source: rtems/cpukit/score/cpu/sh/rtems/score/cpu.h @ 8e407ad

/**
 * @file rtems/score/cpu.h
 */

/*
 *  This include file contains information pertaining to the Hitachi SH
 *  processor.
 *
 *  Authors: Ralf Corsepius (corsepiu@faw.uni-ulm.de) and
 *           Bernd Becker (becker@faw.uni-ulm.de)
 *
 *  COPYRIGHT (c) 1997-1998, FAW Ulm, Germany
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 *
 *
 *  COPYRIGHT (c) 1998-2006.
 *  On-Line Applications Research Corporation (OAR).
 *
 *  The license and distribution terms for this file may be
 *  found in the file LICENSE in this distribution or at
 *  http://www.rtems.com/license/LICENSE.
 *
 *  $Id$
 */

#ifndef _RTEMS_SCORE_CPU_H
#define _RTEMS_SCORE_CPU_H

#ifdef __cplusplus
extern "C" {
#endif

#include <rtems/score/sh.h>              /* pick up machine definitions */
#ifndef ASM
#include <rtems/score/types.h>
#endif
#if 0 && defined(__SH4__)
#include <rtems/score/sh4_regs.h>
#endif

/* conditional compilation parameters */

/*
 *  Should the calls to _Thread_Enable_dispatch be inlined?
 *
 *  If TRUE, then they are inlined.
 *  If FALSE, then a subroutine call is made.
 *
 *  Basically this is an example of the classic trade-off of size
 *  versus speed.  Inlining the call (TRUE) typically increases the
 *  size of RTEMS while speeding up the enabling of dispatching.
 *  [NOTE: In general, the _Thread_Dispatch_disable_level will
 *  only be 0 or 1 unless you are in an interrupt handler and that
 *  interrupt handler invokes the executive.]  When not inlined
 *  something calls _Thread_Enable_dispatch which in turns calls
 *  _Thread_Dispatch.  If the enable dispatch is inlined, then
 *  one subroutine call is avoided entirely.]
 */

#define CPU_INLINE_ENABLE_DISPATCH       FALSE

/*
 *  Should the body of the search loops in _Thread_queue_Enqueue_priority
 *  be unrolled one time?  In unrolled each iteration of the loop examines
 *  two "nodes" on the chain being searched.  Otherwise, only one node
 *  is examined per iteration.
 *
 *  If TRUE, then the loops are unrolled.
 *  If FALSE, then the loops are not unrolled.
 *
 *  The primary factor in making this decision is the cost of disabling
 *  and enabling interrupts (_ISR_Flash) versus the cost of rest of the
 *  body of the loop.  On some CPUs, the flash is more expensive than
 *  one iteration of the loop body.  In this case, it might be desirable
 *  to unroll the loop.  It is important to note that on some CPUs, this
 *  code is the longest interrupt disable period in RTEMS.  So it is
 *  necessary to strike a balance when setting this parameter.
 */

#define CPU_UNROLL_ENQUEUE_PRIORITY      TRUE

/*
 *  Does the CPU follow the simple vectored interrupt model?
 *
 *  If TRUE, then RTEMS allocates the vector table it internally manages.
 *  If FALSE, then the BSP is assumed to allocate and manage the vector
 *  table
 *
 *  SH Specific Information:
 *
 *  XXX document implementation including references if appropriate
 */
#define CPU_SIMPLE_VECTORED_INTERRUPTS TRUE

/*
 *  Does RTEMS manage a dedicated interrupt stack in software?
 *
 *  If TRUE, then a stack is allocated in _ISR_Handler_initialization.
 *  If FALSE, nothing is done.
 *
 *  If the CPU supports a dedicated interrupt stack in hardware,
 *  then it is generally the responsibility of the BSP to allocate it
 *  and set it up.
 *
 *  If the CPU does not support a dedicated interrupt stack, then
 *  the porter has two options: (1) execute interrupts on the
 *  stack of the interrupted task, and (2) have RTEMS manage a dedicated
 *  interrupt stack.
 *
 *  If this is TRUE, CPU_ALLOCATE_INTERRUPT_STACK should also be TRUE.
 *
 *  Only one of CPU_HAS_SOFTWARE_INTERRUPT_STACK and
 *  CPU_HAS_HARDWARE_INTERRUPT_STACK should be set to TRUE.  It is
 *  possible that both are FALSE for a particular CPU.  Although it
 *  is unclear what that would imply about the interrupt processing
 *  procedure on that CPU.
 */

