Commit Graph

1036 Commits

Author SHA1 Message Date
Alfred Perlstein
61ce6eeee3 Fixups for the initial allocation by dillon:
1) allocate fewer buckets
  2) when failing to allocate swap zone, keep reducing the zone by
     a third rather than a half in order to reduce the chance of
     allocating way too little.

I also moved around some code for readability.

Suggested by: dillon
Reviewed by: dillon
2001-08-02 07:54:58 +00:00
Jake Burkholder
3a9b5daf48 Oops. Last commit to vm_object.c should have got these files too.
Remove the use of atomic ops to manipulate vm_object and vm_page flags.
Giant is required here, so they are superfluous.

Discussed with:	dillon
2001-07-31 04:09:52 +00:00
Jake Burkholder
b06805ad34 Remove the use of atomic ops to manipulate vm_object and vm_page flags.
Giant is required here, so they are superfluous.

Discussed with:	dillon
2001-07-31 04:03:53 +00:00
Ian Dowse
a4821e444e Permit direct swapping to NFS regular files using swapon(2). We
already allow this for NFS swap configured via BOOTP, so it is
known to work fine.

For many diskless configurations is is more flexible to have the
client set up swapping itself; it can recreate a sparse swap file
to save on server space for example, and it works with a non-NFS
root filesystem such as an in-kernel filesystem image.
2001-07-28 20:18:38 +00:00
Assar Westerlund
d3e5863fa9 make vm_page_select_cache static
Requested by:	bde
2001-07-23 12:34:31 +00:00
Assar Westerlund
0379d76358 (vm_page_select_cache): add prototype 2001-07-21 17:08:15 +00:00
Benno Rice
1f246456a5 The i386-specific includes in this file were "fixed" by bracketing them with
#ifndef __alpha__.  Fix this for the rest of the world by turning it into
#ifdef __i386__.

Reviewed by:	obrien
2001-07-15 04:11:51 +00:00
Dag-Erling Smørgrav
bf3009895e Fix missing newline and terminator at the end of the vm.zone sysctl. 2001-07-09 03:37:33 +00:00
Matt Jacob
f343cf2135 Apply field bandages to the includes so compiles happen on alpha. 2001-07-05 06:13:44 +00:00
Matthew Dillon
7197571105 Move vm_page_zero_idle() from machine-dependant sections to a
machine-independant source file, vm/vm_zeroidle.c.  It was exactly the
same for all platforms and updating them all was getting annoying.
2001-07-05 01:32:42 +00:00
Matthew Dillon
6d03d577a5 Reorg vm_page.c into vm_page.c, vm_pageq.c, and vm_contig.c (for contigmalloc).
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... :-)
2001-07-04 23:27:09 +00:00
Matthew Dillon
1b40f8c036 Change inlines back into mainline code in preparation for mutexing. Also,
most of these inlines had been bloated in -current far beyond their
original intent.  Normalize prototypes and function declarations to be ANSI
only (half already were).  And do some general cleanup.

(kernel size also reduced by 50-100K, but that isn't the prime intent)
2001-07-04 20:15:18 +00:00
Matthew Dillon
54d9214595 whitespace / register cleanup 2001-07-04 19:00:13 +00:00
Matthew Dillon
0cddd8f023 With Alfred's permission, remove vm_mtx in favor of a fine-grained approach
(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.
2001-07-04 16:20:28 +00:00
John Baldwin
b62b9b648b Fix a XXX comment by moving the initialization of the number of pbuf's
for the vnode pager to a new vnode pager init method instead of making it
a hack in getpages().
2001-07-03 07:35:56 +00:00
John Baldwin
6d541bf1ae - Protect all accesses to nsw_[rw]count{,_{,a}sync} with the pbuf mutex.
- Don't drop the vm mutex while grabbing the pbuf mutex to manipulate
  said variables.
2001-06-22 21:12:19 +00:00
Bosko Milekic
08442f8a82 Introduce numerous SMP friendly changes to the mbuf allocator. Namely,
introduce a modified allocation mechanism for mbufs and mbuf clusters; one
which can scale under SMP and which offers the possibility of resource
reclamation to be implemented in the future. Notable advantages:

 o Reduce contention for SMP by offering per-CPU pools and locks.
 o Better use of data cache due to per-CPU pools.
 o Much less code cache pollution due to excessively large allocation macros.
 o Framework for `grouping' objects from same page together so as to be able
   to possibly free wired-down pages back to the system if they are no longer
   needed by the network stacks.

