62 Commits

Author SHA1 Message Date
7bc711c296 Update pythonbpf/functions_pass.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-10-02 05:01:32 +05:30
80c3519b95 Fix local_sym_tab usage in binary_ops 2025-10-02 04:58:39 +05:30
71b97e3e20 Add iter to LocalSymbol 2025-10-02 04:56:34 +05:30
12ba3605e9 Fix local_sym_tab usage in helpers 2025-10-02 04:53:04 +05:30
d7427f306f Fix usage of local_sym_tab in expr_pass 2025-10-02 04:50:31 +05:30
0142381ce2 Remove local_var_metadata from expr_pass 2025-10-02 04:44:14 +05:30
9223d7b5c5 Remove local_var_metadata from helpers 2025-10-02 04:40:44 +05:30
3b74ade455 Remove occurences of local_var_metadata from functions_pass, use LocalSymbol.var 2025-10-02 04:35:10 +05:30
dadcb69f1c Store LocalSymbol in allocate_mem 2025-10-02 04:27:10 +05:30
2fd2a46838 Add LocalSymbol dataclass 2025-10-02 04:13:24 +05:30
1a66887f48 move helper annotations to helpers module 2025-10-02 01:55:32 +05:30
23f3cbcea7 add type annotations 2025-10-02 01:43:05 +05:30
429f51437f Merge pull request #15 from pythonbpf/static-type-checks
Static type checks
2025-10-02 01:38:46 +05:30
c92272dd35 workflow update 2025-10-02 01:37:36 +05:30
8792740eb0 workflow update 2025-10-02 01:36:14 +05:30
cf5faaad7f remove pointless type annotation
Signed-off-by: varun-r-mallya <varunrmallya@gmail.com>
2025-10-02 01:27:03 +05:30
59b3d6514b fix ruff errors 2025-10-02 01:23:55 +05:30
3c956e671a add static type checking
Signed-off-by: varun-r-mallya <varunrmallya@gmail.com>
2025-10-02 01:11:54 +05:30
8650297866 make type checks viable 2025-10-02 00:51:23 +05:30
6831f11179 Fix fstrings in examples, add alternate map attr access 2025-10-02 00:22:59 +05:30
d4e8e1bf73 Fix unterminated fstrings 2025-10-02 00:14:51 +05:30
08f2b283c9 Merge pull request #10 from pythonbpf/helper-refactor
bpf_helper_handler refactor
2025-10-02 00:08:59 +05:30
c38ecf6623 Merge branch 'master' into helper-refactor 2025-10-02 00:06:19 +05:30
81807ace34 Fix simple_string_print docstring 2025-10-01 23:59:07 +05:30
2f02f94b61 Merge pull request #14 from pythonbpf/ringbuf
make default map unspec
2025-10-01 23:58:54 +05:30
690ff7ffbc Remove unnecessary prints 2025-10-01 23:57:22 +05:30
bda88d3f8e make default map unspec 2025-10-01 23:57:00 +05:30
ba3e02052d Register output in HelperHandlerRegistry 2025-10-01 23:56:16 +05:30
9099b3eaec Replace logger.warn with logger.warning 2025-10-01 23:55:16 +05:30
03da7c5cfc Merge pull request #13 from pythonbpf/ringbuf
Add ringbuf support
2025-10-01 23:52:28 +05:30
cecf45061c Fix line length nitpicks 2025-10-01 23:51:25 +05:30
da9df2e6bf add ringbuf map type 2025-10-01 23:51:18 +05:30
929eef31ef Add has_handler to HelperHandlerRegistry 2025-10-01 23:38:38 +05:30
28cc0c5eec Refactor handle_helper_call 2025-10-01 23:32:27 +05:30
99d6c193f6 Fix calling of _simple_string_print 2025-10-01 22:53:19 +05:30
4f33db206c Refactor bpf_perf_event_output_emitter 2025-10-01 22:49:50 +05:30
6ccbab402f Complete printk refactor 2025-10-01 22:12:30 +05:30
7b01f1dde3 Complete helpers for fstrings in helper_utils 2025-10-01 21:43:11 +05:30
8ceb1d1ac3 add int32 type 2025-10-01 21:39:16 +05:30
668343532f add map types for completion 2025-10-01 21:22:44 +05:30
84ad58b775 Add ringbuf type hinting. 2025-10-01 21:14:20 +05:30
17f60d721b Add _process_*_in_fval to helper_utils 2025-10-01 20:26:18 +05:30
d18c69fae1 Add _handle_fstring_print scaffolding 2025-10-01 19:56:20 +05:30
9c58116c82 Use get_flags_val in bpf_map_update_elem_emitter 2025-10-01 18:38:18 +05:30
18f164bdec Add get_flags_val to helper_utils 2025-10-01 18:35:11 +05:30
8d9ff2df3b Fix import in sys_sync example 2025-10-01 18:28:40 +05:30
ffcd2de44d Replace usage of get_key_ptr with get_or_create_ptr_from_arg 2025-10-01 18:25:22 +05:30
8dd2746411 rename get_key_ptr to get_or_create_ptr_from_arg 2025-10-01 18:21:42 +05:30
7f6c318069 Use get_key_ptr in map_update helper 2025-10-01 18:14:32 +05:30
d2e0f17ca8 Use key_arg instead of call in get_key_ptr 2025-10-01 18:14:09 +05:30
4af6c4dcad Refactor bpf_map_delete_elem_emitter 2025-10-01 18:00:51 +05:30
5c8b132cb9 Add responsive images for light and dark modes
Updated image display for light and dark modes in README.
2025-10-01 17:45:23 +05:30
244ea143d4 Refactor bpf_map_lookup_elem_emitter, add utils 2025-10-01 17:36:05 +05:30
58c372bcb3 Merge pull request #12 from pythonbpf/ruff-errors
Ruff errors
2025-10-01 16:11:54 +05:30
168ab29be3 Format function definitions in bpf_helper_handler 2025-10-01 04:04:32 +05:30
61f6743f0a Use HelperHandleRegitry 2025-10-01 03:53:11 +05:30
6cd07498fe Create HelperProcessorRegistry 2025-10-01 03:07:36 +05:30
c27da22bcb remove ruff errors. May contain breaking changes. 2025-10-01 00:54:04 +05:30
b095828ae2 remove some ruff errors 2025-10-01 00:49:23 +05:30
7e45864552 Move helper scripts to a new dir, make temp fixes to allow this 2025-09-30 23:57:31 +05:30
fa2ff0a242 Use BPFHelperID Enums in bpf_helper_handler 2025-09-30 23:51:05 +05:30
c1466a5bca Add BPFHelperID enum to bpf_helper_handler 2025-09-30 23:43:29 +05:30
34 changed files with 1063 additions and 822 deletions

View File

@ -5,10 +5,7 @@ name: Format
on: on:
workflow_dispatch: workflow_dispatch:
pull_request:
push: push:
branches:
- master
jobs: jobs:
pre-commit: pre-commit:

View File

@ -35,22 +35,21 @@ repos:
- id: requirements-txt-fixer - id: requirements-txt-fixer
- id: trailing-whitespace - id: trailing-whitespace
#- repo: https://github.com/astral-sh/ruff-pre-commit - repo: https://github.com/astral-sh/ruff-pre-commit
# rev: "v0.4.2" rev: "v0.4.2"
# hooks: hooks:
# - id: ruff - id: ruff
# args: ["--fix", "--show-fixes"] args: ["--fix", "--show-fixes"]
# - id: ruff-format - id: ruff-format
# exclude: ^(docs) exclude: ^(docs)|^(tests)|^(examples)
## Checking static types # Checking static types
#- repo: https://github.com/pre-commit/mirrors-mypy - repo: https://github.com/pre-commit/mirrors-mypy
# rev: "v1.10.0" rev: "v1.10.0"
# hooks: hooks:
# - id: mypy - id: mypy
# files: "setup.py" exclude: ^(tests)|^(examples)
# args: [] additional_dependencies: [types-setuptools]
# additional_dependencies: [types-setuptools]
# Changes tabs to spaces # Changes tabs to spaces
- repo: https://github.com/Lucas-C/pre-commit-hooks - repo: https://github.com/Lucas-C/pre-commit-hooks

View File

@ -1,4 +1,14 @@
<img src="https://github.com/user-attachments/assets/b175bf39-23cb-475d-a6e1-7b5c99a1ed72" alt="pythonbpf" width="450"> <picture>
<source
media="(prefers-color-scheme: light)"
srcset="https://github.com/user-attachments/assets/f3738131-d7cb-4b5c-8699-c7010295a159"
width="450"
alt="Lightmode image">
<img
src="https://github.com/user-attachments/assets/b175bf39-23cb-475d-a6e1-7b5c99a1ed72"
width="450"
alt="Darkmode image">
</picture>
<!-- Badges --> <!-- Badges -->
<p align="center"> <p align="center">
<!-- PyPI --> <!-- PyPI -->
@ -50,12 +60,13 @@ pip install pythonbpf pylibbpf
```python ```python
import time import time
from pythonbpf import bpf, map, section, bpfglobal, BPF from pythonbpf import bpf, map, section, bpfglobal, BPF
from pythonbpf.helpers import pid from pythonbpf.helper import pid
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from pylibbpf import * from pylibbpf import *
from ctypes import c_void_p, c_int64, c_uint64, c_int32 from ctypes import c_void_p, c_int64, c_uint64, c_int32
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
# This program attaches an eBPF tracepoint to sys_enter_clone, # This program attaches an eBPF tracepoint to sys_enter_clone,
# counts per-PID clone syscalls, stores them in a hash map, # counts per-PID clone syscalls, stores them in a hash map,
# and then plots the distribution as a histogram using matplotlib. # and then plots the distribution as a histogram using matplotlib.
