Merge pull request #8 from pythonbpf/refactor

Add dwarf module

demo/bcc.py

@@ -1,46 +0,0 @@
-from __future__ import print_function
-from bcc import BPF
-from bcc.utils import printb
-
-# load BPF program
-b = BPF(text="""
-#include <uapi/linux/ptrace.h>
-
-BPF_HASH(last);
-
-int do_trace(struct pt_regs *ctx) {
-    u64 ts, *tsp, delta, key = 0;
-
-    // attempt to read stored timestamp
-    tsp = last.lookup(&key);
-    if (tsp != NULL) {
-        delta = bpf_ktime_get_ns() - *tsp;
-        if (delta < 1000000000) {
-            // output if time is less than 1 second
-            bpf_trace_printk("%d\\n", delta / 1000000);
-        }
-        last.delete(&key);
-    }
-
-    // update stored timestamp
-    ts = bpf_ktime_get_ns();
-    last.update(&key, &ts);
-    return 0;
-}
-""")
-
-b.attach_kprobe(event=b.get_syscall_fnname("sync"), fn_name="do_trace")
-print("Tracing for quick sync's... Ctrl-C to end")
-
-# TODO
-# format output
-start = 0
-while 1:
-    try:
-        (task, pid, cpu, flags, ts, ms) = b.trace_fields()
-        if start == 0:
-            start = ts
-        ts = ts - start
-        printb(b"At time %.2f s: multiple syncs detected, last %s ms ago" % (ts, ms))
-    except KeyboardInterrupt:
-        exit()

examples/execve3.py

@@ -10,18 +10,10 @@ from ctypes import c_void_p, c_int64, c_int32, c_uint64
 def last() -> HashMap:
     return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
 
-
-@bpf
-@section("tracepoint/syscalls/sys_enter_execve")
-def hello(ctx: c_void_p) -> c_int32:
-    print("entered")
-    print("multi constant support")
-    return c_int32(0)
-
-
 @bpf
 @section("tracepoint/syscalls/sys_exit_execve")
 def hello_again(ctx: c_void_p) -> c_int64:
+    print("multi constant support")
     print("exited")
     key = 0
     delta = 0
@@ -45,11 +37,9 @@ def hello_again(ctx: c_void_p) -> c_int64:
 
     return c_int64(0)
 
-
 @bpf
 @bpfglobal
 def LICENSE() -> str:
     return "GPL"
 
-
 compile()

examples/execve4.py

@@ -10,7 +10,6 @@ from ctypes import c_void_p, c_int64, c_int32, c_uint64
 def last() -> HashMap:
     return HashMap(key=c_uint64, value=c_uint64, max_entries=3)
 
-
 @bpf
 @section("blk_start_request")
 def trace_start(ctx: c_void_p) -> c_int32:

examples/hello_world.py

@@ -1,15 +0,0 @@
-# This is what it is going to look like
-# pylint: disable-all# type: ignore
-from pythonbpf.decorators import tracepoint, syscalls, bpfglobal, bpf
-from ctypes import c_void_p, c_int32
-
-@bpf
-@tracepoint(syscalls.sys_clone)
-def trace_clone(ctx: c_void_p) -> c_int32:
-    print("Hello, World!")
-    return c_int32(0)
-
-@bpf
-@bpfglobal
-def LICENSE() -> str:
-    return "GPL"

pythonbpf/codegen.py

@@ -5,6 +5,7 @@ from .functions_pass import func_proc
 from pythonbpf.maps import maps_proc
 from .structs.structs_pass import structs_proc
 from .globals_pass import globals_processing
+from .debuginfo import DW_LANG_C11, DwarfBehaviorEnum
 import os
 import subprocess
 import inspect
@@ -12,6 +13,8 @@ from pathlib import Path
 from pylibbpf import BpfProgram
 import tempfile
 
+VERSION = "v0.1.3"
+
 
 def find_bpf_chunks(tree):
     """Find all functions decorated with @bpf in the AST."""
@@ -50,16 +53,18 @@ def compile_to_ir(filename: str, output: str):
     module.triple = "bpf"
 
     if not hasattr(module, '_debug_compile_unit'):
-        module._file_metadata = module.add_debug_info("DIFile", {       # type: ignore
+        module._file_metadata = module.add_debug_info("DIFile", {  # type: ignore
             "filename": filename,
             "directory": os.path.dirname(filename)
         })
 
