ARMv8-M Security Extension's cmse_nonsecure_entry: clear registers

    gcc/ChangeLog:
    2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
		Thomas Preud'homme  <thomas.preudhomme@arm.com>

	* config/arm/arm.c (output_return_instruction): Clear
	registers.
	(thumb2_expand_return): Likewise.
	(thumb1_expand_epilogue): Likewise.
	(thumb_exit): Likewise.
	(arm_expand_epilogue): Likewise.
	(cmse_nonsecure_entry_clear_before_return): New.
	(comp_not_to_clear_mask_str_un): New.
	(compute_not_to_clear_mask): New.
	* config/arm/thumb1.md (*epilogue_insns): Change length attribute.
	* config/arm/thumb2.md (*thumb2_return): Disable for
	cmse_nonsecure_entry functions.
	(*thumb2_cmse_entry_return): Duplicate thumb2_return pattern for
	cmse_nonsecure_entry functions.

    gcc/testsuite/ChangeLog:
    2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
		Thomas Preud'homme  <thomas.preudhomme@arm.com>

	* gcc.target/arm/cmse/cmse.exp: Test different multilibs separate.
	* gcc.target/arm/cmse/struct-1.c: New.
	* gcc.target/arm/cmse/bitfield-1.c: New.
	* gcc.target/arm/cmse/bitfield-2.c: New.
	* gcc.target/arm/cmse/bitfield-3.c: New.
	* gcc.target/arm/cmse/baseline/cmse-2.c: New.
	* gcc.target/arm/cmse/baseline/softfp.c: New.
	* gcc.target/arm/cmse/mainline/soft/cmse-5.c: New.
	* gcc.target/arm/cmse/mainline/hard/cmse-5.c: New.
	* gcc.target/arm/cmse/mainline/hard-sp/cmse-5.c: New.
	* gcc.target/arm/cmse/mainline/softfp/cmse-5.c: New.
	* gcc.target/arm/cmse/mainline/softfp-sp/cmse-5.c: New.


Co-Authored-By: Thomas Preud'homme <thomas.preudhomme@arm.com>

From-SVN: r243190

gcc/ChangeLog

 2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
 	    Thomas Preud'homme  <thomas.preudhomme@arm.com>
 
+	* config/arm/arm.c (output_return_instruction): Clear
+	registers.
+	(thumb2_expand_return): Likewise.
+	(thumb1_expand_epilogue): Likewise.
+	(thumb_exit): Likewise.
+	(arm_expand_epilogue): Likewise.
+	(cmse_nonsecure_entry_clear_before_return): New.
+	(comp_not_to_clear_mask_str_un): New.
+	(compute_not_to_clear_mask): New.
+	* config/arm/thumb1.md (*epilogue_insns): Change length attribute.
+	* config/arm/thumb2.md (*thumb2_return): Disable for
+	cmse_nonsecure_entry functions.
+	(*thumb2_cmse_entry_return): Duplicate thumb2_return pattern for
+	cmse_nonsecure_entry functions.
+
+2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
+	    Thomas Preud'homme  <thomas.preudhomme@arm.com>
+
 	* config/arm/arm.c (use_return_insn): Change to return with  bxns
 	when cmse_nonsecure_entry.
 	(output_return_instruction): Likewise.

gcc/config/arm/arm.c

@@ -16297,6 +16297,279 @@ note_invalid_constants (rtx_insn *insn, HOST_WIDE_INT address, int do_pushes)
   return;
 }
 
