RISC-V: Add .insn support.

	gas/ChangeLog
	2018-03-07  Kito Cheng  <kito.cheng@gmail.com>
	* config/tc-riscv.c (opcode_name_list): New.
	(opcode_names_hash): Likewise.
	(init_opcode_names_hash): Likewise.
	(opcode_name_lookup): Likewise.
	(validate_riscv_insn): New argument length, and add new format
	which used in .insn directive.
	(md_begin): Refine hash table initialization logic into
	init_opcode_hash.
	(init_opcode_hash): New.
	(my_getOpcodeExpression): Parse opcode name for .insn.
	(riscv_ip): New argument hash, able to handle .insn directive.
	(s_riscv_insn): Handler for .insn directive.
	(riscv_pseudo_table): New entry for .insn.
	* doc/c-riscv.texi: Add documentation for .insn directive.
	* testsuite/gas/riscv/insn.d: Add testcase for .insn directive.
	* testsuite/gas/riscv/insn.s: Likewise.

	include/ChangeLog
	2018-03-07  Kito Cheng  <kito.cheng@gmail.com>
	* opcode/riscv.h (OP_MASK_FUNCT3): New.
	(OP_SH_FUNCT3): Likewise.
	(OP_MASK_FUNCT7): Likewise.
	(OP_SH_FUNCT7): Likewise.
	(OP_MASK_OP2): Likewise.
	(OP_SH_OP2): Likewise.
	(OP_MASK_CFUNCT4): Likewise.
	(OP_SH_CFUNCT4): Likewise.
	(OP_MASK_CFUNCT3): Likewise.
	(OP_SH_CFUNCT3): Likewise.
	(riscv_insn_types): Likewise.

	opcodes/ChangeLog
	2018-03-07  Kito Cheng  <kito.cheng@gmail.com>
	* riscv-opc.c (riscv_insn_types): New.

3 files changed, 673 insertions, 27 deletions

diff --git a/gas/ChangeLog b/gas/ChangeLog
index 4d77ef1..aeb927a 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,3 +1,22 @@
+2018-03-14  Kito Cheng  <kito.cheng@gmail.com>
+
+	* config/tc-riscv.c (opcode_name_list): New.
+	(opcode_names_hash): Likewise.
+	(init_opcode_names_hash): Likewise.
+	(opcode_name_lookup): Likewise.
+	(validate_riscv_insn): New argument length, and add new format
+	which used in .insn directive.
+	(md_begin): Refine hash table initialization logic into
+	init_opcode_hash.
+	(init_opcode_hash): New.
+	(my_getOpcodeExpression): Parse opcode name for .insn.
+	(riscv_ip): New argument hash, able to handle .insn directive.
+	(s_riscv_insn): Handler for .insn directive.
+	(riscv_pseudo_table): New entry for .insn.
+	* doc/c-riscv.texi: Add documentation for .insn directive.
+	* testsuite/gas/riscv/insn.d: Add testcase for .insn directive.
+	* testsuite/gas/riscv/insn.s: Likewise.
+
 2018-03-13  Nick Clifton  <nickc@redhat.com>
 
 	* po/ru.po: Updated Russian translation.
diff --git a/gas/config/tc-riscv.c b/gas/config/tc-riscv.c
index f1bc7f9..454f283 100644
--- a/gas/config/tc-riscv.c
+++ b/gas/config/tc-riscv.c
@@ -221,6 +221,9 @@ riscv_set_arch (const char *s)
 /* Handle of the OPCODE hash table.  */
 static struct hash_control *op_hash = NULL;
 
+/* Handle of the type of .insn hash table.  */
+static struct hash_control *insn_type_hash = NULL;
+
 /* This array holds the chars that always start a comment.  If the
     pre-processor is disabled, these aren't very useful */
 const char comment_chars[] = "#";
@@ -391,6 +394,111 @@ relaxed_branch_length (fragS *fragp, asection *sec, int update)
   return length;
 }
 
