fixes for a number of ZAM optimization bugs

src/script_opt/Expr.cc

@@ -1468,7 +1468,7 @@ ExprPtr AssignExpr::Reduce(Reducer* c, StmtPtr& red_stmt) {
 
         auto ind1_e = ind_e->Op1()->Reduce(c, ind1_stmt);
         auto ind2_e = ind_e->Op2()->Reduce(c, ind2_stmt);
-        auto rhs_e = op2->Reduce(c, rhs_stmt);
+        auto rhs_e = op2->ReduceToSingleton(c, rhs_stmt);
 
         red_stmt = MergeStmts(MergeStmts(rhs_reduce, ind1_stmt), ind2_stmt, rhs_stmt);
 

src/script_opt/ScriptOpt.cc

@@ -56,7 +56,7 @@ bool is_lambda(const ScriptFunc* f) { return lambdas.count(f) > 0; }
 
 bool is_when_lambda(const ScriptFunc* f) { return when_lambdas.count(f) > 0; }
 
-const FuncInfo* analyze_global_stmts(Stmt* stmts) {
+size_t analyze_global_stmts(Stmt* stmts) {
     // We ignore analysis_options.only_{files,funcs} - if they're in use, later
     // logic will keep this function from being compiled, but it's handy
     // now to enter it into "funcs" so we have a FuncInfo to return.
@@ -72,9 +72,11 @@ const FuncInfo* analyze_global_stmts(Stmt* stmts) {
     global_stmts->AddBody(stmts->ThisPtr(), empty_inits, sc->Length());
 
     funcs.emplace_back(global_stmts, sc, stmts->ThisPtr(), 0);
-    return &funcs.back();
+    return funcs.size() - 1;
 }
 
+const FuncInfo& get_global_stmts(size_t global_ind) { return funcs[global_ind]; }
+
 void add_func_analysis_pattern(AnalyOpt& opts, const char* pat) {
     try {
         std::string full_pat = std::string("^(") + pat + ")$";

src/script_opt/ScriptOpt.h

@@ -171,9 +171,16 @@ extern bool is_lambda(const ScriptFunc* f);
 extern bool is_when_lambda(const ScriptFunc* f);
 
 // Analyze the given top-level statement(s) for optimization.  Returns
-// a pointer to a FuncInfo for an argument-less quasi-function that can
+// an opaque value that can be provided to get_global_stmts() to retrieve
-// be Invoked, or its body executed directly, to execute the statements.
+// the corresponding FuncInfo, which reflects an argument-less quasi-function
-extern const FuncInfo* analyze_global_stmts(Stmt* stmts);
+// that can be Invoked, or its body executed directly, to execute the
+// statements.  This indirection is used in case in between the call to
+// analyze_global_stmts() and using the value subsequently, the FuncInfo may
+// have been updated or shifted.  a pointer to a FuncInfo for an argument-less
+// quasi-function that can be Invoked, or its body executed directly, to
+// execute the statements.
+extern size_t analyze_global_stmts(Stmt* stmts);
+extern const FuncInfo& get_global_stmts(size_t handle);
 
 // Add a pattern to the "only_funcs" list.
 extern void add_func_analysis_pattern(AnalyOpt& opts, const char* pat);

src/script_opt/Stmt.cc

@@ -171,7 +171,7 @@ void IfStmt::Inline(Inliner* inl) {
 }
 
 bool IfStmt::IsReduced(Reducer* c) const {
-    if ( ! e->IsReducedConditional(c) )
+    if ( e->IsConst() || ! e->IsReducedConditional(c) )
         return NonReduced(e.get());
 
     return s1->IsReduced(c) && s2->IsReduced(c);
@@ -707,7 +707,7 @@ bool StmtList::ReduceStmt(unsigned int& s_i, std::vector<StmtPtr>& f_stmts, Redu
 
         if ( e->Tag() != EXPR_ASSIGN ) {
             f_stmts.push_back(std::move(stmt));
-            return false;
+            return did_change;
         }
 
         auto a = e->AsAssignExpr();
@@ -715,7 +715,7 @@ bool StmtList::ReduceStmt(unsigned int& s_i, std::vector<StmtPtr>& f_stmts, Redu
 
         if ( lhs->Tag() != EXPR_NAME ) {
             f_stmts.push_back(std::move(stmt));
-            return false;
+            return did_change;
         }
 
         auto var = lhs->AsNameExpr();

src/script_opt/ZAM/Ops.in

@@ -2089,7 +2089,7 @@ macro BuildWhen(timeout)
 		if ( v )
 			local_aggrs.push_back(v);
 		}
-	(void)make_intrusive<trigger::Trigger>(wi, wi->WhenExprGlobals(), local_aggrs, timeout, f, z.loc);
+	(void)make_intrusive<trigger::Trigger>(wi, wi->WhenExprGlobals(), local_aggrs, timeout, f, z.loc.get());
 
 ########################################
 # Internal

src/script_opt/ZAM/Support.cc

@@ -77,8 +77,8 @@ void ZAM_run_time_error(const char* msg) {
     ZAM_error = true;
 }
 
-void ZAM_run_time_error(const Location* loc, const char* msg) {
+void ZAM_run_time_error(std::shared_ptr<Location> loc, const char* msg) {
-    reporter->RuntimeError(loc, "%s", msg);
+    reporter->RuntimeError(loc.get(), "%s", msg);
     ZAM_error = true;
 }
 
@@ -87,12 +87,12 @@ void ZAM_run_time_error(const char* msg, const Obj* o) {
     ZAM_error = true;
 }
 