+/* This function computes the clear mask and PADDING_BITS_TO_CLEAR for structs
+   and unions in the context of ARMv8-M Security Extensions.  It is used as a
+   helper function for both 'cmse_nonsecure_call' and 'cmse_nonsecure_entry'
+   functions.  The PADDING_BITS_TO_CLEAR pointer can be the base to either one
+   or four masks, depending on whether it is being computed for a
+   'cmse_nonsecure_entry' return value or a 'cmse_nonsecure_call' argument
+   respectively.  The tree for the type of the argument or a field within an
+   argument is passed in ARG_TYPE, the current register this argument or field
+   starts in is kept in the pointer REGNO and updated accordingly, the bit this
+   argument or field starts at is passed in STARTING_BIT and the last used bit
+   is kept in LAST_USED_BIT which is also updated accordingly.  */
+
+static unsigned HOST_WIDE_INT
+comp_not_to_clear_mask_str_un (tree arg_type, int * regno,
+			       uint32_t * padding_bits_to_clear,
+			       unsigned starting_bit, int * last_used_bit)
+
+{
+  unsigned HOST_WIDE_INT not_to_clear_reg_mask = 0;
+
+  if (TREE_CODE (arg_type) == RECORD_TYPE)
+    {
+      unsigned current_bit = starting_bit;
+      tree field;
+      long int offset, size;
+
+
+      field = TYPE_FIELDS (arg_type);
+      while (field)
+	{
+	  /* The offset within a structure is always an offset from
+	     the start of that structure.  Make sure we take that into the
+	     calculation of the register based offset that we use here.  */
+	  offset = starting_bit;
+	  offset += TREE_INT_CST_ELT (DECL_FIELD_BIT_OFFSET (field), 0);
+	  offset %= 32;
+
+	  /* This is the actual size of the field, for bitfields this is the
+	     bitfield width and not the container size.  */
+	  size = TREE_INT_CST_ELT (DECL_SIZE (field), 0);
+
+	  if (*last_used_bit != offset)
+	    {
+	      if (offset < *last_used_bit)
+		{
+		  /* This field's offset is before the 'last_used_bit', that
+		     means this field goes on the next register.  So we need to
+		     pad the rest of the current register and increase the
+		     register number.  */
+		  uint32_t mask;
+		  mask  = ((uint32_t)-1) - ((uint32_t) 1 << *last_used_bit);
+		  mask++;
+
+		  padding_bits_to_clear[*regno] |= mask;
+		  not_to_clear_reg_mask |= HOST_WIDE_INT_1U << *regno;
+		  (*regno)++;
+		}
+	      else
+		{
+		  /* Otherwise we pad the bits between the last field's end and
+		     the start of the new field.  */
+		  uint32_t mask;
+
+		  mask = ((uint32_t)-1) >> (32 - offset);
+		  mask -= ((uint32_t) 1 << *last_used_bit) - 1;
+		  padding_bits_to_clear[*regno] |= mask;
+		}
+	      current_bit = offset;
+	    }
+
+	  /* Calculate further padding bits for inner structs/unions too.  */
+	  if (RECORD_OR_UNION_TYPE_P (TREE_TYPE (field)))
+	    {
+	      *last_used_bit = current_bit;
+	      not_to_clear_reg_mask
+		|= comp_not_to_clear_mask_str_un (TREE_TYPE (field), regno,
+						  padding_bits_to_clear, offset,
+						  last_used_bit);
+	    }
+	  else
+	    {
+	      /* Update 'current_bit' with this field's size.  If the
+		 'current_bit' lies in a subsequent register, update 'regno' and
+		 reset 'current_bit' to point to the current bit in that new
+		 register.  */
+	      current_bit += size;
+	      while (current_bit >= 32)
+		{
+		  current_bit-=32;
+		  not_to_clear_reg_mask |= HOST_WIDE_INT_1U << *regno;
+		  (*regno)++;
+		}
+	      *last_used_bit = current_bit;
+	    }
+
+	  field = TREE_CHAIN (field);
+	}
+      not_to_clear_reg_mask |= HOST_WIDE_INT_1U << *regno;
+    }
+  else if (TREE_CODE (arg_type) == UNION_TYPE)
+    {
+      tree field, field_t;
+      int i, regno_t, field_size;
+      int max_reg = -1;
+      int max_bit = -1;
+      uint32_t mask;
+      uint32_t padding_bits_to_clear_res[NUM_ARG_REGS]
+	= {-1, -1, -1, -1};
+
+      /* To compute the padding bits in a union we only consider bits as
+	 padding bits if they are always either a padding bit or fall outside a
+	 fields size for all fields in the union.  */
+      field = TYPE_FIELDS (arg_type);
+      while (field)
+	{
+	  uint32_t padding_bits_to_clear_t[NUM_ARG_REGS]
+	    = {0U, 0U, 0U, 0U};
+	  int last_used_bit_t = *last_used_bit;
+	  regno_t = *regno;
+	  field_t = TREE_TYPE (field);
+
+	  /* If the field's type is either a record or a union make sure to
+	     compute their padding bits too.  */
+	  if (RECORD_OR_UNION_TYPE_P (field_t))
+	    not_to_clear_reg_mask
+	      |= comp_not_to_clear_mask_str_un (field_t, &regno_t,
+						&padding_bits_to_clear_t[0],
+						starting_bit, &last_used_bit_t);
+	  else
+	    {
+	      field_size = TREE_INT_CST_ELT (DECL_SIZE (field), 0);
+	      regno_t = (field_size / 32) + *regno;
+	      last_used_bit_t = (starting_bit + field_size) % 32;
+	    }
+
+	  for (i = *regno; i < regno_t; i++)
+	    {
+	      /* For all but the last register used by this field only keep the
+		 padding bits that were padding bits in this field.  */
+	      padding_bits_to_clear_res[i] &= padding_bits_to_clear_t[i];
+	    }
+
+	    /* For the last register, keep all padding bits that were padding
+	       bits in this field and any padding bits that are still valid
+	       as padding bits but fall outside of this field's size.  */
+	    mask = (((uint32_t) -1) - ((uint32_t) 1 << last_used_bit_t)) + 1;
+	    padding_bits_to_clear_res[regno_t]
+	      &= padding_bits_to_clear_t[regno_t] | mask;
+
+	  /* Update the maximum size of the fields in terms of registers used
+	     ('max_reg') and the 'last_used_bit' in said register.  */
+	  if (max_reg < regno_t)
+	    {
+	      max_reg = regno_t;
+	      max_bit = last_used_bit_t;
+	    }
+	  else if (max_reg == regno_t && max_bit < last_used_bit_t)
+	    max_bit = last_used_bit_t;
+
+	  field = TREE_CHAIN (field);
+	}
+
+      /* Update the current padding_bits_to_clear using the intersection of the
+	 padding bits of all the fields.  */
+      for (i=*regno; i < max_reg; i++)
+	padding_bits_to_clear[i] |= padding_bits_to_clear_res[i];
+
+      /* Do not keep trailing padding bits, we do not know yet whether this
+	 is the end of the argument.  */
+      mask = ((uint32_t) 1 << max_bit) - 1;
+      padding_bits_to_clear[max_reg]
+	|= padding_bits_to_clear_res[max_reg] & mask;
+
+      *regno = max_reg;
+      *last_used_bit = max_bit;
+    }
+  else
+    /* This function should only be used for structs and unions.  */
+    gcc_unreachable ();
+
+  return not_to_clear_reg_mask;
+}
+
+/* In the context of ARMv8-M Security Extensions, this function is used for both
+   'cmse_nonsecure_call' and 'cmse_nonsecure_entry' functions to compute what
+   registers are used when returning or passing arguments, which is then
+   returned as a mask.  It will also compute a mask to indicate padding/unused
+   bits for each of these registers, and passes this through the
+   PADDING_BITS_TO_CLEAR pointer.  The tree of the argument type is passed in
+   ARG_TYPE, the rtl representation of the argument is passed in ARG_RTX and
+   the starting register used to pass this argument or return value is passed
+   in REGNO.  It makes use of 'comp_not_to_clear_mask_str_un' to compute these
+   for struct and union types.  */
+
+static unsigned HOST_WIDE_INT
+compute_not_to_clear_mask (tree arg_type, rtx arg_rtx, int regno,
+			     uint32_t * padding_bits_to_clear)
+
+{
+  int last_used_bit = 0;
+  unsigned HOST_WIDE_INT not_to_clear_mask;
+
+  if (RECORD_OR_UNION_TYPE_P (arg_type))
+    {
+      not_to_clear_mask
+	= comp_not_to_clear_mask_str_un (arg_type, &regno,
+					 padding_bits_to_clear, 0,
+					 &last_used_bit);
+
+
+      /* If the 'last_used_bit' is not zero, that means we are still using a
+	 part of the last 'regno'.  In such cases we must clear the trailing
+	 bits.  Otherwise we are not using regno and we should mark it as to
+	 clear.  */
+      if (last_used_bit != 0)
+	padding_bits_to_clear[regno]
+	  |= ((uint32_t)-1) - ((uint32_t) 1 << last_used_bit) + 1;
+      else
+	not_to_clear_mask &= ~(HOST_WIDE_INT_1U << regno);
+    }
+  else
+    {
+      not_to_clear_mask = 0;
+      /* We are not dealing with structs nor unions.  So these arguments may be
+	 passed in floating point registers too.  In some cases a BLKmode is
+	 used when returning or passing arguments in multiple VFP registers.  */
+      if (GET_MODE (arg_rtx) == BLKmode)
+	{
+	  int i, arg_regs;
+	  rtx reg;
+
+	  /* This should really only occur when dealing with the hard-float
+	     ABI.  */
+	  gcc_assert (TARGET_HARD_FLOAT_ABI);
+
+	  for (i = 0; i < XVECLEN (arg_rtx, 0); i++)
+	    {
+	      reg = XEXP (XVECEXP (arg_rtx, 0, i), 0);
+	      gcc_assert (REG_P (reg));
+
+	      not_to_clear_mask |= HOST_WIDE_INT_1U << REGNO (reg);
+
+	      /* If we are dealing with DF mode, make sure we don't
+		 clear either of the registers it addresses.  */
+	      arg_regs = ARM_NUM_REGS (GET_MODE (reg));
+	      if (arg_regs > 1)
+		{
+		  unsigned HOST_WIDE_INT mask;
+		  mask = HOST_WIDE_INT_1U << (REGNO (reg) + arg_regs);
+		  mask -= HOST_WIDE_INT_1U << REGNO (reg);
+		  not_to_clear_mask |= mask;
+		}
+	    }
+	}
+      else
+	{
+	  /* Otherwise we can rely on the MODE to determine how many registers
+	     are being used by this argument.  */
+	  int arg_regs = ARM_NUM_REGS (GET_MODE (arg_rtx));
+	  not_to_clear_mask |= HOST_WIDE_INT_1U << REGNO (arg_rtx);
+	  if (arg_regs > 1)
+	    {
+	      unsigned HOST_WIDE_INT
+	      mask = HOST_WIDE_INT_1U << (REGNO (arg_rtx) + arg_regs);
+	      mask -= HOST_WIDE_INT_1U << REGNO (arg_rtx);
+	      not_to_clear_mask |= mask;
+	    }
+	}
+    }
+
+  return not_to_clear_mask;
+}
+
 /* Rewrite move insn into subtract of 0 if the condition codes will
    be useful in next conditional jump insn.  */
 
