| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Use register g6 for the per-CPU control of the current processor. The
register g6 is reserved for the operating system by the SPARC ABI. On
Linux register g6 is used for a similar purpose with the same method
since 1996.
The register g6 must be initialized during system startup and then must
remain unchanged.
Since the per-CPU control is used in all critical sections of the
operating system, this is a performance optimization for the operating
system core procedures. An additional benefit is that the low-level
context switch and interrupt processing code is now identical on non-SMP
and SMP configurations.
|
|
|
|
|
|
| |
The registers g2 through g4 are reserved for applications. GCC uses
them as volatile registers by default. So they are treated like
volatile registers in RTEMS as well.
|
|
|
|
|
|
|
|
|
| |
Add optional method _CPU_Get_current_per_CPU_control() to obtain the
per-CPU control of the current processor.
This is optional. Not every CPU port needs this. It is only an
optional optimization variant. In case this macro is undefined, the
default implementation using the current processor index will be used.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add and use _CPU_SMP_Start_processor(). Add and use
_CPU_SMP_Finalize_initialization(). This makes most
_CPU_SMP_Initialize() functions a bit simpler since we can calculate the
minimum value of the count of processors requested by the application
configuration and the count of physically or virtually available
processors in the high-level code.
The CPU port has now the ability to signal a processor start failure.
With the support for clustered/partitioned scheduling the presence of
particular processors can be configured to be optional or mandatory.
There will be a fatal error only in case mandatory processors are not
present.
The CPU port may use a timeout to monitor the start of a processor.
|
| |
|
| |
|
|
|
|
| |
Rename Priority_bit_map_Control in Priority_bit_map_Word.
|
| |
|
| |
|
|
|
|
|
|
| |
According to AAPCS, section 5.2.1.2, "Stack constraints at a public
interface" the stack must be 8 byte aligned. This was not the case
during interrupt processing.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Rename _SMP_Request_other_cores_to_perform_first_context_switch() into
_SMP_Request_start_multitasking() since this requests now a multitasking
start on all configured and available processors. The name corresponds
_Thread_Start_multitasking() and
_SMP_Start_multitasking_on_secondary_processor() actions issued in
response to this request. Move in source file to right place.
Rename PER_CPU_STATE_READY_TO_BEGIN_MULTITASKING into
PER_CPU_STATE_READY_TO_START_MULTITASKING.
Rename PER_CPU_STATE_BEGIN_MULTITASKING into
PER_CPU_STATE_REQUEST_START_MULTITASKING.
Rename _SMP_Request_other_cores_to_shutdown() into
_SMP_Request_shutdown().
Add a per-CPU state lock to protect all changes. This was necessary to
offer a controlled shutdown of the system (atomic read/writes alone are
not sufficient for this kind of synchronization).
Add documentation for Per_CPU_State.
Delete debug output.
New tests smptests/smpfatal01 and smptests/smpfatal02.
|
|
|
|
|
|
|
|
| |
The SPARC processors supported by RTEMS have no built-in CPU counter
support. We have to use some hardware counter module for this purpose.
The BSP must provide a 32-bit register which contains the current CPU
counter value and a function for the difference calculation. It can use
for example the GPTIMER instance used for the clock driver.
|
|
|
|
|
|
|
| |
Remove RTEMS_COMPILER_PURE_ATTRIBUTE from _SMP_Get_current_processor()
and all _CPU_SMP_Get_current_processor(). Make inline ASM statements
volatile again. Test smptests/smpmigration01 showed that GCC optimizes
too much otherwise.
|
|
|
|
| |
Rename _Internal_error_Occurred() into _Terminate().
|
|
|
|
|
| |
Rename bsp_smp_initialize() into _CPU_SMP_Initialize() since every CPU
port must supply this function.
|
|
|
|
|
|
|
|
|
|
|
|
| |
Do not return to BSP context in the exit() shutdown path. This makes it
possible to re-use the initialization stack. It can be used for the
interrupt stack for example. On targets with a small RAM this is a
considerable benefit.
This change eliminates also some special cases and simplifies the code.
