Fix local_sym_tab accesses in expr_pass

examples/c-form/ex7.bpf.c

@@ -1,34 +1,47 @@
 // SPDX-License-Identifier: GPL-2.0
+
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+struct trace_entry {
+  short unsigned int type;
+  unsigned char flags;
+  unsigned char preempt_count;
+  int pid;
+};
+
+struct trace_event_raw_sys_enter {
+  struct trace_entry ent;
+  long int id;
+  long unsigned int args[6];
+  char __data[0];
+};
 
 struct event {
-    __u32 pid;
-    __u32 uid;
-    __u64 ts;
+  __u32 pid;
+  __u32 uid;
+  __u64 ts;
 };
 
 struct {
-    __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-    __uint(key_size, sizeof(int));
-    __uint(value_size, sizeof(int));
+  __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+  __uint(key_size, sizeof(int));
+  __uint(value_size, sizeof(int));
 } events SEC(".maps");
 
 SEC("tp/syscalls/sys_enter_setuid")
-int handle_setuid_entry(struct trace_event_raw_sys_enter *ctx)
-{
-    struct event data = {};
-    
-    // Extract UID from the syscall arguments
-    data.uid = (unsigned int)ctx->args[0];
-    data.ts = bpf_ktime_get_ns();
-    data.pid = bpf_get_current_pid_tgid() >> 32;
-    
-    bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, &data, sizeof(data));
-    
-    return 0;
+int handle_setuid_entry(struct trace_event_raw_sys_enter *ctx) {
+  struct event data = {};
+
+  // Extract UID from the syscall arguments
+  data.uid = (unsigned int)ctx->args[0];
+  data.ts = bpf_ktime_get_ns();
+  data.pid = bpf_get_current_pid_tgid() >> 32;
+
+  bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, &data, sizeof(data));
+
+  return 0;
 }
 
 char LICENSE[] SEC("license") = "GPL";

examples/execve5.py

@@ -21,6 +21,7 @@ def events() -> PerfEventArray:
 @bpf
 @section("tracepoint/syscalls/sys_enter_clone")
 def hello(ctx: c_void_p) -> c_int32:
+    strobj = "Hi"
     dataobj = data_t()
     ts = ktime()
     process_id = pid()

pythonbpf/binary_ops.py

@@ -15,6 +15,7 @@ def recursive_dereferencer(var, builder):
     else:
         raise TypeError(f"Unsupported type for dereferencing: {var.type}")
 
+
 def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab, func):
     print(module)
     left = rval.left
@@ -24,7 +25,7 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
     # Handle left operand
     if isinstance(left, ast.Name):
         if left.id in local_sym_tab:
-            left = recursive_dereferencer(local_sym_tab[left.id], builder)
+            left = recursive_dereferencer(local_sym_tab[left.id][0], builder)
         else:
             raise SyntaxError(f"Undefined variable: {left.id}")
     elif isinstance(left, ast.Constant):
@@ -34,7 +35,7 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
 
     if isinstance(right, ast.Name):
         if right.id in local_sym_tab:
-            right = recursive_dereferencer(local_sym_tab[right.id], builder)
+            right = recursive_dereferencer(local_sym_tab[right.id][0], builder)
         else:
             raise SyntaxError(f"Undefined variable: {right.id}")
     elif isinstance(right, ast.Constant):
@@ -46,36 +47,36 @@ def handle_binary_op(rval, module, builder, var_name, local_sym_tab, map_sym_tab
 
     if isinstance(op, ast.Add):
         builder.store(builder.add(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.Sub):
         builder.store(builder.sub(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.Mult):
         builder.store(builder.mul(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.Div):
         builder.store(builder.sdiv(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.Mod):
         builder.store(builder.srem(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.LShift):
         builder.store(builder.shl(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.RShift):
         builder.store(builder.lshr(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.BitOr):
         builder.store(builder.or_(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.BitXor):
         builder.store(builder.xor(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.BitAnd):
         builder.store(builder.and_(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     elif isinstance(op, ast.FloorDiv):
         builder.store(builder.udiv(left, right),
-                      local_sym_tab[var_name])
+                      local_sym_tab[var_name][0])
     else:
         raise SyntaxError("Unsupported binary operation")