@@ -18720,7 +18993,42 @@ output_return_instruction (rtx operand, bool really_return, bool reverse,
 
 	default:
 	  if (IS_CMSE_ENTRY (func_type))
-	    snprintf (instr, sizeof (instr), "bxns%s\t%%|lr", conditional);
+	    {
+	      /* Check if we have to clear the 'GE bits' which is only used if
+		 parallel add and subtraction instructions are available.  */
+	      if (TARGET_INT_SIMD)
+		snprintf (instr, sizeof (instr),
+			  "msr%s\tAPSR_nzcvqg, %%|lr", conditional);
+	      else
+		snprintf (instr, sizeof (instr),
+			  "msr%s\tAPSR_nzcvq, %%|lr", conditional);
+
+	      output_asm_insn (instr, & operand);
+	      if (TARGET_HARD_FLOAT && !TARGET_THUMB1)
+		{
+		  /* Clear the cumulative exception-status bits (0-4,7) and the
+		     condition code bits (28-31) of the FPSCR.  We need to
+		     remember to clear the first scratch register used (IP) and
+		     save and restore the second (r4).  */
+		  snprintf (instr, sizeof (instr), "push\t{%%|r4}");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "vmrs\t%%|ip, fpscr");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "movw\t%%|r4, #65376");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "movt\t%%|r4, #4095");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "and\t%%|ip, %%|r4");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "vmsr\tfpscr, %%|ip");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "pop\t{%%|r4}");
+		  output_asm_insn (instr, & operand);
+		  snprintf (instr, sizeof (instr), "mov\t%%|ip, %%|lr");
+		  output_asm_insn (instr, & operand);
+		}
+	      snprintf (instr, sizeof (instr), "bxns\t%%|lr");
+	    }
 	  /* Use bx if it's available.  */
 	  else if (arm_arch5 || arm_arch4t)
 	    sprintf (instr, "bx%s\t%%|lr", conditional);
@@ -23027,7 +23335,11 @@ thumb_exit (FILE *f, int reg_containing_return_addr)
 	asm_fprintf (f, "\tadd\t%r, %r\n", SP_REGNUM, ARM_EH_STACKADJ_REGNUM);
 
       if (IS_CMSE_ENTRY (arm_current_func_type ()))
+	{
+	  asm_fprintf (f, "\tmsr\tAPSR_nzcvq, %r\n",
+		       reg_containing_return_addr);
 	  asm_fprintf (f, "\tbxns\t%r\n", reg_containing_return_addr);
+	}
       else
 	asm_fprintf (f, "\tbx\t%r\n", reg_containing_return_addr);
       return;
@@ -23263,7 +23575,18 @@ thumb_exit (FILE *f, int reg_containing_return_addr)
 
