[patch] Fix unaligned accesses generated by IVOPTS

[Eric Botcazou <ebotcazou at adacore dot com>]

Hi,

this is the bug discussed at http://gcc.gnu.org/ml/gcc/2010-04/msg00178.html

As reported by DJ, IVOPTS can generate unaligned accesses on strict alignment 
machines because may_be_unaligned_p overlooks the variable part of the offset 
in the reference it is passed.  The attached C testcase raises a SIGBUS on 
SPARC/Solaris at -O2 with all 4.x versions I tested (4.1, 4.3, 4.5, 4.6) but 
not with 3.4 so this is an old regression.

Bootstrapped/regtested on SPARC/Solaris and SPARC64/Solaris.  OK for mainline 
and for which branches?


2010-04-26  Eric Botcazou  <ebotcazou@adacore.com>

	* tree-ssa-loop-ivopts.c (may_be_unaligned_p): Check the alignment of
	the variable part of the offset as well.  Use highest_pow2_factor for
	all alignment checks.


2010-04-26  DJ Delorie  <dj@redhat.com>

	* gcc.c-torture/execute/20100426-1.c: New test.


-- 
Eric Botcazou

Index: tree-ssa-loop-ivopts.c
===================================================================
--- tree-ssa-loop-ivopts.c	(revision 158675)
+++ tree-ssa-loop-ivopts.c	(working copy)
@@ -1537,16 +1537,18 @@ may_be_unaligned_p (tree ref, tree step)
 
   if (mode != BLKmode)
     {
-      double_int mul;
-      tree al = build_int_cst (TREE_TYPE (step),
-			       GET_MODE_ALIGNMENT (mode) / BITS_PER_UNIT);
+      unsigned mode_align = GET_MODE_ALIGNMENT (mode);
 
-      if (base_align < GET_MODE_ALIGNMENT (mode)
-	  || bitpos % GET_MODE_ALIGNMENT (mode) != 0
-	  || bitpos % BITS_PER_UNIT != 0)
+      if (base_align < mode_align
+	  || (bitpos % mode_align) != 0
+	  || (bitpos % BITS_PER_UNIT) != 0)
 	return true;
 
-      if (!constant_multiple_of (step, al, &mul))
+      if (toffset
+	  && (highest_pow2_factor (toffset) * BITS_PER_UNIT) < mode_align)
+	return true;
+
+      if ((highest_pow2_factor (step) * BITS_PER_UNIT) < mode_align)
 	return true;
     }
 

/* This used to generate unaligned accesses at -O2 because of IVOPTS.  */

struct packed_struct
{
  struct packed_struct1
  {
    unsigned char cc11;
    unsigned char cc12;
  } __attribute__ ((packed)) pst1;
  struct packed_struct2
  {
    unsigned char cc21;
    unsigned char cc22;
    unsigned short ss[104];
    unsigned char cc23[13];
  } __attribute__ ((packed)) pst2[4];
} __attribute__ ((packed));

typedef struct
{
  int ii;
  struct packed_struct buf;
} info_t;

static unsigned short g;

static void __attribute__((noinline))
dummy (unsigned short s)
{
  g = s;
}

static int
foo (info_t *info)
{
  int i, j;

  for (i = 0; i < info->buf.pst1.cc11; i++)
    for (j = 0; j < info->buf.pst2[i].cc22; j++)
      dummy (info->buf.pst2[i].ss[j]);

  return 0;
}

int main(void)
{
  info_t info;
  info.buf.pst1.cc11 = 2;
  info.buf.pst2[0].cc22 = info.buf.pst2[1].cc22 = 8;
  return foo (&info);
}