@ -66,6 +77,7 @@ import matplotlib.pyplot as plt
def hist() -> HashMap: def hist() -> HashMap:
return HashMap(key=c_int32, value=c_uint64, max_entries=4096) return HashMap(key=c_int32, value=c_uint64, max_entries=4096)
@bpf @bpf
@section("tracepoint/syscalls/sys_enter_clone") @section("tracepoint/syscalls/sys_enter_clone")
def hello(ctx: c_void_p) -> c_int64: def hello(ctx: c_void_p) -> c_int64:

View File

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, section, bpfglobal, compile from pythonbpf import bpf, map, section, bpfglobal, compile
from pythonbpf.helpers import ktime from pythonbpf.helper import ktime
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int64, c_uint64 from ctypes import c_void_p, c_int64, c_uint64

View File

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, section, bpfglobal, compile from pythonbpf import bpf, map, section, bpfglobal, compile
from pythonbpf.helpers import ktime from pythonbpf.helper import ktime
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int32, c_uint64 from ctypes import c_void_p, c_int32, c_uint64

View File

@ -10,7 +10,7 @@
"import time\n", "import time\n",
"\n", "\n",
"from pythonbpf import bpf, map, section, bpfglobal, BPF\n", "from pythonbpf import bpf, map, section, bpfglobal, BPF\n",
"from pythonbpf.helpers import pid\n", "from pythonbpf.helper import pid\n",
"from pythonbpf.maps import HashMap\n", "from pythonbpf.maps import HashMap\n",
"from pylibbpf import *\n", "from pylibbpf import *\n",
"from ctypes import c_void_p, c_int64, c_uint64, c_int32\n", "from ctypes import c_void_p, c_int64, c_uint64, c_int32\n",

View File

@ -1,9 +1,9 @@
import time import time
from pythonbpf import bpf, map, section, bpfglobal, BPF from pythonbpf import bpf, map, section, bpfglobal, BPF
from pythonbpf.helpers import pid from pythonbpf.helper import pid
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from pylibbpf import * from pylibbpf import BpfMap
from ctypes import c_void_p, c_int64, c_uint64, c_int32 from ctypes import c_void_p, c_int64, c_uint64, c_int32
import matplotlib.pyplot as plt import matplotlib.pyplot as plt

View File

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, struct, section, bpfglobal, compile from pythonbpf import bpf, map, struct, section, bpfglobal, compile
from pythonbpf.helpers import ktime, pid from pythonbpf.helper import ktime, pid
from pythonbpf.maps import PerfEventArray from pythonbpf.maps import PerfEventArray
from ctypes import c_void_p, c_int32, c_uint64 from ctypes import c_void_p, c_int32, c_uint64
@ -23,13 +23,11 @@ def events() -> PerfEventArray:
@section("tracepoint/syscalls/sys_enter_clone") @section("tracepoint/syscalls/sys_enter_clone")
def hello(ctx: c_void_p) -> c_int32: def hello(ctx: c_void_p) -> c_int32:
dataobj = data_t() dataobj = data_t()
ts = ktime()
process_id = pid()
strobj = "hellohellohello" strobj = "hellohellohello"
dataobj.pid = pid() dataobj.pid = pid()
dataobj.ts = ktime() dataobj.ts = ktime()
# dataobj.comm = strobj # dataobj.comm = strobj
print(f"clone called at {dataobj.ts} by pid {dataobj.pid}, comm {strobj}") print(f"clone called at {dataobj.ts} by pid" f"{dataobj.pid}, comm {strobj}")
events.output(dataobj) events.output(dataobj)
return c_int32(0) return c_int32(0)

View File

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, section, bpfglobal, compile from pythonbpf import bpf, map, section, bpfglobal, compile
from pythonbpf.helpers import ktime from pythonbpf.helper import ktime
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int64, c_uint64 from ctypes import c_void_p, c_int64, c_uint64

View File

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, section, bpfglobal, compile from pythonbpf import bpf, map, section, bpfglobal, compile
from pythonbpf.helpers import XDP_PASS from pythonbpf.helper import XDP_PASS
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int64 from ctypes import c_void_p, c_int64

View File

@ -1,2 +1,13 @@
from .decorators import bpf, map, section, bpfglobal, struct from .decorators import bpf, map, section, bpfglobal, struct
from .codegen import compile_to_ir, compile, BPF from .codegen import compile_to_ir, compile, BPF
__all__ = [
"bpf",
"map",
"section",
"bpfglobal",
"struct",
"compile_to_ir",
"compile",
"BPF",
]

View File

@ -25,7 +25,7 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
# Handle left operand # Handle left operand
if isinstance(left, ast.Name): if isinstance(left, ast.Name):
if left.id in local_sym_tab: 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: else:
raise SyntaxError(f"Undefined variable: {left.id}") raise SyntaxError(f"Undefined variable: {left.id}")
elif isinstance(left, ast.Constant): elif isinstance(left, ast.Constant):
@ -35,7 +35,7 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
if isinstance(right, ast.Name): if isinstance(right, ast.Name):
if right.id in local_sym_tab: 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: else:
raise SyntaxError(f"Undefined variable: {right.id}") raise SyntaxError(f"Undefined variable: {right.id}")
elif isinstance(right, ast.Constant): elif isinstance(right, ast.Constant):
@ -46,26 +46,26 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
print(f"left is {left}, right is {right}, op is {op}") print(f"left is {left}, right is {right}, op is {op}")
if isinstance(op, ast.Add): 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): 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): 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): 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): 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): 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): 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): 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): 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): 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): 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: else:
raise SyntaxError("Unsupported binary operation") raise SyntaxError("Unsupported binary operation")

View File

@ -1,654 +0,0 @@
import ast
from llvmlite import ir
from .expr_pass import eval_expr
def bpf_ktime_get_ns_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
local_var_metadata=None,
):
"""
Emit LLVM IR for bpf_ktime_get_ns helper function call.
"""
# func is an arg to just have a uniform signature with other emitters
helper_id = ir.Constant(ir.IntType(64), 5)
fn_type = ir.FunctionType(ir.IntType(64), [], var_arg=False)
fn_ptr_type = ir.PointerType(fn_type)
fn_ptr = builder.inttoptr(helper_id, fn_ptr_type)
result = builder.call(fn_ptr, [], tail=False)
return result, ir.IntType(64)
def bpf_map_lookup_elem_emitter(
call,
map_ptr,
module,
builder,
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 call.args and len(call.args) != 1:
raise ValueError(
"Map lookup expects exactly one argument, got " f"{len(call.args)}"
)
key_arg = call.args[0]
if isinstance(key_arg, ast.Name):
key_name = key_arg.id
if local_sym_tab and key_name in local_sym_tab:
key_ptr = local_sym_tab[key_name][0]
else:
raise ValueError(
f"Key variable {key_name} not found in local symbol table."
)
elif isinstance(key_arg, ast.Constant) and isinstance(key_arg.value, int):
# handle constant integer keys
key_val = key_arg.value
key_type = ir.IntType(64)
key_ptr = builder.alloca(key_type)
key_ptr.align = key_type // 8
builder.store(ir.Constant(key_type, key_val), key_ptr)
else:
raise NotImplementedError(
"Only simple variable names are supported as keys in map lookup."
)
if key_ptr is None:
raise ValueError("Key pointer is None.")
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
fn_type = ir.FunctionType(
ir.PointerType(), # Return type: void*
[ir.PointerType(), ir.PointerType()], # Args: (void*, void*)
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
# Helper ID 1 is bpf_map_lookup_elem
fn_addr = ir.Constant(ir.IntType(64), 1)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
result = builder.call(fn_ptr, [map_void_ptr, key_ptr], tail=False)
return result, ir.PointerType()
def bpf_printk_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
local_var_metadata=None,
):
if not hasattr(func, "_fmt_counter"):
func._fmt_counter = 0
if not call.args:
raise ValueError("print expects at least one argument")
if isinstance(call.args[0], ast.JoinedStr):
fmt_parts = []
exprs = []
for value in call.args[0].values:
print("Value in f-string:", ast.dump(value))
if isinstance(value, ast.Constant):
if isinstance(value.value, str):
fmt_parts.append(value.value)
elif isinstance(value.value, int):
fmt_parts.append("%lld")
exprs.append(ir.Constant(ir.IntType(64), value.value))
else:
raise NotImplementedError(
"Only string and integer constants are supported in f-string."
)
elif isinstance(value, ast.FormattedValue):
print("Formatted value:", ast.dump(value))
# TODO: Dirty handling here, only checks for int or str
if isinstance(value.value, ast.Name):
if local_sym_tab and value.value.id in local_sym_tab:
var_ptr, var_type = local_sym_tab[value.value.id]
if isinstance(var_type, ir.IntType):
fmt_parts.append("%lld")
exprs.append(value.value)
elif var_type == ir.PointerType(ir.IntType(8)):
# Case with string
fmt_parts.append("%s")
exprs.append(value.value)
else:
raise NotImplementedError(
"Only integer and pointer types are supported in formatted values."
)
else:
raise ValueError(
f"Variable {value.value.id} not found in local symbol table."
)
elif isinstance(value.value, ast.Attribute):
# object field access from struct
if (
isinstance(value.value.value, ast.Name)
and local_sym_tab
and value.value.value.id in local_sym_tab
):
var_name = value.value.value.id
field_name = value.value.attr
if local_var_metadata and var_name in local_var_metadata:
var_type = local_var_metadata[var_name]
if var_type in struct_sym_tab:
struct_info = struct_sym_tab[var_type]
if field_name in struct_info.fields:
field_type = struct_info.field_type(field_name)
if isinstance(field_type, ir.IntType):
fmt_parts.append("%lld")
exprs.append(value.value)
elif field_type == ir.PointerType(ir.IntType(8)):
fmt_parts.append("%s")
exprs.append(value.value)
else:
raise NotImplementedError(
"Only integer and pointer types are supported in formatted values."