+/* Information about an opcode name, mnemonics and its value.  */
+struct opcode_name_t
+{
+  const char *name;
+  unsigned int val;
+};
+
+/* List for all supported opcode name.  */
+static const struct opcode_name_t opcode_name_list[] =
+{
+  {"C0",        0x0},
+  {"C1",        0x1},
+  {"C2",        0x2},
+
+  {"LOAD",      0x03},
+  {"LOAD_FP",   0x07},
+  {"CUSTOM_0",  0x0b},
+  {"MISC_MEM",  0x0f},
+  {"OP_IMM",    0x13},
+  {"AUIPC",     0x17},
+  {"OP_IMM_32", 0x1b},
+  /* 48b        0x1f.  */
+
+  {"STORE",     0x23},
+  {"STORE_FP",  0x27},
+  {"CUSTOM_1",  0x2b},
+  {"AMO",       0x2f},
+  {"OP",        0x33},
+  {"LUI",       0x37},
+  {"OP_32",     0x3b},
+  /* 64b        0x3f.  */
+
+  {"MADD",      0x43},
+  {"MSUB",      0x47},
+  {"NMADD",     0x4f},
+  {"NMSUB",     0x4b},
+  {"OP_FP",     0x53},
+  /*reserved    0x57.  */
+  {"CUSTOM_2",  0x5b},
+  /* 48b        0x5f.  */
+
+  {"BRANCH",    0x63},
+  {"JALR",      0x67},
+  /*reserved    0x5b.  */
+  {"JAL",       0x6f},
+  {"SYSTEM",    0x73},
+  /*reserved    0x77.  */
+  {"CUSTOM_3",  0x7b},
+  /* >80b       0x7f.  */
+
+  {NULL, 0}
+};
+
+/* Hash table for lookup opcode name.  */
+static struct hash_control *opcode_names_hash = NULL;
+
+/* Initialization for hash table of opcode name.  */
+static void
+init_opcode_names_hash (void)
+{
+  const char *retval;
+  const struct opcode_name_t *opcode;
+
+  for (opcode = &opcode_name_list[0]; opcode->name != NULL; ++opcode)
+    {
+      retval = hash_insert (opcode_names_hash, opcode->name, (void *)opcode);
+
+      if (retval != NULL)
+	as_fatal (_("internal error: can't hash `%s': %s"),
+		  opcode->name, retval);
+    }
+}
+
+/* Find `s` is a valid opcode name or not,
+   return the opcode name info if found.  */
+static const struct opcode_name_t *
+opcode_name_lookup (char **s)
+{
+  char *e;
+  char save_c;
+  struct opcode_name_t *o;
+
+  /* Find end of name.  */
+  e = *s;
+  if (is_name_beginner (*e))
+    ++e;
+  while (is_part_of_name (*e))
+    ++e;
+
+  /* Terminate name.  */
+  save_c = *e;
+  *e = '\0';
+
+  o = (struct opcode_name_t *) hash_find (opcode_names_hash, *s);
+
+  /* Advance to next token if one was recognized.  */
+  if (o)
+    *s = e;
+
+  *e = save_c;
+  expr_end = e;
+
+  return o;
+}
+
 struct regname
 {
   const char *name;
@@ -488,15 +596,24 @@ arg_lookup (char **s, const char *const *array, size_t size, unsigned *regnop)
 
 /* For consistency checking, verify that all bits are specified either
    by the match/mask part of the instruction definition, or by the
-   operand list.  */
+   operand list.
+
+   `length` could be 0, 4 or 8, 0 for auto detection.  */
 static bfd_boolean
-validate_riscv_insn (const struct riscv_opcode *opc)
+validate_riscv_insn (const struct riscv_opcode *opc, int length)
 {
   const char *p = opc->args;
   char c;
   insn_t used_bits = opc->mask;
-  int insn_width = 8 * riscv_insn_length (opc->match);
-  insn_t required_bits = ~0ULL >> (64 - insn_width);
+  int insn_width;
+  insn_t required_bits;
+
+  if (length == 0)
+    insn_width = 8 * riscv_insn_length (opc->match);
+  else
+    insn_width = 8 * length;
+
+  required_bits = ~0ULL >> (64 - insn_width);
 
