cpu.h

RTEMS (Real-Time Executive for Multiprocessor Systems) is a free open source real-time operating sys

/*
 *  This include file contains information pertaining to the Hitachi SH
 *  processor.
 *
 *  Authors: Ralf Corsepius ([e-mail]) and
 *           Bernd Becker ([e-mail])
 *
 *  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) 1998-2001.
 *  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: cpu.h,v 1.11.2.1 2003/09/04 18:47:39 joel Exp $
 */

#ifndef _SH_CPU_h
#define _SH_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 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 "NO_CPU_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.
 *
 *  So far, the only CPU in which this option has been used is the
 *  HP PA-RISC.  The HP C compiler and gcc both implicitly use the
 *  floating point registers to perform integer multiplies.  If
 *  a function which you would not think utilize the FP unit DOES,
 *  then one can not easily predict which tasks will use the FP hardware.
 *  In this case, this option should be TRUE.
 *
 *  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
 */

#define CPU_HAS_OWN_HOST_TO_NETWORK_ROUTINES     FALSE

/* __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
 *
 *  Examples structures include the descriptor tables from the i386
 *  and the processor control structure on the i960ca.
 */

/* 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 {
  unsigned32 *r15;	/* stack pointer */

  unsigned32 macl;
  unsigned32 mach;
  unsigned32 *pr;

  unsigned32 *r14;	/* frame pointer/call saved */

  unsigned32 r13;	/* call saved */
  unsigned32 r12;	/* call saved */
  unsigned32 r11;	/* call saved */
  unsigned32 r10;	/* call saved */
  unsigned32 r9;	/* call saved */
  unsigned32 r8;	/* call saved */

  unsigned32 *r7;	/* arg in */
  unsigned32 *r6;	/* arg in */

#if 0
  unsigned32 *r5;	/* arg in */
  unsigned32 *r4;	/* arg in */
#endif

  unsigned32 *r3;	/* scratch */
  unsigned32 *r2;	/* scratch */
  unsigned32 *r1;	/* scratch */

  unsigned32 *r0;	/* arg return */

  unsigned32 gbr;
  unsigned32 sr; 

} Context_Control;

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 */
  unsigned32 fpscr; /* fp control register */
#endif /* SH_HAS_FPU */
} Context_Control_fp;

typedef struct {
} CPU_Interrupt_frame;


/*
 *  The following table contains the information required to configure
 *  the SH processor specific parameters.
 */

typedef struct {
  void       (*pretasking_hook)( void );
  void       (*predriver_hook)( void );
  void       (*postdriver_hook)( void );
  void       (*idle_task)( void );
  boolean      do_zero_of_workspace;
  unsigned32   idle_task_stack_size;
  unsigned32   interrupt_stack_size;
  unsigned32   extra_mpci_receive_server_stack;
  void *     (*stack_allocate_hook)( unsigned32 );
  void       (*stack_free_hook)( void* );
  /* end of fields required on all CPUs */
  unsigned32	clicks_per_second ; /* cpu frequency in Hz */
}   rtems_cpu_table;

/*
 *  Macros to access required entires in the CPU Table are in 
 *  the file rtems/system.h.
 */

/*
 *  Macros to access SH specific additions to the CPU Table
 */

#define rtems_cpu_configuration_get_clicks_per_second() \
  (_CPU_Table.clicks_per_second)
   
/*
 *  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

/*
 *  On some CPUs, RTEMS supports a software managed interrupt stack.
 *  This stack is allocated by the Interrupt Manager and the switch
 *  is performed in _ISR_Handler.  These variables contain pointers
 *  to the lowest and highest addresses in the chunk of memory allocated
 *  for the interrupt stack.  Since it is unknown whether the stack
 *  grows up or down (in general), this give the CPU dependent
 *  code the option of picking the version it wants to use.
 *
 *  NOTE: These two variables are required if the macro
 *        CPU_HAS_SOFTWARE_INTERRUPT_STACK is defined as TRUE.
 */

SCORE_EXTERN void               *_CPU_Interrupt_stack_low;
SCORE_EXTERN void               *_CPU_Interrupt_stack_high;

/*
 *  With some compilation systems, it is difficult if not impossible to
 *  call a high-level language routine from assembly language.  This
 *  is especially true of commercial Ada compilers and name mangling
 *  C++ ones.  This variable can be optionally defined by the CPU porter
 *  and contains the address of the routine _Thread_Dispatch.  This
 *  can make it easier to invoke that routine at the end of the interrupt
 *  sequence (if a dispatch is necessary).
 */

SCORE_EXTERN void           (*_CPU_Thread_dispatch_pointer)();

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

/* XXX: if needed, put more variables here */
SCORE_EXTERN void CPU_delay( unsigned32 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