)
else:
raise ValueError(
f"Field {field_name} not found in struct {var_type}."
)
else:
raise ValueError(
f"Struct type {var_type} for variable {var_name} not found in struct symbol table."
)
else:
raise ValueError(
f"Metadata for variable {var_name} not found in local variable metadata."
)
else:
raise ValueError(
f"Variable {value.value.value.id} not found in local symbol table."
)
else:
raise NotImplementedError(
"Only simple variable names are supported in formatted values."
)
else:
raise NotImplementedError("Unsupported value type in f-string.")
fmt_str = "".join(fmt_parts) + "\n" + "\0"
fmt_name = f"{func.name}____fmt{func._fmt_counter}"
func._fmt_counter += 1
fmt_gvar = ir.GlobalVariable(
module, ir.ArrayType(ir.IntType(8), len(fmt_str)), name=fmt_name
)
fmt_gvar.global_constant = True
fmt_gvar.initializer = ir.Constant( # type: ignore
ir.ArrayType(ir.IntType(8), len(fmt_str)), bytearray(fmt_str.encode("utf8"))
)
fmt_gvar.linkage = "internal"
fmt_gvar.align = 1 # type: ignore
fmt_ptr = builder.bitcast(fmt_gvar, ir.PointerType())
args = [fmt_ptr, ir.Constant(ir.IntType(32), len(fmt_str))]
# Only 3 args supported in bpf_printk
if len(exprs) > 3:
print(
"Warning: bpf_printk supports up to 3 arguments, extra arguments will be ignored."
)
for expr in exprs[:3]:
print(f"{ast.dump(expr)}")
val, _ = eval_expr(
func,
module,
builder,
expr,
local_sym_tab,
None,
struct_sym_tab,
local_var_metadata,
)
if val:
if isinstance(val.type, ir.PointerType):
val = builder.ptrtoint(val, ir.IntType(64))
elif isinstance(val.type, ir.IntType):
if val.type.width < 64:
val = builder.sext(val, ir.IntType(64))
else:
print(
"Warning: Only integer and pointer types are supported in bpf_printk arguments. Others will be converted to 0."
)
val = ir.Constant(ir.IntType(64), 0)
args.append(val)
else:
print(
"Warning: Failed to evaluate expression for bpf_printk argument. It will be converted to 0."
)
args.append(ir.Constant(ir.IntType(64), 0))
fn_type = ir.FunctionType(
ir.IntType(64), [ir.PointerType(), ir.IntType(32)], var_arg=True
)
fn_ptr_type = ir.PointerType(fn_type)
fn_addr = ir.Constant(ir.IntType(64), 6)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
return builder.call(fn_ptr, args, tail=True)
for arg in call.args:
if isinstance(arg, ast.Constant) and isinstance(arg.value, str):
fmt_str = arg.value + "\n" + "\0"
fmt_name = f"{func.name}____fmt{func._fmt_counter}"
func._fmt_counter += 1
fmt_gvar = ir.GlobalVariable(
module, ir.ArrayType(ir.IntType(8), len(fmt_str)), name=fmt_name
)
fmt_gvar.global_constant = True
fmt_gvar.initializer = ir.Constant( # type: ignore
ir.ArrayType(ir.IntType(8), len(fmt_str)),
bytearray(fmt_str.encode("utf8")),
)
fmt_gvar.linkage = "internal"
fmt_gvar.align = 1 # type: ignore
fmt_ptr = builder.bitcast(fmt_gvar, ir.PointerType())
fn_type = ir.FunctionType(
ir.IntType(64), [ir.PointerType(), ir.IntType(32)], var_arg=True
)
fn_ptr_type = ir.PointerType(fn_type)
fn_addr = ir.Constant(ir.IntType(64), 6)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
builder.call(
fn_ptr, [fmt_ptr, ir.Constant(ir.IntType(32), len(fmt_str))], tail=True
)
return None
def bpf_map_update_elem_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
local_var_metadata=None,
):
"""
Emit LLVM IR for bpf_map_update_elem helper function call.
Expected call signature: map.update(key, value, flags=0)
"""
if not call.args or len(call.args) < 2 or len(call.args) > 3:
raise ValueError(
"Map update expects 2 or 3 arguments (key, value, flags), got "
f"{len(call.args)}"
)
key_arg = call.args[0]
value_arg = call.args[1]
flags_arg = call.args[2] if len(call.args) > 2 else None
# Handle key
if isinstance(key_arg, ast.Name):
key_name = key_arg.id
if local_sym_tab and key_name in local_sym_tab:
key_ptr = local_sym_tab[key_name][0]
else:
raise ValueError(
f"Key variable {key_name} not found in local symbol table."
)
elif isinstance(key_arg, ast.Constant) and isinstance(key_arg.value, int):
# Handle constant integer keys
key_val = key_arg.value
key_type = ir.IntType(64)
key_ptr = builder.alloca(key_type)
key_ptr.align = key_type.width // 8
builder.store(ir.Constant(key_type, key_val), key_ptr)
else:
raise NotImplementedError(
"Only simple variable names and integer constants are supported as keys in map update."
)
# Handle value
if isinstance(value_arg, ast.Name):
value_name = value_arg.id
if local_sym_tab and value_name in local_sym_tab:
value_ptr = local_sym_tab[value_name][0]
else:
raise ValueError(
f"Value variable {value_name} not found in local symbol table."
)
elif isinstance(value_arg, ast.Constant) and isinstance(value_arg.value, int):
# Handle constant integers
value_val = value_arg.value
value_type = ir.IntType(64)
value_ptr = builder.alloca(value_type)
value_ptr.align = value_type.width // 8
builder.store(ir.Constant(value_type, value_val), value_ptr)
else:
raise NotImplementedError(
"Only simple variable names and integer constants are supported as values in map update."
)
# Handle flags argument (defaults to 0)
if flags_arg is not None:
if isinstance(flags_arg, ast.Constant) and isinstance(flags_arg.value, int):
flags_val = flags_arg.value
elif isinstance(flags_arg, ast.Name):
flags_name = flags_arg.id
if local_sym_tab and flags_name in local_sym_tab:
# Assume it's a stored integer value, load it
flags_ptr = local_sym_tab[flags_name][0]
flags_val = builder.load(flags_ptr)
else:
raise ValueError(
f"Flags variable {flags_name} not found in local symbol table."
)
else:
raise NotImplementedError(
"Only integer constants and simple variable names are supported as flags in map update."
)
else:
flags_val = 0
if key_ptr is None or value_ptr is None:
raise ValueError("Key pointer or value pointer is None.")
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
fn_type = ir.FunctionType(
ir.IntType(64),
[ir.PointerType(), ir.PointerType(), ir.PointerType(), ir.IntType(64)],
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
# helper id
fn_addr = ir.Constant(ir.IntType(64), 2)
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, key_ptr, value_ptr, flags_const], tail=False
)
return result, None
def bpf_map_delete_elem_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
local_var_metadata=None,
):
"""
Emit LLVM IR for bpf_map_delete_elem helper function call.
Expected call signature: map.delete(key)
"""
# Check for correct number of arguments
if not call.args or len(call.args) != 1:
raise ValueError(
"Map delete expects exactly 1 argument (key), got " f"{len(call.args)}"
)
key_arg = call.args[0]
# Handle key argument
if isinstance(key_arg, ast.Name):
key_name = key_arg.id
if local_sym_tab and key_name in local_sym_tab:
key_ptr = local_sym_tab[key_name][0]
else:
raise ValueError(
f"Key variable {key_name} not found in local symbol table."
)
elif isinstance(key_arg, ast.Constant) and isinstance(key_arg.value, int):
# Handle constant integer keys
key_val = key_arg.value
key_type = ir.IntType(64)
key_ptr = builder.alloca(key_type)
key_ptr.align = key_type.width // 8
builder.store(ir.Constant(key_type, key_val), key_ptr)
else:
raise NotImplementedError(
"Only simple variable names and integer constants are supported as keys in map delete."
)
if key_ptr is None:
raise ValueError("Key pointer is None.")
# Cast map pointer to void*
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
# Define function type for bpf_map_delete_elem
fn_type = ir.FunctionType(
ir.IntType(64), # Return type: int64 (status code)
[ir.PointerType(), ir.PointerType()], # Args: (void*, void*)
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
# Helper ID 3 is bpf_map_delete_elem
fn_addr = ir.Constant(ir.IntType(64), 3)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
# Call the helper function
result = builder.call(fn_ptr, [map_void_ptr, key_ptr], tail=False)
return result, None
def bpf_get_current_pid_tgid_emitter(
call,
map_ptr,
module,
builder,
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.
"""
# func is an arg to just have a uniform signature with other emitters
helper_id = ir.Constant(ir.IntType(64), 14)
fn_type = ir.FunctionType(ir.IntType(64), [], var_arg=False)
fn_ptr_type = ir.PointerType(fn_type)
fn_ptr = builder.inttoptr(helper_id, fn_ptr_type)
result = builder.call(fn_ptr, [], tail=False)
# Extract the lower 32 bits (PID) using bitwise AND with 0xFFFFFFFF
mask = ir.Constant(ir.IntType(64), 0xFFFFFFFF)
pid = builder.and_(result, mask)
return pid, ir.IntType(64)
def bpf_perf_event_output_handler(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
local_var_metadata=None,
):
if len(call.args) != 1:
raise ValueError(
"Perf event output expects exactly one argument (data), got "
f"{len(call.args)}"
)
data_arg = call.args[0]
ctx_ptr = func.args[0] # First argument to the function is ctx
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]
else:
raise ValueError(
f"Data variable {data_name} not found in local symbol table."
