summaryrefslogtreecommitdiff
path: root/sys/arch/amd64/include
AgeCommit message (Collapse)Author
2005-05-25This patch is mortly art's work and was done *a year* ago. Art wants to thankNiklas Hallqvist
everyone for the prompt review and ok of this work ;-) Yeah, that includes me too, or maybe especially me. I am sorry. Change the sched_lock to a mutex. This fixes, among other things, the infamous "telnet localhost &" problem. The real bug in that case was that the sched_lock which is by design a non-recursive lock, was recursively acquired, and not enough releases made us hold the lock in the idle loop, blocking scheduling on the other processors. Some of the other processors would hold the biglock though, which made it impossible for cpu 0 to enter the kernel... A nice deadlock. Let me just say debugging this for days just to realize that it was all fixed in an old diff noone ever ok'd was somewhat of an anti-climax. This diff also changes splsched to be correct for all our architectures.
2005-05-25comment typoJason Wright
2005-04-19nothing uses spllowersoftclock() anymoreMichael Shalayeff
2005-04-19CLKF_BASEPRI we do not have no more; noticed by miodMichael Shalayeff
2005-04-14internal _BSD_WCTRANS_T_, _BSD_MSTATE_T_, _BSD_WCTYPE_T_ types.Marc Espie
2005-04-11use MD #define to choose stackgap size per-architecture. on sparc, specialTheo de Raadt
case sun4c/sun4 -- because address space is more constrained
2005-04-08add rcs idsJolan Luff
2005-02-13Remove __P usage in sys that has crept back in.Jonathan Gray
'Looks fine' millert@, ok miod@
2005-01-10proper SET_PC_REGS,Marc Espie
okay kettenis@, something-vaguely-looking-like-an-okay mickey@
2004-12-07remove old and unused NetBSD specific cruft.Brad Smith
2004-11-28MAXSLP is not really an MD-configurable define so move it to param.h; miod@ ↵Michael Shalayeff
testing
2004-11-26Kill __HAVE_EVCOUNT, now that all architectures provide them.Miod Vallat
2004-11-10Remove __cplusplus crud.Alexander Yurchenko
2004-11-02Remove __HAVE_NWSCONS and related remnants of pre-wscons days; no functionalMiod Vallat
change.
2004-09-16Rely upon __LP64__ to choose {U,}LONG_{MIN,MAX} values, rather than aMiod Vallat
homegrown define. ok deraadt@
2004-08-21Enter cdboot, a CD-specific second-stage bootrap. Based on the i386Tom Cosgrove
cdboot that Toby and I put together at the hackathon. "go for it" deraadt@
2004-08-06rename sparc kill_user_windows() to pmap_unuse_final(). provide empty stubsTheo de Raadt
on all other architectures. remove last architecture dependent #ifdef from uvm code.
2004-08-06provide md USPACE_ALIGN zero on all but mips; deradat@ pefo@ okMichael Shalayeff
2004-07-22mutex instead of SIMPLELOCK for mp ddb.Artur Grabowski
"reads good" niklas@ "looks good" andreas@ "works" tedu@
2004-07-20MD mutex implementation on amd64.Artur Grabowski
2004-07-19Implement __HAVE_PMAP_DIRECT on amd64 using large pages. At this momentArtur Grabowski
it's limited to 512GB (one L4 page table entry) physical memory. Only used carefully at this moment, but more improvements are in the pipeline. tested by many, deraadt@ ok.
2004-07-15put int into a typeTheo de Raadt
2004-06-28Use new event counter API for interrupt counting on amd64. Based in partTheo de Raadt
on some changes in the i386 codebase.
2004-06-26deinline splraise, spllower and setsoftint.Artur Grabowski
Makes the kernel smaller and faster. deraadt@ ok
2004-06-25'machine cpuinfo' and 'machine ddbcpu' in ddb for amd64Andreas Gunnarsson
2004-06-25SMP support. Big parts from NetBSD, but with some really serious debuggingArtur Grabowski
done by me, niklas and others. Especially wrt. NXE support. Still needs some polishing, especially in dmesg messages, but we're now building kernel faster than ever.
2004-06-22Switch amd64 to __HAVE_CPUINFOArtur Grabowski
deraadt@ ok
2004-06-13debranch SMP, have funNiklas Hallqvist
2004-05-20Make MINGDTSIZ a multiple of PAGE_SIZE to avoid destroying the gdt table.Thomas Nordin
ok tom@ toby@
2004-05-20Properly flush instruction cache for ptrace(PT_WRTIE_{DI}, ...) on powerpcMark Kettenis
and m68k. ok drahn@, millert@
2004-05-13activate systrace on amd64, while here get rid of syscall_{plain,fancy}Nikolay Sturm
instead use syscall() as everywhere else ok mickey, tested and ok tedu@
2004-05-13Fix userland profiling on amd64, update to new NetBSD version of file.Dale Rahn
kernel profiling does not yet work. ok marc@
2004-05-07spllower should return the previous level, to match other archs.Ted Unangst
"looks right" miod
2004-04-19remove the GATEWAY junk thingy; at the same time, select a new fatTheo de Raadt
cluster value that noone will really need to crank.
2004-03-09simplify the delay stuffTheo de Raadt
2004-02-28rename our NPXCW settingTheo de Raadt
2004-02-28sysctl hw.cpuspeed outputTheo de Raadt
2004-02-27move to amd64_() functionsTheo de Raadt
2004-02-27put a bit more flesh in the sysctl machdep; parts from tomTheo de Raadt
2004-02-27move to amd64 MACHINE_ARCHTheo de Raadt
2004-02-26put the goo there for ldt handling, even if we do not do it yetTheo de Raadt
2004-02-25dkcsum stuff for amd64, written by tom, who cannot commit it at the moment.Theo de Raadt
now the amd64 knows what drive it was booted from.
2004-02-23get use of NX; partially from netbsd; passes the regress; deraadt@ okMichael Shalayeff
2004-02-23provide _barrier method w/ {l,s,m}fence instructionsMichael Shalayeff
2004-02-23fix a pastoMichael Shalayeff
2004-02-23add a comment on set/clr 64bit opsMichael Shalayeff
2004-02-13save/restore fpu state around the signal handler. skip a gap on unempty ↵Michael Shalayeff
stack per abi. form drahn@ and deraadt@
2004-02-11permit installboot to at least compile... remove some crudTheo de Raadt
2004-02-10Relocation types, used by ld.soDale Rahn
2004-02-09repair cpu dmesg print a bitMichael Shalayeff
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-09 00:46:31 +0000