[PATCH, i386]: Fix PR 66648, incorrect memcpy expansion with unrolled_loop strategy at -O2

[Uros Bizjak]

We have to emit check for main loop execution UNLESS we guarantee that
min_size is at least equal to size_needed. In this testcase, VRP
declared minimum copying size, and after unaligned prologue
adjustment, min_size was still non-zero. The !min_size check didn't
account for the case that min_size can be non-zero, but still less
than size_needed.

2015-07-25  Uros Bizjak  <ubiz...@gmail.com>

    PR target/66648
    * config/i386/i386.c (ix86_expand_set_or_movmem): Emit main loop
    execution guard when min_size is less than size_needed.

testsuite/ChangeLog:

2015-07-25  Uros Bizjak  <ubiz...@gmail.com>

    PR target/66648
    * gcc.target/i386/pr66648.c: New test.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Committed to mainline, will be backported to release branches.

Uros.

Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c  (revision 224993)
+++ config/i386/i386.c  (working copy)
@@ -25008,7 +25008,8 @@ ix86_expand_set_or_movmem (rtx dst, rtx src, rtx c
       dst = change_address (dst, BLKmode, destreg);
       set_mem_align (dst, desired_align * BITS_PER_UNIT);
       epilogue_size_needed = 0;
-      if (need_zero_guard && !min_size)
+      if (need_zero_guard
+         && min_size < (unsigned HOST_WIDE_INT) size_needed)
        {
          /* It is possible that we copied enough so the main loop will not
             execute.  */
@@ -25140,7 +25141,7 @@ ix86_expand_set_or_movmem (rtx dst, rtx src, rtx c
          max_size -= align_bytes;
        }
       if (need_zero_guard
-         && !min_size
+         && min_size < (unsigned HOST_WIDE_INT) size_needed
          && (count < (unsigned HOST_WIDE_INT) size_needed
              || (align_bytes == 0
                  && count < ((unsigned HOST_WIDE_INT) size_needed
Index: testsuite/gcc.target/pr66648.c
===================================================================
--- testsuite/gcc.target/pr66648.c      (revision 0)
+++ testsuite/gcc.target/pr66648.c      (working copy)
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mstringop-strategy=unrolled_loop -mtune=nocona" } */
+
+#define PATTERN 0xdeadbeef
+#define SIZE    32
+
+struct S { int i; char str[SIZE]; int j; };
+
+void __attribute__((noclone, noinline))
+my_memcpy (char *, const char *, unsigned int);
+
+void
+my_memcpy (char *dst, const char *src, unsigned int len)
+{
+  if (len < 8)
+    __builtin_abort ();
+
+  __builtin_memcpy (dst, src, len);
+}
+
+int
+main (void)
+{
+  const char str[SIZE]= "1234567890123456789012345678901";
+  struct S *s = __builtin_malloc (sizeof (struct S));
+
+  s->j = PATTERN;
+  my_memcpy (s->str, str, SIZE);
+  if (s->j != PATTERN)
+    __builtin_abort ();
+
+  return 0;
+}