summaryrefslogtreecommitdiffstats
path: root/sys/amd64
Commit message (Expand)AuthorAgeFilesLines
* netchild's mega-patch to isolate compiler dependencies into a centraljoerg2005-03-0215-84/+122
* Catch up with the "physical memory" sysctl change.obrien2005-03-011-0/+2
* MFi386: Sync whitespace and an abbreviationpeter2005-02-281-4/+4
* MFi386: Update alc's copyright noticepeter2005-02-281-1/+1
* MFi386: Bring over John's local apic timer codepeter2005-02-288-89/+219
* Typo.pjd2005-02-281-1/+1
* Spell "options" correctly as "options ".obrien2005-02-281-7/+7
* Connect "options MP_WATCHDOG" to the LINT builds.obrien2005-02-281-0/+5
* MFi386: rev 1.3:obrien2005-02-271-20/+31
* Remove recently added note about DEVICE_POLLING not working with SMP.trhodes2005-02-251-1/+0
* Remove acpi_perf from {ARCH}/conf/NOTES, to make tinderbox happy.delphij2005-02-251-3/+0
* According to kern_poll.c, you cannot use DEVICE_POLLING with SMP. Add atrhodes2005-02-231-0/+1
* MFi386: r1.17: Treat pin 0 as IRQ 0 rather than ExtINT if mixed mode is notjhb2005-02-221-2/+3
* - Add a new quirk to indicate that pin 0 of the first I/O APIC is reallyjhb2005-02-221-2/+8
* Use a common multi-inclusion protection, and add such aru2005-02-191-4/+4
* - Add a custom version of exec_copyin_args() to deal with the 32-bitjhb2005-02-182-84/+118
* MFi386 rev 1.61: Fix a few bugs in the legacy cpu attachment ivars.njl2005-02-151-3/+2
* MFi386: read from RTC_INTR after writing to RTC_STATUSBpeter2005-02-081-0/+2
* Since we are quite unlikely to ever face another platform whichphk2005-02-061-16/+13
* Staticize the legacy cpu devclasses and revert the name for the acpi_cpunjl2005-02-061-1/+1
* Finish the job of sorting all includes and fix the build by includingnjl2005-02-061-18/+15
* Make cpu_est_clockrate() more accurate by disabling interrupts for thenjl2005-02-051-2/+10
* Build cpufreq and acpi_perf on platforms that are likely to be able tonjl2005-02-051-0/+3
* Implement proper handling of PG_G mappings in pmap_protect(). (I don'talc2005-02-051-1/+4
* MFi386: Merge updates to the cpu pseudo-driver. Compile, not runtimenjl2005-02-041-26/+64
* Add an implementation of cpu_est_clockrate(9). This function estimates thenjl2005-02-041-7/+47
* o Split out kernel part of execve(2) syscall into two parts: one thatsobomax2005-01-291-9/+9
* JumboMFi386: use bitmapped IPI handler. Update elcr and default mptablepeter2005-01-2113-138/+298
* MFi386: handle PSL_T properly across fork. Typo fix.peter2005-01-211-1/+13
* MFi386: whitespace, copyright header, etc updatespeter2005-01-216-7/+3
* MFi386: use %rip - 1 for the symbol search address (for noreturn funcs)peter2005-01-211-2/+8
* Remove redundant code to drop per-thread debug register state fromjhb2005-01-141-7/+0
* There are no PC98 amd64 machines, so gc a few stray ifdefs.imp2005-01-112-9/+0
* Introduce bus_dmamap_load_mbuf_sg(). Instead of taking a callback arg, thisscottl2005-01-072-13/+53
* These are no longer relevant. They are scripts for extracting hintsimp2005-01-071-115/+0
* Begin all license/copyright comments with /*-imp2005-01-0534-34/+34
* PC98 will never be defined for amd64imp2005-01-051-5/+0
* o Use tab instead of spaces for puc(4) line.kuriyama2005-01-051-4/+4
* Minor sync to i386 GENERIC in the form of comments and whitespace.jhb2004-12-301-2/+3
* MFi386: Restore cpu_reset proxy code to enable reset from ddb on an AP.njl2004-12-271-4/+39
* Reduce diffs to i386.njl2004-12-271-16/+11
* Get rid of #ifdef for legacy system. Move that into the MD code.imp2004-12-241-0/+7
* Modify pmap_enter_quick() so that it expects the page queues to be lockedalc2004-12-231-3/+2
* Use vtopde() instead of pmap_pde() in pmap_kextract(); vtopde() is smalleralc2004-12-211-1/+1
* In the common case, pmap_enter_quick() completes without sleeping.alc2004-12-151-2/+12
* MFi386: rev 1.12: re-allow fast interrupts to cause preemptionpeter2004-12-061-2/+0
* Replace (inlined) pmap_pte() calls with smaller, faster code wherealc2004-12-041-7/+7
* For efficiency eliminate the call to pmap_pte() from pmap_protect()'s andalc2004-12-021-14/+18
* Change gdb_cpu_setreg() to not take the value to which to set themarcel2004-12-012-5/+4
* Remove unused cnt variable for the SMP case. Trim some excessive blankpeter2004-11-301-5/+1
OpenPOWER on IntegriCloud