Commit Graph

95 Commits

Author SHA1 Message Date
Dag-Erling Smørgrav
ae7f84a9a4 Parly revert r239255: reinstate a default maxswzone on i386, where KVA is
scarce, but set it slightly higher so we can handle 8 GB of swap.
2012-08-27 13:22:27 +00:00
Dag-Erling Smørgrav
e2082935f0 As discussed on -current, remove the hardcoded default maxswzone.
MFC after:	3 weeks
2012-08-14 17:01:21 +00:00
Attilio Rao
68b739cd6f Add the possibility to specify from kernel configs MAXCPU value.
This patch is going to help in cases like mips flavours where you
want a more granular support on MAXCPU.

No MFC is previewed for this patch.

Tested by:	pluknet
Approved by:	re (kib)
2011-07-19 00:37:24 +00:00
John Baldwin
1368987ae4 Move {amd64,i386}/pci/pci_bus.c and {amd64,i386}/include/pci_cfgreg.h to
the x86 tree.  The $PIR code is still only enabled on i386 and not amd64.
While here, make the qpi(4) driver on conditional on 'device pci'.
2011-06-22 21:04:13 +00:00
Alan Cox
fe105d45a2 Add a new sysctl for reporting all of the supported page sizes.
Reviewed by:	jhb
MFC after:	3 weeks
2009-09-18 17:04:57 +00:00
Poul-Henning Kamp
a254d1f16d Get rid of the _NO_NAMESPACE_POLLUTION kludge by creating an
architecture specific include file containing the _ALIGN*
stuff which <sys/socket.h> needs.
2009-09-08 20:45:40 +00:00
Sam Leffler
8c393fd1f0 Cleanup ALIGNED_POINTER:
o add to platforms where it was missing (arm, i386, powerpc, sparc64, sun4v)
o define as "1" on amd64 and i386 where there is no restriction
o make the type returned consistent with ALIGN
o remove _ALIGNED_POINTER
o make associated comments consistent

Reviewed by:	bde, imp, marcel
Approved by:	re (kensmith)
2009-07-05 17:45:48 +00:00
John Baldwin
8aba835b8e Bump CACHE_LINE_SIZE to 128 for x86. Intel's manuals explicitly recommend
using 128 byte alignment for locks.  (See IA-32 SDM Vol 3A 7.11.6.7)
2009-05-18 19:33:59 +00:00
Robert Watson
9725389e1e Don't conditionally define CACHE_LINE_SHIFT, as we anticipate sizing
a fair number of static data structures, making this an unlikely
option to try to change without also changing source code. [1]

Change default cache line size on ia64, sparc64, and sun4v to 128
bytes, as this was what rtld-elf was already using on those
platforms. [2]

Suggested by:	bde [1], jhb [2]
MFC after:	2 weeks
2009-04-20 12:59:23 +00:00
Robert Watson
22037b2d2c Add description and cautionary note regarding CACHE_LINE_SIZE.
MFC after:	2 weeks
Suggested by:	alc
2009-04-19 21:26:36 +00:00
Robert Watson
a93fa8f2bb For each architecture, define CACHE_LINE_SHIFT and a derived
CACHE_LINE_SIZE constant.  These constants are intended to
over-estimate the cache line size, and be used at compile-time
when a run-time tuning alternative isn't appropriate or
available.

Defaults for all architectures are 64 bytes, except powerpc
where it is 128 bytes (used on G5 systems).

