summaryrefslogtreecommitdiffstats
path: root/cpukit (follow)
Commit message (Collapse)AuthorAgeFilesLines
* score: PR2179: Fix initially locked PCP mutexesSebastian Huber2014-05-231-3/+16
| | | | | Elevate the priority of the creating task to the ceiling priority in case a semaphore is created as initially locked.
* cpuset.c: Fix formattingJoel Sherrill2014-05-221-3/+3
|
* rtems: Fix sp2038 test.Chris Johns2014-05-221-14/+93
| | | | | | | | Avoid using newlib's gmtime_r call which fails with a max signed int. Add an RTEMS specific version for 1/1/1988 to 31/12/2100. Update sp2038 to test every day from 1/1/1988 to 31/12/2100. Only days need be tested as the code splits the seconds based on days.
* rtems: Simplify rtems_semaphore_obtain()Sebastian Huber2014-05-221-2/+4
|
* schedulersmpimpl.h: Fix spacingJoel Sherrill2014-05-211-2/+2
|
* score: _Thread_Set_life_protection()Sebastian Huber2014-05-211-4/+0
| | | | | | | Enable usage of _Thread_Set_life_protection() in thread dispatch critical sections. This can be used to enable the thread life-protection with thread dispatching disabled and then enable thread dispatching.
* score: Add and use _Scheduler_Get_index_by_id()Sebastian Huber2014-05-211-2/+8
|
* score: Add const qualifierSebastian Huber2014-05-211-1/+1
|
* score: Add comment regarding TLS workspace sizeSebastian Huber2014-05-211-0/+8
|
* score: Simplify _Scheduler_Set()Sebastian Huber2014-05-211-1/+1
|
* rtems: Clarify task set/get scheduler parametersSebastian Huber2014-05-203-10/+10
|
* score: SMP scheduler support documentationSebastian Huber2014-05-201-1/+5
|
* dosfs: Fix read from invalid memory areaSebastian Huber2014-05-161-1/+1
|
* score: Simplify SMP scheduler supportSebastian Huber2014-05-161-8/+3
|
* score: Fix state diagramSebastian Huber2014-05-161-0/+1
|
* score: Split SMP scheduler enqueue functionSebastian Huber2014-05-153-86/+220
| | | | | | | | Extract code from _Scheduler_SMP_Enqueue_ordered() and move it to the new function _Scheduler_SMP_Enqueue_scheduled_ordered() to avoid untestable execution paths. Add and use function _Scheduler_SMP_Unblock().
* score: Make _Thread_queue_Requeue() staticSebastian Huber2014-05-154-76/+48
| | | | | | This function is only used by _Thread_Change_priority(). Make it static to avoid the function call overhead in the performance critical function _Thread_Change_priority().
* score: Add and use _Scheduler_SMP_Start_idle()Sebastian Huber2014-05-159-52/+39
|
* score: Add and use _Scheduler_default_Schedule()Sebastian Huber2014-05-158-32/+38
|
* score: Simplify _Thread_Change_priority()Sebastian Huber2014-05-1542-975/+470
| | | | | | | | | | | | | | | | | | | | | | | | The function to change a thread priority was too complex. Simplify it with a new scheduler operation. This increases the average case performance due to the simplified logic. The interrupt disabled critical section is a bit prolonged since now the extract, update and enqueue steps are executed atomically. This should however not impact the worst-case interrupt latency since at least for the Deterministic Priority Scheduler this sequence can be carried out with a wee bit of instructions and no loops. Add _Scheduler_Change_priority() to replace the sequence of - _Thread_Set_transient(), - _Scheduler_Extract(), - _Scheduler_Enqueue(), and - _Scheduler_Enqueue_first(). Delete STATES_TRANSIENT, _States_Is_transient() and _Thread_Set_transient() since this state is now superfluous. With this change it is possible to get rid of the SCHEDULER_SMP_NODE_IN_THE_AIR state. This considerably simplifies the implementation of the new SMP locking protocols.
* score: Add and use _Scheduler_Get_context()Sebastian Huber2014-05-147-9/+17
|
* score: _Scheduler_priority_Ready_queue_requeue()Sebastian Huber2014-05-141-22/+0
| | | | Delete unused function _Scheduler_priority_Ready_queue_requeue().
* score: Add STATES_RESTARTINGSebastian Huber2014-05-143-1/+4
| | | | Use separate state for thread restart.
* score: TypoSebastian Huber2014-05-141-1/+1
|
* monitor: Support STATES_MIGRATINGSebastian Huber2014-05-141-0/+1
|
* score: Use Scheduler_Context for SMP schedulerSebastian Huber2014-05-143-73/+88
| | | | | | Use the basic Scheduler_Context for the general SMP scheduler operations to avoid usage of structure offsets to get the specialized context variants.
