summaryrefslogtreecommitdiffstats
path: root/sys/amd64
Commit message (Expand)AuthorAgeFilesLines
* Put in place the infrastructure for improved UP and SMP TLB management.alc1999-04-025-42/+101
* Purging lint from the Bruce filter.phk1999-03-302-4/+10
* Delete all references to the "aic" driver. It isn't in the tree, andken1999-03-291-2/+1
* Ifdef declaration of a conditionally defined function "timezero".dt1999-03-282-2/+6
* Link the bb structures together as we find them.phk1999-03-212-4/+20
* Eliminate a pointless TLB flush from the SMP idle loop.alc1999-03-202-14/+2
* Change btrl/btsl to cmpl/movl, since each cpu now has their own copyjlemon1999-03-182-10/+10
* Look for the right ACPI table signature.msmith1999-03-161-2/+2
* Rewert the atapi CDROM driver's name to wcd.sos1999-03-161-2/+2
* pmap_qenter/pmap_qremove:alc1999-03-131-89/+62
* Increased kernel virtual address space to 1GB. NOTE: You MUST have fixeddg1999-03-111-4/+4
* Fix two tests against hex. values for CPUID.roberto1999-03-101-3/+3
* Make TIMER_FREQ a normal, undocumented option. Raise confusion tophk1999-03-091-1/+2
* Expose a slightly-lower-level interface to timeouts which allows callerswollman1999-03-061-1/+3
* The magic "no-cpu" cpu number is 0xff. Don't misrepresent cpubde1999-03-053-9/+9
* Fix an SMP-only TLB invalidation bug. Specifically, disablealc1999-03-051-1/+5
* Correct casts in vtophys and avtophys to be vm_offset_t.dg1999-03-021-3/+3
* Update to know about current kernel directory layout.mckusick1999-02-281-22/+31
* Removed all traces of `p_switchtime'. The relevant timestamp is per-cpu,bde1999-02-283-28/+15
* Don't call assign_apic_irq with a value for irq that is out of range.tegge1999-02-263-6/+6
* Don't forget to update `switchticks' in corner cases (except forbde1999-02-252-4/+8
* Added a per-cpu variable `switchticks' for use in scheduling.bde1999-02-222-2/+4
* Rename hid device to uhid (HID: Human Interface Device)n_hibma1999-02-211-2/+2
* Removed uhub from list. Mandatory with usb device and this was alreadyn_hibma1999-02-201-2/+1
* Really make the "Rename nlpt to lpt." purported to have been made inobrien1999-02-201-2/+2
* Bit 24 of the Feature Flag is FXSR (for Fast FP Save and Restore).roberto1999-02-201-2/+2
* Introduce machine-dependent macro pgtok() to convert page count to numberluoqi1999-02-193-15/+15
* Hide access to vmspace:vm_pmap with inline function vmspace_pmap(). Thisluoqi1999-02-195-19/+16
* On the i386, load the ELF dynamic linker where an mmap(0, ...) wouldjdp1999-02-191-5/+7
* Add a little bit more identifying information to the myriad PCI networkwollman1999-02-181-14/+17
* * Change sysctl from using linker_set to construct its tree using SLISTs.dfr1999-02-161-1/+2
* MF3: add SYSVMSGjkh1999-02-141-3/+5
* Rename nlpt to lpt.nsouch1999-02-141-2/+2
* Don't pass PSL_NT to vm86 signal handlers. Some vm86/real modebde1999-02-131-2/+8
* Zero p->retval[1] when starting a process. This value ends up in %edxmsmith1999-02-111-1/+8
* Fix typosjkoshy1999-02-111-3/+3
* Use ppbus instead of the lpt driver. Throw in a (commented-out) vpo entrydes1999-02-101-2/+8
* Adjust idle zero-page fill hysteresis based on tests. Use 2/3 and 4/5dillon1999-02-081-4/+8
* Rip out PQ_ZERO queue. PQ_ZERO functionality is now combined in withdillon1999-02-081-19/+23
* Change the load address of the ELF dynamic linker from "2L*MAXDSIZ"jdp1999-02-071-1/+11
* replace previous stupid comment with one more appropriateadam1999-02-041-2/+1
* remind that apm is required in order for timekeeping to workadam1999-02-041-1/+2
* Recognize Pentium II Xeon, Celeron and Pentium III cpus. Because CPUkato1999-02-042-3/+13
* Fixed the type of target_page to vm_offset_t (unsigned). This fixes adg1999-02-031-8/+8
* Check for signals while reading /dev/urandom. Reading 10MB frombde1999-02-021-1/+12
* Added a hopefully-machine-independent macro for determining if abde1999-02-021-1/+3
* Use offset to _pc98_system_parameter instead of immediate value whichkato1999-01-312-8/+12
* Moved pc98_system_parameter from .text to .data to make ELF kernelkato1999-01-302-20/+18
* More const fixes for -Wall, -Wcast-qualdillon1999-01-291-2/+2
* More -Wall / -Wcast-qual cleanup. Also, EXEC_SET can't usedillon1999-01-292-5/+5
OpenPOWER on IntegriCloud