   if ((used_bits & opc->match) != (opc->match & required_bits))
     {
@@ -536,8 +653,22 @@ validate_riscv_insn (const struct riscv_opcode *opc)
 	  case 'V': USE_BITS (OP_MASK_CRS2, OP_SH_CRS2); break;
 	  case '<': used_bits |= ENCODE_RVC_IMM (-1U); break;
 	  case '>': used_bits |= ENCODE_RVC_IMM (-1U); break;
+	  case '8': used_bits |= ENCODE_RVC_UIMM8 (-1U); break;
+	  case 'S': USE_BITS (OP_MASK_CRS1S, OP_SH_CRS1S); break;
 	  case 'T': USE_BITS (OP_MASK_CRS2, OP_SH_CRS2); break;
 	  case 'D': USE_BITS (OP_MASK_CRS2S, OP_SH_CRS2S); break;
+	  case 'F': /* funct */
+	    switch (c = *p++)
+	      {
+		case '4': USE_BITS (OP_MASK_CFUNCT4, OP_SH_CFUNCT4); break;
+		case '3': USE_BITS (OP_MASK_CFUNCT3, OP_SH_CFUNCT3); break;
+		default:
+		  as_bad (_("internal: bad RISC-V opcode"
+			    " (unknown operand type `CF%c'): %s %s"),
+			  c, opc->name, opc->args);
+		  return FALSE;
+	      }
+	    break;
 	  default:
 	    as_bad (_("internal: bad RISC-V opcode (unknown operand type `C%c'): %s %s"),
 		    c, opc->name, opc->args);
@@ -562,6 +693,7 @@ validate_riscv_insn (const struct riscv_opcode *opc)
       case 'm':	USE_BITS (OP_MASK_RM,		OP_SH_RM);	break;
       case 's':	USE_BITS (OP_MASK_RS1,		OP_SH_RS1);	break;
       case 't':	USE_BITS (OP_MASK_RS2,		OP_SH_RS2);	break;
+      case 'r':	USE_BITS (OP_MASK_RS3,          OP_SH_RS3);     break;
       case 'P':	USE_BITS (OP_MASK_PRED,		OP_SH_PRED); break;
       case 'Q':	USE_BITS (OP_MASK_SUCC,		OP_SH_SUCC); break;
       case 'o':
@@ -574,6 +706,31 @@ validate_riscv_insn (const struct riscv_opcode *opc)
       case '[': break;
       case ']': break;
       case '0': break;
+      case 'F': /* funct */
+	switch (c = *p++)
+	  {
+	    case '7': USE_BITS (OP_MASK_FUNCT7, OP_SH_FUNCT7); break;
+	    case '3': USE_BITS (OP_MASK_FUNCT3, OP_SH_FUNCT3); break;
+	    case '2': USE_BITS (OP_MASK_FUNCT2, OP_SH_FUNCT2); break;
+	    default:
+	      as_bad (_("internal: bad RISC-V opcode"
+			" (unknown operand type `F%c'): %s %s"),
+		      c, opc->name, opc->args);
+	    return FALSE;
+	  }
+	break;
+      case 'O': /* opcode */
+	switch (c = *p++)
+	  {
+	    case '4': USE_BITS (OP_MASK_OP, OP_SH_OP); break;
+	    case '2': USE_BITS (OP_MASK_OP2, OP_SH_OP2); break;
+	    default:
+	      as_bad (_("internal: bad RISC-V opcode"
+			" (unknown operand type `F%c'): %s %s"),
+		      c, opc->name, opc->args);
+	     return FALSE;
+	  }
+	break;
       default:
 	as_bad (_("internal: bad RISC-V opcode "
 		  "(unknown operand type `%c'): %s %s"),
@@ -597,52 +754,73 @@ struct percent_op_match
   bfd_reloc_code_real_type reloc;
 };
 
-/* This function is called once, at assembler startup time.  It should set up
-   all the tables, etc. that the MD part of the assembler will need.  */
-
-void
-md_begin (void)
+/* Common hash table initialization function for
+   instruction and .insn directive.  */
+static struct hash_control *
+init_opcode_hash (const struct riscv_opcode *opcodes,
+		  bfd_boolean insn_directive_p)
 {
   int i = 0;
-  unsigned long mach = xlen == 64 ? bfd_mach_riscv64 : bfd_mach_riscv32;
-
-  if (! bfd_set_arch_mach (stdoutput, bfd_arch_riscv, mach))
-    as_warn (_("Could not set architecture and machine"));
-
-  op_hash = hash_new ();
-
-  while (riscv_opcodes[i].name)
+  int length;
+  struct hash_control *hash = hash_new ();
+  while (opcodes[i].name)
     {
-      const char *name = riscv_opcodes[i].name;
+      const char *name = opcodes[i].name;
       const char *hash_error =
-	hash_insert (op_hash, name, (void *) &riscv_opcodes[i]);
+	hash_insert (hash, name, (void *) &opcodes[i]);
 
       if (hash_error)
 	{
 	  fprintf (stderr, _("internal error: can't hash `%s': %s\n"),
-		   riscv_opcodes[i].name, hash_error);
+		   opcodes[i].name, hash_error);
 	  /* Probably a memory allocation problem?  Give up now.  */
 	  as_fatal (_("Broken assembler.  No assembly attempted."));
 	}
 