* score: Capitalize SMP acronymSebastian Huber2014-05-142-50/+50
|
* score: SMP scheduler documentationSebastian Huber2014-05-141-0/+308
|
* score: Introduce scheduler nodesSebastian Huber2014-05-1439-229/+552
| | | | | | | | | | | | Rename scheduler per-thread information into scheduler nodes using Scheduler_Node as the base type. Use inheritance for specialized schedulers. Move the scheduler specific states from the thread control block into the scheduler node structure. Validate the SMP scheduler node state transitions in case RTEMS_DEBUG is defined.
* score: Scheduler documentationSebastian Huber2014-05-148-62/+57
|
* sparc: Change asm to __asm__ to compile with -std=c99.Daniel Cederman2014-05-141-1/+1
|
* score: Move out of __RTEMS_HAVE_SYS_CPUSET_H__Sebastian Huber2014-05-121-34/+34
| | | | | Move _Scheduler_Get() and _Scheduler_Set() out of the #if defined(__RTEMS_HAVE_SYS_CPUSET_H__) block.
* rtems: Move extern "C" in <rtems.h>Sebastian Huber2014-05-121-4/+4
| | | | Do not cover the includes with an extern "C".
* score: Fix CPU context usage on SMPSebastian Huber2014-05-0810-41/+93
| | | | | | | | | | We must not alter the is executing indicator in _CPU_Context_Initialize() since this would cause an invalid state during a self restart. The is executing indicator must be valid at creation time since otherwise _Thread_Kill_zombies() uses an undefined value for not started threads. This could result in a system life lock.
* configure: Paravirtualization for all targetsSebastian Huber2014-05-081-7/+3
| | | | Virtual machines with paravirtualization exist not only on x86.
* rtems: Fix ASR SMP supportSebastian Huber2014-05-072-3/+24
| | | | Initialize the ISR lock only once and destroy it properly.
* score: Fix SMP startupSebastian Huber2014-05-071-1/+3
|
* score: Implement forced thread migrationSebastian Huber2014-05-0729-137/+403
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current implementation of task migration in RTEMS has some implications with respect to the interrupt latency. It is crucial to preserve the system invariant that a task can execute on at most one processor in the system at a time. This is accomplished with a boolean indicator in the task context. The processor architecture specific low-level task context switch code will mark that a task context is no longer executing and waits that the heir context stopped execution before it restores the heir context and resumes execution of the heir task. So there is one point in time in which a processor is without a task. This is essential to avoid cyclic dependencies in case multiple tasks migrate at once. Otherwise some supervising entity is necessary to prevent life-locks. Such a global supervisor would lead to scalability problems so this approach is not used. Currently the thread dispatch is performed with interrupts disabled. So in case the heir task is currently executing on another processor then this prolongs the time of disabled interrupts since one processor has to wait for another processor to make progress. It is difficult to avoid this issue with the interrupt latency since interrupts normally store the context of the interrupted task on its stack. In case a task is marked as not executing we must not use its task stack to store such an interrupt context. We cannot use the heir stack before it stopped execution on another processor. So if we enable interrupts during this transition we have to provide an alternative task independent stack for this time frame. This issue needs further investigation.
* score: Delete _SMP_Test_message_default_handlerSebastian Huber2014-05-071-7/+1
| | | | | A default handler is not necessary. The test message sender must ensure that a handler is installed.
* score: DocumentationSebastian Huber2014-05-072-4/+12
|
* posix: Fix POSIX keys initializationSebastian Huber2014-05-061-5/+5
| | | | | Always initialize the freechain. This prevents a NULL pointer access in case no initial key value pairs are defined.
* score: Use atomic operations for SMP messagesSebastian Huber2014-05-053-19/+15
|
* score: Add SMP test message handlerSebastian Huber2014-05-052-0/+36
| | | | | This handler can be used to test the inter-processor interrupt implementation.
* score: SMP_FATAL_SCHEDULER_WITHOUT_PROCESSORSSebastian Huber2014-05-055-23/+29
| | | | | Avoid the SMP_FATAL_SCHEDULER_WITHOUT_PROCESSORS fatal error and make it a run-time error in rtems_scheduler_ident() and _Scheduler_Get_by_id().
* score: Fix TLS size usageSebastian Huber2014-05-053-7/+11
|
* score: TypoSebastian Huber2014-04-301-1/+1
|
* score: Statically initialize _ISR_Vector_tableSebastian Huber2014-04-2916-141/+26
|
* sapi: Report profiling only if enabled for testsSebastian Huber2014-04-291-0/+2
|
* score: Avoid copy and pasteSebastian Huber2014-04-281-19/+15
|
* sapi: Add profiling done messageSebastian Huber2014-04-281-0/+6
|
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-10 05:36:00 +0000