summaryrefslogtreecommitdiffstats
path: root/cpukit/score/include/rtems/score (follow)
Commit message (Collapse)AuthorAgeFilesLines
* score: PR2136: Fix _Thread_Change_priority()Sebastian Huber2013-08-2010-20/+119
| | | | | | | | | | | | | | | Add call to _Scheduler_Schedule() in missing path after _Thread_Set_transient() in _Thread_Change_priority(). See also sptests/spintrcritical19. Add thread parameter to _Scheduler_Schedule(). This parameter is currently unused but may be used in future SMP schedulers. Do heir selection in _Scheduler_Schedule(). Use _Scheduler_Update_heir() for this in the particular scheduler implementation. Add and use _Scheduler_Generic_block().
* score: Per-CPU thread dispatch disable levelSebastian Huber2013-08-095-72/+92
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Use a per-CPU thread dispatch disable level. So instead of one global thread dispatch disable level we have now one instance per processor. This is a major performance improvement for SMP. On non-SMP configurations this may simplifiy the interrupt entry/exit code. The giant lock is still present, but it is now decoupled from the thread dispatching in _Thread_Dispatch(), _Thread_Handler(), _Thread_Restart_self() and the interrupt entry/exit. Access to the giant lock is now available via _Giant_Acquire() and _Giant_Release(). The giant lock is still implicitly acquired via _Thread_Dispatch_decrement_disable_level(). The giant lock is only acquired for high-level operations in interrupt handlers (e.g. release of a semaphore, sending of an event). As a side-effect this change fixes the lost thread dispatch necessary indication bug in _Thread_Dispatch(). A per-CPU thread dispatch disable level greatly simplifies the SMP support for the interrupt entry/exit code since no spin locks have to be acquired in this area. It is only necessary to get the current processor index and use this to calculate the address of the own per-CPU control. This reduces the interrupt latency considerably. All elements for the interrupt entry/exit code are now part of the Per_CPU_Control structure: thread dispatch disable level, ISR nest level and thread dispatch necessary. Nothing else is required (except CPU port specific stuff like on SPARC).
* score: Add and use _Per_CPU_Acquire_all().Sebastian Huber2013-08-091-0/+30
| | | | | | | Add and use _Per_CPU_Release_all(). The context switch user extensions are invoked in _Thread_Dispatch(). This change is necessary to avoid the giant lock in _Thread_Dispatch().
* smp: Use ISR lock in per-CPU controlSebastian Huber2013-08-091-11/+19
| | | | | | | Rename _Per_CPU_Lock_acquire() to _Per_CPU_ISR_disable_and_acquire(). Rename _Per_CPU_Lock_release() to _Per_CPU_Release_and_ISR_enable(). Add _Per_CPU_Acquire() and _Per_CPU_Release().
* score/cpu: Add CPU_Per_CPU_controlSebastian Huber2013-08-091-2/+7
| | | | Add CPU port specific per-CPU control.
* score: Rename _Scheduler_simple_Update()Sebastian Huber2013-08-083-15/+11
| | | | Rename _Scheduler_simple_Update() in _Scheduler_default_Update().
* score: Rename _Scheduler_simple_Allocate(), etc.Sebastian Huber2013-08-083-33/+24
| | | | | Rename _Scheduler_simple_Allocate() in _Scheduler_default_Allocate(). Rename _Scheduler_simple_Free() in _Scheduler_default_Free().
* score: Rename _Scheduler_priority_Release_job()Sebastian Huber2013-08-084-17/+14
| | | | | Rename _Scheduler_priority_Release_job() into _Scheduler_default_Release_job().
* correct comments about atomic apiWeiY2013-08-062-10/+10
|
* smp: Generalize _Thread_Start_multitasking()Sebastian Huber2013-08-051-1/+1
| | | | | | | | | | Add context parameter to _Thread_Start_multitasking() and use this function in rtems_smp_secondary_cpu_initialize(). This avoids duplication of code. Fix missing floating point context initialization in rtems_smp_secondary_cpu_initialize(). Now performed via _Thread_Start_multitasking().