MFC after:	2 weeks
Discussed on:   arch@
2009-04-19 20:19:13 +00:00
John Baldwin
3d074cf37b Bump MAXCPU to 32 now that 32 CPU x86 systems exist.
Tested by:	rwatson, mdtansca
Approved by:	peter
2008-10-01 21:59:04 +00:00
Kip Macy
dec9f63538 add NPGPTD_SHIFT for the nkpt calculation
MFC after:	1 month
2008-09-25 07:05:17 +00:00
John Birrell
e483943791 When building a kernel module, define MAXCPU the same as SMP so
that modules work with and without SMP.
2008-03-27 05:03:26 +00:00
Warner Losh
d5e61c97a6 By popular demand, move __HAVE_ACPI and __PCI_REROUTE_INTERRUPT into
param.h.  Per request, I've placed these just after the
_NO_NAMESPACE_POLLUTION ifndef.  I've not renamed anything yet, but
may since we don't need the __.

Submitted by: bde, jhb, scottl, many others.
2006-01-09 06:05:57 +00:00
Ruslan Ermilov
224d140293 Drop _MACHINE_ARCH and _MACHINE defines (not to be confused with
MACHINE_ARCH and MACHINE).  Their purpose was to be able to test
in cpp(1), but cpp(1) only understands integer type expressions.
Using such unsupported expressions introduced a number of subtle
bugs, which were discovered by compiling with -Wundef.
2005-12-06 13:27:21 +00:00
David Schultz
ab44ebf537 Remove UAREA_PAGES.
Reviewed by:	arch@
2004-11-20 02:29:50 +00:00
Scott Long
9923b511ed Turn PREEMPTION into a kernel option. Make sure that it's defined if
FULL_PREEMPTION is defined.  Add a runtime warning to ULE if PREEMPTION is
enabled (code inspired by the PREEMPTION warning in kern_switch.c).  This
is a possible MT5 candidate.
2004-09-02 18:59:15 +00:00
Julian Elischer
df3a834f7e Give up trying to make preemption dependent on SCHED_4BSD
the list of breakages was getting too long
2004-09-01 20:41:18 +00:00
Julian Elischer
6222ded017 Don't ask for this for modules. no modules need to know about preemption at the moment 2004-09-01 18:29:57 +00:00
Scott Long
f164d4148e Protect the PREEMPTION logic with #ifdef _KERNEL to fix the build. 2004-09-01 10:12:08 +00:00
Julian Elischer
02ea3bcab9 Only turn preemption for 4bsd.
it's still poison for ULE.
2004-09-01 09:01:32 +00:00
Julian Elischer
6804a3ab6d Give the 4bsd scheduler the ability to wake up idle processors
when there is new work to be done.

MFC after:	5 days
2004-09-01 06:42:02 +00:00
Scott Long
9352fe30a0 Turn off PREEMPTION by default while it gets debugged. It's been causing
4 weeks of problems including deadlocks and instant panics.  Note that the
real bugs are likely in the scheduler.
2004-08-01 14:31:45 +00:00
John Baldwin
0c0b25ae91 Implement preemption of kernel threads natively in the scheduler rather
than as one-off hacks in various other parts of the kernel:
- Add a function maybe_preempt() that is called from sched_add() to
  determine if a thread about to be added to a run queue should be
  preempted to directly.  If it is not safe to preempt or if the new
  thread does not have a high enough priority, then the function returns
  false and sched_add() adds the thread to the run queue.  If the thread
  should be preempted to but the current thread is in a nested critical
  section, then the flag TDF_OWEPREEMPT is set and the thread is added
  to the run queue.  Otherwise, mi_switch() is called immediately and the
  thread is never added to the run queue since it is switch to directly.
  When exiting an outermost critical section, if TDF_OWEPREEMPT is set,
  then clear it and call mi_switch() to perform the deferred preemption.
- Remove explicit preemption from ithread_schedule() as calling
  setrunqueue() now does all the correct work.  This also removes the
  do_switch argument from ithread_schedule().
- Do not use the manual preemption code in mtx_unlock if the architecture
  supports native preemption.
- Don't call mi_switch() in a loop during shutdown to give ithreads a
  chance to run if the architecture supports native preemption since
  the ithreads will just preempt DELAY().
- Don't call mi_switch() from the page zeroing idle thread for
  architectures that support native preemption as it is unnecessary.
- Native preemption is enabled on the same archs that supported ithread
  preemption, namely alpha, i386, and amd64.

