[PATCH 2/5] RISC-V: Relax the -march string for accept any order

[Kito Cheng <kito.cheng@sifive.com>]

-march was require canonical order before, however it's not easy for
most user when we have so many extension, so this patch is relax the
constraint, -march accept the ISA string in any order, it only has few
requirement:

1. Must start with rv[32|64][e|i|g].
2. Multi-letter and single letter extension must be separated by
   at least one underscore(`_`).

gcc/ChangeLog:

	* common/config/riscv/riscv-common.cc
	(riscv_subset_list::parse_single_std_ext): New parameter.
	(riscv_subset_list::parse_single_multiletter_ext): Ditto.
	(riscv_subset_list::parse_single_ext): Ditto.
	(riscv_subset_list::parse): Relax the order for the input of ISA
	string.
	* config/riscv/riscv-subset.h
	(riscv_subset_list::parse_single_std_ext): New parameter.
	(riscv_subset_list::parse_single_multiletter_ext): Ditto.
	(riscv_subset_list::parse_single_ext): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/arch-33.c: New.
	* gcc.target/riscv/arch-34.c: New.
---
 gcc/common/config/riscv/riscv-common.cc  | 91 ++++++++++++++----------
 gcc/config/riscv/riscv-subset.h          |  6 +-
 gcc/testsuite/gcc.target/riscv/arch-33.c |  5 ++
 gcc/testsuite/gcc.target/riscv/arch-34.c |  5 ++
 4 files changed, 67 insertions(+), 40 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/arch-33.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/arch-34.c

diff --git a/gcc/common/config/riscv/riscv-common.cc b/gcc/common/config/riscv/riscv-common.cc
index f0359380451..891ecfce464 100644
--- a/gcc/common/config/riscv/riscv-common.cc
+++ b/gcc/common/config/riscv/riscv-common.cc
@@ -1132,10 +1132,12 @@ riscv_subset_list::parse_std_ext (const char *p)
      Points to the end of extensions.
 
    Arguments:
-     `p`: Current parsing position.  */
+     `p`: Current parsing position.
+     `exact_single_p`: True if input string is exactly an extension and end
+     with '\0'.  */
 
 const char *
-riscv_subset_list::parse_single_std_ext (const char *p)
+riscv_subset_list::parse_single_std_ext (const char *p, bool exact_single_p)
 {
   if (*p == 'x' || *p == 's' || *p == 'z')
     {
@@ -1146,6 +1148,11 @@ riscv_subset_list::parse_single_std_ext (const char *p)
       return nullptr;
     }
 
+  if (exact_single_p && strlen (p) > 1)
+    {
+      return nullptr;
+    }
+
   unsigned major_version = 0;
   unsigned minor_version = 0;
   bool explicit_version_p = false;
@@ -1296,13 +1303,16 @@ riscv_subset_list::check_conflict_ext ()
    Arguments:
      `p`: Current parsing position.
      `ext_type`: What kind of extensions, 's', 'z' or 'x'.
-     `ext_type_str`: Full name for kind of extension.  */
+     `ext_type_str`: Full name for kind of extension.
+     `exact_single_p`: True if input string is exactly an extension and end
+     with '\0'.   */
 
 
 const char *
 riscv_subset_list::parse_single_multiletter_ext (const char *p,
 						 const char *ext_type,
-						 const char *ext_type_str)
+						 const char *ext_type_str,
+						 bool exact_single_p)
 {
   unsigned major_version = 0;
   unsigned minor_version = 0;
@@ -1314,6 +1324,7 @@ riscv_subset_list::parse_single_multiletter_ext (const char *p,
   char *subset = xstrdup (p);
   const char *end_of_version;
   bool explicit_version_p = false;
+  char *q = subset;
   char *ext;
   char backup;
   size_t len = strlen (p);
@@ -1321,6 +1332,17 @@ riscv_subset_list::parse_single_multiletter_ext (const char *p,
   bool found_any_number = false;
   bool found_minor_version = false;
 
+  if (!exact_single_p)
+    {
+      /* Extension may not ended with '\0', may come with another extension
+	 which concat by '_' */
+      /* Parse until end of this extension including version number.  */
+      while (*++q != '\0' && *q != '_')
+	;
+
+      len = q - subset;
+    }
+
   end_of_version_pos = len;
   /* Find the begin of version string.  */
   for (i = len -1; i > 0; --i)
@@ -1505,21 +1527,26 @@ riscv_subset_list::parse_multiletter_ext (const char *p,
      Points to the end of extensions.
 