)
# Check is 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)
else:
raise ValueError(
f"Struct type {data_type} for variable {data_name} not found in struct symbol table."
)
else:
raise ValueError(
f"Metadata for variable {data_name} not found in local variable metadata."
)
# BPF_F_CURRENT_CPU is -1 in 32 bit
flags_val = ir.Constant(ir.IntType(64), 0xFFFFFFFF)
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
data_void_ptr = builder.bitcast(data_ptr, ir.PointerType())
fn_type = ir.FunctionType(
ir.IntType(64),
[
ir.PointerType(ir.IntType(8)),
ir.PointerType(),
ir.IntType(64),
ir.PointerType(),
ir.IntType(64),
],
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
# helper id
fn_addr = ir.Constant(ir.IntType(64), 25)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
result = builder.call(
fn_ptr,
[ctx_ptr, map_void_ptr, flags_val, data_void_ptr, size_val],
tail=False,
)
return result, None
else:
raise NotImplementedError(
"Only simple object names are supported as data in perf event output."
)
helper_func_list = {
"lookup": bpf_map_lookup_elem_emitter,
"print": bpf_printk_emitter,
"ktime": bpf_ktime_get_ns_emitter,
"update": bpf_map_update_elem_emitter,
"delete": bpf_map_delete_elem_emitter,
"pid": bpf_get_current_pid_tgid_emitter,
"output": bpf_perf_event_output_handler,
}
def handle_helper_call(
call,
module,
builder,
func,
local_sym_tab=None,
map_sym_tab=None,
struct_sym_tab=None,
local_var_metadata=None,
):
print(local_var_metadata)
if isinstance(call.func, ast.Name):
func_name = call.func.id
if func_name in helper_func_list:
# it is not a map method call
return helper_func_list[func_name](
call,
None,
module,
builder,
func,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
else:
raise NotImplementedError(
f"Function {func_name} is not implemented as a helper function."
)
elif isinstance(call.func, ast.Attribute):
# likely a map method call
if isinstance(call.func.value, ast.Call) and isinstance(
call.func.value.func, ast.Name
):
map_name = call.func.value.func.id
method_name = call.func.attr
if map_sym_tab and map_name in map_sym_tab:
map_ptr = map_sym_tab[map_name]
if method_name in helper_func_list:
print(local_var_metadata)
return helper_func_list[method_name](
call,
map_ptr,
module,
builder,
func,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
else:
raise NotImplementedError(
f"Map method {method_name} is not implemented as a helper function."
)
else:
raise ValueError(f"Map variable {map_name} not found in symbol tables.")
elif isinstance(call.func.value, ast.Name):
obj_name = call.func.value.id
method_name = call.func.attr
if map_sym_tab and obj_name in map_sym_tab:
map_ptr = map_sym_tab[obj_name]
if method_name in helper_func_list:
return helper_func_list[method_name](
call,
map_ptr,
module,
builder,
func,
local_sym_tab,
struct_sym_tab,
local_var_metadata,
)
else:
raise NotImplementedError(
f"Map method {method_name} is not implemented as a helper function."
)
else:
raise ValueError(f"Map variable {obj_name} not found in symbol tables.")
else:
raise NotImplementedError("Attribute not supported for map method calls.")
return None

View File

@ -141,7 +141,7 @@ def compile() -> bool:
success = True success = True
success = compile_to_ir(str(caller_file), str(ll_file)) and success success = compile_to_ir(str(caller_file), str(ll_file)) and success
success = ( success = bool(
subprocess.run( subprocess.run(
[ [
"llc", "llc",

View File

@ -1,3 +1,5 @@
from .dwarf_constants import * from .dwarf_constants import * # noqa: F403
from .dtypes import * from .dtypes import * # noqa: F403
from .debug_info_generator import DebugInfoGenerator from .debug_info_generator import DebugInfoGenerator
__all__ = ["DebugInfoGenerator"]

View File

@ -21,6 +21,10 @@ class DebugInfoGenerator:
) )
return self._type_cache[key] return self._type_cache[key]
def get_int32_type(self) -> Any:
"""Get debug info for signed 32-bit integer"""
return self.get_basic_type("int", 32, dc.DW_ATE_signed)
def get_uint32_type(self) -> Any: def get_uint32_type(self) -> Any:
"""Get debug info for unsigned 32-bit integer""" """Get debug info for unsigned 32-bit integer"""
return self.get_basic_type("unsigned int", 32, dc.DW_ATE_unsigned) return self.get_basic_type("unsigned int", 32, dc.DW_ATE_unsigned)

View File

@ -10,15 +10,13 @@ def eval_expr(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab=None, structs_sym_tab=None,
local_var_metadata=None,
): ):
print(f"Evaluating expression: {ast.dump(expr)}") print(f"Evaluating expression: {ast.dump(expr)}")
print(local_var_metadata)
if isinstance(expr, ast.Name): if isinstance(expr, ast.Name):
if expr.id in local_sym_tab: 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) 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: else:
print(f"Undefined variable {expr.id}") print(f"Undefined variable {expr.id}")
return None return None
@ -32,7 +30,7 @@ def eval_expr(
return None return None
elif isinstance(expr, ast.Call): elif isinstance(expr, ast.Call):
# delayed import to avoid circular dependency # delayed import to avoid circular dependency
from .bpf_helper_handler import helper_func_list, handle_helper_call from pythonbpf.helper import HelperHandlerRegistry, handle_helper_call
if isinstance(expr.func, ast.Name): if isinstance(expr.func, ast.Name):
# check deref # check deref
@ -51,7 +49,7 @@ def eval_expr(
return None return None
if isinstance(arg, ast.Name): if isinstance(arg, ast.Name):
if arg.id in local_sym_tab: if arg.id in local_sym_tab:
arg = local_sym_tab[arg.id][0] arg = local_sym_tab[arg.id].var
else: else:
print(f"Undefined variable {arg.id}") print(f"Undefined variable {arg.id}")
return None return None
@ -60,10 +58,10 @@ def eval_expr(
return None return None
# Since we are handling only name case, directly take type from sym tab # Since we are handling only name case, directly take type from sym tab
val = builder.load(arg) 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 # check for helpers
if expr.func.id in helper_func_list: if HelperHandlerRegistry.has_handler(expr.func.id):
return handle_helper_call( return handle_helper_call(
expr, expr,
module, module,
@ -72,7 +70,6 @@ def eval_expr(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
elif isinstance(expr.func, ast.Attribute): elif isinstance(expr.func, ast.Attribute):
print(f"Handling method call: {ast.dump(expr.func)}") print(f"Handling method call: {ast.dump(expr.func)}")
@ -80,7 +77,7 @@ def eval_expr(
expr.func.value.func, ast.Name expr.func.value.func, ast.Name
): ):
method_name = expr.func.attr method_name = expr.func.attr
if method_name in helper_func_list: if HelperHandlerRegistry.has_handler(method_name):
return handle_helper_call( return handle_helper_call(
expr, expr,
module, module,
@ -89,13 +86,12 @@ def eval_expr(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
elif isinstance(expr.func.value, ast.Name): elif isinstance(expr.func.value, ast.Name):
obj_name = expr.func.value.id obj_name = expr.func.value.id
method_name = expr.func.attr method_name = expr.func.attr
if obj_name in map_sym_tab: if obj_name in map_sym_tab:
if method_name in helper_func_list: if HelperHandlerRegistry.has_handler(method_name):
return handle_helper_call( return handle_helper_call(
expr, expr,
module, module,
@ -104,24 +100,21 @@ def eval_expr(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
elif isinstance(expr, ast.Attribute): elif isinstance(expr, ast.Attribute):
if isinstance(expr.value, ast.Name): if isinstance(expr.value, ast.Name):
var_name = expr.value.id var_name = expr.value.id
attr_name = expr.attr attr_name = expr.attr
if var_name in local_sym_tab: if var_name in local_sym_tab:
var_ptr, var_type = local_sym_tab[var_name] var_ptr, var_type, var_metadata = local_sym_tab[var_name]
print(f"Loading attribute " f"{attr_name} from variable {var_name}") print(f"Loading attribute {attr_name} from variable {var_name}")
print(f"Variable type: {var_type}, Variable ptr: {var_ptr}") print(f"Variable type: {var_type}, Variable ptr: {var_ptr}")
print(local_var_metadata) metadata = structs_sym_tab[var_metadata]
if local_var_metadata and var_name in local_var_metadata: if attr_name in metadata.fields:
metadata = structs_sym_tab[local_var_metadata[var_name]] gep = metadata.gep(builder, var_ptr, attr_name)
if attr_name in metadata.fields: val = builder.load(gep)
gep = metadata.gep(builder, var_ptr, attr_name) field_type = metadata.field_type(attr_name)
val = builder.load(gep) return val, field_type
field_type = metadata.field_type(attr_name)
return val, field_type
print("Unsupported expression evaluation") print("Unsupported expression evaluation")
return None return None
@ -134,11 +127,9 @@ def handle_expr(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
): ):
"""Handle expression statements in the function body.""" """Handle expression statements in the function body."""
