15 Commits

16 changed files with 222 additions and 368 deletions

View File

@ -41,14 +41,14 @@ repos:
- id: ruff
args: ["--fix", "--show-fixes"]
- id: ruff-format
exclude: ^(tests/|examples/|docs/)
exclude: ^(docs)|^(tests)|^(examples)
# 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

View File

@ -22,5 +22,9 @@ 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

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

View File

@ -1,5 +1,9 @@
import ast
from llvmlite import ir
from logging import Logger
import logging
logger: Logger = logging.getLogger(__name__)
def recursive_dereferencer(var, builder):
@ -17,7 +21,7 @@ def recursive_dereferencer(var, builder):
def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab, func):
print(module)
logger.info(f"module {module}")
left = rval.left
right = rval.right
op = rval.op
@ -25,7 +29,7 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
# 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)
left = recursive_dereferencer(local_sym_tab[left.id].var, builder)
else:
raise SyntaxError(f"Undefined variable: {left.id}")
elif isinstance(left, ast.Constant):
@ -35,7 +39,7 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
if isinstance(right, ast.Name):
if right.id in local_sym_tab:
right = recursive_dereferencer(local_sym_tab[right.id][0], builder)
right = recursive_dereferencer(local_sym_tab[right.id].var, builder)
else:
raise SyntaxError(f"Undefined variable: {right.id}")
elif isinstance(right, ast.Constant):
@ -43,29 +47,29 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
else:
raise SyntaxError("Unsupported right operand type")
print(f"left is {left}, right is {right}, op is {op}")
logger.info(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])
builder.store(builder.add(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.Sub):
builder.store(builder.sub(left, right), local_sym_tab[var_name][0])
builder.store(builder.sub(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.Mult):
builder.store(builder.mul(left, right), local_sym_tab[var_name][0])
builder.store(builder.mul(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.Div):
builder.store(builder.sdiv(left, right), local_sym_tab[var_name][0])
builder.store(builder.sdiv(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.Mod):
builder.store(builder.srem(left, right), local_sym_tab[var_name][0])
builder.store(builder.srem(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.LShift):
builder.store(builder.shl(left, right), local_sym_tab[var_name][0])
builder.store(builder.shl(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.RShift):
builder.store(builder.lshr(left, right), local_sym_tab[var_name][0])
builder.store(builder.lshr(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.BitOr):
builder.store(builder.or_(left, right), local_sym_tab[var_name][0])
builder.store(builder.or_(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.BitXor):
builder.store(builder.xor(left, right), local_sym_tab[var_name][0])
builder.store(builder.xor(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.BitAnd):
builder.store(builder.and_(left, right), local_sym_tab[var_name][0])
builder.store(builder.and_(left, right), local_sym_tab[var_name].var)
elif isinstance(op, ast.FloorDiv):
builder.store(builder.udiv(left, right), local_sym_tab[var_name][0])
builder.store(builder.udiv(left, right), local_sym_tab[var_name].var)
else:
raise SyntaxError("Unsupported binary operation")