This change should largely be a NOP for the default case as committed
except that we will do fewer context switches in a few cases and will
avoid the run queues completely when preempting.

Approved by:	scottl (with his re@ hat)
2004-07-02 20:21:44 +00:00
Warner Losh
f36cfd49ad Remove advertising clause from University of California Regent's
license, per letter dated July 22, 1999 and email from Peter Wemm,
Alan Cox and Robert Watson.

Approved by: core, peter, alc, rwatson
2004-04-07 20:46:16 +00:00
Alan Cox
49a2507bd1 Migrate the thread stack management functions from the machine-dependent
to the machine-independent parts of the VM.  At the same time, this
introduces vm object locking for the non-i386 platforms.

Two details:

1. KSTACK_GUARD has been removed in favor of KSTACK_GUARD_PAGES.  The
different machine-dependent implementations used various combinations
of KSTACK_GUARD and KSTACK_GUARD_PAGES.  To disable guard page, set
KSTACK_GUARD_PAGES to 0.

2. Remove the (unnecessary) clearing of PG_ZERO in vm_thread_new.  In
5.x, (but not 4.x,) PG_ZERO can only be set if VM_ALLOC_ZERO is passed
to vm_page_alloc() or vm_page_grab().
2003-06-14 23:23:55 +00:00
Jake Burkholder
7ab9b220d9 - Add support for PAE and more than 4 gigs of ram on x86, dependent on the
kernel opition 'options PAE'.  This will only work with device drivers which
  either use busdma, or are able to handle 64 bit physical addresses.

Thanks to Lanny Baron from FreeBSD Systems for the loan of a test machine
with 6 gigs of ram.

Sponsored by:	DARPA, Network Associates Laboratories, FreeBSD Systems
2003-03-30 05:24:52 +00:00
Jake Burkholder
227f9a1c58 - Add vm_paddr_t, a physical address type. This is required for systems
where physical addresses larger than virtual addresses, such as i386s
  with PAE.
- Use this to represent physical addresses in the MI vm system and in the
  i386 pmap code.  This also changes the paddr parameter to d_mmap_t.
- Fix printf formats to handle physical addresses >4G in the i386 memory
  detection code, and due to kvtop returning vm_paddr_t instead of u_long.

Note that this is a name change only; vm_paddr_t is still the same as
vm_offset_t on all currently supported platforms.

Sponsored by:	DARPA, Network Associates Laboratories
Discussed with:	re, phk (cdevsw change)
2003-03-25 00:07:06 +00:00
Jake Burkholder
910548dea7 - Added macros NPGPTD, NBPTD, and NPDEPTD, for dealing with the size of the
page directory.
- Use these instead of the magic constants 1 or PAGE_SIZE where appropriate.
  There are still numerous assumptions that the page directory is exactly
  1 page.

Sponsored by:	DARPA, Network Associates Laboratories
2003-02-23 21:20:00 +00:00
Peter Wemm
66422f5b7a Initiate deorbit burn for the i386-only a.out related support. Moves are
under way to move the remnants of the a.out toolchain to ports.  As the
comment in src/Makefile said, this stuff is deprecated and one should not
expect this to remain beyond 4.0-REL.  It has already lasted WAY beyond
that.

Notable exceptions:
gcc - I have not touched the a.out generation stuff there.
ldd/ldconfig - still have some code to interface with a.out rtld.
old as/ld/etc - I have not removed these yet, pending their move to ports.
some includes - necessary for ldd/ldconfig for now.

Tested on: i386 (extensively), alpha
2002-09-17 01:49:00 +00:00
Matthew Dillon
ec61f55d42 Reduce the maximum KVA reserved for swap meta structures from 70 to 32 MB.
Reduce the swap meta calculation by a factor of 2, it's still massive overkill.

