PR 106101: IBM zSystems: Fix strict_low_part problem

This avoids generating illegal (strict_low_part (reg ...)) RTXs. This
required two changes:

1. Do not use gen_lowpart to generate the inner expression of a
STRICT_LOW_PART.  gen_lowpart might fold the SUBREG either because
there is already a paradoxical subreg or because it can directly be
applied to the register. A new wrapper function makes sure that we
always end up having an actual SUBREG.

2. Change the movstrict patterns to enforce a SUBREG as inner operand
of the STRICT_LOW_PARTs.  The new predicate introduced for the
destination operand requires a SUBREG expression with a
register_operand as inner operand.  However, since reload strips away
the majority of the SUBREGs we have to accept single registers as well
once we reach reload.

Bootstrapped and regression tested on IBM zSystems 64 bit.

gcc/ChangeLog:

	PR target/106101
	* config/s390/predicates.md (subreg_register_operand): New
	predicate.
	* config/s390/s390-protos.h (s390_gen_lowpart_subreg): New
	function prototype.
	* config/s390/s390.cc (s390_gen_lowpart_subreg): New function.
	(s390_expand_insv): Use s390_gen_lowpart_subreg instead of
	gen_lowpart.
	* config/s390/s390.md ("*get_tp_64", "*zero_extendhisi2_31")
	("*zero_extendqisi2_31", "*zero_extendqihi2_31"): Likewise.
	("movstrictqi", "movstricthi", "movstrictsi"): Use the
	subreg_register_operand predicate instead of register_operand.

gcc/testsuite/ChangeLog:

	PR target/106101
	* gcc.c-torture/compile/pr106101.c: New test.

4 files changed, 54 insertions, 22 deletions

diff --git a/gcc/config/s390/predicates.md b/gcc/config/s390/predicates.md
index 33194d3..430cf6e 100644
--- a/gcc/config/s390/predicates.md
+++ b/gcc/config/s390/predicates.md
@@ -594,3 +594,15 @@
 (define_predicate "addv_const_operand"
   (and (match_code "const_int")
        (match_test "INTVAL (op) >= -32768 && INTVAL (op) <= 32767")))
+
+; Match (subreg (reg ...)) operands.
+; Used for movstrict destination operands
+; When replacing pseudos with hard regs reload strips away the
+; subregs. Accept also plain registers then to prevent the insn from
+; becoming unrecognizable.
+(define_predicate "subreg_register_operand"
+  (ior (and (match_code "subreg")
+	    (match_test "register_operand (SUBREG_REG (op), GET_MODE (SUBREG_REG (op)))"))
+       (and (match_code "reg")
+	    (match_test "reload_completed || reload_in_progress")
+	    (match_test "register_operand (op, GET_MODE (op))"))))
diff --git a/gcc/config/s390/s390-protos.h b/gcc/config/s390/s390-protos.h
index fd4acaa..765d843a 100644
--- a/gcc/config/s390/s390-protos.h
+++ b/gcc/config/s390/s390-protos.h
@@ -50,6 +50,7 @@ extern void s390_set_has_landing_pad_p (bool);
 extern bool s390_hard_regno_rename_ok (unsigned int, unsigned int);
 extern int s390_class_max_nregs (enum reg_class, machine_mode);
 extern bool s390_return_addr_from_memory(void);
+extern rtx s390_gen_lowpart_subreg (machine_mode, rtx);
 extern bool s390_fma_allowed_p (machine_mode);
 #if S390_USE_TARGET_ATTRIBUTE
 extern tree s390_valid_target_attribute_tree (tree args,
diff --git a/gcc/config/s390/s390.cc b/gcc/config/s390/s390.cc
index 5aaf76a..5e06bf9 100644
--- a/gcc/config/s390/s390.cc
+++ b/gcc/config/s390/s390.cc
@@ -458,6 +458,31 @@ s390_return_addr_from_memory ()
   return cfun_gpr_save_slot(RETURN_REGNUM) == SAVE_SLOT_STACK;
 }
 
+/* Generate a SUBREG for the MODE lowpart of EXPR.
+
+   In contrast to gen_lowpart it will always return a SUBREG
+   expression.  This is useful to generate STRICT_LOW_PART
+   expressions.  */
+rtx
+s390_gen_lowpart_subreg (machine_mode mode, rtx expr)
+{
+  rtx lowpart = gen_lowpart (mode, expr);
+
+  /* There might be no SUBREG in case it could be applied to the hard
+     REG rtx or it could be folded with a paradoxical subreg.  Bring
+     it back.  */
+  if (!SUBREG_P (lowpart))
+    {
+      machine_mode reg_mode = TARGET_ZARCH ? DImode : SImode;
+      gcc_assert (REG_P (lowpart));
+      lowpart = gen_lowpart_SUBREG (mode,
+				    gen_rtx_REG (reg_mode,
+						 REGNO (lowpart)));
+    }
+
+  return lowpart;
+}
+
 /* Return nonzero if it's OK to use fused multiply-add for MODE.  */
 bool
 s390_fma_allowed_p (machine_mode mode)
@@ -6520,7 +6545,7 @@ s390_expand_insv (rtx dest, rtx op1, rtx op2, rtx src)
       /* Emit a strict_low_part pattern if possible.  */
       if (smode_bsize == bitsize && bitpos == mode_bsize - smode_bsize)
 	{
-	  rtx low_dest = gen_lowpart (smode, dest);
+	  rtx low_dest = s390_gen_lowpart_subreg (smode, dest);
 	  rtx low_src = gen_lowpart (smode, src);
 