       do
 	{
-	  if (riscv_opcodes[i].pinfo != INSN_MACRO)
+	  if (opcodes[i].pinfo != INSN_MACRO)
 	    {
-	      if (!validate_riscv_insn (&riscv_opcodes[i]))
+	      if (insn_directive_p)
+		length = ((name[0] == 'c') ? 2 : 4);
+	      else
+		length = 0; /* Let assembler determine the length. */
+	      if (!validate_riscv_insn (&opcodes[i], length))
 		as_fatal (_("Broken assembler.  No assembly attempted."));
 	    }
+	  else
+	    gas_assert (!insn_directive_p);
 	  ++i;
 	}
-      while (riscv_opcodes[i].name && !strcmp (riscv_opcodes[i].name, name));
+      while (opcodes[i].name && !strcmp (opcodes[i].name, name));
     }
 
+  return hash;
+}
+
+/* This function is called once, at assembler startup time.  It should set up
+   all the tables, etc. that the MD part of the assembler will need.  */
+
+void
+md_begin (void)
+{
+  unsigned long mach = xlen == 64 ? bfd_mach_riscv64 : bfd_mach_riscv32;
+
+  if (! bfd_set_arch_mach (stdoutput, bfd_arch_riscv, mach))
+    as_warn (_("Could not set architecture and machine"));
+
+  op_hash = init_opcode_hash (riscv_opcodes, FALSE);
+  insn_type_hash = init_opcode_hash (riscv_insn_types, TRUE);
+
   reg_names_hash = hash_new ();
   hash_reg_names (RCLASS_GPR, riscv_gpr_names_numeric, NGPR);
   hash_reg_names (RCLASS_GPR, riscv_gpr_names_abi, NGPR);
   hash_reg_names (RCLASS_FPR, riscv_fpr_names_numeric, NFPR);
   hash_reg_names (RCLASS_FPR, riscv_fpr_names_abi, NFPR);
 
+  opcode_names_hash = hash_new ();
+  init_opcode_names_hash ();
+
 #define DECLARE_CSR(name, num) hash_reg_name (RCLASS_CSR, #name, num);
 #define DECLARE_CSR_ALIAS(name, num) DECLARE_CSR(name, num);
 #include "opcode/riscv-opc.h"
@@ -1186,6 +1364,23 @@ my_getSmallExpression (expressionS *ep, bfd_reloc_code_real_type *reloc,
   return reloc_index;
 }
 
+/* Parse opcode name, could be an mnemonics or number.  */
+static size_t
+my_getOpcodeExpression (expressionS *ep, bfd_reloc_code_real_type *reloc,
+			char *str, const struct percent_op_match *percent_op)
+{
+  const struct opcode_name_t *o = opcode_name_lookup (&str);
+
+  if (o != NULL)
+    {
+      ep->X_op = O_constant;
+      ep->X_add_number = o->val;
+      return 0;
+    }
+
+  return my_getSmallExpression (ep, reloc, str, percent_op);
+}
+
 /* Detect and handle implicitly zero load-store offsets.  For example,
    "lw t0, (t1)" is shorthand for "lw t0, 0(t1)".  Return TRUE iff such
    an implicit offset was detected.  */
@@ -1211,7 +1406,7 @@ riscv_handle_implicit_zero_offset (expressionS *ep, const char *s)
 
 static const char *
 riscv_ip (char *str, struct riscv_cl_insn *ip, expressionS *imm_expr,
-	  bfd_reloc_code_real_type *imm_reloc)
+	  bfd_reloc_code_real_type *imm_reloc, struct hash_control *hash)
 {
   char *s;
   const char *args;
@@ -1234,7 +1429,7 @@ riscv_ip (char *str, struct riscv_cl_insn *ip, expressionS *imm_expr,
 	break;
       }
 
-  insn = (struct riscv_opcode *) hash_find (op_hash, str);
+  insn = (struct riscv_opcode *) hash_find (hash, str);
 
