re PR tree-optimization/65215 (Bswap load miscompilation)

	PR tree-optimization/65215
	* tree-ssa-math-opts.c (find_bswap_or_nop_load): Return false
	for PDP endian targets.
	(perform_symbolic_merge, find_bswap_or_nop_1, find_bswap_or_nop):
	Fix up formatting issues.
	(bswap_replace): Likewise.  For BYTES_BIG_ENDIAN, if the final access
	size is smaller than the original, adjust MEM_REF offset by the
	difference of sizes.  Use is_gimple_mem_ref_addr instead of
	is_gimple_min_invariant test to avoid adding address temporaries.

	* gcc.c-torture/execute/pr65215-1.c: New test.
	* gcc.c-torture/execute/pr65215-2.c: New test.
	* gcc.c-torture/execute/pr65215-3.c: New test.
	* gcc.c-torture/execute/pr65215-4.c: New test.
	* gcc.c-torture/execute/pr65215-5.c: New test.

From-SVN: r221033

8 files changed, 197 insertions, 17 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index f303d0a..1bbd014 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,15 @@
+2015-02-26  Jakub Jelinek  <jakub@redhat.com>
+
+	PR tree-optimization/65215
+	* tree-ssa-math-opts.c (find_bswap_or_nop_load): Return false
+	for PDP endian targets.
+	(perform_symbolic_merge, find_bswap_or_nop_1, find_bswap_or_nop):
+	Fix up formatting issues.
+	(bswap_replace): Likewise.  For BYTES_BIG_ENDIAN, if the final access
+	size is smaller than the original, adjust MEM_REF offset by the
+	difference of sizes.  Use is_gimple_mem_ref_addr instead of
+	is_gimple_min_invariant test to avoid adding address temporaries.
+
 2015-02-26  Martin Liska  <mliska@suse.cz>
 	    Jan Hubicka  <hubicka@ucw.cz>
 
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 03135ee..1852d25 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2015-02-26  Jakub Jelinek  <jakub@redhat.com>
+
+	PR tree-optimization/65215
+	* gcc.c-torture/execute/pr65215-1.c: New test.
+	* gcc.c-torture/execute/pr65215-2.c: New test.
+	* gcc.c-torture/execute/pr65215-3.c: New test.
+	* gcc.c-torture/execute/pr65215-4.c: New test.
+	* gcc.c-torture/execute/pr65215-5.c: New test.
+
 2015-02-26  Tom de Vries  <tom@codesourcery.com>
 