#define CPU_HAS_SOFTWARE_INTERRUPT_STACK TRUE
#define CPU_HAS_HARDWARE_INTERRUPT_STACK FALSE

/*
 * We define the interrupt stack in the linker script
 */
#define CPU_ALLOCATE_INTERRUPT_STACK FALSE

/*
 *  Does the RTEMS invoke the user's ISR with the vector number and
 *  a pointer to the saved interrupt frame (1) or just the vector
 *  number (0)?
 */

#define CPU_ISR_PASSES_FRAME_POINTER 0

/*
 *  Does the CPU have hardware floating point?
 *
 *  If TRUE, then the RTEMS_FLOATING_POINT task attribute is supported.
 *  If FALSE, then the RTEMS_FLOATING_POINT task attribute is ignored.
 *
 *  We currently support sh1 only, which has no FPU, other SHes have an FPU
 *
 *  The macro name "SH_HAS_FPU" should be made CPU specific.
 *  It indicates whether or not this CPU model has FP support.  For
 *  example, it would be possible to have an i386_nofp CPU model
 *  which set this to false to indicate that you have an i386 without
 *  an i387 and wish to leave floating point support out of RTEMS.
 */

#if SH_HAS_FPU
#define CPU_HARDWARE_FP TRUE
#define CPU_SOFTWARE_FP FALSE
#else
#define CPU_SOFTWARE_FP FALSE
#define CPU_HARDWARE_FP FALSE
#endif

/*
 *  Are all tasks RTEMS_FLOATING_POINT tasks implicitly?
 *
 *  If TRUE, then the RTEMS_FLOATING_POINT task attribute is assumed.
 *  If FALSE, then the RTEMS_FLOATING_POINT task attribute is followed.
 *
 *  If CPU_HARDWARE_FP is FALSE, then this should be FALSE as well.
 */

#if SH_HAS_FPU
#define CPU_ALL_TASKS_ARE_FP     TRUE
#else
#define CPU_ALL_TASKS_ARE_FP     FALSE
#endif

/*
 *  Should the IDLE task have a floating point context?
 *
 *  If TRUE, then the IDLE task is created as a RTEMS_FLOATING_POINT task
 *  and it has a floating point context which is switched in and out.
 *  If FALSE, then the IDLE task does not have a floating point context.
 *
 *  Setting this to TRUE negatively impacts the time required to preempt
 *  the IDLE task from an interrupt because the floating point context
 *  must be saved as part of the preemption.
 */

#if SH_HAS_FPU
#define CPU_IDLE_TASK_IS_FP     TRUE
#else
#define CPU_IDLE_TASK_IS_FP      FALSE
#endif

/*
 *  Should the saving of the floating point registers be deferred
 *  until a context switch is made to another different floating point
 *  task?
 *
 *  If TRUE, then the floating point context will not be stored until
 *  necessary.  It will remain in the floating point registers and not
 *  disturned until another floating point task is switched to.
 *
 *  If FALSE, then the floating point context is saved when a floating
 *  point task is switched out and restored when the next floating point
 *  task is restored.  The state of the floating point registers between
 *  those two operations is not specified.
 *
 *  If the floating point context does NOT have to be saved as part of
 *  interrupt dispatching, then it should be safe to set this to TRUE.
 *
 *  Setting this flag to TRUE results in using a different algorithm
 *  for deciding when to save and restore the floating point context.
 *  The deferred FP switch algorithm minimizes the number of times
 *  the FP context is saved and restored.  The FP context is not saved
 *  until a context switch is made to another, different FP task.
 *  Thus in a system with only one FP task, the FP context will never
 *  be saved or restored.
 */

#if SH_HAS_FPU
#define CPU_USE_DEFERRED_FP_SWITCH      FALSE
#else
#define CPU_USE_DEFERRED_FP_SWITCH      TRUE
#endif