X-MFC after: immediately
2002-08-31 21:15:29 +00:00
Poul-Henning Kamp
6380601f64 Move MI stuff out of MD param.h files.
It can all still be overridden in the MD files should need suddenly arise.
2002-05-14 20:35:29 +00:00
Julian Elischer
b40ce4165d KSE Milestone 2
Note ALL MODULES MUST BE RECOMPILED
make the kernel aware that there are smaller units of scheduling than the
process. (but only allow one thread per process at this time).
This is functionally equivalent to teh previousl -current except
that there is a thread associated with each process.

Sorry john! (your next MFC will be a doosie!)

Reviewed by: peter@freebsd.org, dillon@freebsd.org

X-MFC after:    ha ha ha ha
2001-09-12 08:38:13 +00:00
Peter Wemm
268bdb43f9 Optionize UPAGES for the i386. As part of this I split some of the low
level implementation stuff out of machine/globaldata.h to avoid exposing
UPAGES to lots more places.  The end result is that we can double
the kernel stack size with 'options UPAGES=4' etc.

This is mainly being done for the benefit of a MFC to RELENG_4 at some
point.  -current doesn't really need this so much since each interrupt
runs on its own kstack.
2001-08-25 02:20:02 +00:00
Matthew Dillon
2f9e4e8025 Limit the amount of KVM reserved for the buffer cache and for swap-meta
information.  The default limits only effect machines with > 1GB of ram
and can be overriden with two new kernel conf variables VM_SWZONE_SIZE_MAX
and VM_BCACHE_SIZE_MAX, or with loader variables kern.maxswzone and
kern.maxbcache.  This has the effect of leaving more KVM available for
sizing NMBCLUSTERS and 'maxusers' and should avoid tripups where a sysad
adds memory to a machine and then sees the kernel panic on boot due to
running out of KVM.

Also change the default swap-meta auto-sizing calculation to allocate half
of what it was previously allocating.  The prior defaults were way too high.
Note that we cannot afford to run out of swap-meta structures so we still
stay somewhat conservative here.
2001-08-20 00:41:12 +00:00
Jeroen Ruigrok van der Werven
6b1d8ceabe Fix CMSG and ALIGN macro usage.
Previously we had to include <machine/param.h> or <sys/param.h> bogusly
due to the fact that <sys/socket.h> CMSG macros needed the ALIGN macro,
which was defined in param.h.  However, including param.h was a disaster
for namespace pollution.
This solution, as contributed by shin a while ago, fixes it elegantly
by wrapping the definitions around some namespace pollution preventer
definitions.
This patch was long overdue.
This should allow any network programmer to use <sys/socket.h> as
before.

PR:		19971, 20530
Submitted by:	Martin Kaeske <MartinKaeske@lausitz.net>
		Mark Andrews <Mark.Andrews@nominum.com>
Patch submitted by:	shin
Reviewed by:	bde
2000-11-08 16:59:25 +00:00
Paul Saab
c794ceb56a Implement write combining for crashdumps. This is useful when
write caching is disabled on both SCSI and IDE disks where large
memory dumps could take up to an hour to complete.

Taking an i386 scsi based system with 512MB of ram and timing (in
seconds) how long it took to complete a dump, the following results
were obtained:

Before:				After:
	WCE           TIME		WCE           TIME
	------------------		------------------
	1	141.820972		1	 15.600111
	0	797.265072		0	 65.480465

Obtained from:	Yahoo!
Reviewed by:	peter
2000-10-17 10:05:49 +00:00
Bosko Milekic
ec222a71d9 Cleanup comment in machine/param.h regarding mbuf-related sizes, and get rid
of MCLOFSET, which does not appear to be used anywhere anymore, and if it is,
it probably shouldn't be.
2000-10-08 03:52:27 +00:00
Paul Saab
92b123a002 Move MAXCPU from machine/smp.h to machine/param.h to fix breakage
with !SMP kernels.  Also, replace NCPUS with MAXCPU since they are
redundant.
2000-09-23 12:18:06 +00:00
Jonathan Lemon
863bdc0cff Change the mbuf size from 128 -> 256. Increasing the mbuf header size
caused some headers not to fit in MHLEN any more.  This matches the
current size on the alpha, so it shouldn't cause problems.

