstance(cur_type, ir.PointerType):
depth += 1
cur_type = cur_type.pointee
return cur_type, depth
def _deref_to_depth(func, builder, val, target_depth):
"""Dereference a pointer to a certain depth."""
cur_val = val
cur_type = val.type
for depth in range(target_depth):
if not isinstance(val.type, ir.PointerType):
logger.error("Cannot dereference further, non-pointer type")
return None
# dereference with null check
pointee_type = cur_type.pointee
null_check_block = builder.block
not_null_block = func.append_basic_block(name=f"deref_not_null_{depth}")
merge_block = func.append_basic_block(name=f"deref_merge_{depth}")
null_ptr = ir.Constant(cur_type, None)
is_not_null = builder.icmp_signed("!=", cur_val, null_ptr)
logger.debug(f"Inserted null check for pointer at depth {depth}")
builder.cbranch(is_not_null, not_null_block, merge_block)
builder.position_at_end(not_null_block)
dereferenced_val = builder.load(cur_val)
logger.debug(f"Dereferenced to depth {depth - 1}, type: {pointee_type}")
builder.branch(merge_block)
builder.position_at_end(merge_block)
phi = builder.phi(pointee_type, name=f"deref_result_{depth}")
zero_value = (
ir.Constant(pointee_type, 0)
if isinstance(pointee_type, ir.IntType)
else ir.Constant(pointee_type, None)
)
phi.add_incoming(zero_value, null_check_block)
phi.add_incoming(dereferenced_val, not_null_block)
# Continue with phi result
cur_val = phi
cur_type = pointee_type
return cur_val
def _normalize_types(func, builder, lhs, rhs):
"""Normalize types for comparison."""
logger.info(f"Normalizing types: {lhs.type} vs {rhs.type}")
if isinstance(lhs.type, ir.IntType) and isinstance(rhs.type, ir.IntType):
if lhs.type.width < rhs.type.width:
lhs = builder.sext(lhs, rhs.type)
else:
rhs = builder.sext(rhs, lhs.type)
return lhs, rhs
elif not isinstance(lhs.type, ir.PointerType) and not isinstance(
rhs.type, ir.PointerType
):
logger.error(f"Type mismatch: {lhs.type} vs {rhs.type}")
return None, None
else:
lhs_base, lhs_depth = _get_base_type_and_depth(lhs.type)
rhs_base, rhs_depth = _get_base_type_and_depth(rhs.type)
if lhs_base == rhs_base:
if lhs_depth < rhs_depth:
rhs = _deref_to_depth(func, builder, rhs, rhs_depth - lhs_depth)
elif rhs_depth < lhs_depth:
lhs = _deref_to_depth(func, builder, lhs, lhs_depth - rhs_depth)
return _normalize_types(func, builder, lhs, rhs)
def convert_to_bool(builder, val):
"""Convert a value to boolean."""
if val.type == ir.IntType(1):
return val
if isinstance(val.type, ir.PointerType):
zero = ir.Constant(val.type, None)
else:
zero = ir.Constant(val.type, 0)
return builder.icmp_signed("!=", val, zero)
def handle_comparator(func, builder, op, lhs, rhs):
"""Handle comparison operations."""
if lhs.type != rhs.type:
lhs, rhs = _normalize_types(func, builder, lhs, rhs)
if lhs is None or rhs is None:
return None
if type(op) not in COMPARISON_OPS:
logger.error(f"Unsupported comparison operator: {type(op)}")
return None
predicate = COMPARISON_OPS[type(op)]
result = builder.icmp_signed(predicate, lhs, rhs)
logger.debug(f"Comparison result: {result}")
return result, ir.IntType(1)