/*
 *  Does this port provide a CPU dependent IDLE task implementation?
 *
 *  If TRUE, then the routine _CPU_Thread_Idle_body
 *  must be provided and is the default IDLE thread body instead of
 *  _CPU_Thread_Idle_body.
 *
 *  If FALSE, then use the generic IDLE thread body if the BSP does
 *  not provide one.
 *
 *  This is intended to allow for supporting processors which have
 *  a low power or idle mode.  When the IDLE thread is executed, then
 *  the CPU can be powered down.
 *
 *  The order of precedence for selecting the IDLE thread body is:
 *
 *    1.  BSP provided
 *    2.  CPU dependent (if provided)
 *    3.  generic (if no BSP and no CPU dependent)
 */

#define CPU_PROVIDES_IDLE_THREAD_BODY    TRUE

/*
 *  Does the stack grow up (toward higher addresses) or down
 *  (toward lower addresses)?
 *
 *  If TRUE, then the grows upward.
 *  If FALSE, then the grows toward smaller addresses.
 */

#define CPU_STACK_GROWS_UP               FALSE

/*
 *  The following is the variable attribute used to force alignment
 *  of critical RTEMS structures.  On some processors it may make
 *  sense to have these aligned on tighter boundaries than
 *  the minimum requirements of the compiler in order to have as
 *  much of the critical data area as possible in a cache line.
 *
 *  The placement of this macro in the declaration of the variables
 *  is based on the syntactically requirements of the GNU C
 *  "__attribute__" extension.  For example with GNU C, use
 *  the following to force a structures to a 32 byte boundary.
 *
 *      __attribute__ ((aligned (32)))
 *
 *  NOTE:  Currently only the Priority Bit Map table uses this feature.
 *         To benefit from using this, the data must be heavily
 *         used so it will stay in the cache and used frequently enough
 *         in the executive to justify turning this on.
 */

#define CPU_STRUCTURE_ALIGNMENT __attribute__ ((aligned(16)))

/*
 *  Define what is required to specify how the network to host conversion
 *  routines are handled.
 *
 *  NOTE: SHes can be big or little endian, the default is big endian
 */

/* __LITTLE_ENDIAN__ is defined if -ml is given to gcc */
#if defined(__LITTLE_ENDIAN__)
#define CPU_BIG_ENDIAN                           FALSE
#define CPU_LITTLE_ENDIAN                        TRUE
#else
#define CPU_BIG_ENDIAN                           TRUE
#define CPU_LITTLE_ENDIAN                        FALSE
#endif

/*
 *  The following defines the number of bits actually used in the
 *  interrupt field of the task mode.  How those bits map to the
 *  CPU interrupt levels is defined by the routine _CPU_ISR_Set_level().
 */

#define CPU_MODES_INTERRUPT_MASK   0x0000000f

/*
 *  Processor defined structures required for cpukit/score.
 */

/* may need to put some structures here.  */

/*
 * Contexts
 *
 *  Generally there are 2 types of context to save.
 *     1. Interrupt registers to save
 *     2. Task level registers to save
 *
 *  This means we have the following 3 context items:
 *     1. task level context stuff::  Context_Control
 *     2. floating point task stuff:: Context_Control_fp
 *     3. special interrupt level context :: Context_Control_interrupt
 *
 *  On some processors, it is cost-effective to save only the callee
 *  preserved registers during a task context switch.  This means
 *  that the ISR code needs to save those registers which do not
 *  persist across function calls.  It is not mandatory to make this
 *  distinctions between the caller/callee saves registers for the
 *  purpose of minimizing context saved during task switch and on interrupts.
 *  If the cost of saving extra registers is minimal, simplicity is the
 *  choice.  Save the same context on interrupt entry as for tasks in
 *  this case.
 *
 *  Additionally, if gdb is to be made aware of RTEMS tasks for this CPU, then
 *  care should be used in designing the context area.
 *
 *  On some CPUs with hardware floating point support, the Context_Control_fp
 *  structure will not be used or it simply consist of an array of a
 *  fixed number of bytes.   This is done when the floating point context
 *  is dumped by a "FP save context" type instruction and the format
 *  is not really defined by the CPU.  In this case, there is no need
 *  to figure out the exact format -- only the size.  Of course, although
 *  this is enough information for RTEMS, it is probably not enough for
 *  a debugger such as gdb.  But that is another problem.
 */

typedef struct {
  uint32_t   *r15;      /* stack pointer */

  uint32_t   macl;
  uint32_t   mach;
  uint32_t   *pr;