View File

@ -12,8 +12,12 @@ import inspect
from pathlib import Path
from pylibbpf import BpfProgram
import tempfile
from logging import Logger
import logging
VERSION = "v0.1.3"
logger: Logger = logging.getLogger(__name__)
VERSION = "v0.1.4"
def find_bpf_chunks(tree):
@ -30,11 +34,11 @@ def find_bpf_chunks(tree):
def processor(source_code, filename, module):
tree = ast.parse(source_code, filename)
print(ast.dump(tree, indent=4))
logger.debug(ast.dump(tree, indent=4))
bpf_chunks = find_bpf_chunks(tree)
for func_node in bpf_chunks:
print(f"Found BPF function/struct: {func_node.name}")
logger.info(f"Found BPF function/struct: {func_node.name}")
structs_sym_tab = structs_proc(tree, module, bpf_chunks)
map_sym_tab = maps_proc(tree, module, bpf_chunks)
@ -44,7 +48,10 @@ def processor(source_code, filename, module):
globals_processing(tree, module)
def compile_to_ir(filename: str, output: str):
def compile_to_ir(filename: str, output: str, loglevel=logging.WARNING):
logging.basicConfig(
level=loglevel, format="%(asctime)s [%(levelname)s] %(name)s: %(message)s"
)
with open(filename) as f:
source = f.read()
@ -121,7 +128,7 @@ def compile_to_ir(filename: str, output: str):
module.add_named_metadata("llvm.ident", [f"PythonBPF {VERSION}"])
print(f"IR written to {output}")
logger.info(f"IR written to {output}")
with open(output, "w") as f:
f.write(f'source_filename = "{filename}"\n')
f.write(str(module))
@ -130,7 +137,7 @@ def compile_to_ir(filename: str, output: str):
return output
def compile() -> bool:
def compile(loglevel=logging.WARNING) -> bool:
# Look one level up the stack to the caller of this function
caller_frame = inspect.stack()[1]
caller_file = Path(caller_frame.filename).resolve()
@ -139,7 +146,9 @@ def compile() -> bool:
o_file = caller_file.with_suffix(".o")
success = True
success = compile_to_ir(str(caller_file), str(ll_file)) and success
success = (
compile_to_ir(str(caller_file), str(ll_file), loglevel=loglevel) and success
)
success = bool(
subprocess.run(
@ -157,11 +166,11 @@ def compile() -> bool:
and success
)
print(f"Object written to {o_file}")
logger.info(f"Object written to {o_file}")
return success
def BPF() -> BpfProgram:
def BPF(loglevel=logging.WARNING) -> BpfProgram:
caller_frame = inspect.stack()[1]
src = inspect.getsource(caller_frame.frame)
with tempfile.NamedTemporaryFile(
@ -174,7 +183,7 @@ def BPF() -> BpfProgram:
f.write(src)
f.flush()
source = f.name
compile_to_ir(source, str(inter.name))
compile_to_ir(source, str(inter.name), loglevel=loglevel)
subprocess.run(
[
"llc",

View File

@ -1,5 +1,9 @@
import ast
from llvmlite import ir
from logging import Logger
import logging
logger: Logger = logging.getLogger(__name__)
def eval_expr(
@ -10,17 +14,15 @@ def eval_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)
logger.info(f"Evaluating expression: {ast.dump(expr)}")
if isinstance(expr, ast.Name):
if expr.id in local_sym_tab:
var = local_sym_tab[expr.id][0]
var = local_sym_tab[expr.id].var
val = builder.load(var)
return val, local_sym_tab[expr.id][1] # return value and type
return val, local_sym_tab[expr.id].ir_type # return value and type
else:
print(f"Undefined variable {expr.id}")
logger.info(f"Undefined variable {expr.id}")
return None
elif isinstance(expr, ast.Constant):
if isinstance(expr.value, int):
@ -28,7 +30,7 @@ def eval_expr(
elif isinstance(expr.value, bool):
return ir.Constant(ir.IntType(1), int(expr.value)), ir.IntType(1)
else:
print("Unsupported constant type")
logger.info("Unsupported constant type")
return None
elif isinstance(expr, ast.Call):
# delayed import to avoid circular dependency
@ -37,9 +39,9 @@ def eval_expr(
if isinstance(expr.func, ast.Name):
# check deref
if expr.func.id == "deref":
print(f"Handling deref {ast.dump(expr)}")
logger.info(f"Handling deref {ast.dump(expr)}")
if len(expr.args) != 1:
print("deref takes exactly one argument")
logger.info("deref takes exactly one argument")
return None
arg = expr.args[0]
if (
@ -47,20 +49,20 @@ def eval_expr(
and isinstance(arg.func, ast.Name)
and arg.func.id == "deref"
):
print("Multiple deref not supported")
logger.info("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]
arg = local_sym_tab[arg.id].var
else:
print(f"Undefined variable {arg.id}")
logger.info(f"Undefined variable {arg.id}")
return None
if arg is None:
print("Failed to evaluate deref argument")
logger.info("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]
return val, local_sym_tab[expr.args[0].id].ir_type
# check for helpers
if HelperHandlerRegistry.has_handler(expr.func.id):
@ -72,10 +74,9 @@ def eval_expr(
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)}")
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
):
@ -89,7 +90,6 @@ 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
@ -104,25 +104,22 @@ def eval_expr(
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")
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
logger.info("Unsupported expression evaluation")
return None
@ -134,11 +131,9 @@ def handle_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)
logger.info(f"Handling expression: {ast.dump(expr)}")
call = expr.value
if isinstance(call, ast.Call):
eval_expr(
@ -149,7 +144,6 @@ def handle_expr(
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
)
else:
print("Unsupported expression type")
logger.info("Unsupported expression type")

