aboutsummaryrefslogtreecommitdiff
path: root/sys/ia64/ia64/mp_machdep.c
Commit message (Expand)AuthorAgeFilesLines
* Remove ia64.Marcel Moolenaar2014-07-071-543/+0
* Retire smp_active. It was racey and caused demonstrated problems withScott Long2014-04-261-1/+1
* Fix and improve exception tracing:Marcel Moolenaar2014-03-181-0/+9
* In intr_event_handle() we already save and set td_intr_frame, soMarcel Moolenaar2014-03-171-0/+4
* Don't enable interrupts before we call sched_throw(). InterruptsMarcel Moolenaar2013-11-101-2/+0
* Use LOG2_ID_PAGE_SIZE again for the identity mapping in regions 6 & 7.Marcel Moolenaar2013-11-011-2/+2
* Purge the translation cache of APs before we unleash them. To thatMarcel Moolenaar2013-10-311-0/+2
* Respect the kern.smp.disabled tunable. When we're scanning the MADT inMarcel Moolenaar2013-10-311-0/+5
* Replace kernel virtual address space allocation with vmem. This providesJeff Roberson2013-08-071-1/+2
* Move PCPU initialization to a new function called cpu_pcpu_setup().Marcel Moolenaar2012-07-081-3/+2
* Unleash the APs at SI_SUB_KICK_SCHEDULER so that we have them allMarcel Moolenaar2012-07-081-2/+1
* MFCAttilio Rao2011-06-261-2/+16
|\
| * Switch to the event timers infrastructure. This includes:Marcel Moolenaar2011-06-251-2/+16
* | Remove the usage of pc_cpumask and pc_other_cpus from ia64.Attilio Rao2011-06-151-9/+7
|/
* MFCAttilio Rao2011-05-311-4/+4
|\
| * On multi-core, multi-threaded PPC systems, it is important that the threadsNathan Whitehorn2011-05-311-4/+4
* | Fix remaining bits that actually weren't converted by mistake.Attilio Rao2011-05-131-3/+4
* | Commit the support for removing cpumask_t and replacing it directly withAttilio Rao2011-05-051-7/+7
|/
* Stop linking against a direct-mapped virtual address and insteadMarcel Moolenaar2011-04-301-65/+124
* Add a new ipi_cpu() function to the MI IPI API that can be used to send anJohn Baldwin2010-08-061-0/+10
* Allocate and setup an interrupt vector for corrected machine checks.Marcel Moolenaar2010-07-031-0/+2
* Change the (generic) argument to ia64_store_mca_state() from theMarcel Moolenaar2010-04-131-7/+8
* Implement interrupt to CPU binding. Assign interrupts to CPUs in aMarcel Moolenaar2010-03-271-0/+6
* Rename disable_intr() to ia64_disable_intr() and rename enable_intr()Marcel Moolenaar2010-03-261-1/+1
* Only use the interval timer for clock interrupts on the BSP andMarcel Moolenaar2010-03-261-3/+2
* Fix interrupt handling by extending the critical region so thatMarcel Moolenaar2010-03-221-10/+0
* Revamp the interrupt code based on the previous commit:Marcel Moolenaar2010-03-171-30/+96
* Some code churn:Marcel Moolenaar2010-02-141-12/+14
* Revamp bus_space access functions:Marcel Moolenaar2009-12-301-1/+1
* Define struct pcpu_md as the only MD field of struct pcpu (pc_acpi_idMarcel Moolenaar2009-12-071-11/+11
* Allocate the VHPT for each CPU in cpu_mp_start(), rather thanMarcel Moolenaar2009-12-071-4/+10
* Decouple ACPI CPU Ids from FreeBSD's cpuid. The ACPI Ids can beMarcel Moolenaar2009-08-161-18/+14
* Implement a facility for dynamic per-cpu variables.Jeff Roberson2009-06-231-0/+3
* ia64: Move MCA information retrieval to a per-CPU kthreadRink Springer2009-05-271-8/+26
* Mark the BSP as being awake. This supresses the messageMarcel Moolenaar2009-02-101-1/+2
* Atomically increment the number of awoken APs as all APs willMarcel Moolenaar2008-10-191-1/+1
* Remove ipi_all() and ipi_self() as the former hasn't been used atMarius Strobl2008-09-281-31/+0
* Sanitize the malloc types: M_PMAP is not used in pmap.c, so don'tMarcel Moolenaar2008-04-191-3/+3
* - Remove the old smp cpu topology specification with a new, more flexibleJeff Roberson2008-03-021-0/+7
* Clear pending interrupts before we enable external interrupts.Marcel Moolenaar2007-08-061-5/+20
* Replace "__asm __volatile()" by equivalent support functions fromMarcel Moolenaar2007-08-041-6/+6
* Explicitly map the VHPT on all processors. Previously we wereMarcel Moolenaar2007-07-301-0/+1
* Include <sys/sched.h> for sched_throw().Marcel Moolenaar2007-06-061-0/+1
* Commit 10/14 of sched_lock decomposition.Jeff Roberson2007-06-041-16/+1
* Now that printf() needs the PCPU, set it up before we call printf().Marcel Moolenaar2006-11-181-2/+2
* Since DELAY() was moved, most <machine/clock.h> #includes have beenPoul-Henning Kamp2006-05-161-1/+0
* Correct the spinlock nesting of the idle thread of the APs before weMarcel Moolenaar2006-02-111-12/+10
* Modify the way we account for CPU time spent (step 1)Poul-Henning Kamp2006-02-071-1/+1
* o s/vhpt_size/pmap_vhpt_log2size/gMarcel Moolenaar2005-09-031-4/+2
* Fix the problem with the IPI for the lazy context switching of theMarcel Moolenaar2005-08-131-0/+1
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-12 13:20:21 +0000