-        module._debug_compile_unit = module.add_debug_info("DICompileUnit", {       # type: ignore
-            "language": 29,  # DW_LANG_C11
-            "file": module._file_metadata,      # type: ignore
-            "producer": "PythonBPF DSL Compiler",
-            "isOptimized": True,
+        module._debug_compile_unit = module.add_debug_info("DICompileUnit", {  # type: ignore
+            "language": DW_LANG_C11,
+            "file": module._file_metadata,  # type: ignore
+            "producer": f"PythonBPF {VERSION}",
+            "isOptimized": True,  # TODO: This is probably not true
+            # TODO: add a global field here that keeps track of all the globals. Works without it, but I think it might
+            # be required for kprobes.
             "runtimeVersion": 0,
             "emissionKind": 1,
             "splitDebugInlining": False,
@@ -67,32 +72,32 @@ def compile_to_ir(filename: str, output: str):
         }, is_distinct=True)
 
         module.add_named_metadata(
-            "llvm.dbg.cu", module._debug_compile_unit)        # type: ignore
+            "llvm.dbg.cu", module._debug_compile_unit)  # type: ignore
 
     processor(source, filename, module)
 
-    wchar_size = module.add_metadata([ir.Constant(ir.IntType(32), 1),
+    wchar_size = module.add_metadata([DwarfBehaviorEnum.ERROR_IF_MISMATCH,
                                       "wchar_size",
                                       ir.Constant(ir.IntType(32), 4)])
-    frame_pointer = module.add_metadata([ir.Constant(ir.IntType(32), 7),
+    frame_pointer = module.add_metadata([DwarfBehaviorEnum.OVERRIDE_USE_LARGEST,
                                          "frame-pointer",
                                          ir.Constant(ir.IntType(32), 2)])
     # Add Debug Info Version (3 = DWARF v3, which LLVM expects)
-    debug_info_version = module.add_metadata([ir.Constant(ir.IntType(32), 2),
+    debug_info_version = module.add_metadata([DwarfBehaviorEnum.WARNING_IF_MISMATCH,
                                               "Debug Info Version",
                                               ir.Constant(ir.IntType(32), 3)])
 
-    # Add explicit DWARF version (4 is common, works with LLVM BPF backend)
-    dwarf_version = module.add_metadata([ir.Constant(ir.IntType(32), 2),
+    # Add explicit DWARF version 5
+    dwarf_version = module.add_metadata([DwarfBehaviorEnum.OVERRIDE_USE_LARGEST,
                                          "Dwarf Version",
-                                         ir.Constant(ir.IntType(32), 4)])
+                                         ir.Constant(ir.IntType(32), 5)])
 
     module.add_named_metadata("llvm.module.flags", wchar_size)
     module.add_named_metadata("llvm.module.flags", frame_pointer)
     module.add_named_metadata("llvm.module.flags", debug_info_version)
     module.add_named_metadata("llvm.module.flags", dwarf_version)
 
-    module.add_named_metadata("llvm.ident", ["llvmlite PythonBPF v0.0.1"])
+    module.add_named_metadata("llvm.ident", [f"PythonBPF {VERSION}"])
 
     print(f"IR written to {output}")
     with open(output, "w") as f:

pythonbpf/debuginfo/__init__.py

@@ -0,0 +1,3 @@
+from .dwarf_constants import *
+from .dtypes import *
+from .debug_info_generator import DebugInfoGenerator