   /* Return to caller.  */
   if (IS_CMSE_ENTRY (arm_current_func_type ()))
+    {
+      /* This is for the cases where LR is not being used to contain the return
+         address.  It may therefore contain information that we might not want
+	 to leak, hence it must be cleared.  The value in R0 will never be a
+	 secret at this point, so it is safe to use it, see the clearing code
+	 in 'cmse_nonsecure_entry_clear_before_return'.  */
+      if (reg_containing_return_addr != LR_REGNUM)
+	asm_fprintf (f, "\tmov\tlr, r0\n");
+
+      asm_fprintf (f, "\tmsr\tAPSR_nzcvq, %r\n", reg_containing_return_addr);
       asm_fprintf (f, "\tbxns\t%r\n", reg_containing_return_addr);
+    }
   else
     asm_fprintf (f, "\tbx\t%r\n", reg_containing_return_addr);
 }
@@ -24130,6 +24453,149 @@ thumb1_expand_prologue (void)
     cfun->machine->lr_save_eliminated = 0;
 }
 
+/* Clear caller saved registers not used to pass return values and leaked
+   condition flags before exiting a cmse_nonsecure_entry function.  */
+
+void
+cmse_nonsecure_entry_clear_before_return (void)
+{
+  uint64_t to_clear_mask[2];
+  uint32_t padding_bits_to_clear = 0;
+  uint32_t * padding_bits_to_clear_ptr = &padding_bits_to_clear;
+  int regno, maxregno = IP_REGNUM;
+  tree result_type;
+  rtx result_rtl;
+
+  to_clear_mask[0] = (1ULL << (NUM_ARG_REGS)) - 1;
+  to_clear_mask[0] |= (1ULL << IP_REGNUM);
+
+  /* If we are not dealing with -mfloat-abi=soft we will need to clear VFP
+     registers.  We also check that TARGET_HARD_FLOAT and !TARGET_THUMB1 hold
+     to make sure the instructions used to clear them are present.  */
+  if (TARGET_HARD_FLOAT && !TARGET_THUMB1)
+    {
+      uint64_t float_mask = (1ULL << (D7_VFP_REGNUM + 1)) - 1;
+      maxregno = LAST_VFP_REGNUM;
+
+      float_mask &= ~((1ULL << FIRST_VFP_REGNUM) - 1);
+      to_clear_mask[0] |= float_mask;
+
+      float_mask = (1ULL << (maxregno - 63)) - 1;
+      to_clear_mask[1] = float_mask;
+
+      /* Make sure we don't clear the two scratch registers used to clear the
+	 relevant FPSCR bits in output_return_instruction.  */
+      emit_use (gen_rtx_REG (SImode, IP_REGNUM));
+      to_clear_mask[0] &= ~(1ULL << IP_REGNUM);
+      emit_use (gen_rtx_REG (SImode, 4));
+      to_clear_mask[0] &= ~(1ULL << 4);
+    }
+
+  /* If the user has defined registers to be caller saved, these are no longer
+     restored by the function before returning and must thus be cleared for
+     security purposes.  */
+  for (regno = NUM_ARG_REGS; regno < LAST_VFP_REGNUM; regno++)
+    {
+      /* We do not touch registers that can be used to pass arguments as per
+	 the AAPCS, since these should never be made callee-saved by user
+	 options.  */
+      if (IN_RANGE (regno, FIRST_VFP_REGNUM, D7_VFP_REGNUM))
+	continue;
+      if (IN_RANGE (regno, IP_REGNUM, PC_REGNUM))
+	continue;
+      if (call_used_regs[regno])
+	to_clear_mask[regno / 64] |= (1ULL << (regno % 64));
+    }
+
+  /* Make sure we do not clear the registers used to return the result in.  */
+  result_type = TREE_TYPE (DECL_RESULT (current_function_decl));
+  if (!VOID_TYPE_P (result_type))
+    {
+      result_rtl = arm_function_value (result_type, current_function_decl, 0);
+
+      /* No need to check that we return in registers, because we don't
+	 support returning on stack yet.  */
+      to_clear_mask[0]
+	&= ~compute_not_to_clear_mask (result_type, result_rtl, 0,
+				       padding_bits_to_clear_ptr);
+    }
+
+  if (padding_bits_to_clear != 0)
+    {
+      rtx reg_rtx;
+      /* Padding bits to clear is not 0 so we know we are dealing with
+	 returning a composite type, which only uses r0.  Let's make sure that
+	 r1-r3 is cleared too, we will use r1 as a scratch register.  */
+      gcc_assert ((to_clear_mask[0] & 0xe) == 0xe);
+
+      reg_rtx = gen_rtx_REG (SImode, R1_REGNUM);
+
+      /* Fill the lower half of the negated padding_bits_to_clear.  */
+      emit_move_insn (reg_rtx,
+		      GEN_INT ((((~padding_bits_to_clear) << 16u) >> 16u)));
+
+      /* Also fill the top half of the negated padding_bits_to_clear.  */
+      if (((~padding_bits_to_clear) >> 16) > 0)
+	emit_insn (gen_rtx_SET (gen_rtx_ZERO_EXTRACT (SImode, reg_rtx,
+						      GEN_INT (16),
+						      GEN_INT (16)),
+				GEN_INT ((~padding_bits_to_clear) >> 16)));
+
+      emit_insn (gen_andsi3 (gen_rtx_REG (SImode, R0_REGNUM),
+			   gen_rtx_REG (SImode, R0_REGNUM),
+			   reg_rtx));
+    }
+
+  for (regno = R0_REGNUM; regno <= maxregno; regno++)
+    {
+      if (!(to_clear_mask[regno / 64] & (1ULL << (regno % 64))))
+	continue;
+
+      if (IS_VFP_REGNUM (regno))
+	{
+	  /* If regno is an even vfp register and its successor is also to
+	     be cleared, use vmov.  */
+	  if (TARGET_VFP_DOUBLE
+	      && VFP_REGNO_OK_FOR_DOUBLE (regno)
+	      && to_clear_mask[regno / 64] & (1ULL << ((regno % 64) + 1)))
+	    {
+	      emit_move_insn (gen_rtx_REG (DFmode, regno),
+			      CONST1_RTX (DFmode));
+	      emit_use (gen_rtx_REG (DFmode, regno));
+	      regno++;
+	    }
+	  else
+	    {
+	      emit_move_insn (gen_rtx_REG (SFmode, regno),
+			      CONST1_RTX (SFmode));
+	      emit_use (gen_rtx_REG (SFmode, regno));
+	    }
+	}
+      else
+	{
+	  if (TARGET_THUMB1)
+	    {
+	      if (regno == R0_REGNUM)
+		emit_move_insn (gen_rtx_REG (SImode, regno),
+				const0_rtx);
+	      else
+		/* R0 has either been cleared before, see code above, or it
+		   holds a return value, either way it is not secret
+		   information.  */
+		emit_move_insn (gen_rtx_REG (SImode, regno),
+				gen_rtx_REG (SImode, R0_REGNUM));
+	      emit_use (gen_rtx_REG (SImode, regno));
+	    }
+	  else
+	    {
+	      emit_move_insn (gen_rtx_REG (SImode, regno),
+			      gen_rtx_REG (SImode, LR_REGNUM));
+	      emit_use (gen_rtx_REG (SImode, regno));
+	    }
+	}
+    }
+}
+
 /* Generate pattern *pop_multiple_with_stack_update_and_return if single
    POP instruction can be generated.  LR should be replaced by PC.  All
    the checks required are already done by  USE_RETURN_INSN ().  Hence,
@@ -24179,6 +24645,8 @@ thumb2_expand_return (bool simple_return)
     }
   else
     {
+      if (IS_CMSE_ENTRY (arm_current_func_type ()))
+	cmse_nonsecure_entry_clear_before_return ();
       emit_jump_insn (simple_return_rtx);
     }
 }
@@ -24237,6 +24705,10 @@ thumb1_expand_epilogue (void)
 
