summaryrefslogtreecommitdiffstats
path: root/sys/amd64/include
Commit message (Expand)AuthorAgeFilesLines
* sys/sys/limits.h:kan2003-05-192-3/+3
* Initialize logical_cpus_mask when the logical CPUs are enumerated inalc2003-05-151-2/+5
* Collect the nastiness for preserving the kernel MSR_GSBASE around thepeter2003-05-152-1/+36
* Use compile time constants for things like PTmap[] etc because they'repeter2003-05-151-7/+3
* Add BASIC i386 binary support for the amd64 kernel. This is largelypeter2003-05-145-4/+35
* For the page fault handler, save %cr2 in the outer trap handler so thatpeter2003-05-122-0/+4
* Sync ucontext with reality. The struct trapframe changes need to bepeter2003-05-121-11/+11
* AMD64 physical space is much larger than i386, de-i386 the bus_space andpeter2003-05-126-1373/+157
* Give a %fs and %gs to userland. Use swapgs to obtain the kernel %GS.basepeter2003-05-122-1/+21
* Make atdevbase long for the KERNBASE > 4GB casepeter2003-05-111-1/+1
* Provide a fake varargs implementation for lint's benefit. This waypeter2003-05-102-0/+17
* Remove _ARCH_INDIRECT ifdefs. They existed for lib/msun/* on i386, whichpeter2003-05-101-63/+0
* bcopyb() isn't used on amd64 kernel (it only exists for i386/pcvt)peter2003-05-101-1/+0
* Include the MXCSR initial values, based on the AMD docs. This filepeter2003-05-092-0/+4
* Style fixes.kan2003-05-041-8/+11
* Slight reorg and added AMD64 support. A couple of the MODINFOMD_* valuespeter2003-05-011-0/+34
* Commit MD parts of a loosely functional AMD64 port. This is based onpeter2003-05-0142-1642/+719
* Repocopy from x86_64/... to amd64/...peter2003-04-301-8/+7
* Deprecate machine/limits.h in favor of new sys/limits.h.kan2003-04-291-64/+4
* Use inlines for loading and storing page table entries. Use cmpxchg8b forjake2003-04-281-7/+45
* Add a new sys/limits.h file which in turn depends on machine/_limits.hkan2003-04-231-53/+35
* Backout my last commit.davidxu2003-04-201-4/+4
* Don't return garbage in high 16 bits.davidxu2003-04-191-4/+4
* Change the operation parameter of bus_dmamap_sync() from anmux2003-04-101-10/+6
* Remove invalid cast to vm_offset_t to avoid truncating a physical addressjake2003-04-081-1/+1
* Better fix for previous previous which still allows the 4megs of kva atjake2003-04-072-3/+3
* Define ovbcopy() as a macro which expands to the equivalent bcopy() call,des2003-04-041-4/+5
* Bandaid fix for previous commit while I figure out why it broke. Thisjake2003-04-041-2/+2
* - Removed APTD and associated macros, it is no longer used.jake2003-04-031-9/+7
* Commit a partial lazy thread switch mechanism for i386. it isn't as lazypeter2003-04-024-2/+26
* - Add support for PAE and more than 4 gigs of ram on x86, dependent on thejake2003-03-303-6/+74
* - Remove invalid casts.jake2003-03-301-1/+1
* - Convert all uses of pmap_pte and get_ptbase to pmap_pte_quick. Whenjake2003-03-301-1/+1
* Nuke options HTT infavor of machdep.hlt_logical_cpus tunable/sysctl.ps2003-03-262-21/+89
* - Add vm_paddr_t, a physical address type. This is required for systemsjake2003-03-254-11/+13
* Expand the APIC ID mask field of the ICR register to 8 bits intead of justjhb2003-03-171-1/+1
* Made the prototypes for pmap_kenter and pmap_kremove MD. These functionsjake2003-03-161-0/+2
* Use bus_space_handle_t to represent host port and virtual addresses;jake2003-03-112-24/+24
* Wrap the hyperthreading support code with the HTT kernel option.jhb2003-03-041-0/+21
* Remove some long unused declarations. (For example, the PV flags have notalc2003-02-271-6/+0
* Correctly set BUS_SPACE_MAXSIZE in all the busdma backends.mux2003-02-262-2/+2
* - Added inlines pmap_is_current, pmap_is_alternate and pmap_set_alternatejake2003-02-251-1/+1
* - Removed UMAXPTDI and UMAXPTEOFF.jake2003-02-242-3/+1
* The mpbiosreason variable does not used for pc98.nyan2003-02-241-0/+2
* Allow machines with one CPU and a valid mp table to boot an SMP kernel.tegge2003-02-231-0/+2
* Previous commit missed a 1 that should be NGPTD, and an NPDEPG that shouldjake2003-02-231-1/+1
* - Added macros NPGPTD, NBPTD, and NPDEPTD, for dealing with the size of thejake2003-02-231-4/+4
* - Added macros PDESHIFT and PTESHIFT, use these instead of magic constantsjake2003-02-231-2/+2
* The root of the splay tree maintained within the pm_pteobj always refersalc2003-02-221-1/+0
* Back out M_* changes, per decision of the TRB.imp2003-02-191-4/+4
OpenPOWER on IntegriCloud