  uint32_t   *r14;      /* frame pointer/call saved */

  uint32_t   r13;       /* call saved */
  uint32_t   r12;       /* call saved */
  uint32_t   r11;       /* call saved */
  uint32_t   r10;       /* call saved */
  uint32_t   r9;        /* call saved */
  uint32_t   r8;        /* call saved */

  uint32_t   *r7;       /* arg in */
  uint32_t   *r6;       /* arg in */

#if 0
  uint32_t   *r5;       /* arg in */
  uint32_t   *r4;       /* arg in */
#endif

  uint32_t   *r3;       /* scratch */
  uint32_t   *r2;       /* scratch */
  uint32_t   *r1;       /* scratch */

  uint32_t   *r0;       /* arg return */

  uint32_t   gbr;
  uint32_t   sr;

} Context_Control;

#define _CPU_Context_Get_SP( _context ) \
  (_context)->r15

typedef struct {
#if SH_HAS_FPU
#ifdef SH4_USE_X_REGISTERS
  union {
    float f[16];
    double d[8];
  } x;
#endif
  union {
    float f[16];
    double d[8];
  } r;
  float fpul;       /* fp communication register */
  uint32_t   fpscr; /* fp control register */
#endif /* SH_HAS_FPU */
} Context_Control_fp;

typedef struct {
} CPU_Interrupt_frame;

/*
 *  This variable is optional.  It is used on CPUs on which it is difficult
 *  to generate an "uninitialized" FP context.  It is filled in by
 *  _CPU_Initialize and copied into the task's FP context area during
 *  _CPU_Context_Initialize.
 */

#if SH_HAS_FPU
SCORE_EXTERN Context_Control_fp  _CPU_Null_fp_context;
#endif

/*
 *  Nothing prevents the porter from declaring more CPU specific variables.
 */

/* XXX: if needed, put more variables here */
SCORE_EXTERN void CPU_delay( uint32_t   microseconds );

/*
 *  The size of the floating point context area.  On some CPUs this
 *  will not be a "sizeof" because the format of the floating point
 *  area is not defined -- only the size is.  This is usually on
 *  CPUs with a "floating point save context" instruction.
 */

#define CPU_CONTEXT_FP_SIZE sizeof( Context_Control_fp )

/*
 *  Amount of extra stack (above minimum stack size) required by
 *  MPCI receive server thread.  Remember that in a multiprocessor
 *  system this thread must exist and be able to process all directives.
 */

#define CPU_MPCI_RECEIVE_SERVER_EXTRA_STACK 0

/*
 *  This defines the number of entries in the ISR_Vector_table managed
 *  by RTEMS.
 */

#define CPU_INTERRUPT_NUMBER_OF_VECTORS      256
#define CPU_INTERRUPT_MAXIMUM_VECTOR_NUMBER  (CPU_INTERRUPT_NUMBER_OF_VECTORS - 1)

/*
 *  This is defined if the port has a special way to report the ISR nesting
 *  level.  Most ports maintain the variable _ISR_Nest_level.
 */

#define CPU_PROVIDES_ISR_IS_IN_PROGRESS FALSE

/*
 *  Should be large enough to run all RTEMS tests.  This ensures
 *  that a "reasonable" small application should not have any problems.
 *
 *  We have been able to run the sptests with this value, but have not
 *  been able to run the tmtest suite.
 */

#define CPU_STACK_MINIMUM_SIZE          4096

/*
 *  CPU's worst alignment requirement for data types on a byte boundary.  This
 *  alignment does not take into account the requirements for the stack.
 */
#if defined(__SH4__)
/* FIXME: sh3 and SH3E? */
#define CPU_ALIGNMENT              8
#else
#define CPU_ALIGNMENT              4
#endif

/*
 *  This number corresponds to the byte alignment requirement for the
 *  heap handler.  This alignment requirement may be stricter than that
 *  for the data types alignment specified by CPU_ALIGNMENT.  It is
 *  common for the heap to follow the same alignment requirement as
 *  CPU_ALIGNMENT.  If the CPU_ALIGNMENT is strict enough for the heap,
 *  then this should be set to CPU_ALIGNMENT.
 *
 *  NOTE:  This does not have to be a power of 2.  It does have to
 *         be greater or equal to than CPU_ALIGNMENT.
 */