 	* go.test/go-test.exp (go-gc-tests): Add missing cleanup for cmpout.
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr65215-1.c b/gcc/testsuite/gcc.c-torture/execute/pr65215-1.c
new file mode 100644
index 0000000..07b89fc
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr65215-1.c
@@ -0,0 +1,24 @@
+/* PR tree-optimization/65215 */
+
+static inline unsigned int
+foo (unsigned int x)
+{
+  return (x >> 24) | ((x >> 8) & 0xff00) | ((x << 8) & 0xff0000) | (x << 24);
+}
+
+__attribute__((noinline, noclone)) unsigned int
+bar (unsigned long long *x)
+{
+  return foo (*x);
+}
+
+int
+main ()
+{
+  if (__CHAR_BIT__ != 8 || sizeof (unsigned int) != 4 || sizeof (unsigned long long) != 8)
+    return 0;
+  unsigned long long l = foo (0xdeadbeefU) | 0xfeedbea800000000ULL;
+  if (bar (&l) != 0xdeadbeefU)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr65215-2.c b/gcc/testsuite/gcc.c-torture/execute/pr65215-2.c
new file mode 100644
index 0000000..a284205
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr65215-2.c
@@ -0,0 +1,24 @@
+/* PR tree-optimization/65215 */
+
+static inline unsigned int
+foo (unsigned int x)
+{
+  return (x >> 24) | ((x >> 8) & 0xff00) | ((x << 8) & 0xff0000) | (x << 24);
+}
+
+__attribute__((noinline, noclone)) unsigned long long
+bar (unsigned long long *x)
+{
+  return ((unsigned long long) foo (*x) << 32) | foo (*x >> 32);
+}
+
+int
+main ()
+{
+  if (__CHAR_BIT__ != 8 || sizeof (unsigned int) != 4 || sizeof (unsigned long long) != 8)
+    return 0;
+  unsigned long long l = foo (0xfeedbea8U) | ((unsigned long long) foo (0xdeadbeefU) << 32);
+  if (bar (&l) != 0xfeedbea8deadbeefULL)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr65215-3.c b/gcc/testsuite/gcc.c-torture/execute/pr65215-3.c
new file mode 100644
index 0000000..0874e19
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr65215-3.c
@@ -0,0 +1,31 @@
+/* PR tree-optimization/65215 */
+
+struct S { unsigned long long l1 : 24, l2 : 8, l3 : 32; };
+
+static inline unsigned int
+foo (unsigned int x)
+{
+  return (x >> 24) | ((x >> 8) & 0xff00) | ((x << 8) & 0xff0000) | (x << 24);
+}
+
+__attribute__((noinline, noclone)) unsigned long long
+bar (struct S *x)
+{
+  unsigned long long x1 = foo (((unsigned int) x->l1 << 8) | x->l2);
+  unsigned long long x2 = foo (x->l3);
+  return (x2 << 32) | x1;
+}
+
+int
+main ()
+{
+  if (__CHAR_BIT__ != 8 || sizeof (unsigned int) != 4 || sizeof (unsigned long long) != 8)
+    return 0;
+  struct S s = { 0xdeadbeU, 0xefU, 0xfeedbea8U };
+  unsigned long long l = bar (&s);
+  if (foo (l >> 32) != s.l3
+      || (foo (l) >> 8) != s.l1
+      || (foo (l) & 0xff) != s.l2)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr65215-4.c b/gcc/testsuite/gcc.c-torture/execute/pr65215-4.c
new file mode 100644
index 0000000..8044d12
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr65215-4.c
@@ -0,0 +1,27 @@
+/* PR tree-optimization/65215 */
+
+struct S { unsigned long long l1 : 48; };
+
+static inline unsigned int
+foo (unsigned int x)
+{
+  return (x >> 24) | ((x >> 8) & 0xff00) | ((x << 8) & 0xff0000) | (x << 24);
+}
+
+__attribute__((noinline, noclone)) unsigned int
+bar (struct S *x)
+{
+  return foo (x->l1);
+}
+
+int
+main ()
+{
+  if (__CHAR_BIT__ != 8 || sizeof (unsigned int) != 4 || sizeof (unsigned long long) != 8)
+    return 0;
+  struct S s;
+  s.l1 = foo (0xdeadbeefU) | (0xfeedULL << 32);
+  if (bar (&s) != 0xdeadbeefU)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr65215-5.c b/gcc/testsuite/gcc.c-torture/execute/pr65215-5.c
new file mode 100644
index 0000000..c30d11f
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr65215-5.c
@@ -0,0 +1,27 @@
+/* PR tree-optimization/65215 */
+
+__attribute__((noinline, noclone)) unsigned int
+foo (unsigned char *p)
+{
+  return ((unsigned int) p[0] << 24) | (p[1] << 16) | (p[2] << 8) | p[3];
+}
+
+__attribute__((noinline, noclone)) unsigned int
+bar (unsigned char *p)
+{
+  return ((unsigned int) p[3] << 24) | (p[2] << 16) | (p[1] << 8) | p[0];
+}
+
+struct S { unsigned int a; unsigned char b[5]; };
+
+int
+main ()
+{
+  struct S s = { 1, { 2, 3, 4, 5, 6 } };
+  if (__CHAR_BIT__ != 8 || sizeof (unsigned int) != 4)
+    return 0;
+  if (foo (&s.b[1]) != 0x03040506U
+      || bar (&s.b[1]) != 0x06050403U)
+    __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/tree-ssa-math-opts.c b/gcc/tree-ssa-math-opts.c
index e30116d..c22a677 100644
--- a/gcc/tree-ssa-math-opts.c
+++ b/gcc/tree-ssa-math-opts.c
@@ -1780,6 +1780,10 @@ find_bswap_or_nop_load (gimple stmt, tree ref, struct symbolic_number *n)
   int unsignedp, volatilep;
   tree offset, base_addr;
 
