PR target/58901: reload: Handle SUBREG of MEM with a mode-dependent address

Fix an ICE with the handling of RTL expressions like:

(subreg:QI (mem/c:SI (plus:SI (plus:SI (mult:SI (reg/v:SI 0 %r0 [orig:67 i ] [67])
                    (const_int 4 [0x4]))
                (reg/v/f:SI 7 %r7 [orig:59 doacross ] [59]))
            (const_int 40 [0x28])) [1 MEM[(unsigned int *)doacross_63 + 40B + i_106 * 4]+0 S4 A32]) 0)

that causes the compilation of libgomp to fail:

during RTL pass: reload
.../libgomp/ordered.c: In function 'GOMP_doacross_wait':
.../libgomp/ordered.c:507:1: internal compiler error: in change_address_1, at emit-rtl.c:2275
  507 | }
      | ^
0x10a3462b change_address_1
	.../gcc/emit-rtl.c:2275
0x10a353a7 adjust_address_1(rtx_def*, machine_mode, poly_int<1u, long>, int, int, int, poly_int<1u, long>)
	.../gcc/emit-rtl.c:2409
0x10ae2993 alter_subreg(rtx_def**, bool)
	.../gcc/final.c:3368
0x10ae25cf cleanup_subreg_operands(rtx_insn*)
	.../gcc/final.c:3322
0x110922a3 reload(rtx_insn*, int)
	.../gcc/reload1.c:1232
0x10de2bf7 do_reload
	.../gcc/ira.c:5812
0x10de3377 execute
	.../gcc/ira.c:5986

in a `vax-netbsdelf' build, where an attempt is made to change the mode
of the contained memory reference to the mode of the containing SUBREG.
Such RTL expressions are produced by the VAX shift and rotate patterns
(`ashift', `ashiftrt', `rotate', `rotatert') where the count operand
always has the QI mode regardless of the mode, either SI or DI, of the
datum shifted or rotated.

Such a mode change cannot work where the memory reference uses the
indexed addressing mode, where a multiplier is implied that in the VAX
ISA depends on the width of the memory access requested and therefore
changing the machine mode would change the address calculation as well.

Avoid the attempt then by forcing the reload of any SUBREGs containing
a mode-dependent memory reference, also fixing these regressions:

FAIL: gcc.c-torture/compile/pr46883.c   -Os  (internal compiler error)
FAIL: gcc.c-torture/compile/pr46883.c   -Os  (test for excess errors)
FAIL: gcc.c-torture/execute/20120808-1.c   -O2  (internal compiler error)
FAIL: gcc.c-torture/execute/20120808-1.c   -O2  (test for excess errors)
FAIL: gcc.c-torture/execute/20120808-1.c   -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions  (internal compiler error)
FAIL: gcc.c-torture/execute/20120808-1.c   -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions  (test for excess errors)
FAIL: gcc.c-torture/execute/20120808-1.c   -O3 -g  (internal compiler error)
FAIL: gcc.c-torture/execute/20120808-1.c   -O3 -g  (test for excess errors)
FAIL: gcc.c-torture/execute/20120808-1.c   -O2 -flto -fno-use-linker-plugin -flto-partition=none  (internal compiler error)
FAIL: gcc.c-torture/execute/20120808-1.c   -O2 -flto -fno-use-linker-plugin -flto-partition=none  (test for excess errors)
FAIL: gcc.c-torture/execute/20120808-1.c   -O2 -flto -fuse-linker-plugin -fno-fat-lto-objects  (internal compiler error)
FAIL: gcc.c-torture/execute/20120808-1.c   -O2 -flto -fuse-linker-plugin -fno-fat-lto-objects  (test for excess errors)
FAIL: gcc.dg/20050629-1.c (internal compiler error)
FAIL: gcc.dg/20050629-1.c (test for excess errors)
FAIL: c-c++-common/torture/pr53505.c   -Os  (internal compiler error)
FAIL: c-c++-common/torture/pr53505.c   -Os  (test for excess errors)
FAIL: gfortran.dg/coarray_failed_images_1.f08   -Os  (internal compiler error)
FAIL: gfortran.dg/coarray_stopped_images_1.f08   -Os  (internal compiler error)

With test case #0 included it causes a reload with:

(insn 15 14 16 4 (set (reg:SI 31)
        (ashift:SI (const_int 1 [0x1])
            (subreg:QI (reg:SI 30 [ MEM[(int *)s_8(D) + 4B + _5 * 4] ]) 0))) "pr58901-0.c":15:12 94 {ashlsi3}
     (expr_list:REG_DEAD (reg:SI 30 [ MEM[(int *)s_8(D) + 4B + _5 * 4] ])
        (nil)))

as follows:

Reloads for insn # 15
Reload 0: reload_in (SI) = (reg:SI 30 [ MEM[(int *)s_8(D) + 4B + _5 * 4] ])
	ALL_REGS, RELOAD_FOR_INPUT (opnum = 2)
	reload_in_reg: (reg:SI 30 [ MEM[(int *)s_8(D) + 4B + _5 * 4] ])
	reload_reg_rtx: (reg:SI 5 %r5)

resulting in:

(insn 37 14 15 4 (set (reg:SI 5 %r5)
        (mem/c:SI (plus:SI (plus:SI (mult:SI (reg/v:SI 1 %r1 [orig:25 i ] [25])
                        (const_int 4 [0x4]))
                    (reg/v/f:SI 4 %r4 [orig:29 s ] [29]))
                (const_int 4 [0x4])) [1 MEM[(int *)s_8(D) + 4B + _5 * 4]+0 S4 A32])) "pr58901-0.c":15:12 12 {movsi_2}
     (nil))
(insn 15 37 16 4 (set (reg:SI 2 %r2 [31])
        (ashift:SI (const_int 1 [0x1])
            (reg:QI 5 %r5))) "pr58901-0.c":15:12 94 {ashlsi3}
     (nil))

and assembly like:

.L3:
	movl 4(%r4)[%r1],%r5
	ashl %r5,$1,%r2
	xorl2 %r2,%r0
	incl %r1
	cmpl %r1,%r3
	jneq .L3

produced for the loop, providing optimization has been enabled.

Likewise with test case #1 the reload of:

(insn 17 16 18 4 (set (reg:SI 34)
        (and:SI (subreg:SI (reg/v:DI 27 [ t ]) 4)
            (const_int 1 [0x1]))) "pr58901-1.c":18:20 77 {*andsi_const_int}
     (expr_list:REG_DEAD (reg/v:DI 27 [ t ])
        (nil)))

is as follows:

Reloads for insn # 17
Reload 0: reload_in (DI) = (reg/v:DI 27 [ t ])
	reload_out (SI) = (reg:SI 2 %r2 [34])
	ALL_REGS, RELOAD_OTHER (opnum = 0)
	reload_in_reg: (reg/v:DI 27 [ t ])
	reload_out_reg: (reg:SI 2 %r2 [34])
	reload_reg_rtx: (reg:DI 4 %r4)

resulting in:

(insn 40 16 17 4 (set (reg:DI 4 %r4)
        (mem/c:DI (plus:SI (mult:SI (reg/v:SI 1 %r1 [orig:26 i ] [26])
                    (const_int 8 [0x8]))
                (reg/v/f:SI 3 %r3 [orig:30 s ] [30])) [1 MEM[(const struct s *)s_13(D) + _7 * 8]+0 S8 A32])) "pr58901-1.c":18:20 11 {movdi}
     (nil))
(insn 17 40 41 4 (set (reg:SI 4 %r4)
        (and:SI (reg:SI 5 %r5 [+4 ])
            (const_int 1 [0x1]))) "pr58901-1.c":18:20 77 {*andsi_const_int}
     (nil))

and assembly like:

.L3:
	movq (%r3)[%r1],%r4
	bicl3 $-2,%r5,%r4
	addl2 %r4,%r0
	jaoblss %r0,%r1,.L3

First posted at: <https://gcc.gnu.org/ml/gcc/2014-06/msg00060.html>.

2020-12-05  Matt Thomas  <[email protected]>
	    Maciej W. Rozycki  <[email protected]>

	gcc/
	PR target/58901
	* reload.c (push_reload): Also reload the inner expression of a
	SUBREG for pseudos associated with a mode-dependent memory
	reference.
	(find_reloads): Force a reload likewise.

2020-12-05  Maciej W. Rozycki  <[email protected]>

	gcc/testsuite/
	PR target/58901
	* gcc.c-torture/compile/pr58901-0.c: New test.
	* gcc.c-torture/compile/pr58901-1.c: New test.