   argsStart = s;
   for ( ; insn && insn->name && strcmp (insn->name, str) == 0; insn++)
@@ -1259,7 +1454,12 @@ riscv_ip (char *str, struct riscv_cl_insn *ip, expressionS *imm_expr,
 		{
 		  if (!insn->match_func (insn, ip->insn_opcode))
 		    break;
-		  if (riscv_insn_length (insn->match) == 2 && !riscv_opts.rvc)
+
+		  /* For .insn, insn->match and insn->mask are 0.  */
+		  if (riscv_insn_length ((insn->match == 0 && insn->mask == 0)
+					 ? ip->insn_opcode
+					 : insn->match) == 2
+		      && !riscv_opts.rvc)
 		    break;
 		}
 	      if (*s != '\0')
@@ -1328,6 +1528,15 @@ rvc_imm_done:
 		    break;
 		  ip->insn_opcode |= ENCODE_RVC_IMM (imm_expr->X_add_number);
 		  goto rvc_imm_done;
+		case '8':
+		  if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
+		      || imm_expr->X_op != O_constant
+		      || !VALID_RVC_UIMM8 (imm_expr->X_add_number)
+		      || imm_expr->X_add_number < 0
+		      || imm_expr->X_add_number >= 256)
+		    break;
+		  ip->insn_opcode |= ENCODE_RVC_UIMM8 (imm_expr->X_add_number);
+		  goto rvc_imm_done;
 		case 'i':
 		  if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
 		      || imm_expr->X_op != O_constant
@@ -1457,6 +1666,12 @@ rvc_lui:
 		  goto branch;
 		case 'a':
 		  goto jump;
+		case 'S': /* Floating-point RS1 x8-x15.  */
+		  if (!reg_lookup (&s, RCLASS_FPR, &regno)
+		      || !(regno >= 8 && regno <= 15))
+		    break;
+		  INSERT_OPERAND (CRS1S, *ip, regno % 8);
+		  continue;
 		case 'D': /* Floating-point RS2 x8-x15.  */
 		  if (!reg_lookup (&s, RCLASS_FPR, &regno)
 		      || !(regno >= 8 && regno <= 15))
@@ -1468,6 +1683,45 @@ rvc_lui:
 		    break;
 		  INSERT_OPERAND (CRS2, *ip, regno);
 		  continue;
+		case 'F':
+		  switch (*++args)
+		    {
+		      case '4':
+		        if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
+			    || imm_expr->X_op != O_constant
+			    || imm_expr->X_add_number < 0
+			    || imm_expr->X_add_number >= 16)
+			  {
+			    as_bad (_("bad value for funct4 field, "
+				      "value must be 0...15"));
+			    break;
+			  }
+
+			INSERT_OPERAND (CFUNCT4, *ip, imm_expr->X_add_number);
+			imm_expr->X_op = O_absent;
+			s = expr_end;
+			continue;
+		      case '3':
+			if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
+			    || imm_expr->X_op != O_constant
+			    || imm_expr->X_add_number < 0
+			    || imm_expr->X_add_number >= 8)
+			  {
+			    as_bad (_("bad value for funct3 field, "
+				      "value must be 0...7"));
+			    break;
+			  }
+			INSERT_OPERAND (CFUNCT3, *ip, imm_expr->X_add_number);
+			imm_expr->X_op = O_absent;
+			s = expr_end;
+			continue;
+		      default:
+			as_bad (_("bad compressed FUNCT field"
+				  " specifier 'CF%c'\n"),
+				*args);
+		    }
+		  break;
+
 		default:
 		  as_bad (_("bad RVC field specifier 'C%c'\n"), *args);
 		}
@@ -1561,6 +1815,7 @@ rvc_lui:
 	    case 'd':		/* Destination register.  */
 	    case 's':		/* Source register.  */
 	    case 't':		/* Target register.  */
+	    case 'r':		/* rs3.  */
 	      if (reg_lookup (&s, RCLASS_GPR, &regno))
 		{
 		  c = *args;
@@ -1580,6 +1835,9 @@ rvc_lui:
 		    case 't':
 		      INSERT_OPERAND (RS2, *ip, regno);
 		      break;
+		    case 'r':
+		      INSERT_OPERAND (RS3, *ip, regno);
+		      break;
 		    }
 		  continue;
 		}
@@ -1712,6 +1970,99 @@ jump:
 	      else
 		*imm_reloc = BFD_RELOC_RISCV_CALL;
 	      continue;
+	    case 'O':
+	      switch (*++args)
+		{
+		case '4':
+		  if (my_getOpcodeExpression (imm_expr, imm_reloc, s, p)
+		      || imm_expr->X_op != O_constant
+		      || imm_expr->X_add_number < 0
+		      || imm_expr->X_add_number >= 128
+		      || (imm_expr->X_add_number & 0x3) != 3)
+		    {
+		      as_bad (_("bad value for opcode field, "
+				"value must be 0...127 and "
+				"lower 2 bits must be 0x3"));
+		      break;
+		    }
+
+		  INSERT_OPERAND (OP, *ip, imm_expr->X_add_number);
+		  imm_expr->X_op = O_absent;
+		  s = expr_end;
+		  continue;
+		case '2':
+		  if (my_getOpcodeExpression (imm_expr, imm_reloc, s, p)
+		      || imm_expr->X_op != O_constant
+		      || imm_expr->X_add_number < 0
+		      || imm_expr->X_add_number >= 3)
+		    {
+		      as_bad (_("bad value for opcode field, "
+				"value must be 0...2"));
+		      break;
+		    }
+
+		  INSERT_OPERAND (OP2, *ip, imm_expr->X_add_number);
+		  imm_expr->X_op = O_absent;
+		  s = expr_end;
+		  continue;
+		default:
+		  as_bad (_("bad Opcode field specifier 'O%c'\n"), *args);
+		}
+	      break;
+
+	    case 'F':
+	      switch (*++args)
+		{
+		case '7':
+		  if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
+		      || imm_expr->X_op != O_constant
+		      || imm_expr->X_add_number < 0
+		      || imm_expr->X_add_number >= 128)
+		    {
+		      as_bad (_("bad value for funct7 field, "
+				"value must be 0...127"));
+		      break;
+		    }
+
+		  INSERT_OPERAND (FUNCT7, *ip, imm_expr->X_add_number);
+		  imm_expr->X_op = O_absent;
+		  s = expr_end;
+		  continue;
+		case '3':
+		  if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
+		      || imm_expr->X_op != O_constant
+		      || imm_expr->X_add_number < 0
+		      || imm_expr->X_add_number >= 8)
+		    {
+		      as_bad (_("bad value for funct3 field, "
+			        "value must be 0...7"));
+		      break;
+		    }
+
+		  INSERT_OPERAND (FUNCT3, *ip, imm_expr->X_add_number);
+		  imm_expr->X_op = O_absent;
+		  s = expr_end;
+		  continue;
+		case '2':
+		  if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
+		      || imm_expr->X_op != O_constant
+		      || imm_expr->X_add_number < 0
+		      || imm_expr->X_add_number >= 4)
+		    {
+		      as_bad (_("bad value for funct2 field, "
+			        "value must be 0...3"));
+		      break;
+		    }
+
+		  INSERT_OPERAND (FUNCT2, *ip, imm_expr->X_add_number);
+		  imm_expr->X_op = O_absent;
+		  s = expr_end;
+		  continue;
+
+		default:
+		  as_bad (_("bad FUNCT field specifier 'F%c'\n"), *args);
+		}
+	      break;
 