* score: Delete SYSTEM_STATE_BEGIN_MULTITASKINGSebastian Huber2013-08-052-14/+2
| | | | | Nothing happened between the SYSTEM_STATE_BEGIN_MULTITASKING to SYSTEM_STATE_UP transition.
* score: Use an ISR lock for TODSebastian Huber2013-08-011-10/+25
| | | | | | | | | | | | | Two issues are addressed. 1. On single processor configurations the set/get of the now/uptime timestamps is now consistently protected by ISR disable/enable sequences. Previously nested interrupts could observe partially written values since 64-bit writes are not atomic on 32-bit architectures in general. This could lead to non-monotonic uptime timestamps. 2. The TOD now/uptime maintanence is now independent of the giant lock. This is the first step to remove the giant lock in _Thread_Dispatch().
* score: Move nanoseconds since last tick supportSebastian Huber2013-08-014-26/+56
| | | | | | Move the nanoseconds since last tick support from the Watchdog to the TOD handler. Now the TOD managment is encapsulated in the TOD_Control structure.
* score: Add and use _TOD_Is_set()Sebastian Huber2013-08-011-0/+5
|
* score: Delete _TOD_Activate and _TOD_DeactivateSebastian Huber2013-08-011-18/+0
|
* score: Rename tod.h to todimpl.hSebastian Huber2013-08-012-3/+3
|
* score: ISR lock API changesSebastian Huber2013-08-011-6/+50
|
* score: Add and use _Thread_Update_cpu_time_used()Sebastian Huber2013-08-011-0/+19
| | | | Fix _times().
* score: Add and use ISR locksSebastian Huber2013-07-311-0/+141
| | | | | | | | | | | | ISR locks are low-level locks to protect critical sections accessed by threads and interrupt service routines. On single processor configurations the ISR locks degrade to simple ISR disable/enable sequences. No additional storage or objects are required. This synchronization primitive is supported on SMP configurations. Here SMP locks are used.
* smp: Provide cache optimized Per_CPU_ControlSebastian Huber2013-07-311-14/+32
| | | | Delete _Per_CPU_Information_p.
* score: Format <rtems/score/percpu.h>Sebastian Huber2013-07-311-63/+60
|
* smp: Delete _SMP_Request_other_cores_to_dispatch()Sebastian Huber2013-07-302-9/+14
| | | | | Use an event triggered unicast to inform remote processors about a necessary thread dispatch instead.
* score: Move _Thread_Dispatch_if_necessary()Sebastian Huber2013-07-301-26/+0
| | | | Rename to _RTEMS_Tasks_Dispatch_if_necessary().
* score: Add and use _Thread_Signal_notification()Sebastian Huber2013-07-301-0/+7
|
* smp: Delete _ISR_Disable_on_this_core(), etc.Sebastian Huber2013-07-301-115/+24
| | | | | | | | | | | | | | | | | | | | Delete _ISR_Enable_on_this_core(), _ISR_Flash_on_this_core(), _ISR_SMP_Disable(), _ISR_SMP_Enable(), _ISR_SMP_Flash(). The ISR disable/enable interface has no parameter to pass a specific object. Thus it is only possible to implement a single global lock object with this interface. Using the ISR disable/enable as the giant lock on SMP configurations is not feasible. Potentially blocking resource obtain sequences protected by the thread dispatch disable level are subdivided into smaller ISR disabled critical sections. This works since on single processor configurations there is only one thread of execution that can block. On SMP this is different (image a mutex obtained concurrently by different threads on different processors). The thread dispatch disable level is currently used as the giant lock. There is not need to complicate things with this unused interface.
* smp: Delete _ISR_SMP_Initialize()Sebastian Huber2013-07-301-8/+0
|
* score: Add assert to _Per_CPU_Get()Sebastian Huber2013-07-301-0/+3
| | | | | Thread dispatching must be repressed to use the per CPU control of the current processor consistently.