   if (! df_regs_ever_live_p (LR_REGNUM))
     emit_use (gen_rtx_REG (SImode, LR_REGNUM));
+
+  /* Clear all caller-saved regs that are not used to return.  */
+  if (IS_CMSE_ENTRY (arm_current_func_type ()))
+    cmse_nonsecure_entry_clear_before_return ();
 }
 
 /* Epilogue code for APCS frame.  */
@@ -24671,6 +25143,14 @@ arm_expand_epilogue (bool really_return)
 				   stack_pointer_rtx, stack_pointer_rtx);
     }
 
+    /* Clear all caller-saved regs that are not used to return.  */
+    if (IS_CMSE_ENTRY (arm_current_func_type ()))
+      {
+	/* CMSE_ENTRY always returns.  */
+	gcc_assert (really_return);
+	cmse_nonsecure_entry_clear_before_return ();
+      }
+
   if (!really_return)
     return;
 

gcc/config/arm/thumb1.md

@@ -1869,8 +1869,13 @@
   "*
     return thumb1_unexpanded_epilogue ();
   "
-  ; Length is absolute worst case
-  [(set_attr "length" "44")
+  ; Length is absolute worst case, when using CMSE and if this is an entry
+  ; function an extra 4 (MSR) bytes will be added.
+  [(set (attr "length")
+	(if_then_else
+	 (match_test "IS_CMSE_ENTRY (arm_current_func_type ())")
+	 (const_int 48)
+	 (const_int 44)))
    (set_attr "type" "block")
    ;; We don't clobber the conditions, but the potential length of this
    ;; operation is sufficient to make conditionalizing the sequence

gcc/config/arm/thumb2.md

@@ -1114,12 +1114,31 @@
 
 (define_insn "*thumb2_return"
   [(simple_return)]
-  "TARGET_THUMB2"
+  "TARGET_THUMB2 && !IS_CMSE_ENTRY (arm_current_func_type ())"
   "* return output_return_instruction (const_true_rtx, true, false, true);"
   [(set_attr "type" "branch")
    (set_attr "length" "4")]
 )
 
+(define_insn "*thumb2_cmse_entry_return"
+  [(simple_return)]
+  "TARGET_THUMB2 && IS_CMSE_ENTRY (arm_current_func_type ())"
+  "* return output_return_instruction (const_true_rtx, true, false, true);"
+  [(set_attr "type" "branch")
+   ; This is a return from a cmse_nonsecure_entry function so code will be
+   ; added to clear the APSR and potentially the FPSCR if VFP is available, so
+   ; we adapt the length accordingly.
+   (set (attr "length")
+     (if_then_else (match_test "TARGET_HARD_FLOAT")
+      (const_int 12)
+      (const_int 8)))
+   ; We do not support predicate execution of returns from cmse_nonsecure_entry
+   ; functions because we need to clear the APSR.  Since predicable has to be
+   ; a constant, we had to duplicate the thumb2_return pattern for CMSE entry
+   ; functions.
+   (set_attr "predicable" "no")]
+)
+
 (define_insn_and_split "thumb2_eh_return"
   [(unspec_volatile [(match_operand:SI 0 "s_register_operand" "r")]
 		    VUNSPEC_EH_RETURN)

gcc/testsuite/ChangeLog

 2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
 	    Thomas Preud'homme  <thomas.preudhomme@arm.com>
 
+	* gcc.target/arm/cmse/cmse.exp: Test different multilibs separate.
+	* gcc.target/arm/cmse/struct-1.c: New.
+	* gcc.target/arm/cmse/bitfield-1.c: New.
+	* gcc.target/arm/cmse/bitfield-2.c: New.
+	* gcc.target/arm/cmse/bitfield-3.c: New.
+	* gcc.target/arm/cmse/baseline/cmse-2.c: New.
+	* gcc.target/arm/cmse/baseline/softfp.c: New.
+	* gcc.target/arm/cmse/mainline/soft/cmse-5.c: New.
+	* gcc.target/arm/cmse/mainline/hard/cmse-5.c: New.
+	* gcc.target/arm/cmse/mainline/hard-sp/cmse-5.c: New.
+	* gcc.target/arm/cmse/mainline/softfp/cmse-5.c: New.
+	* gcc.target/arm/cmse/mainline/softfp-sp/cmse-5.c: New.
+
+2016-12-02  Andre Vieira  <andre.simoesdiasvieira@arm.com>
+	    Thomas Preud'homme  <thomas.preudhomme@arm.com>
+
 	* gcc.target/arm/cmse/cmse-4.c: New.
 	* gcc.target/arm/cmse/cmse-9.c: New.
 	* gcc.target/arm/cmse/cmse-10.c: New.