pythonbpf/debuginfo/debug_info_generator.py

@@ -0,0 +1,92 @@
+"""
+Debug information generation module for Python-BPF
+Provides utilities for generating DWARF/BTF debug information
+"""
+
+from . import dwarf_constants as dc
+from typing import Dict, Any, List, Optional, Union
+
+
+class DebugInfoGenerator:
+    def __init__(self, module):
+        self.module = module
+        self._type_cache = {}  # Cache for common debug types
+
+    def get_basic_type(self, name: str, size: int, encoding: int) -> Any:
+        """Get or create a basic type with caching"""
+        key = (name, size, encoding)
+        if key not in self._type_cache:
+            self._type_cache[key] = self.module.add_debug_info("DIBasicType", {
+                "name": name,
+                "size": size,
+                "encoding": encoding
+            })
+        return self._type_cache[key]
+
+    def get_uint32_type(self) -> Any:
+        """Get debug info for unsigned 32-bit integer"""
+        return self.get_basic_type("unsigned int", 32, dc.DW_ATE_unsigned)
+
+    def get_uint64_type(self) -> Any:
+        """Get debug info for unsigned 64-bit integer"""
+        return self.get_basic_type("unsigned long long", 64, dc.DW_ATE_unsigned)
+
+    def create_pointer_type(self, base_type: Any, size: int = 64) -> Any:
+        """Create a pointer type to the given base type"""
+        return self.module.add_debug_info("DIDerivedType", {
+            "tag": dc.DW_TAG_pointer_type,
+            "baseType": base_type,
+            "size": size
+        })
+
+    def create_array_type(self, base_type: Any, count: int) -> Any:
+        """Create an array type of the given base type with specified count"""
+        subrange = self.module.add_debug_info("DISubrange", {"count": count})
+        return self.module.add_debug_info("DICompositeType", {
+            "tag": dc.DW_TAG_array_type,
+            "baseType": base_type,
+            "size": self._compute_array_size(base_type, count),
+            "elements": [subrange]
+        })
+
+    @staticmethod
+    def _compute_array_size(base_type: Any, count: int) -> int:
+        # Extract size from base_type if possible
+        # For simplicity, assuming base_type has a size attribute
+        return getattr(base_type, "size", 32) * count
+
+    def create_struct_member(self, name: str, base_type: Any, offset: int) -> Any:
+        """Create a struct member with the given name, type, and offset"""
+        return self.module.add_debug_info("DIDerivedType", {
+            "tag": dc.DW_TAG_member,
+            "name": name,
+            "file": self.module._file_metadata,
+            "baseType": base_type,
+            "size": getattr(base_type, "size", 64),
+            "offset": offset
+        })
+
+    def create_struct_type(self, members: List[Any], size: int, is_distinct: bool) -> Any:
+        """Create a struct type with the given members and size"""
+        return self.module.add_debug_info("DICompositeType", {
+            "tag": dc.DW_TAG_structure_type,
+            "file": self.module._file_metadata,
+            "size": size,
+            "elements": members,
+        }, is_distinct=is_distinct)
+
+    def create_global_var_debug_info(self, name: str, var_type: Any, is_local: bool = False) -> Any:
+        """Create debug info for a global variable"""
+        global_var = self.module.add_debug_info("DIGlobalVariable", {
+            "name": name,
+            "scope": self.module._debug_compile_unit,
+            "file": self.module._file_metadata,
+            "type": var_type,
+            "isLocal": is_local,
+            "isDefinition": True
+        }, is_distinct=True)
+
+        return self.module.add_debug_info("DIGlobalVariableExpression", {
+            "var": global_var,
+            "expr": self.module.add_debug_info("DIExpression", {})
+        })

pythonbpf/debuginfo/dtypes.py

@@ -0,0 +1,6 @@
+import llvmlite.ir as ir
+
+class DwarfBehaviorEnum:
+    ERROR_IF_MISMATCH = ir.Constant(ir.IntType(32), 1)
+    WARNING_IF_MISMATCH = ir.Constant(ir.IntType(32), 2)
+    OVERRIDE_USE_LARGEST = ir.Constant(ir.IntType(32), 7)

pythonbpf/maps/maps_pass.py

@@ -1,8 +1,8 @@
 import ast
 from llvmlite import ir
-from pythonbpf import dwarf_constants as dc
 from enum import Enum
 from .maps_utils import MapProcessorRegistry
+from ..debuginfo import dwarf_constants as dc, DebugInfoGenerator
 import logging
 
 logger = logging.getLogger(__name__)
@@ -55,53 +55,15 @@ 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 map"""
-    file_metadata = module._file_metadata
-    compile_unit = module._debug_compile_unit
+    generator = DebugInfoGenerator(module)
 
-    # Create basic type for unsigned int (32-bit)
-    uint_type = module.add_debug_info("DIBasicType", {
-        "name": "unsigned int",
-        "size": 32,
-        "encoding": dc.DW_ATE_unsigned
-    })
+    uint_type = generator.get_uint32_type()
+    ulong_type = generator.get_uint64_type()
+    array_type = generator.create_array_type(uint_type, map_params.get("type", BPFMapType.HASH).value)
+    type_ptr = generator.create_pointer_type(array_type, 64)
+    key_ptr = generator.create_pointer_type(array_type if "key_size" in map_params else ulong_type, 64)
+    value_ptr = generator.create_pointer_type(array_type if "value_size" in map_params else ulong_type, 64)
 
