aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
Commit message (Collapse)AuthorAge
* move header files to their own directoryBjoern B. Brandenburg2008-02-05
|
* move LITMUS code to its own directoryBjoern B. Brandenburg2008-02-05
|
* remove old, unneeded modification to timer.cBjoern B. Brandenburg2008-02-05
|
* push litmus_controlled check to RT pluginsBjoern B. Brandenburg2008-02-05
|
* remove sched trace crapBjoern B. Brandenburg2008-02-05
|
* litmus: change time accounting to nanosecond resolutionBjoern B. Brandenburg2008-02-04
|
* litmus: clean up architectureBjoern B. Brandenburg2008-02-03
| | | | | | move activate/deactivate hack to central place remove runqueue knowledge from scheduler plugins separate rt_param.h from accessor macros
* fix schedulers:Bjoern B. Brandenburg2008-02-03
| | | | | - preempt when budget exhausted - don't hold lock while switching
* litmus: export all registered pluginsBjoern B. Brandenburg2008-02-02
|
* litmus: restructure data structures, prepare for nanosecond accuracyBjoern B. Brandenburg2008-02-02
|
* litmus: get rid of WANT_RESCHED and make dummy functions staticBjoern B. Brandenburg2008-02-02
|
* litmus: factor out tick counting into common codeBjoern B. Brandenburg2008-02-02
|
* rip out queue lock implementation. Will be replaced by new Linux FIFO spin ↵Bjoern B. Brandenburg2008-02-02
| | | | locks.
* GSN-EDF: Hopefully the fix that makes it work.Bjoern B. Brandenburg2008-02-02
|
* PSN-EDF: cleanupBjoern B. Brandenburg2008-02-02
|
* litmus: rip out the concept of RT_MODE.Bjoern B. Brandenburg2008-02-02
| | | | | It also rips out scheduler_setup(). This patch is very invasive and only compile-tested.
* move old, now (hopefully) unneded checksBjoern B. Brandenburg2008-02-02
|
* litmus: don't let Linux migrate real-time tasks, ever.Bjoern B. Brandenburg2008-02-02
|
* rip out pfairBjoern B. Brandenburg2008-02-01
|
* rip out scheduler, rework plugin registration, introduce procfs interfaceBjoern B. Brandenburg2008-02-01
|
* rip out stuff that will not be initially portedBjoern B. Brandenburg2008-01-30
|
* litmus core: use LITMUS tracing, not printk, during task mode transitions2007.3Bjoern B. Brandenburg2008-01-28
|
* litmus core: don't leak np_flag upon execBjoern B. Brandenburg2008-01-24
|
* litmus core: don't leak real-time state across forks and mode transitionsBjoern B. Brandenburg2008-01-24
| | | | Always cleanup stale real-time flags, job numbers, etc.
* litmus core: remove prepare_task() system callBjoern B. Brandenburg2008-01-22
| | | | The old real-time task creation has been replaced by the new transitioning method.
* [litmus core] only transition if stack is not in useBjoern B. Brandenburg2008-01-22
| | | | Don't do litmus task mode transitions before we have switched away from the stack of the task doing the transition.
* [GSN-EDF] add additional sanity checkBjoern B. Brandenburg2008-01-22
|
* [litmus core] reject tasks with illegal parametersBjoern B. Brandenburg2008-01-22
|
* [litmus core] task_mode_transition() fixesBjoern B. Brandenburg2008-01-22
| | | | - restore old best-effort priority - allow non-rt tasks to register a np-flag
* [litmus core] add sys_task_mode_transition()Bjoern B. Brandenburg2008-01-18
| | | This allows real-time tasks to become best-effort tasks and vice versa.
* [litmus core] implement rt mode transition mechanicsBjoern B. Brandenburg2008-01-17
| | | This will be the basis for the new BE->RT->BE system call.
* [litmus core] avoid memory leak of service levelsBjoern B. Brandenburg2008-01-17
| | | | A task may have allocated service levels but not be a real-time task on exit.
* [litmus core] unconditionally call litmus_exit()Bjoern B. Brandenburg2008-01-17
| | | | Make the decision whether clean-up is necessary opaque. This will help with porting.
* [cleanup] remove trailing whitespaceBjoern B. Brandenburg2008-01-17
|
* ics: improve error messageBjoern B. Brandenburg2008-01-16
|
* FDSO: don't return a wrong object reference instead of NULLBjoern B. Brandenburg2007-12-20
| | | | | get_inode_object() returned the last inspected object instead of NULL incase that it couln't find the requested object.
* ICS: re-worked for nesting supportBjoern B. Brandenburg2007-12-14
|
* ICS: bug fixes and debugging supportBjoern B. Brandenburg2007-11-20
| | | | | - don't disable preemption - don't spin inside the kernel on behalf of user space - give some debug info (can be turned off)
* ICS: enable ICS system callsBjoern B. Brandenburg2007-11-19
|
* ICS: fix some compile warningsBjoern B. Brandenburg2007-11-19
| | | | - remove stale header - don't implicitly cast function pointer
* ICS: implement rollback mechanicsBjoern B. Brandenburg2007-11-19
| | | rollback the EIP on return to user space if TIF_ROLLBACK_RCS is set
* ICS: arch independent local task rollbackBjoern B. Brandenburg2007-11-19
|
* ICS: implement writer protocol kernel supportBjoern B. Brandenburg2007-11-19
| | | | Writer implementation mostly complete, reader rollback and registry stuff still missing.
* ICS: start implementation of ICS supportBjoern B. Brandenburg2007-11-19
| | | Add platform independent files and enable in FDSO layer.
* FMLP: Rework semaphore allocation to work on top of FDSOBjoern B. Brandenburg2007-11-15
| | | | | Throw out the terribly insecure, wasteful, and brittle static allocations. Many issues remain with this implementation (robustness, etc.) but it is a first step.
* fdso: introduce core infrastructureBjoern B. Brandenburg2007-11-15
| | | | | | | | | This patch introduces "file descriptor attached shared objects" that will be used to manage LITMUS^RT PI semaphores, SRP resources, and ICS. FDSO essentially allows tasks to create and share kernel objects in the context (namespace) of a shared file. This is useful for mmap()-based shared objects that need synchronization primitives. One example would be the FMLP library libso.
* FMLP: Take out unused FIFO semaphores.Bjoern B. Brandenburg2007-11-14
| | | | | This is dead code from an early FMLP version. It is not needed anymore unused FIFO semaphores.
* cleanup: tidy up code before release2007.2Bjoern B. Brandenburg2007-10-27
| | | This gets rid of quite a few FIXMEs and TODOs, as well as some cruft.
* adaptive: reweight if the total system capacity is exceeded.RTAS08Bjoern B. Brandenburg2007-10-26
| | | | Track total utilization for the task set.
* seems to be working like thisBjoern B. Brandenburg2007-10-19
|
generated by cgit v1.2.2 (git 2.25.0) at 2025-04-16 11:49:41 -0400