View File

@ -1,13 +1,27 @@
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
local_var_metadata: dict[str | Any, Any] = {}
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
def get_probe_string(func_node):
@ -32,28 +46,27 @@ def handle_assign(
):
"""Handle assignment statements in the function body."""
if len(stmt.targets) != 1:
print("Unsupported multiassignment")
logger.info("Unsupported multiassignment")
return
num_types = ("c_int32", "c_int64", "c_uint32", "c_uint64")
target = stmt.targets[0]
print(f"Handling assignment to {ast.dump(target)}")
logger.info(f"Handling assignment to {ast.dump(target)}")
if not isinstance(target, ast.Name) and not isinstance(target, ast.Attribute):
print("Unsupported assignment target")
logger.info("Unsupported assignment target")
return
var_name = target.id if isinstance(target, ast.Name) else target.value.id
rval = stmt.value
if isinstance(target, ast.Attribute):
# struct field assignment
field_name = target.attr
if var_name in local_sym_tab and var_name in local_var_metadata:
struct_type = local_var_metadata[var_name]
if var_name in local_sym_tab:
struct_type = local_sym_tab[var_name].metadata
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][0], field_name
builder, local_sym_tab[var_name].var, field_name
)
val = eval_expr(
func,
@ -74,28 +87,31 @@ def handle_assign(
# print(f"Assigned to struct field {var_name}.{field_name}")
pass
if val is None:
print("Failed to evaluate struct field assignment")
logger.info("Failed to evaluate struct field assignment")
return
print(field_ptr)
logger.info(field_ptr)
builder.store(val[0], field_ptr)
print(f"Assigned to struct field {var_name}.{field_name}")
logger.info(f"Assigned to struct field {var_name}.{field_name}")
return
elif isinstance(rval, ast.Constant):
if isinstance(rval.value, bool):
if rval.value:
builder.store(ir.Constant(ir.IntType(1), 1), local_sym_tab[var_name][0])
builder.store(
ir.Constant(ir.IntType(1), 1), local_sym_tab[var_name].var
)
else:
builder.store(ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name][0])
print(f"Assigned constant {rval.value} to {var_name}")
builder.store(
ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name].var
)
logger.info(f"Assigned constant {rval.value} to {var_name}")
elif isinstance(rval.value, int):
# Assume c_int64 for now
# var = builder.alloca(ir.IntType(64), name=var_name)
# var.align = 8
builder.store(
ir.Constant(ir.IntType(64), rval.value), local_sym_tab[var_name][0]
ir.Constant(ir.IntType(64), rval.value), local_sym_tab[var_name].var
)
# local_sym_tab[var_name] = var
print(f"Assigned constant {rval.value} to {var_name}")
logger.info(f"Assigned constant {rval.value} to {var_name}")
elif isinstance(rval.value, str):
str_val = rval.value.encode("utf-8") + b"\x00"
str_const = ir.Constant(
@ -108,14 +124,14 @@ 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][0])
print(f"Assigned string constant '{rval.value}' to {var_name}")
builder.store(str_ptr, local_sym_tab[var_name].var)
logger.info(f"Assigned string constant '{rval.value}' to {var_name}")
else:
print("Unsupported constant type")
logger.info("Unsupported constant type")
elif isinstance(rval, ast.Call):
if isinstance(rval.func, ast.Name):
call_type = rval.func.id
print(f"Assignment call type: {call_type}")
logger.info(f"Assignment call type: {call_type}")
if (
call_type in num_types
and len(rval.args) == 1
@ -126,13 +142,13 @@ 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][0]
ir.Constant(ir_type, rval.args[0].value),
local_sym_tab[var_name].var,
)
print(
logger.info(
f"Assigned {call_type} constant "
f"{rval.args[0].value} to {var_name}"
)
# local_sym_tab[var_name] = var
elif HelperHandlerRegistry.has_handler(call_type):
# var = builder.alloca(ir.IntType(64), name=var_name)
# var.align = 8
@ -144,13 +160,11 @@ def handle_assign(
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
)
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}")
builder.store(val[0], local_sym_tab[var_name].var)
logger.info(f"Assigned constant {rval.func.id} to {var_name}")
elif call_type == "deref" and len(rval.args) == 1:
print(f"Handling deref assignment {ast.dump(rval)}")
logger.info(f"Handling deref assignment {ast.dump(rval)}")
val = eval_expr(
func,
module,
@ -161,28 +175,25 @@ def handle_assign(
structs_sym_tab,
)
if val is None:
