expand: Fix up IFN_ATOMIC_{BIT*,*CMP_0} expansion [PR105951]

Both IFN_ATOMIC_BIT_TEST_AND_* and IFN_ATOMIC_*_FETCH_CMP_0 ifns
are matched if their corresponding optab is implemented for the particular
mode.  The fact that those optabs are implemented doesn't guarantee
they will succeed though, they can just FAIL in their expansion.
The expansion in that case uses expand_atomic_fetch_op as fallback, but
as has been reported and and can be reproduced on the testcases,
even those can fail and we didn't have any fallback after that.
For IFN_ATOMIC_BIT_TEST_AND_* we actually have such calls.  One is
done whenever we lost lhs of the ifn at some point in between matching
it in tree-ssa-ccp.cc and expansion.  The following patch for that case
just falls through and expands as if there was a lhs, creates a temporary
for it.  For the other expand_atomic_fetch_op call in the same expander
and for the only expand_atomic_fetch_op call in the other, this falls
back the hard way, by constructing a CALL_EXPR to the call from which
the ifn has been matched and expanding that.  Either it is lucky and manages
to expand inline, or it emits a libatomic API call.
So that we don't have to rediscover which builtin function to call in the
fallback, we record at tree-ssa-ccp.cc time gimple_call_fn (call) in
an extra argument to the ifn.

2022-06-16  Jakub Jelinek  <[email protected]>

	PR middle-end/105951
	* tree-ssa-ccp.cc (optimize_atomic_bit_test_and,
	optimize_atomic_op_fetch_cmp_0): Remember gimple_call_fn (call)
	as last argument to the internal functions.
	* builtins.cc (expand_ifn_atomic_bit_test_and): Adjust for the
	extra call argument to ifns.  If expand_atomic_fetch_op fails for the
	lhs == NULL_TREE case, fall through into the optab code with
	gen_reg_rtx (mode) as target.  If second expand_atomic_fetch_op
	fails, construct a CALL_EXPR and expand that.
	(expand_ifn_atomic_op_fetch_cmp_0): Adjust for the extra call argument
	to ifns.  If expand_atomic_fetch_op fails, construct a CALL_EXPR and
	expand that.

	* gcc.target/i386/pr105951-1.c: New test.
	* gcc.target/i386/pr105951-2.c: New test.

Author: jakubjelinek

gcc/builtins.cc

@@ -6224,7 +6224,7 @@ expand_ifn_atomic_bit_test_and (gcall *call)
 
   gcc_assert (flag_inline_atomics);
 
-  if (gimple_call_num_args (call) == 4)
+  if (gimple_call_num_args (call) == 5)
     model = get_memmodel (gimple_call_arg (call, 3));
 
   rtx mem = get_builtin_sync_mem (ptr, mode);
@@ -6250,15 +6250,19 @@ expand_ifn_atomic_bit_test_and (gcall *call)
 
   if (lhs == NULL_TREE)
     {
-      val = expand_simple_binop (mode, ASHIFT, const1_rtx,
-				 val, NULL_RTX, true, OPTAB_DIRECT);
+      rtx val2 = expand_simple_binop (mode, ASHIFT, const1_rtx,
+				      val, NULL_RTX, true, OPTAB_DIRECT);
       if (code == AND)
-	val = expand_simple_unop (mode, NOT, val, NULL_RTX, true);
-      expand_atomic_fetch_op (const0_rtx, mem, val, code, model, false);
-      return;
+	val2 = expand_simple_unop (mode, NOT, val2, NULL_RTX, true);
+      if (expand_atomic_fetch_op (const0_rtx, mem, val2, code, model, false))
+	return;
     }
 
-  rtx target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
+  rtx target;
+  if (lhs)
+    target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
+  else
+    target = gen_reg_rtx (mode);
   enum insn_code icode = direct_optab_handler (optab, mode);
   gcc_assert (icode != CODE_FOR_nothing);
   create_output_operand (&ops[0], target, mode);
@@ -6277,6 +6281,22 @@ expand_ifn_atomic_bit_test_and (gcall *call)
     val = expand_simple_unop (mode, NOT, val, NULL_RTX, true);
   rtx result = expand_atomic_fetch_op (gen_reg_rtx (mode), mem, val,
 				       code, model, false);
+  if (!result)
+    {
+      bool is_atomic = gimple_call_num_args (call) == 5;
+      tree tcall = gimple_call_arg (call, 3 + is_atomic);
+      tree fndecl = gimple_call_addr_fndecl (tcall);
+      tree type = TREE_TYPE (TREE_TYPE (fndecl));
+      tree exp = build_call_nary (type, tcall, 2 + is_atomic, ptr,
+				  make_tree (type, val),
+				  is_atomic
+				  ? gimple_call_arg (call, 3)
+				  : integer_zero_node);
+      result = expand_builtin (exp, gen_reg_rtx (mode), NULL_RTX,
+			       mode, !lhs);
+    }
+  if (!lhs)
+    return;
   if (integer_onep (flag))
     {
       result = expand_simple_binop (mode, ASHIFTRT, result, bitval,
@@ -6308,7 +6328,7 @@ expand_ifn_atomic_op_fetch_cmp_0 (gcall *call)
 
