[Rust,front-end,v2,01/37] Use DW_ATE_UTF for the Rust 'char' type

Message ID 20220824115956.737931-2-philip.herron@embecosm.com
State New, archived
Headers
Series [Rust,front-end,v2,01/37] Use DW_ATE_UTF for the Rust 'char' type |

Commit Message

herron.philip@googlemail.com Aug. 24, 2022, 11:59 a.m. UTC
  From: Tom Tromey <tom@tromey.com>

The Rust 'char' type should use the DWARF DW_ATE_UTF encoding.
---
 gcc/dwarf2out.cc | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)
  

Comments

Jason Merrill Aug. 24, 2022, 2:28 p.m. UTC | #1
On 8/24/22 04:59, herron.philip@googlemail.com wrote:
> From: Tom Tromey <tom@tromey.com>
> 
> The Rust 'char' type should use the DWARF DW_ATE_UTF encoding.

The DWARF changes are OK.

> ---
>   gcc/dwarf2out.cc | 23 ++++++++++++++++++++++-
>   1 file changed, 22 insertions(+), 1 deletion(-)
> 
> diff --git a/gcc/dwarf2out.cc b/gcc/dwarf2out.cc
> index e3920c898f5..a8bccbabca4 100644
> --- a/gcc/dwarf2out.cc
> +++ b/gcc/dwarf2out.cc
> @@ -5600,6 +5600,16 @@ is_fortran (const_tree decl)
>     return is_fortran ();
>   }
>   
> +/* Return TRUE if the language is Rust.  */
> +
> +static inline bool
> +is_rust ()
> +{
> +  unsigned int lang = get_AT_unsigned (comp_unit_die (), DW_AT_language);
> +
> +  return lang == DW_LANG_Rust || lang == DW_LANG_Rust_old;
> +}
> +
>   /* Return TRUE if the language is Ada.  */
>   
>   static inline bool
> @@ -13231,7 +13241,11 @@ base_type_die (tree type, bool reverse)
>   	}
>         if (TYPE_STRING_FLAG (type))
>   	{
> -	  if (TYPE_UNSIGNED (type))
> +	  if ((dwarf_version >= 4 || !dwarf_strict)
> +	      && is_rust ()
> +	      && int_size_in_bytes (type) == 4)
> +	    encoding = DW_ATE_UTF;
> +	  else if (TYPE_UNSIGNED (type))
>   	    encoding = DW_ATE_unsigned_char;
>   	  else
>   	    encoding = DW_ATE_signed_char;
> @@ -25201,6 +25215,13 @@ gen_compile_unit_die (const char *filename)
>       }
>     else if (strcmp (language_string, "GNU F77") == 0)
>       language = DW_LANG_Fortran77;
> +  else if (strcmp (language_string, "GNU Rust") == 0)
> +    {
> +      if (dwarf_version >= 5 || !dwarf_strict)
> +	language = DW_LANG_Rust;
> +      else
> +	language = DW_LANG_Rust_old;
> +    }
>     else if (dwarf_version >= 3 || !dwarf_strict)
>       {
>         if (strcmp (language_string, "GNU Ada") == 0)
  

Patch

diff --git a/gcc/dwarf2out.cc b/gcc/dwarf2out.cc
index e3920c898f5..a8bccbabca4 100644
--- a/gcc/dwarf2out.cc
+++ b/gcc/dwarf2out.cc
@@ -5600,6 +5600,16 @@  is_fortran (const_tree decl)
   return is_fortran ();
 }
 
+/* Return TRUE if the language is Rust.  */
+
+static inline bool
+is_rust ()
+{
+  unsigned int lang = get_AT_unsigned (comp_unit_die (), DW_AT_language);
+
+  return lang == DW_LANG_Rust || lang == DW_LANG_Rust_old;
+}
+
 /* Return TRUE if the language is Ada.  */
 
 static inline bool
@@ -13231,7 +13241,11 @@  base_type_die (tree type, bool reverse)
 	}
       if (TYPE_STRING_FLAG (type))
 	{
-	  if (TYPE_UNSIGNED (type))
+	  if ((dwarf_version >= 4 || !dwarf_strict)
+	      && is_rust ()
+	      && int_size_in_bytes (type) == 4)
+	    encoding = DW_ATE_UTF;
+	  else if (TYPE_UNSIGNED (type))
 	    encoding = DW_ATE_unsigned_char;
 	  else
 	    encoding = DW_ATE_signed_char;
@@ -25201,6 +25215,13 @@  gen_compile_unit_die (const char *filename)
     }
   else if (strcmp (language_string, "GNU F77") == 0)
     language = DW_LANG_Fortran77;
+  else if (strcmp (language_string, "GNU Rust") == 0)
+    {
+      if (dwarf_version >= 5 || !dwarf_strict)
+	language = DW_LANG_Rust;
+      else
+	language = DW_LANG_Rust_old;
+    }
   else if (dwarf_version >= 3 || !dwarf_strict)
     {
       if (strcmp (language_string, "GNU Ada") == 0)