print("Failed to evaluate deref argument")
logger.info("Failed to evaluate deref argument")
return
print(f"Dereferenced value: {val}, storing in {var_name}")
builder.store(val[0], local_sym_tab[var_name][0])
# local_sym_tab[var_name] = var
print(f"Dereferenced and assigned to {var_name}")
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}")
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][0])
local_var_metadata[var_name] = call_type
print(f"Assigned struct {call_type} to {var_name}")
# local_sym_tab[var_name] = var
builder.store(ir.Constant(ir_type, None), local_sym_tab[var_name].var)
logger.info(f"Assigned struct {call_type} to {var_name}")
else:
print(f"Unsupported assignment call type: {call_type}")
logger.info(f"Unsupported assignment call type: {call_type}")
elif isinstance(rval.func, ast.Attribute):
print(f"Assignment call attribute: {ast.dump(rval.func)}")
logger.info(f"Assignment call attribute: {ast.dump(rval.func)}")
if isinstance(rval.func.value, ast.Name):
# TODO: probably a struct access
print(f"TODO STRUCT ACCESS {ast.dump(rval)}")
logger.info(f"TODO STRUCT ACCESS {ast.dump(rval)}")
elif isinstance(rval.func.value, ast.Call) and isinstance(
rval.func.value.func, ast.Name
):
@ -198,22 +209,20 @@ 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][0])
# local_sym_tab[var_name] = var
builder.store(val[0], local_sym_tab[var_name].var)
else:
print("Unsupported assignment call structure")
logger.info("Unsupported assignment call structure")
else:
print("Unsupported assignment call function type")
logger.info("Unsupported assignment call function type")
elif isinstance(rval, ast.BinOp):
handle_binary_op(
rval, module, builder, var_name, local_sym_tab, map_sym_tab, func
)
else:
print("Unsupported assignment value type")
logger.info("Unsupported assignment value type")
def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
@ -223,11 +232,11 @@ 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:
print("Unsupported constant type in condition")
logger.info("Unsupported constant type in condition")
return None
elif isinstance(cond, ast.Name):
if cond.id in local_sym_tab:
var = local_sym_tab[cond.id][0]
var = local_sym_tab[cond.id].var
val = builder.load(var)
if val.type != ir.IntType(1):
# Convert nonzero values to true, zero to false
@ -240,12 +249,12 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
val = builder.icmp_signed("!=", val, zero)
return val
else:
print(f"Undefined variable {cond.id} in condition")
logger.info(f"Undefined variable {cond.id} in condition")
return None
elif isinstance(cond, ast.Compare):
lhs = eval_expr(func, module, builder, cond.left, local_sym_tab, map_sym_tab)[0]
if len(cond.ops) != 1 or len(cond.comparators) != 1:
print("Unsupported complex comparison")
logger.info("Unsupported complex comparison")
return None
rhs = eval_expr(
func, module, builder, cond.comparators[0], local_sym_tab, map_sym_tab
@ -260,7 +269,7 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
elif lhs.type.width > rhs.type.width:
rhs = builder.sext(rhs, lhs.type)
else:
print("Type mismatch in comparison")
logger.info("Type mismatch in comparison")
return None
if isinstance(op, ast.Eq):
@ -276,10 +285,10 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
elif isinstance(op, ast.GtE):
return builder.icmp_signed(">=", lhs, rhs)
else:
print("Unsupported comparison operator")
logger.info("Unsupported comparison operator")
return None
else:
print("Unsupported condition expression")
logger.info("Unsupported condition expression")
return None
@ -287,7 +296,7 @@ def handle_if(
func, module, builder, stmt, map_sym_tab, local_sym_tab, structs_sym_tab=None
):
"""Handle if statements in the function body."""
print("Handling if statement")
logger.info("Handling if statement")
# start = builder.block.parent
then_block = func.append_basic_block(name="if.then")
merge_block = func.append_basic_block(name="if.end")
@ -340,9 +349,8 @@ def process_stmt(
did_return,
ret_type=ir.IntType(64),
):
print(f"Processing statement: {ast.dump(stmt)}")
logger.info(f"Processing statement: {ast.dump(stmt)}")
if isinstance(stmt, ast.Expr):
print(local_var_metadata)
handle_expr(
func,
module,
@ -351,7 +359,6 @@ def process_stmt(
local_sym_tab,
map_sym_tab,
structs_sym_tab,
local_var_metadata,
)
elif isinstance(stmt, ast.Assign):
