| Commit message (Collapse) | Author | Age |
|---|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch continues the work to implement a generic pi framework. Under this
framework, each task_struct maintains a stack of held locks, in the order they
are acquired. This stack is mainly used to determine the proper inheritance
when a lock is released. On release, the releasing job iterates through its
semaphore stack to determine if it blocks a higher priority job and inherits
the proper priority as needed. The stack is needed since a blocked job cannot
push this information to the lock holder because the inheritance may not take
place immediately when the job is blocked. Stack operations include push, pop,
update, and peek.
The semaphore stack is really only useful to protocols that support
traditional nesting. Protocols that do not use traditional nesting, such
as FMLP-Long, do not need a stack to track inheritance. So, struct rt_param
now also has a task_struct pointer, eff_priority. eff_priority is used in
almost the same way was rt_param.inh_task was used in the original FMLP
implementation. The slight difference is that eff_priority is set to equal
to self when a job acquires a semaphore with no inheritance. This is
stylistically similar to FMLP using a semaphore stack. Note that FMLP-Long
completely forgoes the use of semaphore stack and only uses eff_priority.
Finally, it is intended that eff_priority also be used with nested protocols.
A job using a nested protocol would set eff_priority equal to the highest
priority received from all held locks. Thus, eff_priority caches the priority
a job inherits (the semaphore stack does not need to be iterated through each
time the job's priority is required).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
First patch in a series to implement a generic priority inheritance
framework that can be used by semaphores that use priority inheritance.
This patch makes pi_semaphore a 'base class' for pi-protocols. pi_semaphore
is updated to include a pi_sem_record field named stack_node. This stack_node
is a linked-list node that a task holding the pi_semaphore instance adds to
their semaphore stack. Note that the task's semaphore stack (or linked-list)
simply chains stack_node's of held semaphores into a single linked-list.
This is safe since there is only one semaphore holder at any given moment.
Finally, FMLP-specific data members out to child class fmlp_semaphore.
|
| |
|
|
|
|
|
|
|
|
|
| |
Feather-Trace rewrites instructions in the kernel's .text segment.
This segment may be write-protected if CONFIG_DEBUG_RODATA is selected.
In this case, fall back to the default flag-based Feather-Trace
implementation. In the future, we could either adopt the ftrace method
of rewriting .text addresses using non-.text mappings or we could
consider replacing Feather-Trace with ftrace altogether.
For now, this patch avoids unexpected runtime errors.
|
| |
|
|
|
|
|
|
| |
Introduces CONFIG_RELEASE_MASTER and makes release
master support dependent on the new symbol. This is
useful because dedicated interrupt handling only applies
to "large" multicore platforms. This will allow us to
not implement smp_send_pull_timers() for all platforms.
|
| |
|
|
|
|
|
|
|
| |
The idea of the Feather-Trace default implementation is that LITMUS^RT should
work without a specialized Feather-Trace implementation present. This was
actually broken.
Changes litmus/feather_trace.h to only include asm/feather_trace.h if actually
promised by the architecture.
|
| |
|
|
|
|
|
|
|
|
| |
NO_ENFORCEMENT - A job may execute beyond its declared execution time.
Jobs notify the kernel that they are complete via liblitmus's
sleep_next_period()
QUANTUM_ENFORCEMENT - The kernel terminates a job if its actual execution
time exceeds the declared execution time.
PRECISE_ENFORCEMENT - Hook declared, but not yet implemented. Plan to
support this policy through hrtimers. Error thrown if specified.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Adapt to new schema for spinlock:
(tglx 20091217)
spinlock - the weakest one, which might sleep in RT
raw_spinlock - spinlock which always spins even on RT
arch_spinlock - the hardware level architecture dependent implementation
----
Most probably, all the spinlocks changed by this commit will be true
spinning lock (raw_spinlock) in PreemptRT (so hopefully we'll need few
changes when porting Litmmus to PreemptRT).
There are a couple of spinlock that the kernel still defines as
spinlock_t (therefore no changes reported in this commit) that might cause
us troubles:
- wait_queue_t lock is defined as spinlock_t; it is used in:
* fmlp.c -- sem->wait.lock
* sync.c -- ts_release.wait.lock
- rwlock_t used in fifo implementation in sched_trace.c
* this need probably to be changed to something always spinning in RT
at the expense of increased locking time.
----
This commit also fixes warnings and errors due to the need to include
slab.h when using kmalloc() and friends.
----
This commit does not compile.
|
| |
|
|
|
|
| |
Improved C-EDF plugin. C-EDF now supports different cluster sizes (based
on L2 and L3 cache sharing) and supports dynamic changes of cluster size
(this requires reloading the plugin).
|
| |
|
|
|
|
|
|
| |
1) High priority task tied to FMLP semaphore in P-EDF scheduling is
incorrectly tracked for tasks acquiring the lock without
contention. (HP is always set to CPU 0 instead of proper CPU.)
2) Race in a print statement from P-EDF's pi_block() causes NULL
pointer dereference.
|
| |
|
|
|
|
|
|
| |
Dealing with preemptions across CPUs in the presence of non-preemptive
sections can be tricky and should not be replicated across (event-driven) plugins.
This patch introduces a generic preemption function that handles
non-preemptive sections (hopefully) correctly.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Re-introduce NP sections in the configuration and in litmus.h. Remove the old
np_flag from rt_param.
If CONFIG_NP_SECTION is disabled, then all non-preemptive section checks are
constant expressions which should get removed by the dead code elimination
during optimization.
Instead of re-implementing sys_exit_np(), we simply repurposed sched_yield()
for calling into the scheduler to trigger delayed preemptions.
|
| |
|
|
|
|
|
|
|
| |
This device only supports mmap()'ing a single page.
This page is shared RW between the kernel and userspace.
It is inteded to allow near-zero-overhead communication
between the kernel and userspace. It's first use will be a
proper implementation of user-signaled
non-preemptable section support.
|
| | |
|
| |
|
|
|
| |
- [ported from 2008.3] Add x86_32 architecture dependent code.
- Add the infrastructure for x86_32 - x86_64 integration.
|
| |
|
|
|
|
|
| |
- Add syscall on x86_64
- Refactor __NR_sleep_next_period -> __NR_complete_job
for both x86_32 and x86_64
|
| |
|
|
|
|
| |
- Binomial heap "heap" names conflicted with priority heap
of cgroup in kernel
- This patch change binomial heap "heap" names in "bheap"
|
| | |
|
| | |
|
| |
|
|
| |
infrastructure
|
| | |
|
| |
|
|
|
| |
Still to be merged:
- arm_release_timer() with no rq locking
|
| |
|
|
|
|
|
|
| |
- fix requesting more than 2^11 pages (MAX_ORDER)
to system allocator
Still to be merged:
- feather-trace generic implementation
|
| | |
|
|
|
Port 2008.3 Core LITMUS^RT infrastructure to Linux 2.6.32
litmus_sched_class implements 4 new methods:
- prio_changed:
void
- switched_to:
void
- get_rr_interval:
return infinity (i.e., 0)
- select_task_rq:
return current cpu
|