    Arguments:
-     `p`: Current parsing position.  */
+     `p`: Current parsing position.
+     `exact_single_p`: True if input string is exactly an extension and end
+     with '\0'.  */
 
 const char *
-riscv_subset_list::parse_single_ext (const char *p)
+riscv_subset_list::parse_single_ext (const char *p, bool exact_single_p)
 {
   switch (p[0])
     {
     case 'x':
-      return parse_single_multiletter_ext (p, "x", "non-standard extension");
+      return parse_single_multiletter_ext (p, "x", "non-standard extension",
+					   exact_single_p);
     case 'z':
-      return parse_single_multiletter_ext (p, "z", "sub-extension");
+      return parse_single_multiletter_ext (p, "z", "sub-extension",
+					   exact_single_p);
     case 's':
-      return parse_single_multiletter_ext (p, "s", "supervisor extension");
+      return parse_single_multiletter_ext (p, "s", "supervisor extension",
+					   exact_single_p);
     default:
-      return parse_single_std_ext (p);
+      return parse_single_std_ext (p, exact_single_p);
     }
 }
 
@@ -1538,37 +1565,27 @@ riscv_subset_list::parse (const char *arch, location_t loc)
   if (p == NULL)
     goto fail;
 
-  /* Parsing standard extension.  */
-  p = subset_list->parse_std_ext (p);
-
-  if (p == NULL)
-    goto fail;
-
-  /* Parsing sub-extensions.  */
-  p = subset_list->parse_multiletter_ext (p, "z", "sub-extension");
-
-  if (p == NULL)
-    goto fail;
-
-  /* Parsing supervisor extension.  */
-  p = subset_list->parse_multiletter_ext (p, "s", "supervisor extension");
-
-  if (p == NULL)
-    goto fail;
-
-  /* Parsing non-standard extension.  */
-  p = subset_list->parse_multiletter_ext (p, "x", "non-standard extension");
+  while (p && *p)
+    {
+      switch (*p)
+	{
+	case '_':
+	  ++p;
+	  continue;
+	case 'e':
+	case 'i':
+	case 'g':
+	  error_at (loc, "%<-march=%s%>: 'i', 'e' or 'g' must be the first extension.",
+		    arch);
+	  goto fail;
+	default:
+	  p = subset_list->parse_single_ext (p, /*exact_single_p=*/ false);
+	}
+    }
 
   if (p == NULL)
     goto fail;
 
-  if (*p != '\0')
-    {
-      error_at (loc, "%<-march=%s%>: unexpected ISA string at end: %qs",
-               arch, p);
-      goto fail;
-    }
-
   for (itr = subset_list->m_head; itr != NULL; itr = itr->next)
     {
       subset_list->handle_implied_ext (itr->name.c_str ());
diff --git a/gcc/config/riscv/riscv-subset.h b/gcc/config/riscv/riscv-subset.h
index c8117d8daf2..a80f9138e5c 100644
--- a/gcc/config/riscv/riscv-subset.h
+++ b/gcc/config/riscv/riscv-subset.h
@@ -71,12 +71,12 @@ private:
 
   const char *parse_std_ext (const char *);
 
-  const char *parse_single_std_ext (const char *);
+  const char *parse_single_std_ext (const char *, bool);
 
   const char *parse_multiletter_ext (const char *, const char *,
 				     const char *);
   const char *parse_single_multiletter_ext (const char *, const char *,
-					    const char *);
+					    const char *, bool);
 
   void handle_implied_ext (const char *);
   bool check_implied_ext ();
@@ -101,7 +101,7 @@ public:
   riscv_subset_list *clone () const;
 
   static riscv_subset_list *parse (const char *, location_t);
-  const char *parse_single_ext (const char *);
+  const char *parse_single_ext (const char *, bool exact_single_p = true);
 
   const riscv_subset_t *begin () const {return m_head;};
   const riscv_subset_t *end () const {return NULL;};
diff --git a/gcc/testsuite/gcc.target/riscv/arch-33.c b/gcc/testsuite/gcc.target/riscv/arch-33.c
new file mode 100644
index 00000000000..3fac9285ca3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/arch-33.c
@@ -0,0 +1,5 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64i_zba____zbs_mac_d -mabi=lp64d" } */
+int foo()
+{
+}
diff --git a/gcc/testsuite/gcc.target/riscv/arch-34.c b/gcc/testsuite/gcc.target/riscv/arch-34.c
new file mode 100644
index 00000000000..9b9f1a7a439
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/arch-34.c
@@ -0,0 +1,5 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64i_xtheadbs_zba_fcd -mabi=lp64d" } */
+int foo()
+{
+}
-- 
2.34.1