   gcc_assert (flag_inline_atomics);
 
-  if (gimple_call_num_args (call) == 4)
+  if (gimple_call_num_args (call) == 5)
     model = get_memmodel (gimple_call_arg (call, 3));
 
   rtx mem = get_builtin_sync_mem (ptr, mode);
@@ -6369,6 +6389,21 @@ expand_ifn_atomic_op_fetch_cmp_0 (gcall *call)
 
   rtx result = expand_atomic_fetch_op (gen_reg_rtx (mode), mem, op,
 				       code, model, true);
+  if (!result)
+    {
+      bool is_atomic = gimple_call_num_args (call) == 5;
+      tree tcall = gimple_call_arg (call, 3 + is_atomic);
+      tree fndecl = gimple_call_addr_fndecl (tcall);
+      tree type = TREE_TYPE (TREE_TYPE (fndecl));
+      tree exp = build_call_nary (type, tcall,
+				  2 + is_atomic, ptr, arg,
+				  is_atomic
+				  ? gimple_call_arg (call, 3)
+				  : integer_zero_node);
+      result = expand_builtin (exp, gen_reg_rtx (mode), NULL_RTX,
+			       mode, !lhs);
+    }
+
   if (lhs)
     {
       result = emit_store_flag_force (target, comp, result, const0_rtx, mode,

gcc/testsuite/gcc.target/i386/pr105951-1.c

@@ -0,0 +1,5 @@
+/* PR middle-end/105951 */
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -march=i386" } */
+
+#include "pr98737-2.c"

gcc/testsuite/gcc.target/i386/pr105951-2.c

@@ -0,0 +1,5 @@
+/* PR middle-end/105951 */
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -march=i386" } */
+
+#include "pr98737-4.c"

gcc/tree-ssa-ccp.cc

@@ -3789,11 +3789,12 @@ optimize_atomic_bit_test_and (gimple_stmt_iterator *gsip,
   tree new_lhs = make_ssa_name (TREE_TYPE (lhs));
   tree flag = build_int_cst (TREE_TYPE (lhs), use_bool);
   if (has_model_arg)
-    g = gimple_build_call_internal (fn, 4, gimple_call_arg (call, 0),
-				    bit, flag, gimple_call_arg (call, 2));
+    g = gimple_build_call_internal (fn, 5, gimple_call_arg (call, 0),
+				    bit, flag, gimple_call_arg (call, 2),
+				    gimple_call_fn (call));
   else
-    g = gimple_build_call_internal (fn, 3, gimple_call_arg (call, 0),
-				    bit, flag);
+    g = gimple_build_call_internal (fn, 4, gimple_call_arg (call, 0),
+				    bit, flag, gimple_call_fn (call));
   gimple_call_set_lhs (g, new_lhs);
   gimple_set_location (g, gimple_location (call));
   gimple_move_vops (g, call);
@@ -4003,14 +4004,16 @@ optimize_atomic_op_fetch_cmp_0 (gimple_stmt_iterator *gsip,
   gimple *g;
   tree flag = build_int_cst (TREE_TYPE (lhs), encoded);
   if (has_model_arg)
-    g = gimple_build_call_internal (fn, 4, flag,
+    g = gimple_build_call_internal (fn, 5, flag,
 				    gimple_call_arg (call, 0),
 				    gimple_call_arg (call, 1),
-				    gimple_call_arg (call, 2));
+				    gimple_call_arg (call, 2),
+				    gimple_call_fn (call));
   else
-    g = gimple_build_call_internal (fn, 3, flag,
+    g = gimple_build_call_internal (fn, 4, flag,
 				    gimple_call_arg (call, 0),
-				    gimple_call_arg (call, 1));
+				    gimple_call_arg (call, 1),
+				    gimple_call_fn (call));
   gimple_call_set_lhs (g, new_lhs);
   gimple_set_location (g, gimple_location (call));
   gimple_move_vops (g, call);