+  /* Not prepared to handle PDP endian.  */
+  if (BYTES_BIG_ENDIAN != WORDS_BIG_ENDIAN)
+    return false;
+
   if (!gimple_assign_load_p (stmt) || gimple_has_volatile_ops (stmt))
     return false;
 
@@ -1860,8 +1864,8 @@ perform_symbolic_merge (gimple source_stmt1, struct symbolic_number *n1,
 	  || !operand_equal_p (n1->base_addr, n2->base_addr, 0))
 	return NULL;
 
-      if (!n1->offset != !n2->offset ||
-          (n1->offset && !operand_equal_p (n1->offset, n2->offset, 0)))
+      if (!n1->offset != !n2->offset
+	  || (n1->offset && !operand_equal_p (n1->offset, n2->offset, 0)))
 	return NULL;
 
       if (n1->bytepos < n2->bytepos)
@@ -1912,8 +1916,8 @@ perform_symbolic_merge (gimple source_stmt1, struct symbolic_number *n1,
       size = TYPE_PRECISION (n1->type) / BITS_PER_UNIT;
       for (i = 0; i < size; i++, inc <<= BITS_PER_MARKER)
 	{
-	  unsigned marker =
-	    (toinc_n_ptr->n >> (i * BITS_PER_MARKER)) & MARKER_MASK;
+	  unsigned marker
+	    = (toinc_n_ptr->n >> (i * BITS_PER_MARKER)) & MARKER_MASK;
 	  if (marker && marker != MARKER_BYTE_UNKNOWN)
 	    toinc_n_ptr->n += inc;
 	}
@@ -2032,7 +2036,7 @@ find_bswap_or_nop_1 (gimple stmt, struct symbolic_number *n, int limit)
 	case RSHIFT_EXPR:
 	case LROTATE_EXPR:
 	case RROTATE_EXPR:
-	  if (!do_shift_rotate (code, n, (int)TREE_INT_CST_LOW (rhs2)))
+	  if (!do_shift_rotate (code, n, (int) TREE_INT_CST_LOW (rhs2)))
 	    return NULL;
 	  break;
 	CASE_CONVERT:
@@ -2104,12 +2108,12 @@ find_bswap_or_nop_1 (gimple stmt, struct symbolic_number *n, int limit)
 	  if (TYPE_PRECISION (n1.type) != TYPE_PRECISION (n2.type))
 	    return NULL;
 
-	  if (!n1.vuse != !n2.vuse ||
-	  (n1.vuse && !operand_equal_p (n1.vuse, n2.vuse, 0)))
+	  if (!n1.vuse != !n2.vuse
+	      || (n1.vuse && !operand_equal_p (n1.vuse, n2.vuse, 0)))
 	    return NULL;
 
-	  source_stmt =
-	    perform_symbolic_merge (source_stmt1, &n1, source_stmt2, &n2, n);
+	  source_stmt
+	    = perform_symbolic_merge (source_stmt1, &n1, source_stmt2, &n2, n);
 
 	  if (!source_stmt)
 	    return NULL;
@@ -2153,12 +2157,12 @@ find_bswap_or_nop (gimple stmt, struct symbolic_number *n, bool *bswap)
      in libgcc, and for initial shift/and operation of the src operand.  */
   limit = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (gimple_expr_type (stmt)));
   limit += 1 + (int) ceil_log2 ((unsigned HOST_WIDE_INT) limit);
-  source_stmt =  find_bswap_or_nop_1 (stmt, n, limit);
+  source_stmt = find_bswap_or_nop_1 (stmt, n, limit);
 
   if (!source_stmt)
     return NULL;
 