 	  switch (smode)
diff --git a/gcc/config/s390/s390.md b/gcc/config/s390/s390.md
index 55c0064..aaa247d 100644
--- a/gcc/config/s390/s390.md
+++ b/gcc/config/s390/s390.md
@@ -1971,11 +1971,12 @@
   "TARGET_ZARCH"
   "#"
   "&& reload_completed"
-  [(set (match_dup 2) (match_dup 3))
+  [(set (match_dup 2) (match_dup 4))
    (set (match_dup 0) (ashift:DI (match_dup 0) (const_int 32)))
-   (set (strict_low_part (match_dup 2)) (match_dup 4))]
+   (set (strict_low_part (match_dup 3)) (match_dup 5))]
   "operands[2] = gen_lowpart (SImode, operands[0]);
-   s390_split_access_reg (operands[1], &operands[4], &operands[3]);")
+   operands[3] = s390_gen_lowpart_subreg (SImode, operands[0]);
+   s390_split_access_reg (operands[1], &operands[5], &operands[4]);")
 
 ; Splitters for storing TLS pointer to %a0:DI.
 
@@ -2522,13 +2523,14 @@
   [(set (match_dup 0) (match_dup 2))]
   "operands[2] = get_pool_constant (operands[1]);")
 
+
 ;
-; movstrictqi instruction pattern(s).
+; movstrict instruction pattern(s).
 ;
 
 (define_insn "movstrictqi"
-  [(set (strict_low_part (match_operand:QI 0 "register_operand" "+d,d"))
-                         (match_operand:QI 1 "memory_operand" "R,T"))]
+  [(set (strict_low_part (match_operand:QI 0 "subreg_register_operand" "+d,d"))
+                         (match_operand:QI 1 "memory_operand"           "R,T"))]
   ""
   "@
    ic\t%0,%1
@@ -2537,13 +2539,9 @@
    (set_attr "cpu_facility" "*,longdisp")
    (set_attr "z10prop" "z10_super_E1,z10_super_E1")])
 
-;
-; movstricthi instruction pattern(s).
-;
-
 (define_insn "movstricthi"
-  [(set (strict_low_part (match_operand:HI 0 "register_operand" "+d,d"))
-                         (match_operand:HI 1 "memory_operand" "Q,S"))
+  [(set (strict_low_part (match_operand:HI 0 "subreg_register_operand" "+d,d"))
+                         (match_operand:HI 1 "memory_operand"           "Q,S"))
    (clobber (reg:CC CC_REGNUM))]
   ""
   "@
@@ -2553,13 +2551,9 @@
    (set_attr "cpu_facility" "*,longdisp")
    (set_attr "z10prop" "z10_super_E1,z10_super_E1")])
 
-;
-; movstrictsi instruction pattern(s).
-;
-
 (define_insn "movstrictsi"
-  [(set (strict_low_part (match_operand:SI 0 "register_operand" "+d,d,d,d"))
-                         (match_operand:SI 1 "general_operand" "d,R,T,t"))]
+  [(set (strict_low_part (match_operand:SI 0 "subreg_register_operand" "+d,d,d,d"))
+                         (match_operand:SI 1 "general_operand"          "d,R,T,t"))]
   "TARGET_ZARCH"
   "@
    lr\t%0,%1
@@ -5019,7 +5013,7 @@
    (parallel
     [(set (strict_low_part (match_dup 2)) (match_dup 1))
      (clobber (reg:CC CC_REGNUM))])]
-  "operands[2] = gen_lowpart (HImode, operands[0]);")
+  "operands[2] = s390_gen_lowpart_subreg (HImode, operands[0]);")
 
 (define_insn_and_split "*zero_extendqisi2_31"
   [(set (match_operand:SI 0 "register_operand" "=&d")
@@ -5029,7 +5023,7 @@
   "&& reload_completed"
   [(set (match_dup 0) (const_int 0))
    (set (strict_low_part (match_dup 2)) (match_dup 1))]
-  "operands[2] = gen_lowpart (QImode, operands[0]);")
+  "operands[2] = s390_gen_lowpart_subreg (QImode, operands[0]);")
 
 ;
 ; zero_extendqihi2 instruction pattern(s).
@@ -5061,7 +5055,7 @@
   "&& reload_completed"
   [(set (match_dup 0) (const_int 0))
    (set (strict_low_part (match_dup 2)) (match_dup 1))]
-  "operands[2] = gen_lowpart (QImode, operands[0]);")
+  "operands[2] = s390_gen_lowpart_subreg (QImode, operands[0]);")
 
 ;
 ; fixuns_trunc(dd|td|sf|df|tf)(si|di)2 expander