RISC-V: correct alignment directive handling for text sections

.insn or data emitted inside text sections can lead to positions not
being at insn granularity. In such situations using alignment
directives should reliably enforce the requested alignment.
Specifically requests to align back to insn granularity may not be
ignored (where, as a subcase thereof, the ordering of ".option norvc"
and e.g. ".p2align 2" should not matter; so far the alignment directive
needs to come first to have any effect). Similarly ahead of emitting
NOPs alignment first needs to be forced back to insn granularity.

The new testcases actually point out a corner case issue in the
disassembler as well, which is being corrected at the same time: We
don't want to print "0x" without any subsequent digits.

1 files changed, 49 insertions, 17 deletions

diff --git a/gas/config/tc-riscv.c b/gas/config/tc-riscv.c
index 301607b..4a57683 100644
--- a/gas/config/tc-riscv.c
+++ b/gas/config/tc-riscv.c
@@ -185,6 +185,9 @@ static enum float_abi float_abi = FLOAT_ABI_DEFAULT;
 
 static unsigned elf_flags = 0;
 
+/* Indicate whether we are already assembling any instructions.  */
+static bool start_assemble = false;
+
 static bool probing_insn_operands;
 
 /* Set the default_isa_spec.  Return 0 if the spec isn't supported.
@@ -282,6 +285,16 @@ riscv_set_rvc (bool rvc_value)
   if (rvc_value)
     elf_flags |= EF_RISCV_RVC;
 
+  if (start_assemble && subseg_text_p (now_seg)
+      && riscv_opts.rvc && !rvc_value)
+    {
+      struct riscv_segment_info_type *info
+	= &seg_info(now_seg)->tc_segment_info_data;
+
+      info->last_insn16 = true;
+      info->rvc = rvc_value;
+    }
+
   riscv_opts.rvc = rvc_value;
 }
 
@@ -354,10 +367,8 @@ riscv_set_arch (const char *s)
   riscv_set_arch_str (&file_arch_str);
   riscv_set_arch_str (&riscv_rps_as.subset_list->arch_str);
 
-  riscv_set_rvc (false);
-  if (riscv_subset_supports (&riscv_rps_as, "c")
-      || riscv_subset_supports (&riscv_rps_as, "zca"))
-    riscv_set_rvc (true);
+  riscv_set_rvc (riscv_subset_supports (&riscv_rps_as, "c")
+		 || riscv_subset_supports (&riscv_rps_as, "zca"));
 
   if (riscv_subset_supports (&riscv_rps_as, "ztso"))
     riscv_set_tso ();
@@ -457,9 +468,6 @@ const char EXP_CHARS[] = "eE";
    As in 0f12.456 or 0d1.2345e12.  */
 const char FLT_CHARS[] = "rRsSfFdDxXpPhH";
 
-/* Indicate we are already assemble any instructions or not.  */
-static bool start_assemble = false;
-
 /* Indicate ELF attributes are explicitly set.  */
 static bool explicit_attr = false;
 
@@ -627,6 +635,7 @@ riscv_mapping_state (enum riscv_seg_mstate to_state,
 
   valueT value = (valueT) (frag_now_fix () - max_chars);
   seg_info (now_seg)->tc_segment_info_data.map_state = to_state;
+  seg_info (now_seg)->tc_segment_info_data.last_insn16 = false;
   const char *arch_str = reset_seg_arch_str
 			 ? riscv_rps_as.subset_list->arch_str : NULL;
   make_mapping_symbol (to_state, value, frag_now, arch_str,
@@ -4237,12 +4246,13 @@ riscv_ip_hardcode (char *str,
 	    generic_bignum[num],
 	    llen);
       memset(ip->insn_long_opcode + repr_bytes, 0, bytes - repr_bytes);
-      return NULL;
     }
-
-  if (bytes < sizeof(values[0]) && values[num - 1] >> (8 * bytes) != 0)
+  else if (bytes < sizeof(values[0]) && values[num - 1] >> (8 * bytes) != 0)
     return _("value conflicts with instruction length");
 
+  if (!riscv_opts.rvc && (bytes & 2))
+    seg_info (now_seg)->tc_segment_info_data.last_insn16 = true;
+
   return NULL;
 }
 
@@ -4929,10 +4939,8 @@ s_riscv_option (int x ATTRIBUTE_UNUSED)
       riscv_update_subset (&riscv_rps_as, name);
       riscv_set_arch_str (&riscv_rps_as.subset_list->arch_str);
 
-      riscv_set_rvc (false);
-      if (riscv_subset_supports (&riscv_rps_as, "c")
-	  || riscv_subset_supports (&riscv_rps_as, "zca"))
-	riscv_set_rvc (true);
+      riscv_set_rvc (riscv_subset_supports (&riscv_rps_as, "c")
+		     || riscv_subset_supports (&riscv_rps_as, "zca"));
 
       if (riscv_subset_supports (&riscv_rps_as, "ztso"))
 	riscv_set_tso ();
@@ -5040,15 +5048,27 @@ riscv_frag_align_code (int n)
   char *nops;
   expressionS ex;
 
-  /* If we are moving to a smaller alignment than the instruction size, then no
-     alignment is required. */
+  /* If we are moving to alignment no larger than the instruction size, then
+     no special alignment handling is required. */
   if (bytes <= insn_alignment)
-    return true;
+    {
+      if (bytes == insn_alignment)
+	seg_info (now_seg)->tc_segment_info_data.last_insn16 = false;
+      return false;
+    }
 
   /* When not relaxing, riscv_handle_align handles code alignment.  */
   if (!riscv_opts.relax)
     return false;
 
+  /* If the last item emitted was not an ordinary insn, first align back to
+     insn granularity.  Don't do this unconditionally, to avoid altering frags
+     when that's not actually needed.  */
+  if (seg_info (now_seg)->tc_segment_info_data.map_state != MAP_INSN
+      || seg_info (now_seg)->tc_segment_info_data.last_insn16)
+    frag_align_code (riscv_opts.rvc ? 1 : 2, 0);
+  seg_info (now_seg)->tc_segment_info_data.last_insn16 = false;
+
   /* Maybe we should use frag_var to create a new rs_align_code fragment,
      rather than just use frag_more to handle an alignment here?  So that we
      don't need to call riscv_mapping_state again later, and then only need
@@ -5366,6 +5386,18 @@ tc_riscv_regname_to_dw2regnum (char *regname)
 }
 
 void
+riscv_elf_section_change_hook (void)
+{
+  struct riscv_segment_info_type *info
+    = &seg_info(now_seg)->tc_segment_info_data;
+
+  if (info->rvc && !riscv_opts.rvc)
+    info->last_insn16 = true;
+
+  info->rvc = riscv_opts.rvc;
+}
+
+void
 riscv_elf_final_processing (void)
 {
   riscv_set_abi_by_arch ();