[gcc(refs/users/aoliva/heads/testme)] -finline-stringops: check base blksize for memset [PR112778]

[Alexandre Oliva]

https://gcc.gnu.org/g:458bbb50ad43837010ef4da769973e3a05f04ef5

commit 458bbb50ad43837010ef4da769973e3a05f04ef5
Author: Alexandre Oliva <oliva@adacore.com>
Date:   Fri Dec 8 21:41:47 2023 -0300

    -finline-stringops: check base blksize for memset [PR112778]
    
    The recently-added logic for -finline-stringops=memset introduced an
    assumption that doesn't necessarily hold, namely, that
    can_store_by_pieces of a larger size implies can_store_by_pieces by
    smaller sizes.  Checks for all sizes the by-multiple-pieces machinery
    might use before committing to an expansion pattern.
    
    
    for  gcc/ChangeLog
    
            PR target/112778
            * builtins.cc (can_store_by_multiple_pieces): New.
            (try_store_by_multiple_pieces): Call it.
    
    for  gcc/testsuite/ChangeLog
    
            PR target/112778
            * gcc.dg/inline-mem-cmp-pr112778.c: New.

Diff:
---
 gcc/builtins.cc                                | 45 +++++++++++++++++++++-----
 gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c | 10 ++++++
 2 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/gcc/builtins.cc b/gcc/builtins.cc
index 38b0acff131..d5135ca162a 100644
--- a/gcc/builtins.cc
+++ b/gcc/builtins.cc
@@ -4284,6 +4284,34 @@ expand_builtin_memset (tree exp, rtx target, machine_mode mode)
   return expand_builtin_memset_args (dest, val, len, target, mode, exp);
 }
 
+/* Check that store_by_pieces allows BITS + LEN (so that we don't
+   expand something too unreasonably long), and every power of 2 in
+   BITS.  */
+static bool
+can_store_by_multiple_pieces (unsigned HOST_WIDE_INT bits,
+			      by_pieces_constfn constfun,
+			      void *constfundata, unsigned int align,
+			      bool memsetp,
+			      unsigned HOST_WIDE_INT len)
+{
+  if (!can_store_by_pieces (bits + len, constfun, constfundata, align, memsetp))
+    return false;
+
+  if (len && !can_store_by_pieces (len, constfun, constfundata, align, memsetp))
+    return false;
+
+  for (int i = ctz_hwi (bits); i >= 0;)
+    {
+      unsigned HOST_WIDE_INT bit = 1;
+      bit <<= i;
+      bits &= ~bit;
+      if (!can_store_by_pieces (bit, constfun, constfundata, align, memsetp))
+	return false;
+    }
+
+  return true;
+}
+
 /* Try to store VAL (or, if NULL_RTX, VALC) in LEN bytes starting at TO.
    Return TRUE if successful, FALSE otherwise.  TO is assumed to be
    aligned at an ALIGN-bits boundary.  LEN must be a multiple of
@@ -4367,8 +4395,9 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
      happen because of the way max_bits and blksize are related, but
      it doesn't hurt to test.  */
   if (blksize > xlenest
-      || !can_store_by_pieces (xlenest, builtin_memset_read_str,
-			       &valc, align, true))
+      || !can_store_by_multiple_pieces (xlenest - blksize,
+					builtin_memset_read_str,
+					&valc, align, true, blksize))
     {
       if (!(flag_inline_stringops & ILSOP_MEMSET))
 	return false;
@@ -4386,17 +4415,17 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
 	     of overflow.  */
 	  if (max_bits < orig_max_bits
 	      && xlenest + blksize >= xlenest
-	      && can_store_by_pieces (xlenest + blksize,
-				      builtin_memset_read_str,
-				      &valc, align, true))
+	      && can_store_by_multiple_pieces (xlenest,
+					       builtin_memset_read_str,
+					       &valc, align, true, blksize))
 	    {
 	      max_loop = true;
 	      break;
 	    }
 	  if (blksize
-	      && can_store_by_pieces (xlenest,
-				      builtin_memset_read_str,
-				      &valc, align, true))
+	      && can_store_by_multiple_pieces (xlenest,
+					       builtin_memset_read_str,
+					       &valc, align, true, 0))
 	    {
 	      max_len += blksize;
 	      min_len += blksize;
diff --git a/gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c b/gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c
new file mode 100644
index 00000000000..fdfc5b6f28c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/inline-mem-cmp-pr112778.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-finline-stringops" } */
+
+char buf[3];
+
+int
+f ()
+{
+  __builtin_memset (buf, 'v', 3);
+}