#define CPU_HEAP_ALIGNMENT         CPU_ALIGNMENT

/*
 *  This number corresponds to the byte alignment requirement for memory
 *  buffers allocated by the partition manager.  This alignment requirement
 *  may be stricter than that for the data types alignment specified by
 *  CPU_ALIGNMENT.  It is common for the partition to follow the same
 *  alignment requirement as CPU_ALIGNMENT.  If the CPU_ALIGNMENT is strict
 *  enough for the partition, then this should be set to CPU_ALIGNMENT.
 *
 *  NOTE:  This does not have to be a power of 2.  It does have to
 *         be greater or equal to than CPU_ALIGNMENT.
 */

#define CPU_PARTITION_ALIGNMENT    CPU_ALIGNMENT

/*
 *  This number corresponds to the byte alignment requirement for the
 *  stack.  This alignment requirement may be stricter than that for the
 *  data types alignment specified by CPU_ALIGNMENT.  If the CPU_ALIGNMENT
 *  is strict enough for the stack, then this should be set to 0.
 *
 *  NOTE:  This must be a power of 2 either 0 or greater than CPU_ALIGNMENT.
 */

#define CPU_STACK_ALIGNMENT        CPU_ALIGNMENT

/*
 *  ISR handler macros
 */

/*
 *  Support routine to initialize the RTEMS vector table after it is allocated.
 *
 *  SH Specific Information: NONE
 */

#define _CPU_Initialize_vectors()

/*
 *  Disable all interrupts for an RTEMS critical section.  The previous
 *  level is returned in _level.
 */

#define _CPU_ISR_Disable( _level) \
  sh_disable_interrupts( _level )

/*
 *  Enable interrupts to the previous level (returned by _CPU_ISR_Disable).
 *  This indicates the end of an RTEMS critical section.  The parameter
 *  _level is not modified.
 */

#define _CPU_ISR_Enable( _level) \
   sh_enable_interrupts( _level)

/*
 *  This temporarily restores the interrupt to _level before immediately
 *  disabling them again.  This is used to divide long RTEMS critical
 *  sections into two or more parts.  The parameter _level is not
 * modified.
 */

#define _CPU_ISR_Flash( _level) \
  sh_flash_interrupts( _level)

/*
 *  Map interrupt level in task mode onto the hardware that the CPU
 *  actually provides.  Currently, interrupt levels which do not
 *  map onto the CPU in a generic fashion are undefined.  Someday,
 *  it would be nice if these were "mapped" by the application
 *  via a callout.  For example, m68k has 8 levels 0 - 7, levels
 *  8 - 255 would be available for bsp/application specific meaning.
 *  This could be used to manage a programmable interrupt controller
 *  via the rtems_task_mode directive.
 */

#define _CPU_ISR_Set_level( _newlevel) \
  sh_set_interrupt_level(_newlevel)

uint32_t   _CPU_ISR_Get_level( void );

/* end of ISR handler macros */

/* Context handler macros */

/*
 *  Initialize the context to a state suitable for starting a
 *  task after a context restore operation.  Generally, this
 *  involves:
 *
 *     - setting a starting address
 *     - preparing the stack
 *     - preparing the stack and frame pointers
 *     - setting the proper interrupt level in the context
 *     - initializing the floating point context
 *
 *  This routine generally does not set any unnecessary register
 *  in the context.  The state of the "general data" registers is
 *  undefined at task start time.
 *
 *  NOTE: This is_fp parameter is TRUE if the thread is to be a floating
 *        point thread.  This is typically only used on CPUs where the
 *        FPU may be easily disabled by software such as on the SPARC
 *        where the PSR contains an enable FPU bit.
 */

/*
 * FIXME: defined as a function for debugging - should be a macro
 */
SCORE_EXTERN void _CPU_Context_Initialize(
  Context_Control       *_the_context,
  void                  *_stack_base,
  uint32_t              _size,
  uint32_t              _isr,
  void    (*_entry_point)(void),
  int                   _is_fp );

/*
 *  This routine is responsible for somehow restarting the currently
 *  executing task.  If you are lucky, then all that is necessary
 *  is restoring the context.  Otherwise, there will need to be
 *  a special assembly routine which does something special in this
 *  case.  Context_Restore should work most of the time.  It will
 *  not work if restarting self conflicts with the stack frame
 *  assumptions of restoring a context.
 */

