B_DEBUG_SPINLOCK_CONTENTION is defined to 1. It typedefs spinlock to a
structure (thus breaking BeOS binary compatibility), containing a
counter which is incremented whenever a thread has to wait for the
spinlock.
* Added macros for spinlock initialization and access and changed
code using spinlocks accordingly. This breaks compilation for BeOS --
the macros should be defined in the respective compatibility wrappers.
* Added generic syscall to get the spinlock counters for the thread and
the team spinlocks.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25752 a95241bf-73f2-0310-859d-f6bbb57e9c96
When specified it desigantes that the interrupt handler should not lock the
vector with a spinlock when executing the installed interrupt handlers. This
is necessary to allow the same interrupt vector to be handled in parallel on
different CPUs. And it is required for the CPU halt to work synchronously when
there is more than one AP CPU. Though the acquire_spinlock() should cause IPIs
to be processed, only this fixed the SMP_MSG_FLAG_SYNC problem for me.
Not locking is safe as long as it is guaranteed that no interrupt handler is
registered or removed while the interrupt handler is running. We can guarantee
this for the SMP interrupt handlers we install in arch_smp_init() as they are
never uninstalled. Probably this flag should be made private though.
Restored the SMP_MSG_FLAG_SYNC when entering the kernel debugger.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23838 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Insert the pause op in all spin wait loops (as macro for platform independent sources or as inline assembly on x86 only files)
* Fix some warnings with tracing on and extended some output
* Minor cleanups here and there
The pause instruction is implemented since P4 systems but is fully backwards compatible (it's a no-op prior to P4). According to Intel specs it reduces performance penalties as memory order violations can be avoided. Also power consumption is reduced. Most of all this will be beneficial to hyper-threading systems as it frees resources to the other logical processor when one logical processor executes a fast spinning loop.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23141 a95241bf-73f2-0310-859d-f6bbb57e9c96
Basically, there was a pretty subtle race between the cpus in main where if the main cpu released the AP cpus and then before the AP cpus had a chance to run the boot cpu started creating the main thread (which causes smp ici messages to be created) the system would livelock, where the boot cpu waited forever for the AP cpu to acknowledge the ICI (for a TLB flush when creating the kernel stack).
Added smp_cpu_rendezvous(), used to synchronize all the cpus to a particular point, and used it a few times in main().
While i was at it i fixed another race that'll probably never happen, but what the hey. Make sure the kernel args are copied into kernel space by the main cpu before letting any other ones use it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@20269 a95241bf-73f2-0310-859d-f6bbb57e9c96
the new cpuid stuff was apparently exacerbating an existing problem where various bits of low level
cpu code (specifically get_current_cpu) weren't really initialized before being used. Changed the
order to set up a fake set of threads to point each cpu at really early in boot to make sure that at
all points in code it can get the current 'thread' and thus the current cpu.
A probably better solution would be to have dr3 point to the current cpu which would then point to the
current thread, but that has a race condition that would require an int disable, etc.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@20160 a95241bf-73f2-0310-859d-f6bbb57e9c96
synchronization as done in init_mtrrs() failed because of that (let the system
hang).
Unfortunately, MTRR still doesn't work on my dual PIII with SMP enabled; that
was just one reason it didn't work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16173 a95241bf-73f2-0310-859d-f6bbb57e9c96
kernel TLBs from being flushed on context switch.
* new arch_cpu_user_TLB_invalidate() that now does what arch_cpu_global_TLB_invalidate()
did before.
* arch_cpu_global_TLB_invalidate() will now flush all TLBs, even those from the
kernel.
* some cleanups.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@15535 a95241bf-73f2-0310-859d-f6bbb57e9c96
* there is now a "Disable Hyper-Threading" safemode in the boot loader
* the SMP & HT menu items are now added in smp.cpp - and are only added
if the system supports one of them.
* more cleanup to smp_apic.h
* removed cpuid() from the boot loader's support.S - instead, it will now
use the one from the kernel.
* added a very weak HT detection: if the MP config only listed one CPU,
and this CPU supports HT, we enable the other logic processor manually -
as this currently doesn't work, it's disabled, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14536 a95241bf-73f2-0310-859d-f6bbb57e9c96
The "data_ptr" parameter is now only freed if you specify SMP_MSG_FLAG_FREE_ARG
when sending the ICI message.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14519 a95241bf-73f2-0310-859d-f6bbb57e9c96
Extracted scheduler_init() from start_scheduler() (which is now called scheduler_start()).
Moved scheduler related function prototypes from thread.h to the new scheduler.h.
Cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14518 a95241bf-73f2-0310-859d-f6bbb57e9c96
kernel_debugger() didn't do enough before; panic() did all the work - but
since the former is a public function as well, I moved all the functionality
to it. Also fixed a possible buffer overrun in panic().
Renamed dbg_* to debug_*.
"serial_debug_port" setting did not ignore negative values.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12889 a95241bf-73f2-0310-859d-f6bbb57e9c96
(mostly happens in the kernel debugger). Not tested, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12835 a95241bf-73f2-0310-859d-f6bbb57e9c96