 	    case 'z':
 	      if (my_getSmallExpression (imm_expr, imm_reloc, s, p)
@@ -1746,7 +2097,7 @@ md_assemble (char *str)
   expressionS imm_expr;
   bfd_reloc_code_real_type imm_reloc = BFD_RELOC_UNUSED;
 
-  const char *error = riscv_ip (str, &insn, &imm_expr, &imm_reloc);
+  const char *error = riscv_ip (str, &insn, &imm_expr, &imm_reloc, op_hash);
 
   if (error)
     {
@@ -2614,6 +2965,40 @@ s_riscv_leb128 (int sign)
   return s_leb128 (sign);
 }
 
+/* Parse the .insn directive.  */
+
+static void
+s_riscv_insn (int x ATTRIBUTE_UNUSED)
+{
+  char *str = input_line_pointer;
+  struct riscv_cl_insn insn;
+  expressionS imm_expr;
+  bfd_reloc_code_real_type imm_reloc = BFD_RELOC_UNUSED;
+  char save_c;
+
+  while (!is_end_of_line[(unsigned char) *input_line_pointer])
+    ++input_line_pointer;
+
+  save_c = *input_line_pointer;
+  *input_line_pointer = '\0';
+
+  const char *error = riscv_ip (str, &insn, &imm_expr,
+				&imm_reloc, insn_type_hash);
+
+  if (error)
+    {
+      as_bad ("%s `%s'", error, str);
+    }
+  else
+    {
+      gas_assert (insn.insn_mo->pinfo != INSN_MACRO);
+      append_insn (&insn, &imm_expr, imm_reloc);
+    }
+
+  *input_line_pointer = save_c;
+  demand_empty_rest_of_line ();
+}
+
 /* Pseudo-op table.  */
 
 static const pseudo_typeS riscv_pseudo_table[] =
@@ -2628,6 +3013,7 @@ static const pseudo_typeS riscv_pseudo_table[] =
   {"bss", s_bss, 0},
   {"uleb128", s_riscv_leb128, 0},
   {"sleb128", s_riscv_leb128, 1},
+  {"insn", s_riscv_insn, 0},
 