print(f"Handling expression: {ast.dump(expr)}") print(f"Handling expression: {ast.dump(expr)}")
print(local_var_metadata)
call = expr.value call = expr.value
if isinstance(call, ast.Call): if isinstance(call, ast.Call):
eval_expr( eval_expr(
@ -149,7 +140,6 @@ def handle_expr(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
else: else:
print("Unsupported expression type") print("Unsupported expression type")

View File

@ -1,13 +1,27 @@
from llvmlite import ir from llvmlite import ir
import ast import ast
import logging
from typing import Any
from dataclasses import dataclass
from .helper import HelperHandlerRegistry, handle_helper_call
from .bpf_helper_handler import helper_func_list, handle_helper_call
from .type_deducer import ctypes_to_ir from .type_deducer import ctypes_to_ir
from .binary_ops import handle_binary_op from .binary_ops import handle_binary_op
from .expr_pass import eval_expr, handle_expr from .expr_pass import eval_expr, handle_expr
local_var_metadata = {} 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): def get_probe_string(func_node):
@ -47,13 +61,12 @@ def handle_assign(
if isinstance(target, ast.Attribute): if isinstance(target, ast.Attribute):
# struct field assignment # struct field assignment
field_name = target.attr field_name = target.attr
if var_name in local_sym_tab and var_name in local_var_metadata: if var_name in local_sym_tab:
struct_type = local_var_metadata[var_name] struct_type = local_sym_tab[var_name].metadata
struct_info = structs_sym_tab[struct_type] struct_info = structs_sym_tab[struct_type]
if field_name in struct_info.fields: if field_name in struct_info.fields:
field_ptr = struct_info.gep( 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( val = eval_expr(
func, func,
@ -83,18 +96,21 @@ def handle_assign(
elif isinstance(rval, ast.Constant): elif isinstance(rval, ast.Constant):
if isinstance(rval.value, bool): if isinstance(rval.value, bool):
if rval.value: 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: else:
builder.store(ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name][0]) builder.store(
ir.Constant(ir.IntType(1), 0), local_sym_tab[var_name].var
)
print(f"Assigned constant {rval.value} to {var_name}") print(f"Assigned constant {rval.value} to {var_name}")
elif isinstance(rval.value, int): elif isinstance(rval.value, int):
# Assume c_int64 for now # Assume c_int64 for now
# var = builder.alloca(ir.IntType(64), name=var_name) # var = builder.alloca(ir.IntType(64), name=var_name)
# var.align = 8 # var.align = 8
builder.store( 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}") print(f"Assigned constant {rval.value} to {var_name}")
elif isinstance(rval.value, str): elif isinstance(rval.value, str):
str_val = rval.value.encode("utf-8") + b"\x00" str_val = rval.value.encode("utf-8") + b"\x00"
@ -108,7 +124,7 @@ def handle_assign(
global_str.global_constant = True global_str.global_constant = True
global_str.initializer = str_const global_str.initializer = str_const
str_ptr = builder.bitcast(global_str, ir.PointerType(ir.IntType(8))) str_ptr = builder.bitcast(global_str, ir.PointerType(ir.IntType(8)))
builder.store(str_ptr, local_sym_tab[var_name][0]) builder.store(str_ptr, local_sym_tab[var_name].var)
print(f"Assigned string constant '{rval.value}' to {var_name}") print(f"Assigned string constant '{rval.value}' to {var_name}")
else: else:
print("Unsupported constant type") print("Unsupported constant type")
@ -126,14 +142,14 @@ def handle_assign(
# var = builder.alloca(ir_type, name=var_name) # var = builder.alloca(ir_type, name=var_name)
# var.align = ir_type.width // 8 # var.align = ir_type.width // 8
builder.store( 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( print(
f"Assigned {call_type} constant " f"Assigned {call_type} constant "
f"{rval.args[0].value} to {var_name}" f"{rval.args[0].value} to {var_name}"
) )
# local_sym_tab[var_name] = var elif HelperHandlerRegistry.has_handler(call_type):
elif call_type in helper_func_list:
# var = builder.alloca(ir.IntType(64), name=var_name) # var = builder.alloca(ir.IntType(64), name=var_name)
# var.align = 8 # var.align = 8
val = handle_helper_call( val = handle_helper_call(
@ -144,10 +160,8 @@ def handle_assign(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
builder.store(val[0], local_sym_tab[var_name][0]) builder.store(val[0], local_sym_tab[var_name].var)
# local_sym_tab[var_name] = var
print(f"Assigned constant {rval.func.id} to {var_name}") print(f"Assigned constant {rval.func.id} to {var_name}")
elif call_type == "deref" and len(rval.args) == 1: elif call_type == "deref" and len(rval.args) == 1:
print(f"Handling deref assignment {ast.dump(rval)}") print(f"Handling deref assignment {ast.dump(rval)}")
@ -164,18 +178,15 @@ def handle_assign(
print("Failed to evaluate deref argument") print("Failed to evaluate deref argument")
return return
print(f"Dereferenced value: {val}, storing in {var_name}") print(f"Dereferenced value: {val}, storing in {var_name}")
builder.store(val[0], local_sym_tab[var_name][0]) builder.store(val[0], local_sym_tab[var_name].var)
# local_sym_tab[var_name] = var
print(f"Dereferenced and assigned to {var_name}") print(f"Dereferenced and assigned to {var_name}")
elif call_type in structs_sym_tab and len(rval.args) == 0: elif call_type in structs_sym_tab and len(rval.args) == 0:
struct_info = structs_sym_tab[call_type] struct_info = structs_sym_tab[call_type]
ir_type = struct_info.ir_type ir_type = struct_info.ir_type
# var = builder.alloca(ir_type, name=var_name) # var = builder.alloca(ir_type, name=var_name)
# Null init # Null init
builder.store(ir.Constant(ir_type, None), local_sym_tab[var_name][0]) builder.store(ir.Constant(ir_type, None), local_sym_tab[var_name].var)
local_var_metadata[var_name] = call_type
print(f"Assigned struct {call_type} to {var_name}") print(f"Assigned struct {call_type} to {var_name}")
# local_sym_tab[var_name] = var
else: else:
print(f"Unsupported assignment call type: {call_type}") print(f"Unsupported assignment call type: {call_type}")
elif isinstance(rval.func, ast.Attribute): elif isinstance(rval.func, ast.Attribute):
@ -189,8 +200,7 @@ def handle_assign(
map_name = rval.func.value.func.id map_name = rval.func.value.func.id
method_name = rval.func.attr method_name = rval.func.attr
if map_name in map_sym_tab: if map_name in map_sym_tab:
map_ptr = map_sym_tab[map_name] if HelperHandlerRegistry.has_handler(method_name):
if method_name in helper_func_list:
val = handle_helper_call( val = handle_helper_call(
rval, rval,
module, module,
@ -199,12 +209,10 @@ def handle_assign(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
# var = builder.alloca(ir.IntType(64), name=var_name) # var = builder.alloca(ir.IntType(64), name=var_name)
# var.align = 8 # var.align = 8
builder.store(val[0], local_sym_tab[var_name][0]) builder.store(val[0], local_sym_tab[var_name].var)
# local_sym_tab[var_name] = var
else: else:
print("Unsupported assignment call structure") print("Unsupported assignment call structure")
else: else:
@ -228,7 +236,7 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
return None return None
elif isinstance(cond, ast.Name): elif isinstance(cond, ast.Name):
if cond.id in local_sym_tab: 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) val = builder.load(var)
if val.type != ir.IntType(1): if val.type != ir.IntType(1):
# Convert nonzero values to true, zero to false # Convert nonzero values to true, zero to false
@ -289,7 +297,7 @@ def handle_if(
): ):
"""Handle if statements in the function body.""" """Handle if statements in the function body."""
