aboutsummaryrefslogtreecommitdiff
path: root/sys/i386
Commit message (Expand)AuthorAgeFilesLines
* Even though I'm not quite sure that the call_func stuff will work properlyAdrian Chadd2009-05-301-2/+3
* Don't schedule a CALL_FUNCTION_VECTOR software IPI if the IPI was signaledAdrian Chadd2009-05-301-3/+3
* Correctly report the IPI IRQs being created; make it clear what vectors they ...Adrian Chadd2009-05-301-4/+4
* Place hostnames and similar information fully under the prison system.Jamie Gritton2009-05-293-13/+5
* Revert to 2-clause.Adrian Chadd2009-05-291-2/+0
* Fix the Xen TOD update when the hypervisor wall clock is nudged.Adrian Chadd2009-05-291-0/+14
* Migrate the Xen hypervisor clock reading routines into somethingAdrian Chadd2009-05-293-49/+141
* Say hello to a very basic, read-only, Xen Hypervisor RTC.Adrian Chadd2009-05-281-0/+191
* We don't need d_thread_t for cross-branch portability here anymore.Warner Losh2009-05-201-4/+4
* Some minor style changes:Warner Losh2009-05-201-22/+14
* Don't bother reading the initial value of the machine check banks duringJohn Baldwin2009-05-201-4/+0
* - Add a tunable 'hw.mca.enabled' that can be used to enable/disable theJohn Baldwin2009-05-181-11/+14
* Add a read-only sysctl hw.pci.mcfg to mirror the tunable by the same name.John Baldwin2009-05-181-0/+5
* Bump CACHE_LINE_SIZE to 128 for x86. Intel's manuals explicitly recommendJohn Baldwin2009-05-181-1/+1
* Add cpu_flush_dcache() for use after non-DMA based I/O so that aMarcel Moolenaar2009-05-181-0/+10
* Somewhere between 2.6.23 and 2.6.27, Linux added SOCK_CLOEXEC andDmitry Chagin2009-05-161-0/+1
* Trim the default set of device hints on i386 and amd64:John Baldwin2009-05-141-42/+0
* FreeBSD right now support 32 CPUs on all the architectures at least.Attilio Rao2009-05-144-78/+21
* Implement simple machine check support for amd64 and i386.John Baldwin2009-05-136-0/+618
* Correct a rare use-after-free error in pmap_copy(). This error wasAlan Cox2009-05-131-2/+4
* Remove unused variables.Christian Brueffer2009-05-121-4/+1
* Do not export AT_CLKTCK when emulating Linux kernel priorDmitry Chagin2009-05-101-1/+11
* Rework r189362, r191883.Dmitry Chagin2009-05-101-1/+2
* - Use "device\t" and "options \t" for consistency.Jun Kuriyama2009-05-106-24/+24
* Regenerate system call tables to use SVN ids.Ed Schouten2009-05-085-7/+12
* Regenerate ibcs2 system call table.Ed Schouten2009-05-083-20/+12
* Burn TTY ioctl bridges in compat layers.Ed Schouten2009-05-082-33/+2
* Introduce a new virtualization container, provisionally named vprocg, to holdMarko Zec2009-05-081-0/+1
* Move the per-prison Linux MIB from a private one-off pointer to the newJamie Gritton2009-05-071-0/+2
* To avoid excessive code duplication move MI definitions to the MIDmitry Chagin2009-05-071-8/+0
* Do not try to initialize LAPIC timer if we are not going to use it.Alexander Motin2009-05-051-1/+1
* Unlock the largest standard CPUID on Intel CPUs for both amd64 and i386 andJung-uk Kim2009-05-041-11/+18
* Oops, sorry. Fix for fix.Alexander Motin2009-05-041-1/+1
* There is no atrtc driver in pc98, so hide atrtcclock_disable variable usageAlexander Motin2009-05-041-0/+2
* Rename statclock_disable variable to atrtcclock_disable that it actually is,Alexander Motin2009-05-034-24/+17
* fix XEN compilationKip Macy2009-05-021-0/+3
* Add support for using i8254 and rtc timers as event sources for i386 SMPAlexander Motin2009-05-024-3/+69
* Move extern variable definitions to the header file.Dmitry Chagin2009-05-021-3/+1
* Small addition to r191720.Alexander Motin2009-05-011-1/+5
* o add uathSam Leffler2009-05-011-1/+2
* Use value -1 instead of 0 for marking unused APIC vectors. This fixesAlexander Motin2009-05-011-5/+11
* Reimplement futexes.Dmitry Chagin2009-05-011-3/+3
* - Fix divide-by-zero panic when SMP kernel is used on UP system[1].Jung-uk Kim2009-04-301-1/+7
* - Add support for cpuid leaf 0xb. This allows us to determine theJeff Roberson2009-04-294-83/+155
* Reduce the number of bounce zones (and thus the number of bounce pagesJohn Baldwin2009-04-231-8/+2
* Adjust the way we number CPUs on x86 so that we attempt to "group" allJohn Baldwin2009-04-221-21/+29
* Don't conditionally define CACHE_LINE_SHIFT, as we anticipate sizingRobert Watson2009-04-201-2/+0
* Add description and cautionary note regarding CACHE_LINE_SIZE.Robert Watson2009-04-191-0/+4
* For each architecture, define CACHE_LINE_SHIFT and a derivedRobert Watson2009-04-191-0/+5
* - Import infrastructure for caching flows as a means of accelerating L3 and L...Kip Macy2009-04-191-0/+2