-    # Create basic type for unsigned long long (64-bit)
-    ulong_type = module.add_debug_info("DIBasicType", {
-        "name": "unsigned long long",
-        "size": 64,
-        "encoding": dc.DW_ATE_unsigned
-    })
-
-    # Create array type for map type field (array of 1 unsigned int)
-    array_subrange = module.add_debug_info(
-        "DISubrange", {"count": map_params.get("type", BPFMapType.HASH).value})
-    array_type = module.add_debug_info("DICompositeType", {
-        "tag": dc.DW_TAG_array_type,
-        "baseType": uint_type,
-        "size": 32,
-        "elements": [array_subrange]
-    })
-
-    # Create pointer types
-    type_ptr = module.add_debug_info("DIDerivedType", {
-        "tag": dc.DW_TAG_pointer_type,
-        "baseType": array_type,
-        "size": 64
-    })
-
-    key_ptr = module.add_debug_info("DIDerivedType", {
-        "tag": dc.DW_TAG_pointer_type,
-        # Adjust based on actual key type
-        "baseType": array_type if "key_size" in map_params else uint_type,
-        "size": 64
-    })
-
-    value_ptr = module.add_debug_info("DIDerivedType", {
-        "tag": dc.DW_TAG_pointer_type,
-        # Adjust based on actual value type
-        "baseType": array_type if "value_size" in map_params else ulong_type,
-        "size": 64
-    })
 
     elements_arr = []
 
@@ -117,69 +79,27 @@ def create_map_debug_info(module, map_global, map_name, map_params):
             ptr = key_ptr
         else:
             ptr = value_ptr
-        member = module.add_debug_info("DIDerivedType", {
-            "tag": dc.DW_TAG_member,
-            "name": elem,
-            "file": file_metadata,
-            "baseType": ptr,
-            "size": 64,
-            "offset": cnt * 64
-        })
+        # TODO: the best way to do this is not 64, but get the size each time. this will not work for structs.
+        member = generator.create_struct_member(elem, ptr, cnt * 64)
         elements_arr.append(member)
         cnt += 1
 
     if "max_entries" in map_params:
-        array_subrange_max_entries = module.add_debug_info(
-            "DISubrange", {"count": map_params["max_entries"]})
-        array_type_max_entries = module.add_debug_info("DICompositeType", {
-            "tag": dc.DW_TAG_array_type,
-            "baseType": uint_type,
-            "size": 32,
-            "elements": [array_subrange_max_entries]
-        })
-        max_entries_ptr = module.add_debug_info("DIDerivedType", {
-            "tag": dc.DW_TAG_pointer_type,
-            "baseType": array_type_max_entries,
-            "size": 64
-        })
-        max_entries_member = module.add_debug_info("DIDerivedType", {
-            "tag": dc.DW_TAG_member,
-            "name": "max_entries",
-            "file": file_metadata,
-            "baseType": max_entries_ptr,
-            "size": 64,
-            "offset": cnt * 64
-        })
+        max_entries_array = generator.create_array_type(uint_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, cnt * 64)
         elements_arr.append(max_entries_member)
 
     # Create the struct type
-    struct_type = module.add_debug_info("DICompositeType", {
-        "tag": dc.DW_TAG_structure_type,
-        "file": file_metadata,
-        "size": 64 * len(elements_arr),  # 4 * 64-bit pointers
-        "elements": elements_arr,
-    }, is_distinct=True)
+    struct_type = generator.create_struct_type(elements_arr, 64 * len(elements_arr), is_distinct=True)
 
     # Create global variable debug info
-    global_var = module.add_debug_info("DIGlobalVariable", {
-        "name": map_name,
-        "scope": compile_unit,
-        "file": file_metadata,
-        "type": struct_type,
-        "isLocal": False,
-        "isDefinition": True
-    }, is_distinct=True)
-
-    # Create global variable expression
-    global_var_expr = module.add_debug_info("DIGlobalVariableExpression", {
-        "var": global_var,
-        "expr": module.add_debug_info("DIExpression", {})
-    })
+    global_var = generator.create_global_var_debug_info(map_name, struct_type, is_local=False)
 
     # Attach debug info to the global variable
-    map_global.set_metadata("dbg", global_var_expr)
+    map_global.set_metadata("dbg", global_var)
 
-    return global_var_expr
+    return global_var
 
 
 @MapProcessorRegistry.register("HashMap")