* score: Add _Assert_Thread_dispatching_repressed()Sebastian Huber2013-07-301-0/+12
|
* score: New header file <rtems/score/assert.h>Sebastian Huber2013-07-301-0/+45
|
* smp: Add and use _Per_CPU_Get()Sebastian Huber2013-07-301-7/+31
| | | | | | Add and use _Per_CPU_Get_by_index() and _Per_CPU_Get_index(). Add _Per_CPU_Send_interrupt(). This avoids direct access of _Per_CPU_Information.
* score: Move object content to public APISebastian Huber2013-07-282-23/+23
|
* score: Move object MP content to public APISebastian Huber2013-07-282-14/+20
|
* score: Merge tod implementation into one fileSebastian Huber2013-07-261-43/+43
| | | | | Delete TOD_MICROSECONDS_PER_SECOND, TOD_MICROSECONDS_TO_TICKS() and TOD_MILLISECONDS_TO_TICKS().
* score: Create object implementation headerSebastian Huber2013-07-265-595/+1022
| | | | | | Move implementation specific parts of object.h and object.inl into new header file objectimpl.h. The object.h contains now only the application visible API.
* Include missing <rtems/score/threaddispatch.h>Sebastian Huber2013-07-261-0/+1
|
* score: Include missing <rtems/score/thread.h>Sebastian Huber2013-07-262-0/+2
|
* score: Move mppkt implementation into mpciimpl.hSebastian Huber2013-07-262-13/+24
|
* score: Create mpci implementation headerSebastian Huber2013-07-263-312/+351
| | | | | Move implementation specific parts of mpci.h into new header file mpciimpl.h. The mpci.h contains now only the application visible API.
* score: Merge objectmp implementation into one fileSebastian Huber2013-07-261-9/+44
|
* score: Create threadq implementation headerSebastian Huber2013-07-2614-479/+499
| | | | | | | | Move implementation specific parts of tqdata.h, threadq.h and threadq.inl into new header file threadqimpl.h. The threadq.h contains now only the application visible API. Delete tqdata.h.
* score: Delete threadq.inlSebastian Huber2013-07-261-15/+11
|
* score: Merge threadmp implementation into one fileSebastian Huber2013-07-261-9/+35
|
* score: Create states implementation headerSebastian Huber2013-07-264-90/+485
| | | | | | Move implementation specific parts of states.h and states.inl into new header file statesimpl.h. The states.h contains now only the application visible API.
* score: Create thread implementation headerSebastian Huber2013-07-264-438/+713
| | | | | | | | Move implementation specific parts of thread.h and thread.inl into new header file threadimpl.h. The thread.h contains now only the application visible API. Remove superfluous header file includes from various files.
* score: Create prioritybitmap implementation headerSebastian Huber2013-07-264-176/+323
| | | | | | | | Move implementation specific parts of prioritybitmap.h and prioritybitmap.inl into new header file prioritybitmapimpl.h. The prioritybitmap.h contains now only the application visible API. Move content of bitfield.h into prioritybitmapimpl.h.
* score: Create scheduler implementation headerSebastian Huber2013-07-262-28/+261
| | | | | | Move implementation specific parts of scheduler.h and scheduler.inl into new header file schedulerimpl.h. The scheduler.h contains now only the application visible API.
* score: Create schedulerpriority impl headerSebastian Huber2013-07-263-16/+218
| | | | | | | | | | | | | Move implementation specific parts of schedulerpriority.h and schedulerpriority.inl into new header file schedulerpriorityimpl.h. The schedulerpriority.h contains now only the application visible API. Add missing includes. Remove superfluous includes. Move declaration of _Priority_Bit_map to prioritybitmap.inl since this variable is used only here. Remove second declaration of _Priority_Major_bit_map.
* score: Create schedulersimple impl headerSebastian Huber2013-07-262-12/+112
| | | | | | Move implementation specific parts of schedulersimple.h and schedulersimple.inl into new header file schedulersimpleimpl.h. The schedulersimple.h contains now only the application visible API.
* score: Move _Heap_Area_overhead() definition.Sebastian Huber2013-07-242-31/+31
| | | | This function is used in bootcard.h.
* score: Include <rtems/score/cpu.h>Sebastian Huber2013-07-241-1/+1
| | | | This file uses CPU_ALIGNMENT.
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-03 13:19:07 +0000