handle_assign(
@ -401,6 +408,7 @@ 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(
@ -426,11 +434,11 @@ def allocate_mem(
)
elif isinstance(stmt, ast.Assign):
if len(stmt.targets) != 1:
print("Unsupported multiassignment")
logger.info("Unsupported multiassignment")
continue
target = stmt.targets[0]
if not isinstance(target, ast.Name):
print("Unsupported assignment target")
logger.info("Unsupported assignment target")
continue
var_name = target.id
rval = stmt.value
@ -441,25 +449,27 @@ def allocate_mem(
ir_type = ctypes_to_ir(call_type)
var = builder.alloca(ir_type, name=var_name)
var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} of type {call_type}")
logger.info(
f"Pre-allocated variable {var_name} of type {call_type}"
)
elif HelperHandlerRegistry.has_handler(call_type):
# Assume return type is int64 for now
ir_type = ir.IntType(64)
var = builder.alloca(ir_type, name=var_name)
var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} for helper")
logger.info(f"Pre-allocated variable {var_name} for helper")
elif call_type == "deref" and len(rval.args) == 1:
# Assume return type is int64 for now
ir_type = ir.IntType(64)
var = builder.alloca(ir_type, name=var_name)
var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} for deref")
logger.info(f"Pre-allocated variable {var_name} for deref")
elif call_type in structs_sym_tab:
struct_info = structs_sym_tab[call_type]
ir_type = struct_info.ir_type
var = builder.alloca(ir_type, name=var_name)
local_var_metadata[var_name] = call_type
print(
has_metadata = True
logger.info(
f"Pre-allocated variable {var_name} "
f"for struct {call_type}"
)
@ -467,40 +477,44 @@ def allocate_mem(
ir_type = ir.PointerType(ir.IntType(64))
var = builder.alloca(ir_type, name=var_name)
# var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} for map")
logger.info(f"Pre-allocated variable {var_name} for map")
else:
print("Unsupported assignment call function type")
logger.info("Unsupported assignment call function type")
continue
elif isinstance(rval, ast.Constant):
if isinstance(rval.value, bool):
ir_type = ir.IntType(1)
var = builder.alloca(ir_type, name=var_name)
var.align = 1
print(f"Pre-allocated variable {var_name} of type c_bool")
logger.info(f"Pre-allocated variable {var_name} of type c_bool")
elif isinstance(rval.value, int):
# Assume c_int64 for now
ir_type = ir.IntType(64)
var = builder.alloca(ir_type, name=var_name)
var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} of type c_int64")
logger.info(f"Pre-allocated variable {var_name} of type c_int64")
elif isinstance(rval.value, str):
ir_type = ir.PointerType(ir.IntType(8))
var = builder.alloca(ir_type, name=var_name)
var.align = 8
print(f"Pre-allocated variable {var_name} of type string")
logger.info(f"Pre-allocated variable {var_name} of type string")
else:
print("Unsupported constant type")
logger.info("Unsupported constant type")
continue
elif isinstance(rval, ast.BinOp):
# Assume c_int64 for now
ir_type = ir.IntType(64)
var = builder.alloca(ir_type, name=var_name)
var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} of type c_int64")
logger.info(f"Pre-allocated variable {var_name} of type c_int64")
else:
print("Unsupported assignment value type")
logger.info("Unsupported assignment value type")
continue
local_sym_tab[var_name] = (var, ir_type)
if has_metadata:
local_sym_tab[var_name] = LocalSymbol(var, ir_type, call_type)
else:
local_sym_tab[var_name] = LocalSymbol(var, ir_type)
return local_sym_tab
@ -525,7 +539,7 @@ def process_func_body(
structs_sym_tab,
)
print(f"Local symbol table: {local_sym_tab.keys()}")
logger.info(f"Local symbol table: {local_sym_tab.keys()}")
for stmt in func_node.body:
did_return = process_stmt(
@ -597,7 +611,7 @@ def func_proc(tree, module, chunks, map_sym_tab, structs_sym_tab):
if is_global:
continue
func_type = get_probe_string(func_node)
print(f"Found probe_string of {func_node.name}: {func_type}")
logger.info(f"Found probe_string of {func_node.name}: {func_type}")
process_bpf_chunk(
func_node,
@ -662,7 +676,7 @@ def infer_return_type(func_node: ast.FunctionDef):
if found_type is None:
found_type = t
elif found_type != t:
raise ValueError("Conflicting return types:" f"{found_type} vs {t}")
raise ValueError(f"Conflicting return types: {found_type} vs {t}")
return found_type or "None"

