litmus-rt.git - The LITMUS^RT kernel.

	Commit message (Collapse)	Author	Age
*	cosmetic	Mac Mollison	2010-10-11
\|
*	Code cleanup	Mac Mollison	2010-10-11
\|
*	Minor	Mac Mollison	2010-10-06
\|
*	Minor	Mac Mollison	2010-10-06
\|
*	Minor	Mac Mollison	2010-10-06
\|
*	Minor	Mac Mollison	2010-10-06
\|
*	Create different global/local funcs for preemption	Mac Mollison	2010-10-06
\|
*	Revert experiments	Mac Mollison	2010-10-05
\|
*	Fix experiment	Mac Mollison	2010-10-05
\|
*	Further experimentation	Mac Mollison	2010-10-05
\|
*	Testing	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Hopeful fix	Mac Mollison	2010-10-05
\|
*	Important Bugfix: > to <	Mac Mollison	2010-10-05
\|
*	More TRACEs	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Add TRACEs	Mac Mollison	2010-10-05
\|
*	Want all sched events	Mac Mollison	2010-10-05
\|
*	Print out task CPU assignment	Mac Mollison	2010-10-05
\|
*	Experiment	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Don't use per-cpu domain locks	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Minor	Mac Mollison	2010-10-05
\|
*	Syntax	Mac Mollison	2010-10-05
\|
*	Update for per-cpu domains	Mac Mollison	2010-10-05
\|
*	Remove all #ifdef FMLP sections	Mac Mollison	2010-10-05
\|
*	Revert last commit	Mac Mollison	2010-10-04
\|
*	Include rt_domain instead of edf_common	Mac Mollison	2010-10-04
\|
*	Revert last change	Mac Mollison	2010-10-04
\|
*	Remove edf_common include, no longer used.	Mac Mollison	2010-10-04
\|
*	Add a wrapper function I missed	Mac Mollison	2010-10-04
\|
*	Added mcrit_ functions	Mac Mollison	2010-10-04
\| \| \| \| \| \| \| \|	Rather than changing edf_higher_prio, use a wrapper around it. All functions that call edf_higher_prio also need to be wrapped and changed to call the edf_higher_prio wrapper. All the wrapper functions and updated calls are within sched_mcrit.c. This commit also restores edf_common.c.
*	Added parentheses	Mac Mollison	2010-10-04
\|
*	Cover "third case" in prio comparison	Mac Mollison	2010-10-04
\|
*	Try accessing crit differently	Mac Mollison	2010-10-04
\|
*	Bugfix	Mac Mollison	2010-10-04
\|
*	Bugfix	Mac Mollison	2010-10-04
\|
*	Go back to using edf_higher_prio (?)	Mac Mollison	2010-10-04
\|
*	Bugfix	Mac Mollison	2010-10-04
\|
*	Check for criticality in sched_mcrit	Mac Mollison	2010-10-04
\| \| \| \|	As opposed to edf_common
*	Fixes	Mac Mollison	2010-10-04
\| \| \| \| \|	- Fix reference to criticality in higher_criticality macro - Fix reference to criticality in TRACE() call
*	Print task criticality	Mac Mollison	2010-10-04
\|
*	Always prioritize higher criticality over lower	Mac Mollison	2010-09-28
\|
*	Cloned GSN-EDF to serve as stub for mcrit	Mac Mollison	2010-09-22
\|
*	Bugfix: avoid link error in Feather-Trace on x86	Bjoern B. Brandenburg	2010-07-16
\| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \|	If no events are defined but Feater-Trace support is enabled, then the current implementation generates a link error because the __event_table sections is absent. > arch/x86/built-in.o: In function `ft_disable_all_events': > (.text+0x242af): undefined reference to `__start___event_table' As a simple work around, we force zero-element array to always be "allocated" in the __event_table section. This ensures that we end up with a zero-byte section if no events are enabled, and does not affect the layout of the section if events are present. > bbb@ludwig:~/dev/litmus2010$ nm vmlinux \| grep event_table > ffffffff81950cdc D __event_table_dummy > ffffffff81950cdc A __start___event_table > ffffffff81950cdc A __stop___event_table
*	Bugfix: avoid conditional compilation dependent error	Andrea Bastoni	2010-07-16
\| \| \| \| \| \| \| \| \| \| \| \|	If RELEASE_MASTER is not selected the "info" hrtimer_start_on_info structure in release_heap structure is not visible and trying to access "info" from reinit_release_heap() causes the following error: error: 'struct release_heap' has no member named 'info' info should not be referenced if RELEASE_MASTER is not used. The problem was first reported by Glenn <gelliott@cs.unc.edu>
*	Bugfix: change __ARCH_HAS_SEND_PULL_TIMERS in CONFIG_ARCH_HAS_SEND_PULL_TIMERS	Andrea Bastoni	2010-06-12
\| \| \| \| \| \| \| \| \|	Commit "0c527966 Make release master support optional" uses __ARCH_HAS_SEND_PULL_TIMERS instead of CONFIG_ARCH_HAS_SEND_PULL_TIMERS (introduced in commit 0fb33c99) to conditionally compile a pull timer related code in rt_domain.c. This code is disabled and pull-timer's state is no longer properly reset. Therefore, a pulled timer cannot be armed anymore.