gcc/testsuite/gcc.target/arm/cmse/baseline/cmse-2.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_base_ok } */
+/* { dg-add-options arm_arch_v8m_base } */
+/* { dg-options "-mcmse" }  */
+
+extern float bar (void);
+
+float __attribute__ ((cmse_nonsecure_entry))
+foo (void)
+{
+  return bar ();
+}
+/* { dg-final { scan-assembler "movs\tr1, r0" } } */
+/* { dg-final { scan-assembler "movs\tr2, r0" } } */
+/* { dg-final { scan-assembler "movs\tr3, r0" } } */
+/* { dg-final { scan-assembler "mov\tip, r0" } } */
+/* { dg-final { scan-assembler "mov\tlr, r0" } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvq," } } */
+/* { dg-final { scan-assembler "bxns" } } */

gcc/testsuite/gcc.target/arm/cmse/baseline/softfp.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_base_ok } */
+/* { dg-add-options arm_arch_v8m_base } */
+/* { dg-options "-mcmse -mfloat-abi=softfp" } */
+
+double __attribute__ ((cmse_nonsecure_call)) (*bar) (float, double);
+
+double
+foo (double a)
+{
+  return bar (1.0f, 2.0) + a;
+}
+
+float __attribute__ ((cmse_nonsecure_entry))
+baz (float a, double b)
+{
+  return (float) bar (a, b);
+}
+
+/* Make sure we are not using FP instructions, since ARMv8-M Baseline does not
+   support such instructions.  */
+/* { dg-final { scan-assembler-not "vmov" } } */
+/* { dg-final { scan-assembler-not "vmsr" } } */
+/* { dg-final { scan-assembler-not "vmrs" } } */
+
+/* Just double checking that we are still doing cmse though.  */
+/* { dg-final { scan-assembler-not "vmrs" } } */
+/* { dg-final { scan-assembler "bl\t__gnu_cmse_nonsecure_call" } } */
+

gcc/testsuite/gcc.target/arm/cmse/bitfield-1.c

+/* { dg-do run } */
+/* { dg-options "--save-temps -mcmse -Wl,--section-start,.gnu.sgstubs=0x20400000" } */
+
+typedef struct
+{
+  unsigned short  a : 6;
+  unsigned char	  b : 3;
+  unsigned char	  c;
+  unsigned short  d : 8;
+} test_st;
+
+test_st __attribute__ ((cmse_nonsecure_entry)) foo (void)
+{
+  test_st t;
+  t.a = 63u;
+  t.b = 7u;
+  t.c = 255u;
+  t.d = 255u;
+  return t;
+}
+
+int
+main (void)
+{
+  test_st t;
+  t = foo ();
+  if (t.a != 63u
+      || t.b != 7u
+      || t.c != 255u
+      || t.d != 255u)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-assembler "movw\tr1, #1855" } } */
+/* { dg-final { scan-assembler "movt\tr1, 65535" } } */
+/* { dg-final { scan-assembler "ands\tr0(, r0)?, r1" } } */
+/* { dg-final { scan-assembler "bxns" } } */
+

gcc/testsuite/gcc.target/arm/cmse/bitfield-2.c

+/* { dg-do run } */
+/* { dg-options "--save-temps -mcmse -Wl,--section-start,.gnu.sgstubs=0x20400000" } */
+
+typedef struct
+{
+  short	      a : 7;
+  signed char b : 3;
+  short	      c : 11;
+} test_st;
+
+test_st __attribute__ ((cmse_nonsecure_entry)) foo (void)
+{
+  test_st t;
+  t.a = -64;
+  t.b = -4 ;
+  t.c = -1024;
+  return t;
+}
+
+int
+main (void)
+{
+  test_st t;
+  t = foo ();
+  if (t.a != -64
+      || t.b != -4
+      || t.c != -1024)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-assembler "movw\tr1, #1919" } } */
+/* { dg-final { scan-assembler "movt\tr1, 2047" } } */
+/* { dg-final { scan-assembler "ands\tr0(, r0)?, r1" } } */
+/* { dg-final { scan-assembler "bxns" } } */
+

gcc/testsuite/gcc.target/arm/cmse/bitfield-3.c

+/* { dg-do run } */
+/* { dg-options "--save-temps -mcmse -Wl,--section-start,.gnu.sgstubs=0x20400000" } */
+
+typedef struct
+{
+  short	      a;
+  signed char b : 2;
+  short		: 1;
+  signed char c : 3;
+} test_st;
+
+test_st __attribute__ ((cmse_nonsecure_entry)) foo (void)
+{
+  test_st t;
+  t.a = -32768;
+  t.b = -2;
+  t.c = -4;
+  return t;
+}
+
+int
+main (void)
+{
+  test_st t;
+  t = foo ();
+  if (t.a != -32768
+      || t.b != -2
+      || t.c != -4)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-assembler "movw\tr1, #65535" } } */
+/* { dg-final { scan-assembler "movt\tr1, 63" } } */
+/* { dg-final { scan-assembler "ands\tr0(, r0)?, r1" } } */
+/* { dg-final { scan-assembler "bxns" } } */
+

gcc/testsuite/gcc.target/arm/cmse/cmse.exp

@@ -43,6 +43,26 @@ set LTO_TORTURE_OPTIONS ""
 gcc-dg-runtest [lsort [glob $srcdir/$subdir/*.c]] \
 	"" $DEFAULT_CFLAGS
 