   { NULL, NULL, 0 },
 };
diff --git a/gas/doc/c-riscv.texi b/gas/doc/c-riscv.texi
index 3f327d6..30e6125 100644
--- a/gas/doc/c-riscv.texi
+++ b/gas/doc/c-riscv.texi
@@ -17,6 +17,7 @@
 @menu
 * RISC-V-Options::        RISC-V Options
 * RISC-V-Directives::     RISC-V Directives
+* RISC-V-Formats::        RISC-V Instruction Formats
 @end menu
 
 @node RISC-V-Options
@@ -148,4 +149,244 @@ opportunistically relax some code sequences, but sometimes this behavior is not
 desirable.
 @end table
 
+@cindex INSN directives
+@item .insn @var{value}
+@itemx .insn @var{value}
+This directive permits the numeric representation of an instructions
+and makes the assembler insert the operands according to one of the
+instruction formats for @samp{.insn} (@ref{RISC-V-Formats}).
+For example, the instruction @samp{add a0, a1, a2} could be written as
+@samp{.insn r 0x33, 0, 0, a0, a1, a2}.
+
 @end table
+
+@node RISC-V-Formats
+@section Instruction Formats
+@cindex instruction formats, risc-v
+@cindex RISC-V instruction formats
+
+The RISC-V Instruction Set Manual Volume I: User-Level ISA lists 12
+instruction formats where some of the formats have multiple variants.
+For the @samp{.insn} pseudo directive the assembler recognizes some
+of the formats.
+Typically, the most general variant of the instruction format is used
+by the @samp{.insn} directive.
+
+The following table lists the abbreviations used in the table of
+instruction formats:
+
+@display
+@multitable @columnfractions .15 .40
+@item opcode @tab Unsigned immediate or opcode name for 7-bits opcode.
+@item opcode2 @tab Unsigned immediate or opcode name for 2-bits opcode.
+@item func7 @tab Unsigned immediate for 7-bits function code.
+@item func4 @tab Unsigned immediate for 4-bits function code.
+@item func3 @tab Unsigned immediate for 3-bits function code.
+@item func2 @tab Unsigned immediate for 2-bits function code.
+@item rd @tab Destination register number for operand x, can be GPR or FPR.
+@item rd' @tab Destination register number for operand x,
+only accept s0-s1, a0-a5, fs0-fs1 and fa0-fa5.
+@item rs1 @tab First source register number for operand x, can be GPR or FPR.
+@item rs1' @tab First source register number for operand x,
+only accept s0-s1, a0-a5, fs0-fs1 and fa0-fa5.
+@item rs2 @tab Second source register number for operand x, can be GPR or FPR.
+@item rs2' @tab Second source register number for operand x,
+only accept s0-s1, a0-a5, fs0-fs1 and fa0-fa5.
+@item simm12 @tab Sign-extended 12-bit immediate for operand x.
+@item simm20 @tab Sign-extended 20-bit immediate for operand x.
+@item simm6 @tab Sign-extended 6-bit immediate for operand x.
+@item uimm8 @tab Unsigned 8-bit immediate for operand x.
+@item symbol @tab Symbol or lable reference for operand x.
+@end multitable
+@end display
+
+The following table lists all available opcode name:
+
+@table @code
+@item C0
+@item C1
+@item C2
+Opcode space for compressed instructions.
+
+@item LOAD
+Opcode space for load instructions.
+
+@item LOAD_FP
+Opcode space for floating-point load instructions.
+
+@item STORE
+Opcode space for store instructions.
+
+@item STORE_FP
+Opcode space for floating-point store instructions.
+
+@item AUIPC
+Opcode space for auipc instruction.
+
+@item LUI
+Opcode space for lui instruction.
+
+@item BRANCH
+Opcode space for branch instructions.
+
+@item JAL
+Opcode space for jal instruction.
+
+@item JALR
+Opcode space for jalr instruction.
+
+@item OP
+Opcode space for ALU instructions.
+
+@item OP_32
+Opcode space for 32-bits ALU instructions.
+
+@item OP_IMM
+Opcode space for ALU with immediate instructions.
+
+@item OP_IMM_32
+Opcode space for 32-bits ALU with immediate instructions.
+
+@item OP_FP
+Opcode space for floating-point operation instructions.
+
+@item MADD
+Opcode space for madd instruction.
+
+@item MSUB
+Opcode space for msub instruction.
+
+@item NMADD
+Opcode space for nmadd instruction.
+
+@item NMSUB
+Opcode space for msub instruction.
+
+@item AMO
+Opcode space for atomic memory operation instructions.
+
+@item MISC_IMM
+Opcode space for misc instructions.
+
+@item SYSTEM
+Opcode space for system instructions.
+
+@item CUSTOM_0
+@item CUSTOM_1