View File

@ -9,6 +9,10 @@ from .helper_utils import (
simple_string_print,
get_data_ptr_and_size,
)
from logging import Logger
import logging
logger: Logger = logging.getLogger(__name__)
class BPFHelperID(Enum):
@ -19,8 +23,6 @@ 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")
@ -32,7 +34,6 @@ 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.
@ -55,7 +56,6 @@ 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.
@ -91,7 +91,6 @@ 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"):
@ -109,7 +108,6 @@ 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.
@ -140,7 +138,6 @@ 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.
@ -182,114 +179,6 @@ 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(
@ -300,7 +189,6 @@ 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.
@ -338,7 +226,6 @@ 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.
@ -365,7 +252,6 @@ 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(
@ -374,9 +260,7 @@ 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, local_var_metadata
)
data_ptr, size_val = get_data_ptr_and_size(data_arg, local_sym_tab, struct_sym_tab)
# BPF_F_CURRENT_CPU is -1 in 32 bit
flags_val = ir.Constant(ir.IntType(64), 0xFFFFFFFF)
@ -414,7 +298,6 @@ 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."""
@ -433,7 +316,6 @@ def handle_helper_call(
func,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
# Handle direct function calls (e.g., print(), ktime())
@ -444,7 +326,7 @@ def handle_helper_call(
elif isinstance(call.func, ast.Attribute):
method_name = call.func.attr
value = call.func.value
print(f"Handling method call: {ast.dump(call.func)}")
logger.info(f"Handling method call: {ast.dump(call.func)}")
# Get map pointer from different styles of map access
if isinstance(value, ast.Call) and isinstance(value.func, ast.Name):
# Func style: my_map().lookup(key)