pythonbpf/bpf_helper_handler.py

@@ -27,7 +27,7 @@ def bpf_map_lookup_elem_emitter(call, map_ptr, module, builder, func, local_sym_
     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]
+            key_ptr = local_sym_tab[key_name][0]
         else:
             raise ValueError(
                 f"Key variable {key_name} not found in local symbol table.")
@@ -85,6 +85,7 @@ def bpf_printk_emitter(call, map_ptr, module, builder, func, local_sym_tab=None,
                     raise NotImplementedError(
                         "Only string and integer constants are supported in f-string.")
             elif isinstance(value, ast.FormattedValue):
+                print("Formatted value:", ast.dump(value))
                 # Assume int for now
                 fmt_parts.append("%lld")
                 if isinstance(value.value, ast.Name):
@@ -189,7 +190,7 @@ def bpf_map_update_elem_emitter(call, map_ptr, module, builder, func, local_sym_
     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]
+            key_ptr = local_sym_tab[key_name][0]
         else:
             raise ValueError(
                 f"Key variable {key_name} not found in local symbol table.")
@@ -208,7 +209,7 @@ def bpf_map_update_elem_emitter(call, map_ptr, module, builder, func, local_sym_
     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]
+            value_ptr = local_sym_tab[value_name][0]
         else:
             raise ValueError(
                 f"Value variable {value_name} not found in local symbol table.")
@@ -231,7 +232,7 @@ def bpf_map_update_elem_emitter(call, map_ptr, module, builder, func, local_sym_
             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]
+                flags_ptr = local_sym_tab[flags_name][0]
                 flags_val = builder.load(flags_ptr)
             else:
                 raise ValueError(
@@ -284,7 +285,7 @@ def bpf_map_delete_elem_emitter(call, map_ptr, module, builder, func, local_sym_
     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]
+            key_ptr = local_sym_tab[key_name][0]
         else:
             raise ValueError(
                 f"Key variable {key_name} not found in local symbol table.")
@@ -350,7 +351,7 @@ def bpf_perf_event_output_handler(call, map_ptr, module, builder, func, local_sy
     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]
+            data_ptr = local_sym_tab[data_name][0]
         else:
             raise ValueError(
                 f"Data variable {data_name} not found in local symbol table.")

pythonbpf/expr_pass.py

@@ -6,7 +6,7 @@ def eval_expr(func, module, builder, expr, local_sym_tab, map_sym_tab, structs_s
     print(f"Evaluating expression: {expr}")
     if isinstance(expr, ast.Name):
         if expr.id in local_sym_tab:
-            var = local_sym_tab[expr.id]
+            var = local_sym_tab[expr.id][0]
             val = builder.load(var)
             return val
         else:
@@ -37,7 +37,7 @@ def eval_expr(func, module, builder, expr, local_sym_tab, map_sym_tab, structs_s
                     return None
                 if isinstance(arg, ast.Name):
                     if arg.id in local_sym_tab:
-                        arg = local_sym_tab[arg.id]
+                        arg = local_sym_tab[arg.id][0]
                     else:
                         print(f"Undefined variable {arg.id}")
                         return None