155
pythonbpf/expr_pass.py Normal file
View File

@ -0,0 +1,155 @@
import ast
from llvmlite import ir
def eval_expr(
func,
module,
builder,
expr,
local_sym_tab,
map_sym_tab,
structs_sym_tab=None,
local_var_metadata=None,
):
print(f"Evaluating expression: {ast.dump(expr)}")
print(local_var_metadata)
if isinstance(expr, ast.Name):
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):
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):
# 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][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):
print(f"Handling method call: {ast.dump(expr.func)}")
if isinstance(expr.func.value, ast.Call) and isinstance(
expr.func.value.func, ast.Name
):
method_name = expr.func.attr
if HelperHandlerRegistry.has_handler(method_name):
return handle_helper_call(
expr,
module,
builder,
func,
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
method_name = expr.func.attr
if obj_name in map_sym_tab:
if HelperHandlerRegistry.has_handler(method_name):
return handle_helper_call(
expr,
module,
builder,
func,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
)
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 = 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
def handle_expr(
func,
module,
builder,
expr,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
):
"""Handle expression statements in the function body."""
print(f"Handling expression: {ast.dump(expr)}")
print(local_var_metadata)
call = expr.value
if isinstance(call, ast.Call):
eval_expr(
func,
module,
builder,
call,
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
)
else:
print("Unsupported expression type")

View File

@ -1,3 +0,0 @@
from .functions_pass import func_proc
__all__ = ["func_proc"]

View File

@ -1,22 +0,0 @@
from typing import Dict
class StatementHandlerRegistry:
"""Registry for statement handlers."""
_handlers: Dict = {}
@classmethod
def register(cls, stmt_type):
"""Register a handler for a specific statement type."""
def decorator(handler):
cls._handlers[stmt_type] = handler
return handler
return decorator
@classmethod
def __getitem__(cls, stmt_type):
"""Get the handler for a specific statement type."""
return cls._handlers.get(stmt_type, None)

View File

@ -1,45 +0,0 @@
import logging
import ast
from llvmlite import ir
logger: logging.Logger = logging.getLogger(__name__)
XDP_ACTIONS = {
"XDP_ABORTED": 0,
"XDP_DROP": 1,
"XDP_PASS": 2,
"XDP_TX": 3,
"XDP_REDIRECT": 4,
}
def _handle_none_return(builder) -> bool:
"""Handle return or return None -> returns 0."""
builder.ret(ir.Constant(ir.IntType(64), 0))
logger.debug("Generated default return: 0")
return True
def _is_xdp_name(name: str) -> bool:
"""Check if a name is an XDP action"""
return name in XDP_ACTIONS
def _handle_xdp_return(stmt: ast.Return, builder, ret_type) -> bool:
"""Handle XDP returns"""
if not isinstance(stmt.value, ast.Name):
return False
action_name = stmt.value.id
if action_name not in XDP_ACTIONS:
raise ValueError(
f"Unknown XDP action: {action_name}. Available: {XDP_ACTIONS.keys()}"
)
return False
value = XDP_ACTIONS[action_name]
builder.ret(ir.Constant(ret_type, value))
logger.debug(f"Generated XDP action return: {action_name} = {value}")
return True