+if {[check_effective_target_arm_arch_v8m_base_ok]} then {
+    # Baseline only
+    gcc-dg-runtest [lsort [glob $srcdir/$subdir/baseline/*.c]] \
+	    "" $DEFAULT_CFLAGS
+}
+
+if {[check_effective_target_arm_arch_v8m_main_ok]} then {
+    # Mainline -mfloat-abi=soft
+    gcc-dg-runtest [lsort [glob $srcdir/$subdir/mainline/soft/*.c]] \
+	    "-mfloat-abi=soft" $DEFAULT_CFLAGS
+    gcc-dg-runtest [lsort [glob $srcdir/$subdir/mainline/softfp/*.c]] \
+	    "" $DEFAULT_CFLAGS
+    gcc-dg-runtest [lsort [glob $srcdir/$subdir/mainline/softfp-sp/*.c]] \
+	    "" $DEFAULT_CFLAGS
+    gcc-dg-runtest [lsort [glob $srcdir/$subdir/mainline/hard/*.c]] \
+	    "" $DEFAULT_CFLAGS
+    gcc-dg-runtest [lsort [glob $srcdir/$subdir/mainline/hard-sp/*.c]] \
+	    "" $DEFAULT_CFLAGS
+}
+
 set LTO_TORTURE_OPTIONS ${saved-lto_torture_options}
 set dg-do-what-default ${saved-dg-do-what-default}
 

gcc/testsuite/gcc.target/arm/cmse/mainline/hard-sp/cmse-5.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_main_ok } */
+/* { dg-add-options arm_arch_v8m_main } */
+/* { dg-skip-if "Do not combine float-abi= hard | soft | softfp" {*-*-*} {"-mfloat-abi=soft" -mfloat-abi=softfp } {""} } */
+/* { dg-skip-if "Skip these if testing double precision" {*-*-*} {"-mfpu=fpv[4-5]-d16"} {""} } */
+/* { dg-options "-mcmse -mfloat-abi=hard -mfpu=fpv5-sp-d16" }  */
+
+extern float bar (void);
+
+float __attribute__ ((cmse_nonsecure_entry))
+foo (void)
+{
+  return bar ();
+}
+/* { dg-final { scan-assembler "mov\tr0, lr" } } */
+/* { dg-final { scan-assembler "mov\tr1, lr" } } */
+/* { dg-final { scan-assembler "mov\tr2, lr" } } */
+/* { dg-final { scan-assembler "mov\tr3, lr" } } */
+/* { dg-final { scan-assembler-not "vmov\.f32\ts0, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts1, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts2, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts3, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts4, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts5, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts6, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts7, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts8, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts9, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts10, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts11, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts12, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts13, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts14, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts15, #1\.0" } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvq, lr" { target { arm_arch_v8m_main_ok && { ! arm_dsp } } } } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvqg, lr" { target { arm_arch_v8m_main_ok && arm_dsp } } } } */
+/* { dg-final { scan-assembler "push\t{r4}" } } */
+/* { dg-final { scan-assembler "vmrs\tip, fpscr" } } */
+/* { dg-final { scan-assembler "movw\tr4, #65376" } } */
+/* { dg-final { scan-assembler "movt\tr4, #4095" } } */
+/* { dg-final { scan-assembler "and\tip, r4" } } */
+/* { dg-final { scan-assembler "vmsr\tfpscr, ip" } } */
+/* { dg-final { scan-assembler "pop\t{r4}" } } */
+/* { dg-final { scan-assembler "mov\tip, lr" } } */
+/* { dg-final { scan-assembler "bxns" } } */

gcc/testsuite/gcc.target/arm/cmse/mainline/hard/cmse-5.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_main_ok } */
+/* { dg-add-options arm_arch_v8m_main } */
+/* { dg-skip-if "Do not combine float-abi= hard | soft | softfp" {*-*-*} {"-mfloat-abi=soft" -mfloat-abi=softfp } {""} } */
+/* { dg-skip-if "Skip these if testing single precision" {*-*-*} {"-mfpu=*-sp-*"} {""} } */
+/* { dg-options "-mcmse -mfloat-abi=hard -mfpu=fpv5-d16" }  */
+
+extern float bar (void);
+
+float __attribute__ ((cmse_nonsecure_entry))
+foo (void)
+{
+  return bar ();
+}
+/* { dg-final { scan-assembler "mov\tr0, lr" } } */
+/* { dg-final { scan-assembler "mov\tr1, lr" } } */
+/* { dg-final { scan-assembler "mov\tr2, lr" } } */
+/* { dg-final { scan-assembler "mov\tr3, lr" } } */
+/* { dg-final { scan-assembler-not "vmov\.f32\ts0, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts1, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td1, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td2, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td3, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td4, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td5, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td6, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td7, #1\.0" } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvq, lr" { target { arm_arch_v8m_main_ok && { ! arm_dsp } } } } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvqg, lr" { target { arm_arch_v8m_main_ok && arm_dsp } } } } */
+/* { dg-final { scan-assembler "push\t{r4}" } } */
+/* { dg-final { scan-assembler "vmrs\tip, fpscr" } } */
+/* { dg-final { scan-assembler "movw\tr4, #65376" } } */
+/* { dg-final { scan-assembler "movt\tr4, #4095" } } */
+/* { dg-final { scan-assembler "and\tip, r4" } } */
+/* { dg-final { scan-assembler "vmsr\tfpscr, ip" } } */
+/* { dg-final { scan-assembler "pop\t{r4}" } } */
+/* { dg-final { scan-assembler "mov\tip, lr" } } */
+/* { dg-final { scan-assembler "bxns" } } */