View File

@ -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][0]
return local_sym_tab[var_name].var
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][0]
flags_ptr = local_sym_tab[arg.id].var
return builder.load(flags_ptr)
else:
raise ValueError(f"Variable '{arg.id}' not found in local symbol table")
@ -100,7 +100,6 @@ 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 = []
@ -118,7 +117,6 @@ 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)}")
@ -138,7 +136,6 @@ def handle_fstring_print(
builder,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
args.append(arg_value)
@ -158,9 +155,7 @@ def _process_constant_in_fstring(cst, fmt_parts, exprs):
)
def _process_fval(
fval, fmt_parts, exprs, local_sym_tab, struct_sym_tab, local_var_metadata
):
def _process_fval(fval, fmt_parts, exprs, local_sym_tab, struct_sym_tab):
"""Process formatted values in f-string."""
logger.debug(f"Processing formatted value: {ast.dump(fval)}")
@ -173,7 +168,6 @@ def _process_fval(
exprs,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
else:
raise NotImplementedError(
@ -184,13 +178,11 @@ def _process_fval(
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 = local_sym_tab[name_node.id]
_, var_type, tmp = 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, local_var_metadata
):
def _process_attr_in_fval(attr_node, fmt_parts, exprs, local_sym_tab, struct_sym_tab):
"""Process attribute nodes in formatted values."""
if (
isinstance(attr_node.value, ast.Name)
@ -200,12 +192,7 @@ def _process_attr_in_fval(
var_name = attr_node.value.id
field_name = attr_node.attr
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]
var_type = local_sym_tab[var_name].metadata
if var_type not in struct_sym_tab:
raise ValueError(
f"Struct '{var_type}' for '{var_name}' not in symbol table"
@ -263,9 +250,7 @@ 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, local_var_metadata
):
def _prepare_expr_args(expr, func, module, builder, local_sym_tab, struct_sym_tab):
"""Evaluate and prepare an expression to use as an arg for bpf_printk."""
val, _ = eval_expr(
func,
@ -275,7 +260,6 @@ def _prepare_expr_args(
local_sym_tab,
None,
struct_sym_tab,
local_var_metadata,
)
if val:
@ -298,34 +282,26 @@ def _prepare_expr_args(
return ir.Constant(ir.IntType(64), 0)
def get_data_ptr_and_size(data_arg, local_sym_tab, struct_sym_tab, local_var_metadata):
def get_data_ptr_and_size(data_arg, local_sym_tab, struct_sym_tab):
"""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][0]
data_ptr = local_sym_tab[data_name].var
else:
raise ValueError(
f"Data variable {data_name} not found in local symbol table."
)
# Check if data_name is a struct
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."
)
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
else:
raise ValueError(
f"Metadata for variable {data_name} "
"not found in local variable metadata."
)
raise ValueError(f"Struct {data_type} for {data_name} not in symbol table.")
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

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

View File

@ -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 information metadata for BPF maps HASH and PERF_EVENT_ARRAY"""
"""Generate debug info metadata for BPF maps HASH and PERF_EVENT_ARRAY"""
generator = DebugInfoGenerator(module)
uint_type = generator.get_uint32_type()

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):
print(f"Found BPF struct: {cls_node.name}")
logger.info(f"Found BPF struct: {cls_node.name}")
struct_info = process_bpf_struct(cls_node, module)
structs_sym_tab[cls_node.name] = struct_info
return structs_sym_tab

View File

@ -22,29 +22,27 @@ struct {
SEC("tracepoint/syscalls/sys_enter_execve")
int trace_execve(void *ctx)
{
// struct event *e;
// __u64 pid_tgid;
// __u64 uid_gid;
__u32 *e;
struct event *e;
__u64 pid_tgid;
__u64 uid_gid;
// 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();
// bpf_get_current_comm(&e->comm, sizeof(e->comm));
//
// // Submit the event to ringbuffer
__u32 temp = 32;
e = &temp;
// 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_ringbuf_submit(e, 0);
return 0;

View File

@ -1,33 +0,0 @@
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

@ -1,7 +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

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, bpfglobal, section, compile, compile_to_ir, BPF
from pythonbpf.maps import RingBuf
from pythonbpf import bpf, BPF, map, bpfglobal, section, compile, compile_to_ir
from pythonbpf.maps import RingBuf, HashMap
from ctypes import c_int32, c_void_p
@ -9,13 +9,17 @@ 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)
@ -29,5 +33,3 @@ compile_to_ir("ringbuf.py", "ringbuf.ll")
compile()
b = BPF()
b.load_and_attach()
while True:
print("running")