print("Handling if statement") print("Handling if statement")
start = builder.block.parent # start = builder.block.parent
then_block = func.append_basic_block(name="if.then") then_block = func.append_basic_block(name="if.then")
merge_block = func.append_basic_block(name="if.end") merge_block = func.append_basic_block(name="if.end")
if stmt.orelse: if stmt.orelse:
@ -343,7 +351,6 @@ def process_stmt(
): ):
print(f"Processing statement: {ast.dump(stmt)}") print(f"Processing statement: {ast.dump(stmt)}")
if isinstance(stmt, ast.Expr): if isinstance(stmt, ast.Expr):
print(local_var_metadata)
handle_expr( handle_expr(
func, func,
module, module,
@ -352,7 +359,6 @@ def process_stmt(
local_sym_tab, local_sym_tab,
map_sym_tab, map_sym_tab,
structs_sym_tab, structs_sym_tab,
local_var_metadata,
) )
elif isinstance(stmt, ast.Assign): elif isinstance(stmt, ast.Assign):
handle_assign( handle_assign(
@ -402,6 +408,7 @@ def allocate_mem(
module, builder, body, func, ret_type, map_sym_tab, local_sym_tab, structs_sym_tab module, builder, body, func, ret_type, map_sym_tab, local_sym_tab, structs_sym_tab
): ):
for stmt in body: for stmt in body:
has_metadata = False
if isinstance(stmt, ast.If): if isinstance(stmt, ast.If):
if stmt.body: if stmt.body:
local_sym_tab = allocate_mem( local_sym_tab = allocate_mem(
@ -443,7 +450,7 @@ def allocate_mem(
var = builder.alloca(ir_type, name=var_name) var = builder.alloca(ir_type, name=var_name)
var.align = ir_type.width // 8 var.align = ir_type.width // 8
print(f"Pre-allocated variable {var_name} of type {call_type}") print(f"Pre-allocated variable {var_name} of type {call_type}")
elif call_type in helper_func_list: elif HelperHandlerRegistry.has_handler(call_type):
# Assume return type is int64 for now # Assume return type is int64 for now
ir_type = ir.IntType(64) ir_type = ir.IntType(64)
var = builder.alloca(ir_type, name=var_name) var = builder.alloca(ir_type, name=var_name)
@ -459,9 +466,10 @@ def allocate_mem(
struct_info = structs_sym_tab[call_type] struct_info = structs_sym_tab[call_type]
ir_type = struct_info.ir_type ir_type = struct_info.ir_type
var = builder.alloca(ir_type, name=var_name) var = builder.alloca(ir_type, name=var_name)
local_var_metadata[var_name] = call_type has_metadata = True
print( print(
f"Pre-allocated variable {var_name} for struct {call_type}" f"Pre-allocated variable {var_name} "
f"for struct {call_type}"
) )
elif isinstance(rval.func, ast.Attribute): elif isinstance(rval.func, ast.Attribute):
ir_type = ir.PointerType(ir.IntType(64)) ir_type = ir.PointerType(ir.IntType(64))
@ -500,7 +508,11 @@ def allocate_mem(
else: else:
print("Unsupported assignment value type") print("Unsupported assignment value type")
continue 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 return local_sym_tab
@ -656,13 +668,13 @@ def infer_return_type(func_node: ast.FunctionDef):
except Exception: except Exception:
return type(e).__name__ return type(e).__name__
for node in ast.walk(func_node): for walked_node in ast.walk(func_node):
if isinstance(node, ast.Return): if isinstance(walked_node, ast.Return):
t = _expr_type(node.value) t = _expr_type(walked_node.value)
if found_type is None: if found_type is None:
found_type = t found_type = t
elif 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" return found_type or "None"
@ -674,7 +686,7 @@ def assign_string_to_array(builder, target_array_ptr, source_string_ptr, array_l
Copy a string (i8*) to a fixed-size array ([N x i8]*) Copy a string (i8*) to a fixed-size array ([N x i8]*)
""" """
# Create a loop to copy characters one by one # Create a loop to copy characters one by one
entry_block = builder.block # entry_block = builder.block
copy_block = builder.append_basic_block("copy_char") copy_block = builder.append_basic_block("copy_char")
end_block = builder.append_basic_block("copy_end") end_block = builder.append_basic_block("copy_end")

View File

@ -0,0 +1,13 @@
from .helper_utils import HelperHandlerRegistry
from .bpf_helper_handler import handle_helper_call
from .helpers import ktime, pid, deref, XDP_DROP, XDP_PASS
__all__ = [
"HelperHandlerRegistry",
"handle_helper_call",
"ktime",
"pid",
"deref",
"XDP_DROP",
"XDP_PASS",
]

View File

@ -0,0 +1,344 @@
import ast
from llvmlite import ir
from enum import Enum
from .helper_utils import (
HelperHandlerRegistry,
get_or_create_ptr_from_arg,
get_flags_val,
handle_fstring_print,
simple_string_print,
get_data_ptr_and_size,
)
class BPFHelperID(Enum):
BPF_MAP_LOOKUP_ELEM = 1
BPF_MAP_UPDATE_ELEM = 2
BPF_MAP_DELETE_ELEM = 3
BPF_KTIME_GET_NS = 5
BPF_PRINTK = 6
BPF_GET_CURRENT_PID_TGID = 14
BPF_PERF_EVENT_OUTPUT = 25
@HelperHandlerRegistry.register("ktime")
def bpf_ktime_get_ns_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""
Emit LLVM IR for bpf_ktime_get_ns helper function call.
"""
# func is an arg to just have a uniform signature with other emitters
helper_id = ir.Constant(ir.IntType(64), BPFHelperID.BPF_KTIME_GET_NS.value)
fn_type = ir.FunctionType(ir.IntType(64), [], var_arg=False)
fn_ptr_type = ir.PointerType(fn_type)
fn_ptr = builder.inttoptr(helper_id, fn_ptr_type)
result = builder.call(fn_ptr, [], tail=False)
return result, ir.IntType(64)
@HelperHandlerRegistry.register("lookup")
def bpf_map_lookup_elem_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""
Emit LLVM IR for bpf_map_lookup_elem helper function call.
"""
if not call.args or len(call.args) != 1:
raise ValueError(
"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())
fn_type = ir.FunctionType(
ir.PointerType(), # Return type: void*
[ir.PointerType(), ir.PointerType()], # Args: (void*, void*)
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_MAP_LOOKUP_ELEM.value)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
result = builder.call(fn_ptr, [map_void_ptr, key_ptr], tail=False)
return result, ir.PointerType()
@HelperHandlerRegistry.register("print")
def bpf_printk_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""Emit LLVM IR for bpf_printk helper function call."""
if not hasattr(func, "_fmt_counter"):
func._fmt_counter = 0
if not call.args:
raise ValueError("bpf_printk expects at least one argument (format string)")
args = []
if isinstance(call.args[0], ast.JoinedStr):
args = handle_fstring_print(
call.args[0],
module,
builder,
func,
local_sym_tab,
struct_sym_tab,
)
elif isinstance(call.args[0], ast.Constant) and isinstance(call.args[0].value, str):
# TODO: We are only supporting single arguments for now.
# In case of multiple args, the first one will be taken.
args = simple_string_print(call.args[0].value, module, builder, func)
else:
raise NotImplementedError(
"Only simple strings or f-strings are supported in bpf_printk."
)
fn_type = ir.FunctionType(
ir.IntType(64), [ir.PointerType(), ir.IntType(32)], var_arg=True
)
fn_ptr_type = ir.PointerType(fn_type)
fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_PRINTK.value)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
builder.call(fn_ptr, args, tail=True)
return None
@HelperHandlerRegistry.register("update")
def bpf_map_update_elem_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""
Emit LLVM IR for bpf_map_update_elem helper function call.
Expected call signature: map.update(key, value, flags=0)
"""
if not call.args or len(call.args) < 2 or len(call.args) > 3:
raise ValueError(
"Map update expects 2 or 3 args (key, value, flags), "
f"got {len(call.args)}"
)
key_arg = call.args[0]
value_arg = call.args[1]
flags_arg = call.args[2] if len(call.args) > 2 else None
key_ptr = get_or_create_ptr_from_arg(key_arg, builder, local_sym_tab)
value_ptr = get_or_create_ptr_from_arg(value_arg, builder, local_sym_tab)
flags_val = get_flags_val(flags_arg, builder, local_sym_tab)
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
fn_type = ir.FunctionType(
ir.IntType(64),
[ir.PointerType(), ir.PointerType(), ir.PointerType(), ir.IntType(64)],
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_MAP_UPDATE_ELEM.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, key_ptr, value_ptr, flags_const], tail=False
)
return result, None
@HelperHandlerRegistry.register("delete")
def bpf_map_delete_elem_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""
Emit LLVM IR for bpf_map_delete_elem helper function call.
Expected call signature: map.delete(key)
"""
if not call.args or len(call.args) != 1:
raise ValueError(
"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())
# Define function type for bpf_map_delete_elem
fn_type = ir.FunctionType(
ir.IntType(64), # Return type: int64 (status code)
[ir.PointerType(), ir.PointerType()], # Args: (void*, void*)
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_MAP_DELETE_ELEM.value)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
result = builder.call(fn_ptr, [map_void_ptr, key_ptr], tail=False)
return result, None
@HelperHandlerRegistry.register("pid")
def bpf_get_current_pid_tgid_emitter(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""
Emit LLVM IR for bpf_get_current_pid_tgid helper function call.
"""
# func is an arg to just have a uniform signature with other emitters
helper_id = ir.Constant(ir.IntType(64), BPFHelperID.BPF_GET_CURRENT_PID_TGID.value)
fn_type = ir.FunctionType(ir.IntType(64), [], var_arg=False)
fn_ptr_type = ir.PointerType(fn_type)
fn_ptr = builder.inttoptr(helper_id, fn_ptr_type)
result = builder.call(fn_ptr, [], tail=False)
# Extract the lower 32 bits (PID) using bitwise AND with 0xFFFFFFFF
mask = ir.Constant(ir.IntType(64), 0xFFFFFFFF)
pid = builder.and_(result, mask)
return pid, ir.IntType(64)
@HelperHandlerRegistry.register("output")
def bpf_perf_event_output_handler(
call,
map_ptr,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
if len(call.args) != 1:
raise ValueError(
"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)
# BPF_F_CURRENT_CPU is -1 in 32 bit
flags_val = ir.Constant(ir.IntType(64), 0xFFFFFFFF)
map_void_ptr = builder.bitcast(map_ptr, ir.PointerType())
data_void_ptr = builder.bitcast(data_ptr, ir.PointerType())
fn_type = ir.FunctionType(
ir.IntType(64),
[
ir.PointerType(ir.IntType(8)),
ir.PointerType(),
ir.IntType(64),
ir.PointerType(),
ir.IntType(64),
],
var_arg=False,
)
fn_ptr_type = ir.PointerType(fn_type)
# helper id
fn_addr = ir.Constant(ir.IntType(64), BPFHelperID.BPF_PERF_EVENT_OUTPUT.value)
fn_ptr = builder.inttoptr(fn_addr, fn_ptr_type)
result = builder.call(
fn_ptr, [ctx_ptr, map_void_ptr, flags_val, data_void_ptr, size_val], tail=False
)
return result, None
def handle_helper_call(
call,
module,
builder,
func,
local_sym_tab=None,
map_sym_tab=None,
struct_sym_tab=None,
):
"""Process a BPF helper function call and emit the appropriate LLVM IR."""
# Helper function to get map pointer and invoke handler
def invoke_helper(method_name, map_ptr=None):
handler = HelperHandlerRegistry.get_handler(method_name)
if not handler:
raise NotImplementedError(
f"Helper function '{method_name}' is not implemented."