Problem observed by:	   Geoff Rehmet <geoff@is.co.za>
Originally suggested by:   shin
2000-03-29 05:39:04 +00:00
Peter Wemm
7ba4a77549 Reclaim UPAGES_HOLE (8k) that was chopped out of process address space.
The UPAGES have not been there since Jan '96, but the hole was preserved
for BSD/OS binary compatability.  This has been fixed other ways (%ebx
now has a pointer to PS_STRINGS), and the stack is nowhere near where
it used to be so this hack isn't required anymore.
1999-12-11 10:54:06 +00:00
Matthew Dillon
8b22cebb2c Back out a portion of the last commit. DFLTPHYS and MAXPHYS cannot
be set by a kernel conf option due to the struct buf structural
    dependancy (sizing of b_pages[]) creating a conflict with modules
    (which are not compiled with kernel config options overrides).

    We'll be able to sysctl these two later on when the buffer subsystem
    is revamped.
1999-09-22 05:48:31 +00:00
Matthew Dillon
a59d364a23 Change default block size for user VBLK device access from 2K to PAGE_SIZE
(4K on an i386, 8K on an alpha).

    Make BLKDEV_IOSIZE, DFLTPHYS, and MAXPHYS kernel-configurable.
1999-09-22 04:11:55 +00:00
Peter Wemm
c3aac50f28 $Id$ -> $FreeBSD$ 1999-08-28 01:08:13 +00:00
Warner Losh
1684ea5706 Don't define MACHINE, MACHINE_ARCH, _MACHINE or _MACHINE_ARCH if
already defined.  This allows for cross building to work because we
need to lie to make to tell it to use the target names rather than the
host names.

This should have no effect on either architecture.  I've confirmed
that the intel build by make buildworld's for the past 3 months.
1999-03-01 06:10:16 +00:00
Luoqi Chen
1c6d46f93c Introduce machine-dependent macro pgtok() to convert page count to number
of kilobytes. Its definition for each architecture could be optimized to
avoid potential numerical overflows.
1999-02-19 19:34:49 +00:00
Peter Wemm
6c7178bdfb OBJFORMAT_DEFAULT = elf now. (this is where /usr/bin/objformat and
libc/gen/getobjformat.c get their default from)
1999-01-07 06:35:18 +00:00
David Greenman
6cde7a165f Fixed two potentially serious classes of bugs:
1) The vnode pager wasn't properly tracking the file size due to
   "size" being page rounded in some cases and not in others.
   This sometimes resulted in corrupted files. First noticed by
   Terry Lambert.
   Fixed by changing the "size" pager_alloc parameter to be a 64bit
   byte value (as opposed to a 32bit page index) and changing the
   pagers and their callers to deal with this properly.
2) Fixed a bogus type cast in round_page() and trunc_page() that
   caused some 64bit offsets and sizes to be scrambled. Removing
   the cast required adding casts at a few dozen callers.
   There may be problems with other bogus casts in close-by
   macros. A quick check seemed to indicate that those were okay,
   however.
1998-10-13 08:24:45 +00:00
John Polstra
cfa4d73988 Add a new library function getobjformat(). It checks all the
standard places ("/etc/objformat", ${OBJFORMAT}, argv) for an
indication of the user's preferred object file format.  This
consolidates some code that was starting to be duplicated in more
and more places.

Use the new function in ldconfig.

Note: I don't think that gcc should use getobjformat(), even though
it could.  The compiler should limit itself to functions that are
widespread, to ease porting and cross-compilation.
1998-09-09 01:21:25 +00:00