View File

@ -1,30 +1,13 @@
from llvmlite import ir
import ast
import logging
from typing import Any
from dataclasses import dataclass
from pythonbpf.helper import HelperHandlerRegistry, handle_helper_call
from pythonbpf.type_deducer import ctypes_to_ir
from pythonbpf.binary_ops import handle_binary_op
from pythonbpf.expr import eval_expr, handle_expr, convert_to_bool
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
from .return_utils import _handle_none_return, _handle_xdp_return, _is_xdp_name
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):
@ -49,27 +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,
@ -90,31 +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(
@ -127,14 +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
@ -145,12 +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(
f"Assigned {call_type} constant {rval.args[0].value} to {var_name}"
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
@ -162,11 +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,
@ -177,40 +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
):
@ -226,34 +198,96 @@ 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, 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, structs_sym_tab=None
):
val = eval_expr(
func, module, builder, cond, local_sym_tab, map_sym_tab, structs_sym_tab
)[0]
return convert_to_bool(builder, val)
def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
if isinstance(cond, ast.Constant):
if isinstance(cond.value, bool):
return ir.Constant(ir.IntType(1), int(cond.value))
elif isinstance(cond.value, int):
return ir.Constant(ir.IntType(1), int(bool(cond.value)))
else:
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][0]
val = builder.load(var)
if val.type != ir.IntType(1):
# Convert nonzero values to true, zero to false
if isinstance(val.type, ir.PointerType):
# For pointer types, compare with null pointer
zero = ir.Constant(val.type, None)
else:
# For integer types, compare with zero
zero = ir.Constant(val.type, 0)
val = builder.icmp_signed("!=", val, zero)
return val
else:
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:
print("Unsupported complex comparison")
return None
rhs = eval_expr(
func, module, builder, cond.comparators[0], local_sym_tab, map_sym_tab
)[0]
op = cond.ops[0]
if lhs.type != rhs.type:
if isinstance(lhs.type, ir.IntType) and isinstance(rhs.type, ir.IntType):
# Extend the smaller type to the larger type
if lhs.type.width < rhs.type.width:
lhs = builder.sext(lhs, rhs.type)
elif lhs.type.width > rhs.type.width:
rhs = builder.sext(rhs, lhs.type)
else:
print("Type mismatch in comparison")
return None
if isinstance(op, ast.Eq):
return builder.icmp_signed("==", lhs, rhs)
elif isinstance(op, ast.NotEq):
return builder.icmp_signed("!=", lhs, rhs)
elif isinstance(op, ast.Lt):
return builder.icmp_signed("<", lhs, rhs)
elif isinstance(op, ast.LtE):
return builder.icmp_signed("<=", lhs, rhs)
elif isinstance(op, ast.Gt):
return builder.icmp_signed(">", lhs, rhs)
elif isinstance(op, ast.GtE):
return builder.icmp_signed(">=", lhs, rhs)
else:
print("Unsupported comparison operator")
return None
else:
print("Unsupported condition expression")
return None
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")
@ -262,9 +296,7 @@ def handle_if(
else:
else_block = None
cond = handle_cond(
func, module, builder, stmt.test, local_sym_tab, map_sym_tab, structs_sym_tab
)
cond = handle_cond(func, module, builder, stmt.test, local_sym_tab, map_sym_tab)
if else_block:
builder.cbranch(cond, then_block, else_block)
else:
@ -297,27 +329,6 @@ def handle_if(
builder.position_at_end(merge_block)
def handle_return(builder, stmt, local_sym_tab, ret_type):
logger.info(f"Handling return statement: {ast.dump(stmt)}")
if stmt.value is None:
return _handle_none_return(builder)
elif isinstance(stmt.value, ast.Name) and _is_xdp_name(stmt.value.id):
return _handle_xdp_return(stmt, builder, ret_type)
else:
val = eval_expr(
func=None,
module=None,
builder=builder,
expr=stmt.value,
local_sym_tab=local_sym_tab,
map_sym_tab={},
structs_sym_tab={},
)
logger.info(f"Evaluated return expression to {val}")
builder.ret(val[0])
return True
def process_stmt(
func,
module,
@ -329,8 +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,
@ -339,6 +351,7 @@ def process_stmt(
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
)
elif isinstance(stmt, ast.Assign):
handle_assign(
@ -351,12 +364,36 @@ def process_stmt(
func, module, builder, stmt, map_sym_tab, local_sym_tab, structs_sym_tab
)
elif isinstance(stmt, ast.Return):
did_return = handle_return(
builder,
stmt,
local_sym_tab,
ret_type,
)
if stmt.value is None:
builder.ret(ir.Constant(ir.IntType(32), 0))
did_return = True
elif (
isinstance(stmt.value, ast.Call)
and isinstance(stmt.value.func, ast.Name)
and len(stmt.value.args) == 1
and isinstance(stmt.value.args[0], ast.Constant)
and isinstance(stmt.value.args[0].value, int)
):
call_type = stmt.value.func.id
if ctypes_to_ir(call_type) != ret_type:
raise ValueError(
"Return type mismatch: expected"
f"{ctypes_to_ir(call_type)}, got {call_type}"
)
else:
builder.ret(ir.Constant(ret_type, stmt.value.args[0].value))
did_return = True
elif isinstance(stmt.value, ast.Name):
if stmt.value.id == "XDP_PASS":
builder.ret(ir.Constant(ret_type, 2))
did_return = True
elif stmt.value.id == "XDP_DROP":
builder.ret(ir.Constant(ret_type, 1))
did_return = True
else:
raise ValueError("Failed to evaluate return expression")
else:
raise ValueError("Unsupported return value")
return did_return
@ -364,7 +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(
@ -390,17 +426,14 @@ 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
if var_name in local_sym_tab:
logger.info(f"Variable {var_name} already allocated")
continue
if isinstance(rval, ast.Call):
if isinstance(rval.func, ast.Name):
call_type = rval.func.id
@ -408,71 +441,66 @@ 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(
f"Pre-allocated variable {var_name} for struct {call_type}"
local_var_metadata[var_name] = call_type
print(
f"Pre-allocated variable {var_name} "
f"for struct {call_type}"
)
elif isinstance(rval.func, ast.Attribute):
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
@ -497,7 +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(
@ -513,7 +541,7 @@ def process_func_body(
)
if not did_return:
builder.ret(ir.Constant(ir.IntType(64), 0))
builder.ret(ir.Constant(ir.IntType(32), 0))
def process_bpf_chunk(func_node, module, return_type, map_sym_tab, structs_sym_tab):
@ -569,7 +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,
@ -634,7 +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"