 Additional things changed with this addition:

  - Moved some mbuf specific declarations and initializations from
    sys/conf/param.c into mbuf-specific code where they belong.
  - m_getclr() has been renamed to m_get_clrd() because the old name is really
    confusing. m_getclr() HAS been preserved though and is defined to the new
    name. No tree sweep has been done "to change the interface," as the old
    name will continue to be supported and is not depracated. The change was
    merely done because m_getclr() sounds too much like "m_get a cluster."
  - TEMPORARILY disabled mbtypes statistics displaying in netstat(1) and
    systat(1) (see TODO below).
  - Fixed systat(1) to display number of "free mbufs" based on new per-CPU
    stat structures.
  - Fixed netstat(1) to display new per-CPU stats based on sysctl-exported
    per-CPU stat structures. All infos are fetched via sysctl.

 TODO (in order of priority):

  - Re-enable mbtypes statistics in both netstat(1) and systat(1) after
    introducing an SMP friendly way to collect the mbtypes stats under the
    already introduced per-CPU locks (i.e. hopefully don't use atomic() - it
    seems too costly for a mere stat update, especially when other locks are
    already present).
  - Optionally have systat(1) display not only "total free mbufs" but also
    "total free mbufs per CPU pool."
  - Fix minor length-fetching issues in netstat(1) related to recently
    re-enabled option to read mbuf stats from a core file.
  - Move reference counters at least for mbuf clusters into an unused portion
    of the cluster itself, to save space and need to allocate a counter.
  - Look into introducing resource freeing possibly from a kproc.

Reviewed by (in parts): jlemon, jake, silby, terry
Tested by: jlemon (Intel & Alpha), mjacob (Intel & Alpha)
Preliminary performance measurements: jlemon (and me, obviously)
URL: http://people.freebsd.org/~bmilekic/mb_alloc/
2001-06-22 06:35:32 +00:00
John Baldwin
ad6c5bbede Don't lock around swap_pager_swap_init() that is only called once during
the pagedaemon's startup code since it calls malloc which results in lock
order reversals.
2001-06-20 23:34:06 +00:00
John Baldwin
69a78d4666 Put the scheduler, vmdaemon, and pagedaemon kthreads back under Giant for
now.  The proc locking isn't actually safe yet and won't be until the proc
locking is finished.
2001-06-20 00:48:20 +00:00
Matthew Dillon
ef6a93ef81 Cleanup the tabbing 2001-06-11 19:17:05 +00:00
Matthew Dillon
ff2b5645b5 Two fixes to the out-of-swap process termination code. First, start killing
processes a little earlier to avoid a deadlock.  Second, when calculating
the 'largest process' do not just count RSS.  Instead count the RSS + SWAP
used by the process.  Without this the code tended to kill small
inconsequential processes like, oh, sshd, rather then one of the many
'eatmem 200MB' I run on a whim :-).  This fix has been extensively tested on
-stable and somewhat tested on -current and will be MFCd in a few days.

Shamed into fixing this by: ps
2001-06-09 18:06:58 +00:00
Thomas Moestl
5c5c8fa826 Change the way information about swap devices is exported to be more
canonical: define a versioned struct xswdev, and add a sysctl node
handler that allows the user to get this structure for a certain device
index by specifying this index as last element of the MIB.
This new node handler, vm.swap_info, replaces the old vm.nswapdev
and vm.swapdevX.* (where X was the index) sysctls.
2001-06-01 22:53:10 +00:00
Thomas Moestl
d279178df7 Clean up the code exporting interrupt statistics via sysctl a bit:
- 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)
2001-06-01 13:23:28 +00:00
John Baldwin
342a1480aa Don't hold the VM lock across VOP's and other things that can sleep. 2001-05-29 16:58:25 +00:00
John Baldwin
190609dd48 Stick VM syscalls back under Giant if the BLEED option is not defined. 2001-05-24 18:04:29 +00:00
Matthew Dillon
ac8f990bde This patch implements O_DIRECT about 80% of the way. It takes a patchset
Tor created a while ago, removes the raw I/O piece (that has cache coherency
problems), and adds a buffer cache / VM freeing piece.