Author: Matt Thomas

gcc/reload.c

@@ -1043,53 +1043,72 @@ push_reload (rtx in, rtx out, rtx *inloc, rtx *outloc,
      Also reload the inner expression if it does not require a secondary
      reload but the SUBREG does.
 
-     Finally, reload the inner expression if it is a register that is in
+     Also reload the inner expression if it is a register that is in
      the class whose registers cannot be referenced in a different size
      and M1 is not the same size as M2.  If subreg_lowpart_p is false, we
      cannot reload just the inside since we might end up with the wrong
      register class.  But if it is inside a STRICT_LOW_PART, we have
-     no choice, so we hope we do get the right register class there.  */
+     no choice, so we hope we do get the right register class there.
+
+     Finally, reload the inner expression if it is a pseudo that will
+     become a MEM and the MEM has a mode-dependent address, as in that
+     case we obviously cannot change the mode of the MEM to that of the
+     containing SUBREG as that would change the interpretation of the
+     address.  */
 
   scalar_int_mode inner_mode;
   if (in != 0 && GET_CODE (in) == SUBREG
-      && (subreg_lowpart_p (in) || strict_low)
       && targetm.can_change_mode_class (GET_MODE (SUBREG_REG (in)),
 					inmode, rclass)
       && contains_allocatable_reg_of_mode[rclass][GET_MODE (SUBREG_REG (in))]
-      && (CONSTANT_P (SUBREG_REG (in))
-	  || GET_CODE (SUBREG_REG (in)) == PLUS
-	  || strict_low
-	  || (((REG_P (SUBREG_REG (in))
-		&& REGNO (SUBREG_REG (in)) >= FIRST_PSEUDO_REGISTER)
-	       || MEM_P (SUBREG_REG (in)))
-	      && (paradoxical_subreg_p (inmode, GET_MODE (SUBREG_REG (in)))
-		  || (known_le (GET_MODE_SIZE (inmode), UNITS_PER_WORD)
-		      && is_a <scalar_int_mode> (GET_MODE (SUBREG_REG (in)),
-						 &inner_mode)
-		      && GET_MODE_SIZE (inner_mode) <= UNITS_PER_WORD
-		      && paradoxical_subreg_p (inmode, inner_mode)
-		      && LOAD_EXTEND_OP (inner_mode) != UNKNOWN)
-		  || (WORD_REGISTER_OPERATIONS
-		      && partial_subreg_p (inmode, GET_MODE (SUBREG_REG (in)))
-		      && (known_equal_after_align_down
-			  (GET_MODE_SIZE (inmode) - 1,
-			   GET_MODE_SIZE (GET_MODE (SUBREG_REG (in))) - 1,
-			   UNITS_PER_WORD)))))
-	  || (REG_P (SUBREG_REG (in))
-	      && REGNO (SUBREG_REG (in)) < FIRST_PSEUDO_REGISTER
-	      /* The case where out is nonzero
-		 is handled differently in the following statement.  */
-	      && (out == 0 || subreg_lowpart_p (in))
-	      && (complex_word_subreg_p (inmode, SUBREG_REG (in))
-		  || !targetm.hard_regno_mode_ok (subreg_regno (in), inmode)))
-	  || (secondary_reload_class (1, rclass, inmode, in) != NO_REGS
-	      && (secondary_reload_class (1, rclass, GET_MODE (SUBREG_REG (in)),
-					  SUBREG_REG (in))
-		  == NO_REGS))
+      && (strict_low
+	  || (subreg_lowpart_p (in)
+	      && (CONSTANT_P (SUBREG_REG (in))
+		  || GET_CODE (SUBREG_REG (in)) == PLUS
+		  || (((REG_P (SUBREG_REG (in))
+			&& REGNO (SUBREG_REG (in)) >= FIRST_PSEUDO_REGISTER)
+		       || MEM_P (SUBREG_REG (in)))
+		      && (paradoxical_subreg_p (inmode,
+						GET_MODE (SUBREG_REG (in)))
+			  || (known_le (GET_MODE_SIZE (inmode), UNITS_PER_WORD)
+			      && is_a <scalar_int_mode> (GET_MODE (SUBREG_REG
+								   (in)),
+							 &inner_mode)