gcc/testsuite/gcc.target/arm/cmse/mainline/soft/cmse-5.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_main_ok } */
+/* { dg-add-options arm_arch_v8m_main } */
+/* { dg-skip-if "Do not combine float-abi= hard | soft | softfp" {*-*-*} {"-mfloat-abi=hard" -mfloat-abi=softfp } {""} } */
+/* { dg-options "-mcmse -mfloat-abi=soft" }  */
+
+extern float bar (void);
+
+float __attribute__ ((cmse_nonsecure_entry))
+foo (void)
+{
+  return bar ();
+}
+
+/* { dg-final { scan-assembler "mov\tr1, lr" } } */
+/* { dg-final { scan-assembler "mov\tr2, lr" } } */
+/* { dg-final { scan-assembler "mov\tr3, lr" } } */
+/* { dg-final { scan-assembler "mov\tip, lr" } } */
+/* { dg-final { scan-assembler-not "vmov" } } */
+/* { dg-final { scan-assembler-not "vmsr" } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvq, lr" { target { arm_arch_v8m_main_ok && { ! arm_dsp } } } } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvqg, lr" { target { arm_arch_v8m_main_ok && arm_dsp } } } } */
+/* { dg-final { scan-assembler "bxns" } } */
+

gcc/testsuite/gcc.target/arm/cmse/mainline/softfp-sp/cmse-5.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_main_ok } */
+/* { dg-add-options arm_arch_v8m_main } */
+/* { dg-skip-if "Do not combine float-abi= hard | soft | softfp" {*-*-*} {"-mfloat-abi=soft" -mfloat-abi=hard } {""} } */
+/* { dg-skip-if "Skip these if testing double precision" {*-*-*} {"-mfpu=fpv[4-5]-d16"} {""} } */
+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-sp-d16" }  */
+
+extern float bar (void);
+
+float __attribute__ ((cmse_nonsecure_entry))
+foo (void)
+{
+  return bar ();
+}
+/* { dg-final { scan-assembler "__acle_se_foo:" } } */
+/* { dg-final { scan-assembler-not "mov\tr0, lr" } } */
+/* { dg-final { scan-assembler "mov\tr1, lr" } } */
+/* { dg-final { scan-assembler "mov\tr2, lr" } } */
+/* { dg-final { scan-assembler "mov\tr3, lr" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts0, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts1, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts2, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts3, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts4, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts5, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts6, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts7, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts8, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts9, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts10, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts11, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts12, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts13, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts14, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f32\ts15, #1\.0" } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvq, lr" { target { arm_arch_v8m_main_ok && { ! arm_dsp } } } } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvqg, lr" { target { arm_arch_v8m_main_ok && arm_dsp } } } } */
+/* { dg-final { scan-assembler "push\t{r4}" } } */
+/* { dg-final { scan-assembler "vmrs\tip, fpscr" } } */
+/* { dg-final { scan-assembler "movw\tr4, #65376" } } */
+/* { dg-final { scan-assembler "movt\tr4, #4095" } } */
+/* { dg-final { scan-assembler "and\tip, r4" } } */
+/* { dg-final { scan-assembler "vmsr\tfpscr, ip" } } */
+/* { dg-final { scan-assembler "pop\t{r4}" } } */
+/* { dg-final { scan-assembler "mov\tip, lr" } } */
+/* { dg-final { scan-assembler "bxns" } } */

gcc/testsuite/gcc.target/arm/cmse/mainline/softfp/cmse-5.c

+/* { dg-do compile } */
+/* { dg-require-effective-target arm_arch_v8m_main_ok } */
+/* { dg-add-options arm_arch_v8m_main } */
+/* { dg-skip-if "Do not combine float-abi= hard | soft | softfp" {*-*-*} {"-mfloat-abi=soft" -mfloat-abi=hard } {""} } */
+/* { dg-skip-if "Skip these if testing single precision" {*-*-*} {"-mfpu=*-sp-*"} {""} } */
+/* { dg-options "-mcmse -mfloat-abi=softfp -mfpu=fpv5-d16" }  */
+
+extern float bar (void);
+
+float __attribute__ ((cmse_nonsecure_entry))
+foo (void)
+{
+  return bar ();
+}
+/* { dg-final { scan-assembler "__acle_se_foo:" } } */
+/* { dg-final { scan-assembler-not "mov\tr0, lr" } } */
+/* { dg-final { scan-assembler "mov\tr1, lr" } } */
+/* { dg-final { scan-assembler "mov\tr2, lr" } } */
+/* { dg-final { scan-assembler "mov\tr3, lr" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td0, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td1, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td2, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td3, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td4, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td5, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td6, #1\.0" } } */
+/* { dg-final { scan-assembler "vmov\.f64\td7, #1\.0" } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvq, lr" { target { arm_arch_v8m_main_ok && { ! arm_dsp } } } } } */
+/* { dg-final { scan-assembler "msr\tAPSR_nzcvqg, lr" { target { arm_arch_v8m_main_ok && arm_dsp } } } } */
+/* { dg-final { scan-assembler "push\t{r4}" } } */
+/* { dg-final { scan-assembler "vmrs\tip, fpscr" } } */
+/* { dg-final { scan-assembler "movw\tr4, #65376" } } */
+/* { dg-final { scan-assembler "movt\tr4, #4095" } } */
+/* { dg-final { scan-assembler "and\tip, r4" } } */
+/* { dg-final { scan-assembler "vmsr\tfpscr, ip" } } */
+/* { dg-final { scan-assembler "pop\t{r4}" } } */
+/* { dg-final { scan-assembler "mov\tip, lr" } } */
+/* { dg-final { scan-assembler "bxns" } } */

gcc/testsuite/gcc.target/arm/cmse/struct-1.c

+/* { dg-do run } */
+/* { dg-options "--save-temps -mcmse -Wl,--section-start,.gnu.sgstubs=0x20400000" } */
+
+typedef struct
+{
+  unsigned char	  a;
+  unsigned short  b;
+} test_st;
+
+test_st __attribute__ ((cmse_nonsecure_entry)) foo (void)
+{
+  test_st t;
+  t.a = 255u;
+  t.b = 32767u;
+  return t;
+}
+
+int
+main (void)
+{
+  test_st t;
+  t = foo ();
+  if (t.a != 255u || t.b != 32767u)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-assembler "movs\tr1, #255" } } */
+/* { dg-final { scan-assembler "movt\tr1, 65535" } } */
+/* { dg-final { scan-assembler "ands\tr0(, r0)?, r1" } } */
+/* { dg-final { scan-assembler "bxns" } } */
+
+