#define _CPU_Context_Restart_self( _the_context ) \
   _CPU_Context_restore( (_the_context) );

/*
 *  The purpose of this macro is to allow the initial pointer into
 *  a floating point context area (used to save the floating point
 *  context) to be at an arbitrary place in the floating point
 *  context area.
 *
 *  This is necessary because some FP units are designed to have
 *  their context saved as a stack which grows into lower addresses.
 *  Other FP units can be saved by simply moving registers into offsets
 *  from the base of the context area.  Finally some FP units provide
 *  a "dump context" instruction which could fill in from high to low
 *  or low to high based on the whim of the CPU designers.
 */

#define _CPU_Context_Fp_start( _base, _offset ) \
   ( (void *) _Addresses_Add_offset( (_base), (_offset) ) )

/*
 *  This routine initializes the FP context area passed to it to.
 *  There are a few standard ways in which to initialize the
 *  floating point context.  The code included for this macro assumes
 *  that this is a CPU in which a "initial" FP context was saved into
 *  _CPU_Null_fp_context and it simply copies it to the destination
 *  context passed to it.
 *
 *  Other models include (1) not doing anything, and (2) putting
 *  a "null FP status word" in the correct place in the FP context.
 *  SH1, SH2, SH3 have no FPU, but the SH3e and SH4 have.
 */

#if SH_HAS_FPU
#define _CPU_Context_Initialize_fp( _destination ) \
  do { \
     *(*(_destination)) = _CPU_Null_fp_context;\
  } while(0)
#else
#define _CPU_Context_Initialize_fp( _destination ) \
  {  }
#endif

/* end of Context handler macros */

/* Fatal Error manager macros */

/*
 * FIXME: Trap32 ???
 *
 *  This routine copies _error into a known place -- typically a stack
 *  location or a register, optionally disables interrupts, and
 *  invokes a Trap32 Instruction which returns to the breakpoint
 *  routine of cmon.
 */

#ifdef BSP_FATAL_HALT
  /* we manage the fatal error in the board support package */
  void bsp_fatal_halt( uint32_t   _error);
#define _CPU_Fatal_halt( _error ) bsp_fatal_halt( _error)
#else
#define _CPU_Fatal_halt( _error)\
{ \
  asm volatile("mov.l %0,r0"::"m" (_error)); \
  asm volatile("mov #1, r4"); \
  asm volatile("trapa #34"); \
}
#endif

/* end of Fatal Error manager macros */

/* Bitfield handler macros */

/*
 *  This routine sets _output to the bit number of the first bit
 *  set in _value.  _value is of CPU dependent type Priority_Bit_map_control.
 *  This type may be either 16 or 32 bits wide although only the 16
 *  least significant bits will be used.
 *
 *  There are a number of variables in using a "find first bit" type
 *  instruction.
 *
 *    (1) What happens when run on a value of zero?
 *    (2) Bits may be numbered from MSB to LSB or vice-versa.
 *    (3) The numbering may be zero or one based.
 *    (4) The "find first bit" instruction may search from MSB or LSB.
 *
 *  RTEMS guarantees that (1) will never happen so it is not a concern.
 *  (2),(3), (4) are handled by the macros _CPU_Priority_mask() and
 *  _CPU_Priority_bits_index().  These three form a set of routines
 *  which must logically operate together.  Bits in the _value are
 *  set and cleared based on masks built by _CPU_Priority_mask().
 *  The basic major and minor values calculated by _Priority_Major()
 *  and _Priority_Minor() are "massaged" by _CPU_Priority_bits_index()
 *  to properly range between the values returned by the "find first bit"
 *  instruction.  This makes it possible for _Priority_Get_highest() to
 *  calculate the major and directly index into the minor table.
 *  This mapping is necessary to ensure that 0 (a high priority major/minor)
 *  is the first bit found.
 *
 *  This entire "find first bit" and mapping process depends heavily
 *  on the manner in which a priority is broken into a major and minor
 *  components with the major being the 4 MSB of a priority and minor
 *  the 4 LSB.  Thus (0 << 4) + 0 corresponds to priority 0 -- the highest
 *  priority.  And (15 << 4) + 14 corresponds to priority 254 -- the next
 *  to the lowest priority.
 *
 *  If your CPU does not have a "find first bit" instruction, then
 *  there are ways to make do without it.  Here are a handful of ways
 *  to implement this in software:
 *
 *    - a series of 16 bit test instructions
 *    - a "binary search using if's"
 *    - _number = 0
 *      if _value > 0x00ff
 *        _value >>=8
 *        _number = 8;
 *
 *      if _value > 0x0000f
 *        _value >=8
 *        _number += 4
 *
 *      _number += bit_set_table[ _value ]
 *
 *    where bit_set_table[ 16 ] has values which indicate the first
 *      bit set
 */

