aboutsummaryrefslogtreecommitdiff
path: root/sys/ia64/ia64
Commit message (Expand)AuthorAgeFilesLines
* Remove ia64.Marcel Moolenaar2014-07-0743-19585/+0
* Introduce pmap_unwire(). It will replace pmap_change_wiring(). There areAlan Cox2014-07-061-0/+32
* Improve the KTR logs by naming the values.Marcel Moolenaar2014-07-021-53/+59
* Pull in r267961 and r267973 again. Fix for issues reported will follow.Hans Petter Selasky2014-06-282-5/+3
* Revert r267961, r267973:Glen Barber2014-06-272-3/+5
* Extend the meaning of the CTLFLAG_TUN flag to automatically check ifHans Petter Selasky2014-06-272-5/+3
* - Modify vm_page_unwire() and vm_page_enqueue() to directly acceptAttilio Rao2014-06-161-1/+1
* Retire smp_active. It was racey and caused demonstrated problems withScott Long2014-04-261-1/+1
* Fix missed efi.h header change in r263815Ed Maste2014-03-281-1/+1
* Move ia64 efi.h to sys in preparation for amd64 UEFI supportEd Maste2014-03-279-9/+9
* Rename global cnt to vm_cnt to avoid shadowing.Bryan Drewery2014-03-222-3/+3
* Add KTR events for the PMAP interface functionsMarcel Moolenaar2014-03-192-52/+155
* Fix and improve exception tracing:Marcel Moolenaar2014-03-187-80/+427
* In intr_event_handle() we already save and set td_intr_frame, soMarcel Moolenaar2014-03-171-0/+4
* Move the implementation of kdb_cpu_trap() from <machine/kdb.h> toMarcel Moolenaar2014-03-161-0/+13
* Don't use the ITC as the faulting address for external interrupts.Marcel Moolenaar2014-03-162-3/+3
* In intr_event_handle() we already save and set td_intr_frame, soMarcel Moolenaar2014-03-162-7/+6
* Delete stray clause 3 (Advertising clause) and renumber while i'mWarner Losh2014-03-111-1/+1
* When reading physical memory, make sure to access it using the rightMarcel Moolenaar2014-03-041-51/+58
* In pmap_set_pte(), make sure to enforce ordering by inserting a memoryMarcel Moolenaar2014-01-201-2/+4
* In the nested TLB fault handler, for a direct-mapped address, makeMarcel Moolenaar2014-01-151-1/+1
* Add a virt_foreach() that does the same as what phys_foreach() does andMarcel Moolenaar2013-12-281-8/+94
* Add the scaffolding for minidumps. They're just like physical dumps,Marcel Moolenaar2013-12-271-21/+65
* Allow pmap_remove_pages() to be called for physical maps notMarcel Moolenaar2013-12-121-6/+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 Moolenaar2013-11-012-4/+4
* The PAL_PTCE_INFO function returns the counts and strides of theMarcel Moolenaar2013-11-011-10/+10
* Purge the translation cache of APs before we unleash them. To thatMarcel Moolenaar2013-10-312-18/+5
* Respect the kern.smp.disabled tunable. When we're scanning the MADT inMarcel Moolenaar2013-10-311-0/+5
* Add bus_dmamap_load_ma() function to load map with the array ofKonstantin Belousov2013-10-271-0/+11
* The pmap function pmap_clear_reference() is no longer used. Remove it.Alan Cox2013-09-201-31/+0
* On those machines, where sf_bufs do not represent any real object, makeGleb Smirnoff2013-09-061-22/+0
* Significantly reduce the cost, i.e., run time, of calls to madvise(...,Alan Cox2013-08-291-0/+44
* Revert r254501. Instead, reuse the type stability of the struct pmapKonstantin Belousov2013-08-221-2/+2
* The soft and hard busy mechanism rely on the vm object lock to work.Attilio Rao2013-08-091-12/+10
* Replace kernel virtual address space allocation with vmem. This providesJeff Roberson2013-08-071-1/+2
* In ia64_mca_init(), don't limit the allocation of the info block toMarcel Moolenaar2013-07-231-2/+2
* In pmap_mapdev(), if the physical memory range is not covered by an EFIMarcel Moolenaar2013-07-231-1/+1
* o Relax locking assertions for vm_page_find_least()Attilio Rao2013-05-211-1/+2
* Implement the concept of the unmapped VMIO buffers, i.e. buffers whichKonstantin Belousov2013-03-191-0/+2
* Add pmap function pmap_copy_pages(), which copies the content of theKonstantin Belousov2013-03-141-0/+24
* Switch the vm_object mutex to be a rwlock. This will enable in theAttilio Rao2013-03-092-5/+6
* MFcalloutng:Alexander Motin2013-02-281-15/+7
* MFcalloutng:Davide Italiano2013-02-281-3/+4
* kernacc() expects all KVAs to be covered in the kernel map. With theMarcel Moolenaar2013-02-251-4/+4
* Close a race relating to setting the PCPU pointer (r13). Register r13Marcel Moolenaar2013-02-171-5/+5
* Return EFAULT when the address is not a kernel virtual address.Marcel Moolenaar2013-02-161-0/+2
* Eliminate the PC_CURTHREAD symbol and load the current thread'sMarcel Moolenaar2013-02-123-35/+33
* Reform the busdma API so that new types may be added without modifyingKonstantin Belousov2013-02-121-244/+224
* Now that we actually use more memory descriptors, make sure to dumpMarcel Moolenaar2013-02-121-1/+4