summaryrefslogtreecommitdiffstats
path: root/sys/amd64
Commit message (Collapse)AuthorAgeFilesLines
* The per-cpu temporary buffers are not needed since the pcb_save areas havetegge2001-07-172-28/+10
| | | | | | | the proper alignment. Change dummy variable in npxinit from stack to bss to ensure proper alignment. Reviewed by: bde
* Use PCPU_GET(cpuid) instead of curproc->p_oncpu.tegge2001-07-162-18/+18
| | | | Reviewed by: peter
* Fix MCOUNT_ENTER() so it actually compiles in the profiling case.jhb2001-07-141-1/+1
| | | | | Pointy hat to: me Submitted by: Danny J. Zerkel <dzerkel@columbus.rr.com>
* `pcn' supports AMD Am79C97x cards, not Am79C79x cards.dd2001-07-131-1/+1
| | | | | PR: 28946 Submitted by: Ryuichiro Imura <imura@ryu16.org>
* Unbroke kernel if I686_CPU is not defined.sobomax2001-07-131-0/+2
|
* The #define for pcb_savefpu seems to do more harm than good.peter2001-07-121-1/+0
|
* Fix another missed pcb_savefpu reference (inside NPX_DEBUG)peter2001-07-122-4/+4
|
* Forgot this fix from another tree. make enable_sse() a real prototype.peter2001-07-121-1/+1
|
* Move init_sse() out of the "GenuineIntel" section, my AthlonMP systempeter2001-07-121-1/+1
| | | | has it, for example, and it works fine.
* Activate SSE/SIMD. This is the extra context switching support thatpeter2001-07-1222-44/+387
| | | | | | | | | | | | | | | we are required to do if we let user processes use the extra 128 bit registers etc. This is the base part of the diff I got from: http://www.issei.org/issei/FreeBSD/sse.html I believe this is by: Mr. SUZUKI Issei <issei@issei.org> SMP support apparently by: Takekazu KATO <kato@chino.it.okayama-u.ac.jp> Test code by: NAKAMURA Kazushi <kaz@kobe1995.net>, see http://kobe1995.net/~kaz/FreeBSD/SSE.en.html I have fixed a couple of style(9) deviations. I have some followup commits to fix a couple of non-style things.
* Add 'hwatch' and 'dhwatch' ddb commands analogous to 'watch' andbsd2001-07-112-70/+292
| | | | | | | | | | 'dwatch'. The new commands install hardware watchpoints if supported by the architecture and if there are enough registers to cover the desired memory area. No objection by: audit@, hackers@ MFC after: 2 weeks
* A set of changes to reduce the number of include files the kerneljulian2001-07-082-2/+2
| | | | | | takes from /usr/include. I cannot check them on alpha.. (will try beast) Briefly looked at by: Warner Losh <imp@harmony.village.org>
* Move vm_page_zero_idle() from machine-dependant sections to adillon2001-07-051-61/+0
| | | | | machine-independant source file, vm/vm_zeroidle.c. It was exactly the same for all platforms and updating them all was getting annoying.
* Reorg vm_page.c into vm_page.c, vm_pageq.c, and vm_contig.c (for contigmalloc).dillon2001-07-041-1/+1
| | | | | | | | | | | Also removed some spl's and added some VM mutexes, but they are not actually used yet, so this commit does not really make any operational changes to the system. vm_page.c relates to vm_page_t manipulation, including high level deactivation, activation, etc... vm_pageq.c relates to finding free pages and aquiring exclusive access to a page queue (exclusivity part not yet implemented). And the world still builds... :-)
* With Alfred's permission, remove vm_mtx in favor of a fine-grained approachdillon2001-07-046-41/+22
| | | | | | | | | (this commit is just the first stage). Also add various GIANT_ macros to formalize the removal of Giant, making it easy to test in a more piecemeal fashion. These macros will allow us to test fine-grained locks to a degree before removing Giant, and also after, and to remove Giant in a piecemeal fashion via sysctl's on those subsystems which the authors believe can operate without Giant.
* Make the code to read the kernel message buffer via sysctl machine-tmm2001-07-031-42/+0
| | | | | independent and rename the corresponding sysctls from machdep.msgbuf and machdep.msgbuf_clear (i386 only) to kern.msgbuf and kern.msgbuf_clear.
* Add Transmeta Crusoe LongRun support.iwasaki2001-07-031-0/+198
| | | | | | Submitted by: Tamotsu HATTORI <athlete@kta.att.ne.jp> Reviewed by: arch@ folks MFC after: 1 week
* Quiet warning by removing ast() prototype.jhb2001-07-031-1/+0
| | | | Forgotten by: jhb (me)
* Allow Giant to be recursed when a process terminates.jhb2001-07-031-2/+2
|
* gif(4) and stf(4) modernization:brooks2001-07-021-1/+1
| | | | | | | | | | | - Remove gif dependencies from stf. - Make gif and stf into modules - Make gif cloneable. PR: kern/27983 Reviewed by: ru, ume Obtained from: NetBSD MFC after: 1 week
* Repo copy i8237.h to dev/ic so we can get rid of some of the final vestigesimp2001-06-301-1/+1
| | | | of includes of i386 files from non-i386 ports.