View File

@ -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.
@ -56,13 +55,14 @@ 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.
"""
if not call.args or len(call.args) != 1:
raise ValueError(
f"Map lookup expects exactly one argument (key), got {len(call.args)}"
"Map lookup expects exactly one argument (key), got " f"{len(call.args)}"
)
key_ptr = get_or_create_ptr_from_arg(call.args[0], builder, local_sym_tab)
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
@ -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.
@ -145,7 +148,8 @@ def bpf_map_update_elem_emitter(
"""
if not call.args or len(call.args) < 2 or len(call.args) > 3:
raise ValueError(
f"Map update expects 2 or 3 args (key, value, flags), got {len(call.args)}"
"Map update expects 2 or 3 args (key, value, flags), "
f"got {len(call.args)}"
)
key_arg = call.args[0]
@ -178,6 +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(
@ -188,6 +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.
@ -195,7 +308,7 @@ def bpf_map_delete_elem_emitter(
"""
if not call.args or len(call.args) != 1:
raise ValueError(
f"Map delete expects exactly one argument (key), got {len(call.args)}"
"Map delete expects exactly one argument (key), got " f"{len(call.args)}"
)
key_ptr = get_or_create_ptr_from_arg(call.args[0], builder, local_sym_tab)
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
@ -225,6 +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.
@ -251,15 +365,18 @@ 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(
f"Perf event output expects exactly one argument, got {len(call.args)}"
"Perf event output expects exactly one argument, " f"got {len(call.args)}"
)
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)
@ -297,6 +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."""
@ -315,6 +433,7 @@ def handle_helper_call(
func,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
# Handle direct function calls (e.g., print(), ktime())
@ -325,7 +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)

View File

@ -3,7 +3,7 @@ import logging
from collections.abc import Callable
from llvmlite import ir
from pythonbpf.expr import eval_expr
from pythonbpf.expr_pass import eval_expr
logger = logging.getLogger(__name__)
@ -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:
@ -270,7 +286,7 @@ def _prepare_expr_args(expr, func, module, builder, local_sym_tab, struct_sym_ta
val = builder.sext(val, ir.IntType(64))
else:
logger.warning(
"Only int and ptr supported in bpf_printk args. Others default to 0."
"Only int and ptr supported in bpf_printk args. " "Others default to 0."
)
val = ir.Constant(ir.IntType(64), 0)
return 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."
)

