aboutsummaryrefslogtreecommitdiffstats
path: root/arch/i386
Commit message (Collapse)AuthorAge
* move header files to their own directoryBjoern B. Brandenburg2008-02-05
|
* clean up ABI and headersBjoern B. Brandenburg2008-02-03
|
* 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.
* rip out icsBjoern B. Brandenburg2008-02-01
|
* disable system callsBjoern B. Brandenburg2008-02-01
|
* 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| | | | The old real-time task creation has been replaced by the new transitioning method.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] add sys_task_mode_transition()Bjoern B. Brandenburg2008-01-18
| | | This allows real-time tasks to become best-effort tasks and vice versa.
* 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: implement rollback mechanicsBjoern B. Brandenburg2007-11-19
| | | rollback the EIP on return to user space if TIF_ROLLBACK_RCS is set
* LITMUS ABI: Rework syscall interface and expose new FDSO interface.Bjoern B. Brandenburg2007-11-15
| | | | This removes some now unused system calls from LITMUS. Requires a liblitmus update.
* 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.
* adaptive: introduce service level system callsBjoern B. Brandenburg2007-10-04
| | | | | Allow user space to set up service levels, also allow RT tasks to query their current service level.
* add flag based np-sectionsBjoern B. Brandenburg2007-09-13
| | | | | | This commit introduces the infrastructure for flag based np sections. It also features an overhauled GSN-EDF scheduler that respects the flags (and has less bugs).
* Add wait_for_job system callBjoern B. Brandenburg2007-08-21
| | | | Allow userspace to wait for a specific job release.
* Make the inclusion of sched_trace_XXX() and TRACE() a configurable option.Bjoern B. Brandenburg2007-05-17
| | | | This allows us to remove the debugging code from benchmarking kernels.
* Add time stamps for schedule(), the timer interrupt, and the pluginBjoern B. Brandenburg2007-05-16
| | | | scheduler_tick() and schedule() callbacks.
* Start of LITMUS semaphore, PI, and SRP rewrite.Bjoern B. Brandenburg2007-05-14
| | | | | Rearrange the code to get out of the architecture dependent areas of the kernel and make it live in a central file, kernel/litmus_sem.c.
* Remove old, unneeded ASM cruft.Bjoern B. Brandenburg2007-05-14
|
* Kick out commented ASM code.Bjoern B. Brandenburg2007-05-13
|
* Modified SRP semaphores so that waiting for prio to exceed SPC worksJohn M. Calandrino2007-05-10
| | | | correctly, mostly by adding waitqueues and rewriting wait_until_exceed_spc.
* First attempt at FIFO semaphores and PI sems. This may not work...John M. Calandrino2007-05-10
| | | | Before FIFO, everything seemed to be (finally) working ok.
* Development checkpoint. Still having issues.John M. Calandrino2007-05-09
|
* Various changes that I don't want to lose, but the code does not work.John M. Calandrino2007-05-09
|
* Changed printed kernel debug information slightly.John M. Calandrino2007-05-02
|
* Fixed a bug in SRP semaphores after changing to per-processor ceilings.John M. Calandrino2007-05-02
|
* Fixed SRP so that it uses per-processor priority ceilings.John M. Calandrino2007-05-02
|
* Fixed some race conditions in the priority inheritance code, and fixed aJohn M. Calandrino2007-05-01
| | | | glitch or two in GSN-EDF.
* Made changes to protect empty queues from being traversed inJohn M. Calandrino2007-04-26
| | | | semaphore-related calls.
* Commented out timing measurement code after determining that things areJohn M. Calandrino2007-04-26
| | | | working okay.
* Added some quantum alignment measurement capabilities, so that alignmentsJohn M. Calandrino2007-04-26
| | | | could be re-validated after some changes.
* Changed task registration in SRP semaphores so that a pid is used ratherJohn M. Calandrino2007-04-26
| | | | | | than a pointer to a task_struct. This eliminates the need to define the task_struct struct in user space, and also makes the system call cleaner. Required lookup of the task in the new system call.
* Added kernel SRP "semaphore" support, to be included in PSN-EDF, and fixedJohn M. Calandrino2007-04-25
| | | | a small bug in semaphore free methods for all user-level semaphores.
* Fixed some things so that it builds correctly.John M. Calandrino2007-04-25
|
* Removed incomplete zone-based implementation.John M. Calandrino2007-04-25
|
* Added function prototypes for SRP system calls in unistd.h and syscall_table.S.John M. Calandrino2007-04-25
|
* Fixed a few comment inconsistencies. Added stubs for an SRP "semaphore",John M. Calandrino2007-04-25
| | | | | which needs to be expanded in the LSO and by adding system call numbers in kernel space.
* Fixed GSN-EDF to handle correct wakeup of tasks that just exited aJohn M. Calandrino2007-04-24
| | | | semaphore.
* Compiles. Woo! TODO: Fix GSN-EDF so it is suspension-friendly.John M. Calandrino2007-04-24
|
* Fixed the PI issue with down calls, should work now.John M. Calandrino2007-04-24
|
* Fixed a number of issues, subtle and otherwise, with PI semaphores.John M. Calandrino2007-04-24
| | | | | | | | | | PI semaphores now use scheduler callbacks to update priority on a down or up call. Issues with calling down/up and not calling __down_failed or __up_wakeup for PI semaphores has been noted (since priority-related things occured in those calls) and up has been fixed (down is in process). Callbacks are now responsible for the priority checks and updates, and some subtle cases are handled that were missed before. Still need to finish handling GSN-EDF implementation issues related to suspensions.
* Reverted back to spinlocks, added code to higher priority code inJohn M. Calandrino2007-04-23
| | | | edf-common.c, left other stubs untouched until tomorrow.
* Converting spinlocks to queuelocks in my code, and also fixing stubs... inJohn M. Calandrino2007-04-23
| | | | process...
* Merge with git+ssh://cvs.cs.unc.edu/cvs/proj/litmus/repo/litmusJohn M. Calandrino2007-04-23
|\ | | | | | | | | Bjoern's changes + mine. Still need to fill in some stubs and ensure that nothing broke.
| * add system calls sys_enter_np() and sys_exit_np()Bjoern B. Brandenburg2007-04-17
| |
* | Fixed priority inheritance issues with PI semaphores. Added regularJohn M. Calandrino2007-04-23
| | | | | | | | | | semaphores accessible through system calls, so that they can be used with the LSO (for partitioned FMLP).
* | Slight modification to semaphore initialization function, so that itJohn M. Calandrino2007-04-19
| | | | | | | | actually is called at boot.
* | Another small fix to system call sys_pi_sema_init, in order to eliminateJohn M. Calandrino2007-04-19
| | | | | | | | another pointer issue.
* | Made changes in Litmus so that user-space semaphores can work.John M. Calandrino2007-04-19
| | | | | | | | | | | | | | | | A user now makes a system call where a semaphore ID is specified, and the semaphore implementation is hidden away in the kernel. There are a finite number of semaphores and the kernel system call will return an error if it cannot claim one, however user space code in libso does not yet acknowledge this.
* | Added priority inheritance within semaphores - compiles but has not beenJohn M. Calandrino2007-04-18
| | | | | | | | tested.
generated by cgit v1.2.2 (git 2.25.0) at 2025-04-22 06:58:49 -0400