* Move ast() and userret() to sys/kern/subr_trap.c now that they are MI.jhb2001-06-291-120/+0
|
* Remove cruft from old bus.imp2001-06-291-3/+0
|
* Add a new MI pointer to the process' trapframe p_frame instead of usingjhb2001-06-296-29/+28
| | | | | | various differently named pointers buried under p_md. Reviewed by: jake (in principle)
* Grab Giant around trap_pfault() for now.jhb2001-06-291-0/+4
|
* Get kernel profiling on SMP systems closer to working by replacing thejhb2001-06-284-25/+8
| | | | | mcount spin mutex with a very simple non-recursive spinlock implemented using atomic operations.
* Provide access to the IA32 hardware debug registers from the ddbbsd2001-06-284-28/+120
| | | | | | | kernel debugger. Proper use of these registers allows setting hardware watchpoints for use in kernel debugging. MFC after: 2 weeks
* Recognize FC-PGA2 Pentium III (Tualatin).kato2001-06-261-0/+1
|
* Add code to detect Transmeta Crusoe cpus.dfr2001-06-251-2/+55
|
* - Grab the proc lock around CURSIG and postsig(). Don't release the procjhb2001-06-221-3/+4
| | | | | | | | lock until after grabbing the sched_lock to avoid CURSIG racing with psignal. - Don't grab Giant for addupc_task() as it isn't needed. Reported by: tegge (signal race), bde (addupc_task a while back)
* Make the hw.physmem and hw.usermem variables unsigned so that they dontpeter2001-06-221-2/+2
| | | | come up as negative on machines with >2GB ram.
* Initialize mutexes needed early on all in the same place so that thejhb2001-06-181-15/+6
| | | | | | startup routine more closely matches that of alpha and ia64. At some point the common mutexes shared across all platforms probably should move into sys/kern_mutex.c.
* - Add support for decoding syscall names. (Brought over from the new alphajhb2001-06-181-37/+61
| | | | | | | | | | | | trace code that was brought over from NetBSD.) - Check for "syscall_with_err_pushed" as the label prior to a syscall trap frame rather than "Xlcall_syscall" and "Xint0x80_syscall". We don't have a valid trapframe during the short range of code that those two symbols now cover. - Simplify db_next_frame() to avoid duplicating the code for the different trap frame types. - Don't try to trace a swapped-out process. (Brought over from NetBSD via the new alpha trace code.)
* Include sys/pcpu.h to get the prototype for globaldata_register() to quietjhb2001-06-183-0/+3
| | | | a warning.
* Don't assume that resource type is ioport and rid equal 0.nyan2001-06-171-5/+6
|
* Fix "alignemnt" typo.alex2001-06-163-3/+3
|
* Fix warnings:peter2001-06-152-6/+6
| | | | | 908: warning: long unsigned int format, unsigned int arg (arg 3) 887: warning: `timezero' defined but not used
* Hints overhaul:peter2001-06-122-3/+3
| | | | | | | | | - Replace some very poorly thought out API hacks that should have been fixed a long while ago. - Provide some much more flexible search functions (resource_find_*()) - Use strings for storage instead of an outgrowth of the rather inconvenient temporary ioconf table from config(). We already had a fallback to using strings before malloc/vm was running anyway.
* Fix style of defines.obrien2001-06-091-38/+38
|
* Don't hold sched_lock across addupc_task().jhb2001-06-061-1/+1
| | | | | Reported by: David Taylor <davidt@yadt.co.uk> Submitted by: bde
* Properly wrap mtx_intr_enable() macro in "do $bla while (0)"phk2001-06-021-1/+1
|
* Clean up the code exporting interrupt statistics via sysctl a bit:tmm2001-06-016-7/+2
| | | | | | | | | | | | | - move the sysctl code to kern_intr.c - do not use INTRCNT_COUNT, but rather eintrcnt - intrcnt to determine the length of the intrcnt array - move the declarations of intrnames, eintrnames, intrcnt and eintrcnt from machine-dependent include files to sys/interrupt.h - remove the hw.nintr sysctl, it is not needed. - fix various style bugs Requested by: bde Reviewed by: bde (some time ago)
* Quiet warnings by adding a prototype for set_user_ldt_rv() and making itjhb2001-05-301-1/+6
| | | | conditional on #ifdef SMP.
* We can't grab the sched_lock in set_user_ldt() because when it is calledjhb2001-05-302-6/+25
| | | | | | | | | | | from cpu_switch(), curproc has been changed, but the sched_lock owner will not be updated until we return to mi_switch(), thus we deadlock against ourselves. As a workaround, push the acquire and release of sched_lock out to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in set_user_ldt for the same reason. Sleuting by: tmm Tested by: tmm, dougb
* move wx to be part of miibus requiring chipsetsmjacob2001-05-301-1/+1
|
* Remove MFS options from all example kernel configs.phk2001-05-291-1/+0
|
* Remove pcm hints here now that it's gone from GENERIC.jkh2001-05-261-4/+0
| | | | Reminded-by: bde
* Take pcm (audio) back out of GENERIC; there appears to be somejkh2001-05-251-3/+0
| | | | | | | concensus, most notably among the maintainers, that it's better loaded as a module. Finally-pushed-over-the-edge-by-the-anguished-cries-of: rwatson
* Don't acquire Giant just to call trap_fatal(), we are about to panicjhb2001-05-231-4/+0
| | | | | anyway so we'd rather see the printf's then block if the system is hosed.
* pmap_mapdev needs the vm_mtx, aquire it if not already lockedalfred2001-05-231-0/+8
|
OpenPOWER on IntegriCloud