pythonbpf/functions_pass.py

@@ -51,7 +51,7 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
 
             if field_name in struct_info["fields"]:
                 field_idx = struct_info["fields"][field_name]
-                struct_ptr = local_sym_tab[var_name]
+                struct_ptr = local_sym_tab[var_name][0]
                 field_ptr = builder.gep(
                     struct_ptr, [ir.Constant(ir.IntType(32), 0),
                                  ir.Constant(ir.IntType(32), field_idx)],
@@ -68,19 +68,32 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
         if isinstance(rval.value, bool):
             if rval.value:
                 builder.store(ir.Constant(ir.IntType(1), 1),
-                              local_sym_tab[var_name])
+                              local_sym_tab[var_name][0])
             else:
                 builder.store(ir.Constant(ir.IntType(1), 0),
-                              local_sym_tab[var_name])
+                              local_sym_tab[var_name][0])
             print(f"Assigned constant {rval.value} to {var_name}")
         elif isinstance(rval.value, int):
             # Assume c_int64 for now
             # var = builder.alloca(ir.IntType(64), name=var_name)
             # var.align = 8
             builder.store(ir.Constant(ir.IntType(64), rval.value),
-                          local_sym_tab[var_name])
+                          local_sym_tab[var_name][0])
             # local_sym_tab[var_name] = var
             print(f"Assigned constant {rval.value} to {var_name}")
+        elif isinstance(rval.value, str):
+            str_val = rval.value.encode('utf-8') + b'\x00'
+            str_const = ir.Constant(ir.ArrayType(
+                ir.IntType(8), len(str_val)), bytearray(str_val))
+            global_str = ir.GlobalVariable(
+                module, str_const.type, name=f"{var_name}_str")
+            global_str.linkage = 'internal'
+            global_str.global_constant = True
+            global_str.initializer = str_const
+            str_ptr = builder.bitcast(
+                global_str, ir.PointerType(ir.IntType(8)))
+            builder.store(str_ptr, local_sym_tab[var_name][0])
+            print(f"Assigned string constant '{rval.value}' to {var_name}")
         else:
             print("Unsupported constant type")
     elif isinstance(rval, ast.Call):
@@ -92,7 +105,7 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
                 # var = builder.alloca(ir_type, name=var_name)
                 # var.align = ir_type.width // 8
                 builder.store(ir.Constant(
-                    ir_type, rval.args[0].value), local_sym_tab[var_name])
+                    ir_type, rval.args[0].value), local_sym_tab[var_name][0])
                 print(f"Assigned {call_type} constant "
                       f"{rval.args[0].value} to {var_name}")
                 # local_sym_tab[var_name] = var
@@ -101,7 +114,7 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
                 # var.align = 8
                 val = handle_helper_call(
                     rval, module, builder, func, local_sym_tab, map_sym_tab, structs_sym_tab, local_var_metadata)
-                builder.store(val, local_sym_tab[var_name])
+                builder.store(val, local_sym_tab[var_name][0])
                 # local_sym_tab[var_name] = var
                 print(f"Assigned constant {rval.func.id} to {var_name}")
             elif call_type == "deref" and len(rval.args) == 1:
@@ -112,7 +125,7 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
                     print("Failed to evaluate deref argument")
                     return
                 print(f"Dereferenced value: {val}, storing in {var_name}")
-                builder.store(val, local_sym_tab[var_name])
+                builder.store(val, local_sym_tab[var_name][0])
                 # local_sym_tab[var_name] = var
                 print(f"Dereferenced and assigned to {var_name}")
             elif call_type in structs_sym_tab and len(rval.args) == 0:
@@ -121,7 +134,7 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
                 # var = builder.alloca(ir_type, name=var_name)
                 # Null init
                 builder.store(ir.Constant(ir_type, None),
-                              local_sym_tab[var_name])
+                              local_sym_tab[var_name][0])
                 local_var_metadata[var_name] = call_type
                 print(f"Assigned struct {call_type} to {var_name}")
                 # local_sym_tab[var_name] = var
@@ -142,7 +155,7 @@ def handle_assign(func, module, builder, stmt, map_sym_tab, local_sym_tab, struc
                             rval, module, builder, func, local_sym_tab, map_sym_tab, structs_sym_tab, local_var_metadata)
                         # var = builder.alloca(ir.IntType(64), name=var_name)
                         # var.align = 8
-                        builder.store(val, local_sym_tab[var_name])
+                        builder.store(val, local_sym_tab[var_name][0])
                         # local_sym_tab[var_name] = var
             else:
                 print("Unsupported assignment call structure")
@@ -166,7 +179,7 @@ def handle_cond(func, module, builder, cond, local_sym_tab, map_sym_tab):
             return None
     elif isinstance(cond, ast.Name):
         if cond.id in local_sym_tab:
-            var = local_sym_tab[cond.id]
+            var = local_sym_tab[cond.id][0]
             val = builder.load(var)
             if val.type != ir.IntType(1):
                 # Convert nonzero values to true, zero to false
@@ -370,8 +383,14 @@ def allocate_mem(module, builder, body, func, ret_type, map_sym_tab, local_sym_t
                     var.align = ir_type.width // 8
                     print(
                         f"Pre-allocated variable {var_name} of type c_int64")
+                elif isinstance(rval.value, str):
+                    ir_type = ir.PointerType(ir.IntType(8))
+                    var = builder.alloca(ir_type, name=var_name)
+                    var.align = 8
+                    print(
+                        f"Pre-allocated variable {var_name} of type string")
                 else:
-                    print("Unsupported constant type")
+                    print(f"Unsupported constant type")
                     continue
             elif isinstance(rval, ast.BinOp):
                 # Assume c_int64 for now
@@ -383,7 +402,7 @@ def allocate_mem(module, builder, body, func, ret_type, map_sym_tab, local_sym_t
             else:
                 print("Unsupported assignment value type")
                 continue
-            local_sym_tab[var_name] = var
+            local_sym_tab[var_name] = (var, ir_type)
     return local_sym_tab