Delete _Thread_Set_global_exit_status(),
_Thread_Get_global_exit_status() and _Thread_Stop_multitasking().
|
|
|
|
|
|
|
|
|
|
|
|
| |
Instead of SPRG0 (= special purpose register 272) use the new global
symbol _PPC_INTERRUPT_DISABLE_MASK to store the interrupt disable mask.
The benefit is that it is now possible to disable interrupts without
further run-time initialization in boot_card().
At least on Freescale e500 cores this leads also to a faster execution
since the mfmsr and mfspr instruction require four cycles to complete.
The instructions to load the mask value can execute while the mfmsr is
in progress.
|
|
|
|
|
| |
Use a ticket lock implementation based on atomic operations. Delete CPU
port specific SMP lock implementations.
|
|
|
|
| |
Use SWAP instruction with one lock for the system in the SMP case.
|
|
|
|
| |
Add _LEON3_Get_current_processor().
|
|
|
|
|
| |
The instructions to get the processor current index have no
side-effects.
|
|
|
|
|
|
|
|
|
| |
Add a CPU counter interface to allow access to a free-running counter.
It is useful to measure short time intervals. This can be used for
example to enable profiling of critical low-level functions.
Add two busy wait functions rtems_counter_delay_ticks() and
rtems_counter_delay_nanoseconds() implemented via the CPU counter.
|
|
|
|
| |
Recent LEON4 systems use a cache line size of 32 bytes.
|
|
|
|
|
|
|
|
|
|
| |
The _CPU_Context_switch() is a normal function call. The following
registers are volatile (the caller must assume that the register
contents are destroyed by the callee) according to "SYSTEM V APPLICATION
BINARY INTERFACE - SPARC Processor Supplement", Third Edition: g1, o0,
o1, o2, o3, o4, o5. Drop these registers from the context.
Ensure that offset defines match the structure offsets.
|
|
|
|
|
| |
Delete _CPU_Context_switch_to_first_task_smp() and use
_CPU_Context_restore() instead.
|
|
|
|
|
| |
Tested and implemented on ARM, m68k, PowerPC and SPARC. Other
architectures need more work.
|
| |
|
| |
|
| |
|
|
|
|
|
| |
Recent GCC versions use atomic operations based on load/store exclusive
in the C++ library.
|
| |
|
|
|
|
| |
The r2 may be used for thread-local storage.
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
| |
Add proper license and copyright.
|
| |
|
| |
|
|
|
|
| |
This variable must be available for each processor in the system.
|
|
|
|
|
|
| |
Move the _CPU_Context_switch(), _CPU_Context_restore() and
_CPU_Context_switch_to_first_task_smp() code since the method to obtain
the processor index is BSP specific.
|
|
|
|
| |
Interrupt support for per-CPU thread dispatch disable level.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Use a per-CPU thread dispatch disable level. So instead of one global
thread dispatch disable level we have now one instance per processor.
This is a major performance improvement for SMP. On non-SMP
configurations this may simplifiy the interrupt entry/exit code.
The giant lock is still present, but it is now decoupled from the thread
dispatching in _Thread_Dispatch(), _Thread_Handler(),
_Thread_Restart_self() and the interrupt entry/exit. Access to the
giant lock is now available via _Giant_Acquire() and _Giant_Release().
The giant lock is still implicitly acquired via
_Thread_Dispatch_decrement_disable_level().
The giant lock is only acquired for high-level operations in interrupt
handlers (e.g. release of a semaphore, sending of an event).
As a side-effect this change fixes the lost thread dispatch necessary
indication bug in _Thread_Dispatch().
A per-CPU thread dispatch disable level greatly simplifies the SMP
support for the interrupt entry/exit code since no spin locks have to be
acquired in this area. It is only necessary to get the current
processor index and use this to calculate the address of the own per-CPU
control. This reduces the interrupt latency considerably.
All elements for the interrupt entry/exit code are now part of the
Per_CPU_Control structure: thread dispatch disable level, ISR nest level
and thread dispatch necessary. Nothing else is required (except CPU
port specific stuff like on SPARC).
|
|
|
|
| |
Add CPU port specific per-CPU control.
|
| |
|
|
|
|
|
| |
The set of interrupt levels must be a continuous range of non-negative
integers starting at zero.
|