)
return handler(
call,
map_ptr,
module,
builder,
func,
local_sym_tab,
struct_sym_tab,
)
# Handle direct function calls (e.g., print(), ktime())
if isinstance(call.func, ast.Name):
return invoke_helper(call.func.id)
# Handle method calls (e.g., map.lookup(), map.update())
elif isinstance(call.func, ast.Attribute):
method_name = call.func.attr
value = call.func.value
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)
map_name = value.func.id
elif isinstance(value, ast.Name):
# Direct style: my_map.lookup(key)
map_name = value.id
else:
raise NotImplementedError(
f"Unsupported map access pattern: {ast.dump(value)}"
)
# Verify map exists and get pointer
if not map_sym_tab or map_name not in map_sym_tab:
raise ValueError(f"Map '{map_name}' not found in symbol table")
return invoke_helper(method_name, map_sym_tab[map_name])
return None

View File

@ -0,0 +1,307 @@
import ast
import logging
from collections.abc import Callable
from llvmlite import ir
from pythonbpf.expr_pass import eval_expr
logger = logging.getLogger(__name__)
class HelperHandlerRegistry:
"""Registry for BPF helpers"""
_handlers: dict[str, Callable] = {}
@classmethod
def register(cls, helper_name):
"""Decorator to register a handler function for a helper"""
def decorator(func):
cls._handlers[helper_name] = func
return func
return decorator
@classmethod
def get_handler(cls, helper_name):
"""Get the handler function for a helper"""
return cls._handlers.get(helper_name)
@classmethod
def has_handler(cls, helper_name):
"""Check if a handler function is registered for a helper"""
return helper_name in cls._handlers
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
raise ValueError(f"Variable '{var_name}' not found in local symbol table")
def create_int_constant_ptr(value, builder, int_width=64):
"""Create a pointer to an integer constant."""
# Default to 64-bit integer
int_type = ir.IntType(int_width)
ptr = builder.alloca(int_type)
ptr.align = int_type.width // 8
builder.store(ir.Constant(int_type, value), ptr)
return ptr
def get_or_create_ptr_from_arg(arg, builder, local_sym_tab):
"""Extract or create pointer from the call arguments."""
if isinstance(arg, ast.Name):
ptr = get_var_ptr_from_name(arg.id, local_sym_tab)
elif isinstance(arg, ast.Constant) and isinstance(arg.value, int):
ptr = create_int_constant_ptr(arg.value, builder)
else:
raise NotImplementedError(
"Only simple variable names are supported as args in map helpers."
)
return ptr
def get_flags_val(arg, builder, local_sym_tab):
"""Extract or create flags value from the call arguments."""
if not arg:
return 0
if isinstance(arg, ast.Name):
if local_sym_tab and arg.id in local_sym_tab:
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")
elif isinstance(arg, ast.Constant) and isinstance(arg.value, int):
return arg.value
raise NotImplementedError(
"Only var names or int consts are supported as map helpers flags."
)
def simple_string_print(string_value, module, builder, func):
"""Prepare arguments for bpf_printk from a simple string value"""
fmt_str = string_value + "\n\0"
fmt_ptr = _create_format_string_global(fmt_str, func, module, builder)
args = [fmt_ptr, ir.Constant(ir.IntType(32), len(fmt_str))]
return args
def handle_fstring_print(
joined_str,
module,
builder,
func,
local_sym_tab=None,
struct_sym_tab=None,
):
"""Handle f-string formatting for bpf_printk emitter."""
fmt_parts = []
exprs = []
for value in joined_str.values:
logger.debug(f"Processing f-string value: {ast.dump(value)}")
if isinstance(value, ast.Constant):
_process_constant_in_fstring(value, fmt_parts, exprs)
elif isinstance(value, ast.FormattedValue):
_process_fval(
value,
fmt_parts,
exprs,
local_sym_tab,
struct_sym_tab,
)
else:
raise NotImplementedError(f"Unsupported f-string value type: {type(value)}")
fmt_str = "".join(fmt_parts)
args = simple_string_print(fmt_str, module, builder, func)
# NOTE: Process expressions (limited to 3 due to BPF constraints)
if len(exprs) > 3:
logger.warning("bpf_printk supports up to 3 args, extra args will be ignored.")
for expr in exprs[:3]:
arg_value = _prepare_expr_args(
expr,
func,
module,
builder,
local_sym_tab,
struct_sym_tab,
)
args.append(arg_value)
return args
def _process_constant_in_fstring(cst, fmt_parts, exprs):
"""Process constant values in f-string."""
if isinstance(cst.value, str):
fmt_parts.append(cst.value)
elif isinstance(cst.value, int):
fmt_parts.append("%lld")
exprs.append(ir.Constant(ir.IntType(64), cst.value))
else:
raise NotImplementedError(
f"Unsupported constant type in f-string: {type(cst.value)}"
)
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)}")
if isinstance(fval.value, ast.Name):
_process_name_in_fval(fval.value, fmt_parts, exprs, local_sym_tab)
elif isinstance(fval.value, ast.Attribute):
_process_attr_in_fval(
fval.value,
fmt_parts,
exprs,
local_sym_tab,
struct_sym_tab,
)
else:
raise NotImplementedError(
f"Unsupported formatted value in f-string: {type(fval.value)}"
)
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]
_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):
"""Process attribute nodes in formatted values."""
if (
isinstance(attr_node.value, ast.Name)
and local_sym_tab
and attr_node.value.id in local_sym_tab
):
var_name = attr_node.value.id
field_name = attr_node.attr
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"
)
struct_info = struct_sym_tab[var_type]
if field_name not in struct_info.fields:
raise ValueError(f"Field '{field_name}' not found in struct '{var_type}'")
field_type = struct_info.field_type(field_name)
_populate_fval(field_type, attr_node, fmt_parts, exprs)
else:
raise NotImplementedError(
"Only simple attribute on local vars is supported in f-strings."
)
def _populate_fval(ftype, node, fmt_parts, exprs):
"""Populate format parts and expressions based on field type."""
if isinstance(ftype, ir.IntType):
# TODO: We print as signed integers only for now
if ftype.width == 64:
fmt_parts.append("%lld")
exprs.append(node)
elif ftype.width == 32:
fmt_parts.append("%d")
exprs.append(node)
else:
raise NotImplementedError(
f"Unsupported integer width in f-string: {ftype.width}"
)
elif ftype == ir.PointerType(ir.IntType(8)):
# NOTE: We assume i8* is a string
fmt_parts.append("%s")
exprs.append(node)
else:
raise NotImplementedError(f"Unsupported field type in f-string: {ftype}")
def _create_format_string_global(fmt_str, func, module, builder):
"""Create a global variable for the format string."""
fmt_name = f"{func.name}____fmt{func._fmt_counter}"
func._fmt_counter += 1
fmt_gvar = ir.GlobalVariable(
module, ir.ArrayType(ir.IntType(8), len(fmt_str)), name=fmt_name
)
fmt_gvar.global_constant = True
fmt_gvar.initializer = ir.Constant(
ir.ArrayType(ir.IntType(8), len(fmt_str)), bytearray(fmt_str.encode("utf8"))
)
fmt_gvar.linkage = "internal"
fmt_gvar.align = 1
return builder.bitcast(fmt_gvar, ir.PointerType())
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,
module,
builder,
expr,
local_sym_tab,
None,
struct_sym_tab,
)
if val:
if isinstance(val.type, ir.PointerType):
val = builder.ptrtoint(val, ir.IntType(64))
elif isinstance(val.type, ir.IntType):
if val.type.width < 64:
val = builder.sext(val, ir.IntType(64))
else:
logger.warning(
"Only int and ptr supported in bpf_printk args. " "Others default to 0."
)
val = ir.Constant(ir.IntType(64), 0)
return val
else:
logger.warning(
"Failed to evaluate expression for bpf_printk argument. "
"It will be converted to 0."
)
return ir.Constant(ir.IntType(64), 0)
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].var
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
else:
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."
)

View File

@ -1,2 +1,4 @@
from .maps import HashMap, PerfEventArray from .maps import HashMap, PerfEventArray, RingBuf
from .maps_pass import maps_proc from .maps_pass import maps_proc
__all__ = ["HashMap", "PerfEventArray", "maps_proc", "RingBuf"]

View File