+@item CUSTOM_2
+@item CUSTOM_3
+Opcode space for customize instructions.
+
+@end table
+
+An instruction is two or four bytes in length and must be aligned
+on a 2 byte boundary. The first two bits of the instruction specify the
+length of the instruction, 00, 01 and 10 indicates a two byte instruction,
+11 indicates a four byte instruction.
+
+The following table lists the RISC-V instruction formats that are available
+with the @samp{.insn} pseudo directive:
+
+@table @code
+@item R type: .insn r opcode, func3, func7, rd, rs1, rs2
+@verbatim
++-------+-----+-----+-------+----+-------------+
+| func7 | rs2 | rs1 | func3 | rd |      opcode |
++-------+-----+-----+-------+----+-------------+
+31      25    20    15      12   7             0
+@end verbatim
+
+@item R type with 4 register operands: .insn r opcode, func3, func2, rd, rs1, rs2, rs3
+@verbatim
++-----+-------+-----+-----+-------+----+-------------+
+| rs3 | func2 | rs2 | rs1 | func3 | rd |      opcode |
++-----+-------+-----+-----+-------+----+-------------+
+31    27      25    20    15      12   7             0
+@end verbatim
+
+@item I type: .insn i opcode, func3, rd, rs1, simm12
+@verbatim
++-------------+-----+-------+----+-------------+
+|      simm12 | rs1 | func3 | rd |      opcode |
++-------------+-----+-------+----+-------------+
+31            20    15      12   7             0
+@end verbatim
+
+@item S type: .insn s opcode, func3, rd, rs1, simm12
+@verbatim
++--------------+-----+-----+-------+-------------+-------------+
+| simm12[11:5] | rs2 | rs1 | func3 | simm12[4:0] |      opcode |
++--------------+-----+-----+-------+-------------+-------------+
+31             25    20    15      12            7             0
+@end verbatim
+
+@item SB type: .insn sb opcode, func3, rd, rs1, symbol
+@itemx SB type: .insn sb opcode, func3, rd, simm12(rs1)
+@verbatim
++--------------+-----+-----+-------+-------------+-------------+
+| simm21[11:5] | rs2 | rs1 | func3 | simm12[4:0] |      opcode |
++--------------+-----+-----+-------+-------------+-------------+
+31             25    20    15      12            7             0
+@end verbatim
+
+@item U type: .insn u opcode, rd, simm20
+@verbatim
++---------------------------+----+-------------+
+|                    simm20 | rd |      opcode |
++---------------------------+----+-------------+
+31                          12   7             0
+@end verbatim
+
+@item UJ type: .insn uj opcode, rd, symbol
+@verbatim
++------------+--------------+------------+---------------+----+-------------+
+| simm20[20] | simm20[10:1] | simm20[11] | simm20[19:12] | rd |      opcode |
++------------+--------------+------------+---------------+----+-------------+
+31           30             21           20              12   7             0
+@end verbatim
+
+@item CR type: .insn cr opcode2, func4, rd, rs1
+@verbatim
++---------+--------+-----+---------+
+|   func4 | rd/rs1 | rs2 | opcode2 |
++---------+--------+-----+---------+
+15        12       7     2        0
+@end verbatim
+
+@item CI type: .insn ci opcode2, func3, rd, simm6
+@verbatim
++---------+-----+--------+-----+---------+
+|   func3 | imm | rd/rs1 | imm | opcode2 |
++---------+-----+--------+-----+---------+
+15        13    12       7     2         0
+@end verbatim
+
+@item CIW type: .insn ciw opcode2, func3, rd, uimm8
+@verbatim
++---------+--------------+-----+---------+
+|   func3 |          imm | rd' | opcode2 |
++---------+--------------+-----+---------+
+15        13             7     2         0
+@end verbatim
+
+@item CB type: .insn cb opcode2, func3, rs1, symbol
+@verbatim
++---------+--------+------+--------+---------+
+|   func3 | offset | rs1' | offset | opcode2 |
++---------+--------+------+--------+---------+
+15        13       10     7        2         0
+@end verbatim
+
+@item CJ type: .insn cj opcode2, symbol
+@verbatim
++---------+--------------------+---------+
+|   func3 |        jump target | opcode2 |
++---------+--------------------+---------+
+15        13             7     2         0
+@end verbatim
+
+
+@end table
+
+For the complete list of all instruction format variants see
+The RISC-V Instruction Set Manual Volume I: User-Level ISA.