#define CPU_USE_GENERIC_BITFIELD_CODE TRUE
#define CPU_USE_GENERIC_BITFIELD_DATA TRUE

#if (CPU_USE_GENERIC_BITFIELD_CODE == FALSE)

extern uint8_t   _bit_set_table[];

#define _CPU_Bitfield_Find_first_bit( _value, _output ) \
  { \
      _output = 0;\
      if(_value > 0x00ff) \
      { _value >>= 8; _output = 8; } \
      if(_value > 0x000f) \
        { _output += 4; _value >>= 4; } \
      _output += _bit_set_table[ _value]; }

#endif

/* end of Bitfield handler macros */

/*
 *  This routine builds the mask which corresponds to the bit fields
 *  as searched by _CPU_Bitfield_Find_first_bit().  See the discussion
 *  for that routine.
 */

#if (CPU_USE_GENERIC_BITFIELD_CODE == FALSE)

#define _CPU_Priority_Mask( _bit_number ) \
  ( 1 << (_bit_number) )

#endif

/*
 *  This routine translates the bit numbers returned by
 *  _CPU_Bitfield_Find_first_bit() into something suitable for use as
 *  a major or minor component of a priority.  See the discussion
 *  for that routine.
 */

#if (CPU_USE_GENERIC_BITFIELD_CODE == FALSE)

#define _CPU_Priority_bits_index( _priority ) \
  (_priority)

#endif

/* end of Priority handler macros */

/* functions */

/*
 *  _CPU_Initialize
 *
 *  This routine performs CPU dependent initialization.
 */

void _CPU_Initialize(void);

/*
 *  _CPU_ISR_install_raw_handler
 *
 *  This routine installs a "raw" interrupt handler directly into the
 *  processor's vector table.
 */

void _CPU_ISR_install_raw_handler(
  uint32_t    vector,
  proc_ptr    new_handler,
  proc_ptr   *old_handler
);

/*
 *  _CPU_ISR_install_vector
 *
 *  This routine installs an interrupt vector.
 */

void _CPU_ISR_install_vector(
  uint32_t    vector,
  proc_ptr    new_handler,
  proc_ptr   *old_handler
);

/*
 *  _CPU_Install_interrupt_stack
 *
 *  This routine installs the hardware interrupt stack pointer.
 *
 *  NOTE:  It needs only be provided if CPU_HAS_HARDWARE_INTERRUPT_STACK
 *         is TRUE.
 */

void _CPU_Install_interrupt_stack( void );

/*
 *  _CPU_Thread_Idle_body
 *
 *  This routine is the CPU dependent IDLE thread body.
 *
 *  NOTE:  It need only be provided if CPU_PROVIDES_IDLE_THREAD_BODY
 *         is TRUE.
 */

void *_CPU_Thread_Idle_body( uintptr_t ignored );

/*
 *  _CPU_Context_switch
 *
 *  This routine switches from the run context to the heir context.
 */

void _CPU_Context_switch(
  Context_Control  *run,
  Context_Control  *heir
);

/*
 *  _CPU_Context_restore
 *
 *  This routine is generally used only to restart self in an
 *  efficient manner.  It may simply be a label in _CPU_Context_switch.
 */

void _CPU_Context_restore(
  Context_Control *new_context
);

/*
 *  _CPU_Context_save_fp
 *
 *  This routine saves the floating point context passed to it.
 */

void _CPU_Context_save_fp(
  Context_Control_fp **fp_context_ptr
);

/*
 *  _CPU_Context_restore_fp
 *
 *  This routine restores the floating point context passed to it.
 */

void _CPU_Context_restore_fp(
  Context_Control_fp **fp_context_ptr
);


#ifdef __cplusplus
}
#endif

#endif