@ -1,3 +1,4 @@
# This file provides type and function hints only and does not actually give any functionality.
class HashMap: class HashMap:
def __init__(self, key, value, max_entries): def __init__(self, key, value, max_entries):
self.key = key self.key = key
@ -33,3 +34,18 @@ class PerfEventArray:
def output(self, data): def output(self, data):
pass # Placeholder for output method pass # Placeholder for output method
class RingBuf:
def __init__(self, max_entries):
self.max_entries = max_entries
def reserve(self, size: int, flags=0):
if size > self.max_entries:
raise ValueError("size cannot be greater than set maximum entries")
return 0
def submit(self, data, flags=0):
pass
# add discard, output and also give names to flags and stuff

View File

@ -1,11 +1,12 @@
import ast import ast
from logging import Logger
from llvmlite import ir from llvmlite import ir
from enum import Enum from enum import Enum
from .maps_utils import MapProcessorRegistry from .maps_utils import MapProcessorRegistry
from ..debuginfo import DebugInfoGenerator from ..debuginfo import DebugInfoGenerator
import logging import logging
logger = logging.getLogger(__name__) logger: Logger = logging.getLogger(__name__)
def maps_proc(tree, module, chunks): def maps_proc(tree, module, chunks):
@ -13,7 +14,7 @@ def maps_proc(tree, module, chunks):
map_sym_tab = {} map_sym_tab = {}
for func_node in chunks: for func_node in chunks:
if is_map(func_node): if is_map(func_node):
print(f"Found BPF map: {func_node.name}") logger.info(f"Found BPF map: {func_node.name}")
map_sym_tab[func_node.name] = process_bpf_map(func_node, module) map_sym_tab[func_node.name] = process_bpf_map(func_node, module)
return map_sym_tab return map_sym_tab
@ -26,8 +27,41 @@ def is_map(func_node):
class BPFMapType(Enum): class BPFMapType(Enum):
UNSPEC = 0
HASH = 1 HASH = 1
ARRAY = 2
PROG_ARRAY = 3
PERF_EVENT_ARRAY = 4 PERF_EVENT_ARRAY = 4
PERCPU_HASH = 5
PERCPU_ARRAY = 6
STACK_TRACE = 7
CGROUP_ARRAY = 8
LRU_HASH = 9
LRU_PERCPU_HASH = 10
LPM_TRIE = 11
ARRAY_OF_MAPS = 12
HASH_OF_MAPS = 13
DEVMAP = 14
SOCKMAP = 15
CPUMAP = 16
XSKMAP = 17
SOCKHASH = 18
CGROUP_STORAGE_DEPRECATED = 19
CGROUP_STORAGE = 19
REUSEPORT_SOCKARRAY = 20
PERCPU_CGROUP_STORAGE_DEPRECATED = 21
PERCPU_CGROUP_STORAGE = 21
QUEUE = 22
STACK = 23
SK_STORAGE = 24
DEVMAP_HASH = 25
STRUCT_OPS = 26
RINGBUF = 27
INODE_STORAGE = 28
TASK_STORAGE = 29
BLOOM_FILTER = 30
USER_RINGBUF = 31
CGRP_STORAGE = 32
def create_bpf_map(module, map_name, map_params): def create_bpf_map(module, map_name, map_params):
@ -51,13 +85,13 @@ def create_bpf_map(module, map_name, map_params):
def create_map_debug_info(module, map_global, map_name, map_params): def create_map_debug_info(module, map_global, map_name, map_params):
"""Generate debug information metadata for BPF map""" """Generate debug info metadata for BPF maps HASH and PERF_EVENT_ARRAY"""
generator = DebugInfoGenerator(module) generator = DebugInfoGenerator(module)
uint_type = generator.get_uint32_type() uint_type = generator.get_uint32_type()
ulong_type = generator.get_uint64_type() ulong_type = generator.get_uint64_type()
array_type = generator.create_array_type( array_type = generator.create_array_type(
uint_type, map_params.get("type", BPFMapType.HASH).value uint_type, map_params.get("type", BPFMapType.UNSPEC).value
) )
type_ptr = generator.create_pointer_type(array_type, 64) type_ptr = generator.create_pointer_type(array_type, 64)
key_ptr = generator.create_pointer_type( key_ptr = generator.create_pointer_type(
@ -112,6 +146,62 @@ def create_map_debug_info(module, map_global, map_name, map_params):
return global_var return global_var
def create_ringbuf_debug_info(module, map_global, map_name, map_params):
"""Generate debug information metadata for BPF RINGBUF map"""
generator = DebugInfoGenerator(module)
int_type = generator.get_int32_type()
type_array = generator.create_array_type(
int_type, map_params.get("type", BPFMapType.RINGBUF).value
)
type_ptr = generator.create_pointer_type(type_array, 64)
type_member = generator.create_struct_member("type", type_ptr, 0)
max_entries_array = generator.create_array_type(
int_type, map_params["max_entries"])
max_entries_ptr = generator.create_pointer_type(max_entries_array, 64)
max_entries_member = generator.create_struct_member(
"max_entries", max_entries_ptr, 64
)
elements_arr = [type_member, max_entries_member]
struct_type = generator.create_struct_type(
elements_arr, 128, is_distinct=True)
global_var = generator.create_global_var_debug_info(
map_name, struct_type, is_local=False
)
map_global.set_metadata("dbg", global_var)
return global_var
@MapProcessorRegistry.register("RingBuf")
def process_ringbuf_map(map_name, rval, module):
"""Process a BPF_RINGBUF map declaration"""
logger.info(f"Processing Ringbuf: {map_name}")
map_params = {"type": BPFMapType.RINGBUF}
# Parse max_entries if present
if len(rval.args) >= 1 and isinstance(rval.args[0], ast.Constant):
const_val = rval.args[0].value
if isinstance(const_val, int):
map_params["max_entries"] = const_val
for keyword in rval.keywords:
if keyword.arg == "max_entries" and isinstance(keyword.value, ast.Constant):
const_val = keyword.value.value
if isinstance(const_val, int):
map_params["max_entries"] = const_val
logger.info(f"Ringbuf map parameters: {map_params}")
map_global = create_bpf_map(module, map_name, map_params)
create_ringbuf_debug_info(module, map_global, map_name, map_params)
return map_global
@MapProcessorRegistry.register("HashMap") @MapProcessorRegistry.register("HashMap")
def process_hash_map(map_name, rval, module): def process_hash_map(map_name, rval, module):
"""Process a BPF_HASH map declaration""" """Process a BPF_HASH map declaration"""

View File

@ -1,7 +1,11 @@
from collections.abc import Callable
from typing import Any
class MapProcessorRegistry: class MapProcessorRegistry:
"""Registry for map processor functions""" """Registry for map processor functions"""
_processors = {} _processors: dict[str, Callable[..., Any]] = {}
@classmethod @classmethod
def register(cls, map_type_name): def register(cls, map_type_name):

View File

@ -1 +1,3 @@
from .structs_pass import structs_proc from .structs_pass import structs_proc
__all__ = ["structs_proc"]

View File

@ -1,47 +0,0 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <linux/blkdev.h>
#define __TARGET_ARCH_aarch64
#define u64 unsigned long long
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 10240);
__type(key, struct request *);
__type(value, u64);
} start SEC(".maps");
SEC("kprobe/blk_start_request")
int BPF_KPROBE(trace_start_req, struct request *req)
{
u64 ts = bpf_ktime_get_ns();
bpf_map_update_elem(&start, &req, &ts, BPF_ANY);
return 0;
}
SEC("kprobe/blk_mq_start_request")
int BPF_KPROBE(trace_start_mq, struct request *req)
{
u64 ts = bpf_ktime_get_ns();
bpf_map_update_elem(&start, &req, &ts, BPF_ANY);
return 0;
}
SEC("kprobe/blk_account_io_completion")
int BPF_KPROBE(trace_completion, struct request *req)
{
u64 *tsp, delta;
tsp = bpf_map_lookup_elem(&start, &req);
if (tsp) {
delta = bpf_ktime_get_ns() - *tsp;
bpf_printk("%d %x %d\n", req->__data_len,
req->cmd_flags, delta / 1000);
bpf_map_delete_elem(&start, &req);
}
return 0;
}
char LICENSE[] SEC("license") = "GPL";

View File

@ -0,0 +1,51 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <linux/types.h>
// Define the structure to be sent via ringbuf
struct event {
__u32 pid;
__u32 uid;
__u64 timestamp;
char comm[16]; // Process name
};
// Define the ringbuffer map
struct {
__uint(type, BPF_MAP_TYPE_RINGBUF);
__uint(max_entries, 256 * 1024); // 256 KB
} events SEC(".maps");
// Tracepoint for execve system calls
SEC("tracepoint/syscalls/sys_enter_execve")
int trace_execve(void *ctx)
{
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
bpf_ringbuf_submit(e, 0);
return 0;
}
char LICENSE[] SEC("license") = "GPL";

View File

@ -6,6 +6,7 @@ from ctypes import c_void_p, c_int64
@section("sometag1") @section("sometag1")
def sometag(ctx: c_void_p) -> c_int64: def sometag(ctx: c_void_p) -> c_int64:
a = 1 + 2 + 1 a = 1 + 2 + 1
print(f"{a}")
return c_int64(0) return c_int64(0)

View File

@ -1,5 +1,5 @@
from pythonbpf import bpf, map, section, bpfglobal, compile from pythonbpf import bpf, map, section, bpfglobal, compile
from pythonbpf.helpers import XDP_PASS from pythonbpf.helper import XDP_PASS
from pythonbpf.maps import HashMap from pythonbpf.maps import HashMap
from ctypes import c_void_p, c_int64 from ctypes import c_void_p, c_int64

View File

@ -7,6 +7,7 @@ from ctypes import c_void_p, c_int64
@section("sometag1") @section("sometag1")
def sometag(ctx: c_void_p) -> c_int64: def sometag(ctx: c_void_p) -> c_int64:
a = 1 + 2 a = 1 + 2
print(f"{a}")
return c_int64(0) return c_int64(0)

View File

@ -0,0 +1,51 @@
from pythonbpf import bpf, map, struct, section, bpfglobal, compile, compile_to_ir, BPF
from pythonbpf.helper import ktime, pid
from pythonbpf.maps import PerfEventArray
from ctypes import c_void_p, c_int32, c_uint64
# PLACEHOLDER EXAMPLE. THIS SHOULD TECHNICALLY STILL FAIL TESTS
@bpf
@struct
class data_t:
pid: c_uint64
ts: c_uint64
comm: str(16)
@bpf
@map
def events() -> PerfEventArray:
return PerfEventArray(key_size=c_int32, value_size=c_int32)
@bpf
@section("tracepoint/syscalls/sys_enter_clone")
def hello(ctx: c_void_p) -> c_int32:
dataobj = data_t()
ts = ktime()
strobj = "hellohellohello"
dataobj.pid = pid()
dataobj.ts = ktime()
# dataobj.comm = strobj
print(
f"clone called at {dataobj.ts} by pid {dataobj.pid}, comm {strobj} at time {ts}"
)
events.output(dataobj)
return c_int32(0)
@bpf
@bpfglobal
def LICENSE() -> str:
return "GPL"
compile()
compile_to_ir("perf_buffer_map.py", "perf_buffer_map.ll")
b = BPF()
b.load_and_attach()
while True:
print("running")

View File

@ -0,0 +1,35 @@
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
# Define a map
@bpf
@map
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")
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()