-  /* Find real size of result (highest non zero byte).  */
+  /* Find real size of result (highest non-zero byte).  */
   if (n->base_addr)
     {
       int rsize;
@@ -2261,8 +2265,30 @@ bswap_replace (gimple cur_stmt, gimple src_stmt, tree fndecl, tree bswap_type,
       tree load_offset_ptr, aligned_load_type;
       gimple addr_stmt, load_stmt;
       unsigned align;
+      HOST_WIDE_INT load_offset = 0;
 
       align = get_object_alignment (src);
+      /* If the new access is smaller than the original one, we need
+	 to perform big endian adjustment.  */
+      if (BYTES_BIG_ENDIAN)
+	{
+	  HOST_WIDE_INT bitsize, bitpos;
+	  machine_mode mode;
+	  int unsignedp, volatilep;
+	  tree offset;
+
+	  get_inner_reference (src, &bitsize, &bitpos, &offset, &mode,
+			       &unsignedp, &volatilep, false);
+	  if (n->range < (unsigned HOST_WIDE_INT) bitsize)
+	    {
+	      load_offset = (bitsize - n->range) / BITS_PER_UNIT;
+	      unsigned HOST_WIDE_INT l
+		= (load_offset * BITS_PER_UNIT) & (align - 1);
+	      if (l)
+		align = l & -l;
+	    }
+	}
+
       if (bswap
 	  && align < GET_MODE_ALIGNMENT (TYPE_MODE (load_type))
 	  && SLOW_UNALIGNED_ACCESS (TYPE_MODE (load_type), align))
@@ -2274,10 +2300,10 @@ bswap_replace (gimple cur_stmt, gimple src_stmt, tree fndecl, tree bswap_type,
       gsi_move_before (&gsi, &gsi_ins);
       gsi = gsi_for_stmt (cur_stmt);
 
-      /*  Compute address to load from and cast according to the size
-	  of the load.  */
+      /* Compute address to load from and cast according to the size
+	 of the load.  */
       addr_expr = build_fold_addr_expr (unshare_expr (src));
-      if (is_gimple_min_invariant (addr_expr))
+      if (is_gimple_mem_ref_addr (addr_expr))
 	addr_tmp = addr_expr;
       else
 	{
@@ -2291,7 +2317,7 @@ bswap_replace (gimple cur_stmt, gimple src_stmt, tree fndecl, tree bswap_type,
       aligned_load_type = load_type;
       if (align < TYPE_ALIGN (load_type))
 	aligned_load_type = build_aligned_type (load_type, align);
-      load_offset_ptr = build_int_cst (n->alias_set, 0);
+      load_offset_ptr = build_int_cst (n->alias_set, load_offset);
       val_expr = fold_build2 (MEM_REF, aligned_load_type, addr_tmp,
 			      load_offset_ptr);
 
@@ -2328,7 +2354,7 @@ bswap_replace (gimple cur_stmt, gimple src_stmt, tree fndecl, tree bswap_type,
 	    {
 	      fprintf (dump_file,
 		       "%d bit load in target endianness found at: ",
-		       (int)n->range);
+		       (int) n->range);
 	      print_gimple_stmt (dump_file, cur_stmt, 0, 0);
 	    }
 	  return true;
@@ -2395,7 +2421,7 @@ bswap_replace (gimple cur_stmt, gimple src_stmt, tree fndecl, tree bswap_type,
   if (dump_file)
     {
       fprintf (dump_file, "%d bit bswap implementation found at: ",
-	       (int)n->range);
+	       (int) n->range);
       print_gimple_stmt (dump_file, cur_stmt, 0, 0);
     }