summaryrefslogtreecommitdiff
path: root/sys/arch
AgeCommit message (Collapse)Author
2000-02-08evil typo; from Rusty Hunt <alaric@exoinc.com>Michael Shalayeff
2000-02-08Split low ISA memory (<16MB) into its own freelist, which is used last byNiklas Hallqvist
the VM subsystem. This makes isadmaattach panics go away on large memory systems. Also use atop instead of btoc for consistency when dealing with the initial chunks of physical memory to give to UVM.
2000-02-07Rough but working driver for ICP-Vortex RAIDNiklas Hallqvist
2000-02-04In cases where we flush a page from the cache and tlb we want toArtur Grabowski
flush it from the tlb _after_ the cache because some cache flushes can reload the tlb. (fixes random coredumps on some cpus).
2000-02-04esp_init collides with netinet; renamed itTheo de Raadt
2000-02-04Modify ia_iosize so probe messages print correctly for the clock devicesimp
on isa buses.
2000-02-04Some cpus might have the cache running even before we enable it.Artur Grabowski
Uncache the pagetables in pmap_bootstrap4m and recache them again in pmap_cache_enable if we can. This fixes the problems seen on SM30.
2000-02-04Externalize comstop()Angelos D. Keromytis
2000-02-03Prevent overflow in computation of buffer cache limitationNiklas Hallqvist
2000-02-03remove extraneous spaces and tabsMichael Shalayeff
2000-02-03Remove overly verbose printf during driver config.Dale S. Rahn
2000-02-03Define missed when the intial bus_dma code was checked in.Dale S. Rahn
Full dma code not yet integrated.
2000-02-02MD swap macrosMichael Shalayeff
2000-02-01Add Xircom Netwave driver (cnw) commented out.Federico G. Schwindt
2000-02-01Add a bunch of XXX on incorrect handling of pv_flags.Artur Grabowski
None of the noted problems are critical (the code still works), but they can have a severe impact on the performance and they are all really hard to fix in an elegant way.
2000-02-01Opps. Missed two cases of ps_alias_recache.Artur Grabowski
2000-02-01Keep stats of pages we uncache because of bad cache aliases.Artur Grabowski
2000-02-01call vfs_syncwait on standby and suspendMichael Shalayeff
2000-01-31explicitly round segments to a page boundaryMichael Shalayeff
2000-01-31bzero() in get_event tooMichael Shalayeff
2000-01-31Clean up memerr*. (from NetBSD)Artur Grabowski
2000-01-31possibly uninitialized vasriable used in DEBUG code piece; from deraadt@Michael Shalayeff
2000-01-31remove if0ed stinkpad's spinlockMichael Shalayeff
2000-01-30Add the prototype that matthieu forgot on his 11/22/1999 commit.imp
2000-01-29this makes some rough and tough calculations on apmMichael Shalayeff
segment addresses, should be installed (some bioses do report weird values some times)
2000-01-29bring in some mods for apm1.2 proto;Michael Shalayeff
account for 16bit and 32bit code segments at different bases; leave interrupts enabled when calling apm bios; a few more debugging printfs (ifdef'ed appropriately).
2000-01-29get usage of memory maps supplied from /boot.Michael Shalayeff
gives two immidiate advances: memory holes support (two best known are 640k-1M and 15M-16M), and bizaare apm segments placements. /boot must be at least from 2.5 (well, some earlier might work too ;) also, allows usage of new libkvm.
2000-01-29separate clock init, to be called upon resume from apm sleepsMichael Shalayeff
2000-01-29Updated flash and ipic device compatability with MC rev 0x01. zs mods to ↵Steve Murphree
work with LX style 162 boards.
2000-01-29repair busdma calls w/o cookiesMichael Shalayeff
2000-01-28determine eisa motherboard id;Michael Shalayeff
add more daughter devices definitions; enable eisa bus arbitration;
2000-01-27remove bogus commentArtur Grabowski
2000-01-27reduce global symbol pollutionArtur Grabowski
2000-01-27use {round,trunc}_page instead of manually doing the same thingArtur Grabowski
2000-01-27pmap_writetext - use getptep4m/setpgt and avoid one unnecessary table walkArtur Grabowski
2000-01-27It's amazing what you can find with some code reading.Artur Grabowski
In pv_unlink4m we check if the page that was uncached due to bad aliases can be cached again. The check was correct but instead of clearing this flag we clear all other flags except PV_ANC.
2000-01-27goof.Steve Murphree
2000-01-27Took out le* at 0xffffd200. It conflicts with GCSR on some boards.Steve Murphree
2000-01-27Fix for boards with only one zs chip.Steve Murphree
2000-01-27zap setptesw4m, not used anymoreArtur Grabowski
2000-01-27zap getptesw4m, not used anymore (and the comment was bogus)Artur Grabowski
2000-01-27update comment to reflect reality (remove it).Artur Grabowski
2000-01-27pmap_rmk4m: There is no need to flush the segment from the tlb orArtur Grabowski
to zero the table when we have 0 mappings in a segment.
2000-01-26cleanup and simplify pmap_page_protect4m:Artur Grabowski
- Use a normal while-loop when walking the pv lists instead of an ugly hack. - always clean the pte even if we know that it will be freed. - No need to flush the segment from the tlb in kernel. - add some ifdef DIAGNOSTIC. - clear the PV_ANC flag on the pv.
2000-01-26s/PDC_DEBUG/PDCDEBUG/Michael Shalayeff
2000-01-26Replace more table-walks and getpte4m/setpte4m with getptep4m/setpgt4m.Artur Grabowski
2000-01-25some more cautions and debuggings; repair __syscallMichael Shalayeff
2000-01-25better copy and zero inlines in locore;Michael Shalayeff
proper setregs() in machedep; start of hpmc handler; some cleanup here and there;
2000-01-25fix dmesg printTheo de Raadt
2000-01-25cpu_wait(); flush cache in setkpc; explicit bcopy() use in cpu_fork()Michael Shalayeff
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-22 07:58:19 +0000