+			      && GET_MODE_SIZE (inner_mode) <= UNITS_PER_WORD
+			      && paradoxical_subreg_p (inmode, inner_mode)
+			      && LOAD_EXTEND_OP (inner_mode) != UNKNOWN)
+			  || (WORD_REGISTER_OPERATIONS
+			      && partial_subreg_p (inmode,
+						   GET_MODE (SUBREG_REG (in)))
+			      && (known_equal_after_align_down
+				  (GET_MODE_SIZE (inmode) - 1,
+				   GET_MODE_SIZE (GET_MODE (SUBREG_REG
+							    (in))) - 1,
+				   UNITS_PER_WORD)))))
+		  || (REG_P (SUBREG_REG (in))
+		      && REGNO (SUBREG_REG (in)) < FIRST_PSEUDO_REGISTER
+		      /* The case where out is nonzero
+			 is handled differently in the following statement.  */
+		      && (out == 0 || subreg_lowpart_p (in))
+		      && (complex_word_subreg_p (inmode, SUBREG_REG (in))
+			  || !targetm.hard_regno_mode_ok (subreg_regno (in),
+							  inmode)))
+		  || (secondary_reload_class (1, rclass, inmode, in) != NO_REGS
+		      && (secondary_reload_class (1, rclass,
+						  GET_MODE (SUBREG_REG (in)),
+						  SUBREG_REG (in))
+			  == NO_REGS))
+		  || (REG_P (SUBREG_REG (in))
+		      && REGNO (SUBREG_REG (in)) < FIRST_PSEUDO_REGISTER
+		      && !REG_CAN_CHANGE_MODE_P (REGNO (SUBREG_REG (in)),
+						 GET_MODE (SUBREG_REG (in)),
+						 inmode))))
 	  || (REG_P (SUBREG_REG (in))
-	      && REGNO (SUBREG_REG (in)) < FIRST_PSEUDO_REGISTER
-	      && !REG_CAN_CHANGE_MODE_P (REGNO (SUBREG_REG (in)),
-					 GET_MODE (SUBREG_REG (in)), inmode))))
+	      && REGNO (SUBREG_REG (in)) >= FIRST_PSEUDO_REGISTER
+	      && reg_equiv_mem (REGNO (SUBREG_REG (in)))
+	      && (mode_dependent_address_p
+		  (XEXP (reg_equiv_mem (REGNO (SUBREG_REG (in))), 0),
+		   MEM_ADDR_SPACE (reg_equiv_mem (REGNO (SUBREG_REG (in)))))))))
     {
 #ifdef LIMIT_RELOAD_CLASS
       in_subreg_loc = inloc;
@@ -3157,6 +3176,19 @@ find_reloads (rtx_insn *insn, int replace, int ind_levels, int live_known,
 				  && paradoxical_subreg_p (operand_mode[i],
 							   inner_mode)
 				  && LOAD_EXTEND_OP (inner_mode) != UNKNOWN)))
+		      /* We must force a reload of a SUBREG's inner expression
+			 if it is a pseudo that will become a MEM and the MEM
+			 has a mode-dependent address, as in that case we
+			 obviously cannot change the mode of the MEM to that
+			 of the containing SUBREG as that would change the
+			 interpretation of the address.  */
+		      || (REG_P (operand)
+			  && REGNO (operand) >= FIRST_PSEUDO_REGISTER
+			  && reg_equiv_mem (REGNO (operand))
+			  && (mode_dependent_address_p
+			      (XEXP (reg_equiv_mem (REGNO (operand)), 0),
+			       (MEM_ADDR_SPACE
+				(reg_equiv_mem (REGNO (operand)))))))
 		      )
 		    force_reload = 1;
 		}

gcc/testsuite/gcc.c-torture/compile/pr58901-0.c

@@ -0,0 +1,17 @@
+typedef int __attribute__ ((mode (SI))) int_t;
+
+struct s
+{
+  int_t n;
+  int_t c[];
+};
+
+int_t
+ashlsi (int_t x, const struct s *s)
+{
+  int_t i;
+
+  for (i = 0; i < s->n; i++)
+    x ^= 1 << s->c[i];
+  return x;
+}

gcc/testsuite/gcc.c-torture/compile/pr58901-1.c

@@ -0,0 +1,21 @@
+typedef signed int __attribute__ ((mode (SI))) int_t;
+
+struct s
+{
+  int_t n;
+  int_t m : 1;
+  int_t l : 31;
+};
+
+int_t
+movdi (int_t x, const struct s *s)
+{
+  int_t i;
+
+  for (i = 0; i < x; i++)
+    {
+      const struct s t = s[i];
+      x += t.m ? 1 : 0;
+    }
+  return x;
+}