| Commit message (Expand) | Author | Age | Files | Lines |
* | Add a new sysctl for reporting all of the supported page sizes. | alc | 2009-09-18 | 1 | -0/+2 |
* | Get rid of the _NO_NAMESPACE_POLLUTION kludge by creating an | phk | 2009-09-08 | 1 | -6/+6 |
* | Cleanup ALIGNED_POINTER: | sam | 2009-07-05 | 1 | -0/+7 |
* | Bump CACHE_LINE_SIZE to 128 for x86. Intel's manuals explicitly recommend | jhb | 2009-05-18 | 1 | -1/+1 |
* | Don't conditionally define CACHE_LINE_SHIFT, as we anticipate sizing | rwatson | 2009-04-20 | 1 | -2/+0 |
* | Add description and cautionary note regarding CACHE_LINE_SIZE. | rwatson | 2009-04-19 | 1 | -0/+4 |
* | For each architecture, define CACHE_LINE_SHIFT and a derived | rwatson | 2009-04-19 | 1 | -0/+5 |
* | Bump MAXCPU to 32 now that 32 CPU x86 systems exist. | jhb | 2008-10-01 | 1 | -1/+1 |
* | add NPGPTD_SHIFT for the nkpt calculation | kmacy | 2008-09-25 | 1 | -0/+2 |
* | When building a kernel module, define MAXCPU the same as SMP so | jb | 2008-03-27 | 1 | -2/+2 |
* | By popular demand, move __HAVE_ACPI and __PCI_REROUTE_INTERRUPT into | imp | 2006-01-09 | 1 | -0/+3 |
* | Drop _MACHINE_ARCH and _MACHINE defines (not to be confused with | ru | 2005-12-06 | 1 | -7/+0 |
* | Remove UAREA_PAGES. | das | 2004-11-20 | 1 | -1/+0 |
* | Turn PREEMPTION into a kernel option. Make sure that it's defined if | scottl | 2004-09-02 | 1 | -5/+0 |
* | Give up trying to make preemption dependent on SCHED_4BSD | julian | 2004-09-01 | 1 | -4/+1 |
* | Don't ask for this for modules. no modules need to know about preemption at t... | julian | 2004-09-01 | 1 | -1/+1 |
* | Protect the PREEMPTION logic with #ifdef _KERNEL to fix the build. | scottl | 2004-09-01 | 1 | -0/+2 |
* | Only turn preemption for 4bsd. | julian | 2004-09-01 | 1 | -0/+3 |
* | Give the 4bsd scheduler the ability to wake up idle processors | julian | 2004-09-01 | 1 | -2/+0 |
* | Turn off PREEMPTION by default while it gets debugged. It's been causing | scottl | 2004-08-01 | 1 | -0/+3 |
* | Implement preemption of kernel threads natively in the scheduler rather | jhb | 2004-07-02 | 1 | -0/+2 |
* | Remove advertising clause from University of California Regent's | imp | 2004-04-07 | 1 | -4/+0 |
* | Migrate the thread stack management functions from the machine-dependent | alc | 2003-06-14 | 1 | -2/+1 |
* | - Add support for PAE and more than 4 gigs of ram on x86, dependent on the | jake | 2003-03-30 | 1 | -0/+5 |
* | - Add vm_paddr_t, a physical address type. This is required for systems | jake | 2003-03-25 | 1 | -6/+6 |
* | - Added macros NPGPTD, NBPTD, and NPDEPTD, for dealing with the size of the | jake | 2003-02-23 | 1 | -1/+5 |
* | Initiate deorbit burn for the i386-only a.out related support. Moves are | peter | 2002-09-17 | 1 | -7/+0 |
* | Reduce the maximum KVA reserved for swap meta structures from 70 to 32 MB. | dillon | 2002-08-31 | 1 | -3/+5 |
* | Move MI stuff out of MD param.h files. | phk | 2002-05-14 | 1 | -48/+0 |
* | KSE Milestone 2 | julian | 2001-09-12 | 1 | -2/+5 |
* | Optionize UPAGES for the i386. As part of this I split some of the low | peter | 2001-08-25 | 1 | -0/+3 |
* | Limit the amount of KVM reserved for the buffer cache and for swap-meta | dillon | 2001-08-20 | 1 | -0/+16 |
* | Fix CMSG and ALIGN macro usage. | asmodai | 2000-11-08 | 1 | -13/+25 |
* | Implement write combining for crashdumps. This is useful when | ps | 2000-10-17 | 1 | -0/+1 |
* | Cleanup comment in machine/param.h regarding mbuf-related sizes, and get rid | bmilekic | 2000-10-08 | 1 | -7/+3 |
* | Move MAXCPU from machine/smp.h to machine/param.h to fix breakage | ps | 2000-09-23 | 1 | -3/+3 |
* | Change the mbuf size from 128 -> 256. Increasing the mbuf header size | jlemon | 2000-03-29 | 1 | -1/+1 |
* | Reclaim UPAGES_HOLE (8k) that was chopped out of process address space. | peter | 1999-12-11 | 1 | -2/+0 |
* | Back out a portion of the last commit. DFLTPHYS and MAXPHYS cannot | dillon | 1999-09-22 | 1 | -4/+0 |
* | Change default block size for user VBLK device access from 2K to PAGE_SIZE | dillon | 1999-09-22 | 1 | -1/+7 |
* | $Id$ -> $FreeBSD$ | peter | 1999-08-28 | 1 | -1/+1 |
* | Don't define MACHINE, MACHINE_ARCH, _MACHINE or _MACHINE_ARCH if | imp | 1999-03-01 | 1 | -1/+9 |
* | Introduce machine-dependent macro pgtok() to convert page count to number | luoqi | 1999-02-19 | 1 | -1/+3 |
* | OBJFORMAT_DEFAULT = elf now. (this is where /usr/bin/objformat and | peter | 1999-01-07 | 1 | -5/+1 |
* | Fixed two potentially serious classes of bugs: | dg | 1998-10-13 | 1 | -3/+3 |
* | Add a new library function getobjformat(). It checks all the | jdp | 1998-09-09 | 1 | -1/+12 |
* | - hw.machine_arch returns cpu architecture type. | kato | 1998-08-31 | 1 | -2/+4 |
* | Oops, uoff_t can't be used here yet. | bde | 1998-06-15 | 1 | -2/+2 |
* | Removed LOCORE ifdef. This header isn't used for locore stuff. | bde | 1998-06-14 | 1 | -8/+5 |
* | Add better support for larger I/O clusters, including larger physical | dyson | 1998-01-24 | 1 | -2/+3 |