AVR: target/88236, target/115726 - Fix __memx code generation.

PR target/88236
	PR target/115726
gcc/
	* config/avr/avr.md (mov<mode>) [avr_mem_memx_p]: Expand in such a
	way that the destination does not overlap with any hard register
	clobbered / used by xload8qi_A resp. xload<mode>_A.
	* config/avr/avr.cc (avr_out_xload): Avoid early-clobber
	situation for Z by executing just one load when the output register
	overlaps with Z.
gcc/testsuite/
	* gcc.target/avr/torture/pr88236-pr115726.c: New test.

(cherry picked from commit 3d23abd3dd)

gcc/config/avr/avr.cc

@@ -4071,7 +4071,13 @@ avr_out_xload (rtx_insn *insn ATTRIBUTE_UNUSED, rtx *op, int *plen)
   xop[2] = lpm_addr_reg_rtx;
   xop[3] = AVR_HAVE_LPMX ? op[0] : lpm_reg_rtx;
 
-  avr_asm_len (AVR_HAVE_LPMX ? "lpm %3,%a2" : "lpm", xop, plen, -1);
+  if (plen)
+    *plen = 0;
+
+  if (reg_overlap_mentioned_p (xop[3], lpm_addr_reg_rtx))
+    avr_asm_len ("sbrs %1,7", xop, plen, 1);
+
+  avr_asm_len (AVR_HAVE_LPMX ? "lpm %3,%a2" : "lpm", xop, plen, 1);
 
   avr_asm_len ("sbrc %1,7" CR_TAB
                "ld %3,%a2", xop, plen, 2);

gcc/config/avr/avr.md

@@ -715,12 +715,26 @@
         if (!REG_P (addr))
           src = replace_equiv_address (src, copy_to_mode_reg (PSImode, addr));
 
+        rtx dest2 = reg_overlap_mentioned_p (dest, lpm_addr_reg_rtx)
+          ? gen_reg_rtx (<MODE>mode)
+          : dest;
+
         if (!avr_xload_libgcc_p (<MODE>mode))
           /* ; No <mode> here because gen_xload8<mode>_A only iterates over ALL1.
              ; insn-emit does not depend on the mode, it's all about operands.  */
-          emit_insn (gen_xload8qi_A (dest, src));
+          emit_insn (gen_xload8qi_A (dest2, src));
         else
-          emit_insn (gen_xload<mode>_A (dest, src));
+          {
+            rtx reg_22 = gen_rtx_REG (<MODE>mode, 22);
+            if (reg_overlap_mentioned_p (dest2, reg_22)
+                || reg_overlap_mentioned_p (dest2, all_regs_rtx[21]))
+              dest2 = gen_reg_rtx (<MODE>mode);
+
+            emit_insn (gen_xload<mode>_A (dest2, src));
+          }
+
+        if (dest2 != dest)
+          emit_move_insn (dest, dest2);
 
         DONE;
       }

gcc/testsuite/gcc.target/avr/torture/pr88236-pr115726.c

@@ -0,0 +1,115 @@
+/* { dg-do run { target { ! avr_tiny } } } */
+/* { dg-additional-options "-std=gnu99" } */
+
+const __flash char fvals8[] = { 1, 2, 3 };
+char rvals8[] = { 0, 2, 4 };
+
+const __flash int fvals16[] = { 1, 2, 3 };
+int rvals16[] = { 0, 2, 4 };
+
+__attribute__((noinline, noclone))
+char xload8_r30 (const __memx char *pc)
+{
+  register char c __asm ("r30");
+  c = *pc;
+  __asm (";;" : "+r" (c));
+  return c;
+}
+
+__attribute__((noinline, noclone))
+int xload16_r30 (const __memx int *pc)
+{
+  register int c __asm ("r30");
+  c = *pc;
+  __asm (";;" : "+r" (c));
+  return c;
+}
+
+__attribute__((noinline, noclone))
+char xload8_r22 (const __memx char *pc)
+{
+  register char c __asm ("r22");
+  c = *pc;
+  __asm (";;" : "+r" (c));
+  return c;
+}
+
+__attribute__((noinline, noclone))
+int xload16_r22 (const __memx int *pc)
+{
+  register int c __asm ("r22");
+  c = *pc;
+  __asm (";;" : "+r" (c));
+  return c;
+}
+
+__attribute__((noinline, noclone))
+int xload16_r20 (const __memx int *pc)
+{
+  register int c __asm ("r20");
+  c = *pc;
+  __asm (";;" : "+r" (c));
+  return c;
+}
+
+void test8 (void)
+{
+  char c;
+  for (int i = 0; i < 3; ++i)
+    {
+      c = xload8_r30 (fvals8 + i);
+      if (c != 1 + i)
+	__builtin_exit (__LINE__);
+
+      c = xload8_r22 (fvals8 + i);
+      if (c != 1 + i)
+	__builtin_exit (__LINE__);
+
+      c = xload8_r30 (rvals8 + i);
+      if (c != 2 * i)
+	__builtin_exit (__LINE__);
+
+      c = xload8_r22 (rvals8 + i);
+      if (c != 2 * i)
+	__builtin_exit (__LINE__);
+    }
+}
+
+void test16 (void)
+{
+  int c;
+  for (int i = 0; i < 3; ++i)
+    {
+      c = xload16_r30 (fvals16 + i);
+      if (c != 1 + i)
+	__builtin_exit (__LINE__);
+
+      c = xload16_r22 (fvals16 + i);
+      if (c != 1 + i)
+	__builtin_exit (__LINE__);
+
+      c = xload16_r20 (fvals16 + i);
+      if (c != 1 + i)
+	__builtin_exit (__LINE__);
+
+      c = xload16_r30 (rvals16 + i);
+      if (c != 2 * i)
+	__builtin_exit (__LINE__);
+
+      c = xload16_r22 (rvals16 + i);
+      if (c != 2 * i)
+	__builtin_exit (__LINE__);
+
+      c = xload16_r20 (rvals16 + i);
+      if (c != 2 * i)
+	__builtin_exit (__LINE__);
+    }
+}
+
+int main (void)
+{
+  test8();
+  test16();
+
+  return 0;
+}