View File

@ -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

View File

@ -3,7 +3,7 @@ from logging import Logger
from llvmlite import ir
from enum import Enum
from .maps_utils import MapProcessorRegistry
from pythonbpf.debuginfo import DebugInfoGenerator
from ..debuginfo import DebugInfoGenerator
import logging
logger: Logger = logging.getLogger(__name__)
@ -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()
@ -278,7 +278,9 @@ def process_bpf_map(func_node, module):
if handler:
return handler(map_name, rval, module)
else:
logger.warning(f"Unknown map type {rval.func.id}, defaulting to HashMap")
logger.warning(
f"Unknown map type " f"{rval.func.id}, defaulting to HashMap"
)
return process_hash_map(map_name, rval, module)
else:
raise ValueError("Function under @map must return a map")

View File

@ -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

View File

@ -1,28 +1,24 @@
from llvmlite import ir
# TODO: THIS IS NOT SUPPOSED TO MATCH STRINGS :skull:
mapping = {
"c_int8": ir.IntType(8),
"c_uint8": ir.IntType(8),
"c_int16": ir.IntType(16),
"c_uint16": ir.IntType(16),
"c_int32": ir.IntType(32),
"c_uint32": ir.IntType(32),
"c_int64": ir.IntType(64),
"c_uint64": ir.IntType(64),
"c_float": ir.FloatType(),
"c_double": ir.DoubleType(),
"c_void_p": ir.IntType(64),
# Not so sure about this one
"str": ir.PointerType(ir.IntType(8)),
}
def ctypes_to_ir(ctype: str):
mapping = {
"c_int8": ir.IntType(8),
"c_uint8": ir.IntType(8),
"c_int16": ir.IntType(16),
"c_uint16": ir.IntType(16),
"c_int32": ir.IntType(32),
"c_uint32": ir.IntType(32),
"c_int64": ir.IntType(64),
"c_uint64": ir.IntType(64),
"c_float": ir.FloatType(),
"c_double": ir.DoubleType(),
"c_void_p": ir.IntType(64),
# Not so sure about this one
"str": ir.PointerType(ir.IntType(8)),
}
if ctype in mapping:
return mapping[ctype]
raise NotImplementedError(f"No mapping for {ctype}")
def is_ctypes(ctype: str) -> bool:
return ctype in mapping

View File

@ -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;

View File

@ -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)

View File

@ -1,5 +1,3 @@
import logging
from pythonbpf import compile, bpf, section, bpfglobal
from ctypes import c_void_p, c_int64
@ -7,7 +5,8 @@ from ctypes import c_void_p, c_int64
@bpf
@section("sometag1")
def sometag(ctx: c_void_p) -> c_int64:
a = 1 - 1
b = 1 + 2
a = 1 + b
return c_int64(a)
@ -17,4 +16,4 @@ def LICENSE() -> str:
return "GPL"
compile(loglevel=logging.INFO)
compile()

View File

@ -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")

View File

@ -1,34 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
from pythonbpf.maps import HashMap
# NOTE: Decided against fixing this
# as a workaround is assigning the result of lookup to a variable
# and then using that variable in the if statement.
# Might fix in future.
@bpf
@map
def last() -> HashMap:
return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
last.update(0, 1)
if last.lookup(0) > 0:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,34 +0,0 @@
from pythonbpf import bpf, struct, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
# NOTE: Decided against fixing this
# as one workaround is to just check any field of the struct
# in the if statement. Ugly but works.
# Might fix in future.
@bpf
@struct
class data_t:
pid: c_uint64
ts: c_uint64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
dat = data_t()
if dat:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -4,18 +4,6 @@ from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int64
# NOTE: I have decided to not fix this example for now.
# The issue is in line 31, where we are passing an expression.
# The update helper expects a pointer type. But the problem is
# that we must allocate the space for said pointer in the first
# basic block. As that usage is in a different basic block, we
# are unable to cast the expression to a pointer type. (as we never
# allocated space for it).
# Shall we change our space allocation logic? That allows users to
# spam the same helper with the same args, and still run out of
# stack space. So we consider this usage invalid for now.
# Might fix it later.
@bpf
@map
@ -26,12 +14,12 @@ def count() -> HashMap:
@bpf
@section("xdp")
def hello_world(ctx: c_void_p) -> c_int64:
prev = count.lookup(0)
prev = count().lookup(0)
if prev:
count.update(0, prev + 1)
count().update(0, prev + 1)
return XDP_PASS
else:
count.update(0, 1)
count().update(0, 1)
return XDP_PASS

