[PATCH 1/2] Remove the alignment limit on AArch64.

[Philipp Tomsich <philipp dot tomsich at theobroma-systems dot com>]

Updated per Marcus's review.

Remove the artificial limit on code alignment through the use of the
fixed part of a fragment for output generation only, which required
MAX_MEM_FOR_RS_ALIGN_CODE to be large enough to hold the maximum pad.

* config/tc-aarch64.h (MAX_MEM_FOR_RS_ALIGN_CODE): Define to 7.
* config/tc-aarch64.c (aarch64_handle_align): Rewrite to handle large
  alignments with a constant fragment size of MAX_MEM_FOR_RS_ALIGN_CODE.
---
 gas/config/tc-aarch64.c | 77 +++++++++++++++++++------------------------------
 gas/config/tc-aarch64.h |  7 +++--
 2 files changed, 33 insertions(+), 51 deletions(-)

diff --git a/gas/config/tc-aarch64.c b/gas/config/tc-aarch64.c
index 5578dfb..2c11cc9 100644
--- a/gas/config/tc-aarch64.c
+++ b/gas/config/tc-aarch64.c
@@ -5820,80 +5820,61 @@ md_section_align (segT segment ATTRIBUTE_UNUSED, valueT size)
 }
 
 /* This is called from HANDLE_ALIGN in write.c.	 Fill in the contents
-   of an rs_align_code fragment.  */
+   of an rs_align_code fragment.
+
+   Here we fill the frag with the appropriate info for padding the
+   output stream.  The resulting frag will consist of a fixed (fr_fix)
+   and of a repeating (fr_var) part.
+
+   The fixed content is always emitted before the repeating content and
+   these two parts are used as follows in constructing the output:
+   - the fixed part will be used to align to a valid instruction word
+     boundary, in case that we start at a misaligned address; as no
+     executable instruction can live at the misaligned location, we
+     simply fill with zeros;
+   - the variable part will be used to cover the remaining padding and
+     we fill using the AArch64 NOP instruction.
+
+   Note that the size of a RS_ALIGN_CODE fragment is always 7 to provide
+   enough storage space for up to 3 bytes for padding the back to a valid
+   instruction alignment and exactly 4 bytes to store the NOP pattern.
+ */
 
 void
-aarch64_handle_align (fragS * fragP)
+aarch64_handle_align (fragS * frag)
 {
   /* NOP = d503201f */
-  /* AArch64 instructions are always little-endian.  */
+  /* AArch64 instructions are always little-endian */
   static char const aarch64_noop[4] = { 0x1f, 0x20, 0x03, 0xd5 };
 
   int bytes, fix, noop_size;
   char *p;
-  const char *noop;
 
-  if (fragP->fr_type != rs_align_code)
+  if (frag->fr_type != rs_align_code)
     return;
 
   bytes = fragP->fr_next->fr_address - fragP->fr_address - fragP->fr_fix;
   p = fragP->fr_literal + fragP->fr_fix;
-  fix = 0;
-
-  if (bytes > MAX_MEM_FOR_RS_ALIGN_CODE)
-    bytes &= MAX_MEM_FOR_RS_ALIGN_CODE;
 
 #ifdef OBJ_ELF
-  gas_assert (fragP->tc_frag_data.recorded);
+  gas_assert (frag->tc_frag_data.recorded);
 #endif
 
-  noop = aarch64_noop;
   noop_size = sizeof (aarch64_noop);
-  fragP->fr_var = noop_size;
 
-  if (bytes & (noop_size - 1))
+  fix = bytes & (noop_size - 1);
+  if (fix)
     {
-      fix = bytes & (noop_size - 1);
 #ifdef OBJ_ELF
-      insert_data_mapping_symbol (MAP_INSN, fragP->fr_fix, fragP, fix);
+      insert_data_mapping_symbol (MAP_INSN, frag->fr_fix, frag, fix);
 #endif
       memset (p, 0, fix);
       p += fix;
-      bytes -= fix;
+      fragP->fr_fix += fix;
     }
 
-  while (bytes >= noop_size)
-    {
-      memcpy (p, noop, noop_size);
-      p += noop_size;
-      bytes -= noop_size;
-      fix += noop_size;
-    }
-
-  fragP->fr_fix += fix;
-}
-
-/* Called from md_do_align.  Used to create an alignment
-   frag in a code section.  */
-
-void
-aarch64_frag_align_code (int n, int max)
-{
-  char *p;
-
-  /* We assume that there will never be a requirement
-     to support alignments greater than x bytes.  */
-  if (max > MAX_MEM_FOR_RS_ALIGN_CODE)
-    as_fatal (_
-	      ("alignments greater than %d bytes not supported in .text sections"),
-	      MAX_MEM_FOR_RS_ALIGN_CODE + 1);
-
-  p = frag_var (rs_align_code,
-		MAX_MEM_FOR_RS_ALIGN_CODE,
-		1,
-		(relax_substateT) max,
-		(symbolS *) NULL, (offsetT) n, (char *) NULL);
-  *p = 0;
+  memcpy (p, aarch64_noop, noop_size);
+  fragP->fr_var = noop_size;
 }
 
 /* Perform target specific initialisation of a frag.
diff --git a/gas/config/tc-aarch64.h b/gas/config/tc-aarch64.h
index c3220bf..acd4de3 100644
--- a/gas/config/tc-aarch64.h
+++ b/gas/config/tc-aarch64.h
@@ -113,8 +113,9 @@ void aarch64_copy_symbol_attributes (symbolS *, symbolS *);
 
 #define TC_CONS_FIX_NEW cons_fix_new_aarch64
 
-/* Max code alignment is 32 bytes */
-#define MAX_MEM_FOR_RS_ALIGN_CODE 31
+/* Max space for a rs_align_code fragment is 3 unaligned bytes
+   (fr_fix) plus 4 bytes to contain the repeating NOP (fr_var) */
+#define MAX_MEM_FOR_RS_ALIGN_CODE 7
 
 /* For frags in code sections we need to record whether they contain
    code or data.  */
@@ -143,7 +144,7 @@ extern int aarch64_relax_frag (asection *, struct frag *, long);
 #define md_do_align(N, FILL, LEN, MAX, LABEL)					\
   if (FILL == NULL && (N) != 0 && ! need_pass_2 && subseg_text_p (now_seg))	\
     {										\
-      aarch64_frag_align_code (N, MAX);						\
+      frag_align_code (N, MAX);						\
       goto LABEL;								\
     }
 
-- 
1.9.0