-void ZAM_run_time_error(const Location* loc, const char* msg, const Obj* o) {
+void ZAM_run_time_error(std::shared_ptr<Location> loc, const char* msg, const Obj* o) {
-    reporter->RuntimeError(loc, "%s (%s)", msg, obj_desc(o).c_str());
+    reporter->RuntimeError(loc.get(), "%s (%s)", msg, obj_desc(o).c_str());
     ZAM_error = true;
 }
 
-void ZAM_run_time_warning(const Location* loc, const char* msg) {
+void ZAM_run_time_warning(std::shared_ptr<Location> loc, const char* msg) {
     ODesc d;
     loc->Describe(&d);
 

src/script_opt/ZAM/Support.h

@@ -35,14 +35,14 @@ extern TypePtr log_ID_enum_type;
 extern TypePtr any_base_type;
 
 extern void ZAM_run_time_error(const char* msg);
-extern void ZAM_run_time_error(const Location* loc, const char* msg);
+extern void ZAM_run_time_error(std::shared_ptr<Location> loc, const char* msg);
-extern void ZAM_run_time_error(const Location* loc, const char* msg, const Obj* o);
+extern void ZAM_run_time_error(std::shared_ptr<Location> loc, const char* msg, const Obj* o);
 extern void ZAM_run_time_error(const Stmt* stmt, const char* msg);
 extern void ZAM_run_time_error(const char* msg, const Obj* o);
 
 extern bool ZAM_error;
 
-extern void ZAM_run_time_warning(const Location* loc, const char* msg);
+extern void ZAM_run_time_warning(std::shared_ptr<Location> loc, const char* msg);
 
 extern StringVal* ZAM_to_lower(const StringVal* sv);
 extern StringVal* ZAM_sub_bytes(const StringVal* s, zeek_uint_t start, zeek_int_t n);

src/script_opt/ZAM/ZBody.cc

@@ -194,8 +194,12 @@ void ZBody::SetInsts(vector<ZInstI*>& instsI) {
     for ( auto i = 0U; i < end_pc; ++i ) {
         auto& iI = *instsI[i];
         insts_copy[i] = iI;
-        if ( iI.stmt )
+        if ( iI.stmt ) {
-            insts_copy[i].loc = iI.stmt->Original()->GetLocationInfo();
+            auto l = iI.stmt->Original()->GetLocationInfo();
+            if ( l != &no_location )
+                insts_copy[i].loc = std::make_shared<Location>(util::copy_string(l->filename), l->first_line,
+                                                               l->last_line, l->first_column, l->last_column);
+        }
     }
 
     insts = insts_copy;
@@ -358,7 +362,8 @@ void ZBody::ProfileExecution() const {
     }
 }
 
-bool ZBody::CheckAnyType(const TypePtr& any_type, const TypePtr& expected_type, const Location* loc) const {
+bool ZBody::CheckAnyType(const TypePtr& any_type, const TypePtr& expected_type,
+                         const std::shared_ptr<Location>& loc) const {
     if ( IsAny(expected_type) )
         return true;
 
@@ -377,7 +382,7 @@ bool ZBody::CheckAnyType(const TypePtr& any_type, const TypePtr& expected_type,
         char buf[8192];
         snprintf(buf, sizeof buf, "run-time type clash (%s/%s)", type_name(at), type_name(et));
 
-        reporter->RuntimeError(loc, "%s", buf);
+        reporter->RuntimeError(loc.get(), "%s", buf);
         return false;
     }
 

src/script_opt/ZAM/ZBody.h

@@ -58,7 +58,8 @@ protected:
 
     // Run-time checking for "any" type being consistent with
     // expected typed.  Returns true if the type match is okay.
-    bool CheckAnyType(const TypePtr& any_type, const TypePtr& expected_type, const Location* loc) const;
+    bool CheckAnyType(const TypePtr& any_type, const TypePtr& expected_type,
+                      const std::shared_ptr<Location>& loc) const;
 
     StmtPtr Duplicate() override { return {NewRef{}, this}; }
 

src/script_opt/ZAM/ZInst.h

@@ -121,7 +121,7 @@ public:
     ZInstAux* aux = nullptr;
 
     // Location associated with this instruction, for error reporting.
-    const Location* loc = nullptr;
+    std::shared_ptr<Location> loc;
 
     // Interpreter call expression associated with this instruction,
     // for error reporting and stack backtraces.

src/zeek-setup.cc

@@ -923,7 +923,7 @@ SetupResult setup(int argc, char** argv, Options* zopts) {
         exit(reporter->Errors() != 0);
     }
 
-    auto init_stmts = stmts ? analyze_global_stmts(stmts) : nullptr;
+    auto init_stmts_handle = stmts ? analyze_global_stmts(stmts) : 0;
 
     analyze_scripts(options.no_unused_warnings);
 
@@ -1025,13 +1025,14 @@ SetupResult setup(int argc, char** argv, Options* zopts) {
     // cause more severe problems.
     ZEEK_LSAN_ENABLE();
 
-    if ( init_stmts ) {
+    if ( stmts ) {
+        auto& init_stmts = get_global_stmts(init_stmts_handle);
         StmtFlowType flow;
-        Frame f(init_stmts->Scope()->Length(), nullptr, nullptr);
+        Frame f(init_stmts.Scope()->Length(), nullptr, nullptr);
         g_frame_stack.push_back(&f);
 
         try {
-            init_stmts->Body()->Exec(&f, flow);
+            init_stmts.Body()->Exec(&f, flow);
         } catch ( InterpreterException& ) {
             reporter->FatalError("failed to execute script statements at top-level scope");
         }