View File

@ -1,40 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from pythonbpf.helper import XDP_PASS
from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int64
# NOTE: This example exposes the problems with our typing system.
# We can't do steps on line 25 and 27.
# prev is of type i64**. For prev + 1, we deref it down to i64
# To assign it back to prev, we need to go back to i64**.
# We cannot allocate space for the intermediate type now.
# We probably need to track the ref/deref chain for each variable.
@bpf
@map
def count() -> HashMap:
return HashMap(key=c_int64, value=c_int64, max_entries=1)
@bpf
@section("xdp")
def hello_world(ctx: c_void_p) -> c_int64:
prev = count.lookup(0)
if prev:
prev = prev + 1
count.update(0, prev)
return XDP_PASS
else:
count.update(0, 1)
return XDP_PASS
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,20 +0,0 @@
from pythonbpf import compile, bpf, section, bpfglobal
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_sync")
def sometag(ctx: c_void_p) -> c_int64:
b = 1 + 2
a = 1 + b
print(f"{a}")
return c_int64(0)
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,32 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
from pythonbpf.maps import HashMap
@bpf
@map
def last() -> HashMap:
return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
last.update(0, 1)
last.update(1, 2)
x = last.lookup(0)
y = last.lookup(1)
if x and y:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,21 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
if True:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,21 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
if (0 + 1) * 0:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,21 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
if 0:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,30 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
from pythonbpf.maps import HashMap
@bpf
@map
def last() -> HashMap:
return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
# last.update(0, 1)
tsp = last.lookup(0)
if tsp:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,30 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
from pythonbpf.maps import HashMap
@bpf
@map
def last() -> HashMap:
return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
last.update(0, 1)
tsp = last.lookup(0)
if tsp > 0:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,30 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
from pythonbpf.maps import HashMap
@bpf
@map
def last() -> HashMap:
return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
# last.update(0, 1)
tsp = last.lookup(0)
if not tsp:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,32 +0,0 @@
from pythonbpf import bpf, map, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
from pythonbpf.maps import HashMap
@bpf
@map
def last() -> HashMap:
return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
last.update(0, 1)
# last.update(1, 2)
x = last.lookup(0)
y = last.lookup(1)
if x or y:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,29 +0,0 @@
from pythonbpf import bpf, struct, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_uint64
@bpf
@struct
class data_t:
pid: c_uint64
ts: c_uint64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
dat = data_t()
if dat.ts:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,23 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64, c_int32
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
x = 0
y = c_int32(0)
if x == y:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,22 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
x = 0
if x:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,22 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
x = 0
if x * 1:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,22 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
x = 2
if x > 3:
print("Hello, World!")
else:
print("Goodbye, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -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()

View File

@ -1,18 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
return 1 + 1 - 2
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,19 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
a = 2
return a - 2
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,18 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
return True
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,18 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
return 1
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,18 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
return
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,20 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int32
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int32:
print("Hello, World!")
a = 1 # int64
x = 1 # int64
return c_int32(a - x) # typecast to int32
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,18 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int32
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int32:
print("Hello, World!")
return c_int32(1)
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,19 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int32
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int32:
print("Hello, World!")
a = 1 # int64
return c_int32(a) # typecast to int32
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,19 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
a = 1
return a
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -1,19 +0,0 @@
from pythonbpf import bpf, section, bpfglobal, compile
from ctypes import c_void_p, c_int64
from pythonbpf.helper import XDP_PASS
@bpf
@section("tracepoint/syscalls/sys_enter_execve")
def hello_world(ctx: c_void_p) -> c_int64:
print("Hello, World!")
return XDP_PASS
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()

View File

@ -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")