Limit inlining functions called once

as dicussed in PR ipa/103454 there are several benchmarks that regresses
for -finline-functions-called once. Runtmes:
 - tramp3d with -Ofast. 31%
 - exchange2 with -Ofast 11-21%
 - roms O2 9%-10%
 - tonto 2.5-3.5% with LTO
Build times:
 - specfp2006 41% (mostly wrf that builds 71% faster)
 - specint2006 1.5-3%
 - specfp2017 64% (again mostly wrf)
 - specint2017 2.5-3.5%

This patch adds two params to tweak the behaviour:
 1) max-inline-functions-called-once-loop-depth limiting the loop depth
    (this is useful primarily for exchange where the inlined function is in
     loop depth 9)
 2) max-inline-functions-called-once-insns
    We already have large-function-insns/growth parameters, but these are
    limiting also inlining small functions, so reducing them will regress
    very large functions that are hot.

    Because inlining functions called once is meant just as a cleanup pass
    I think it makes sense to have separate limit for it.
gcc/ChangeLog:

2021-12-09  Jan Hubicka  <hubicka@ucw.cz>

	* doc/invoke.texi (max-inline-functions-called-once-loop-depth,
	max-inline-functions-called-once-insns): New parameters.
	* ipa-inline.c (check_callers): Handle
	param_inline_functions_called_once_loop_depth and
	param_inline_functions_called_once_insns.
	(edge_badness): Fix linebreaks.
	* params.opt (param=max-inline-functions-called-once-loop-depth,
	param=max-inline-functions-called-once-insn): New params.

gcc/doc/invoke.texi

@@ -13605,6 +13605,14 @@ The maximum number of backtrack attempts the scheduler should make
 when modulo scheduling a loop.  Larger values can exponentially increase
 compilation time.
 
+@item max-inline-functions-called-once-loop-depth
+Maximal loop depth of a call considered by inline heuristics that tries to
+inline all functions called once.
+
+@item max-inline-functions-called-once-insns
+Maximal estimated size of functions produced while inlining functions called
+once.
+
 @item max-inline-insns-single
 Several parameters control the tree inliner used in GCC@.  This number sets the
 maximum number of instructions (counted in GCC's internal representation) in a

gcc/ipa-inline.c

@@ -1091,20 +1091,30 @@ static bool
 check_callers (struct cgraph_node *node, void *has_hot_call)
 {
   struct cgraph_edge *e;
-   for (e = node->callers; e; e = e->next_caller)
-     {
-       if (!opt_for_fn (e->caller->decl, flag_inline_functions_called_once)
-	   || !opt_for_fn (e->caller->decl, optimize))
-	 return true;
-       if (!can_inline_edge_p (e, true))
-         return true;
-       if (e->recursive_p ())
-	 return true;
-       if (!can_inline_edge_by_limits_p (e, true))
-         return true;
-       if (!(*(bool *)has_hot_call) && e->maybe_hot_p ())
-	 *(bool *)has_hot_call = true;
-     }
+  for (e = node->callers; e; e = e->next_caller)
+    {
+      if (!opt_for_fn (e->caller->decl, flag_inline_functions_called_once)
+	  || !opt_for_fn (e->caller->decl, optimize))
+	return true;
+      if (!can_inline_edge_p (e, true))
+	return true;
+      if (e->recursive_p ())
+	return true;
+      if (!can_inline_edge_by_limits_p (e, true))
+	return true;
+      /* Inlining large functions to large loop depth is often harmful because
+	 of register pressure it implies.  */
+      if ((int)ipa_call_summaries->get (e)->loop_depth
+	  > param_inline_functions_called_once_loop_depth)
+	return true;
+      /* Do not produce gigantic functions.  */
+      if (estimate_size_after_inlining (e->caller->inlined_to ?
+					e->caller->inlined_to : e->caller, e)
+	  > param_inline_functions_called_once_insns)
+	return true;
+      if (!(*(bool *)has_hot_call) && e->maybe_hot_p ())
+	*(bool *)has_hot_call = true;
+    }
   return false;
 }
 
@@ -1327,9 +1337,12 @@ edge_badness (struct cgraph_edge *edge, bool dump)
 		   " %i (compensated)\n",
 		   badness.to_double (),
 		   freq.to_double (),
-		   edge->count.ipa ().initialized_p () ? edge->count.ipa ().to_gcov_type () : -1,
-		   caller->count.ipa ().initialized_p () ? caller->count.ipa ().to_gcov_type () : -1,
-		   inlining_speedup (edge, freq, unspec_edge_time, edge_time).to_double (),
+		   edge->count.ipa ().initialized_p ()
+		   ? edge->count.ipa ().to_gcov_type () : -1,
+		   caller->count.ipa ().initialized_p ()
+		   ? caller->count.ipa ().to_gcov_type () : -1,
+		   inlining_speedup (edge, freq, unspec_edge_time,
+				     edge_time).to_double (),
 		   estimate_growth (callee),
 		   callee_info->growth, overall_growth);
 	}

gcc/params.opt

@@ -545,6 +545,14 @@ The maximum expansion factor when copying basic blocks.
 Common Joined UInteger Var(param_max_hoist_depth) Init(30) Param Optimization
 Maximum depth of search in the dominator tree for expressions to hoist.
 
+-param=max-inline-functions-called-once-loop-depth=
+Common Joined UInteger Var(param_inline_functions_called_once_loop_depth) Init(6) Optimization Param
+Maximum loop depth of a call which is considered for inlining functions called once
+
+-param=max-inline-functions-called-once-insns=
+Common Joined UInteger Var(param_inline_functions_called_once_insns) Init(4000) Optimization Param
+Maximum combinaed size of caller and callee wich is inlined if callee is called once.
+
 -param=max-inline-insns-auto=
 Common Joined UInteger Var(param_max_inline_insns_auto) Init(15) Optimization Param
 The maximum number of instructions when automatically inlining.