Essentially this patch causes O_DIRECT I/O to not be left in the cache, but
does not prevent it from going through the cache, hence the 80%.  For
the last 20% we need a method by which the I/O can be issued directly to
buffer supplied by the user process and bypass the buffer cache entirely,
but still maintain cache coherency.

I also have the code working under -stable but the changes made to sys/file.h
may not be MFCable, so an MFC is not on the table yet.

Submitted by:	tegge, dillon
2001-05-24 07:22:27 +00:00
John Baldwin
e6b961ffbd - Assert Giant is held in the vnode pager methods.
- Lock the VM while walking down a vm_object's backing_object list in
  vnode_pager_lock().
2001-05-23 22:51:23 +00:00
John Baldwin
3614c6fcbb - Add in several asserts of vm_mtx.
- Assert Giant in vm_pageout_scan() for the vnode hacking that it does.
- Don't hold vm_mtx around vget() or vput().
- Lock Giant when calling vm_pageout_scan() from the pagedaemon.  Also,
  lock curproc while setting the P_BUFEXHAUST flag.
- For now we still hold Giant for all of the vm_daemon.  When process
  limits are locked we will be only need Giant for swapout_procs().
2001-05-23 22:48:28 +00:00
John Baldwin
60517fd1f7 - Assert that the vm lock is held for all of _vm_object_allocate().
- Restore the previous order of setting up a new vm_object.  The previous
  had a small bug where we zero'd out the flags after we set the
  OBJ_ONEMAPPING flag.
- Add several asserts of vm_mtx.
- Assert Giant is held rather than locking and unlocking it in a few
  places.
- Add in some #ifdef objlocks code to lock individual vm objects when
  vm objects each have their own lock someday.
- Don't bother acquiring the allproc lock for a ddb command.  If DDB
  blocked on the lock, that would be worse than having an inconsistent
  allproc list.
2001-05-23 22:42:10 +00:00
John Baldwin
21c641b2a9 - Add lots of vm_mtx assertions.
- Add a few KTR tracepoints to track the addition and removal of
  vm_map_entry's and the creation adn free'ing of vmspace's.
- Adjust a few portions of code so that we update the process' vmspace
  pointer to its new vmspace before freeing the old vmspace.
2001-05-23 22:38:00 +00:00
John Baldwin
3a2189d451 - Lock the VM around the pmap_swapin_proc() call in faultin().
- Don't lock Giant in the scheduler() function except for when calling
  faultin().
- In swapout_procs(), lock the VM before the proccess to avoid a lock order
  violation.
- In swapout_procs(), release the allproc lock before calling swapout().
  We restart the process scan after swapping out a process.
- In swapout_procs(), un #if 0 the code to bump the vmspace reference count
  and lock the process' vm structures.  This bug was introduced by me and
  could result in the vmspace being free'd out from under a running
  process.
- Fix an old bug where the vmspace reference count was not free'd if we
  failed the swap_idle_threshold2 test.
2001-05-23 22:35:45 +00:00
John Baldwin
b608320d4a - Fix the sw_alloc_interlock to actually lock itself when the lock is
acquired.
- Assert Giant is held in the strategy, getpages, and putpages methods and
  the getchainbuf, flushchainbuf, and waitchainbuf functions.
- Always call flushchainbuf() w/o the VM lock.
2001-05-23 22:31:15 +00:00
John Baldwin
6d556da5c2 Assert Giant is held for the device pager alloc and getpages methods since
we call the mmap method of the cdevsw of the device we are mmap'ing.
2001-05-23 22:27:52 +00:00
John Baldwin
e4ca250d4b - Obtain Giant in mmap() syscall while messing with file descriptors and
vnodes.
- Fix an old bug that would leak a reference to a fd if the vnode being
  mmap'd wasn't of type VREG or VCHR.
- Lock Giant in vm_mmap() around calls into the VM that can call into
  pager routines that need Giant or into other VM routines that need
  Giant.
- Replace code that used a goto to jump around the else branch of a test
  to use an else branch instead.
2001-05-23 22:17:43 +00:00
John Baldwin
bb10bb4978 Acquire Giant around vm_map_remove() inside of the obreak() syscall for
vm_object_terminate().
2001-05-23 22:13:10 +00:00
John Baldwin
576f0c5fa4 Take a more conservative approach and still lock Giant around VM faults
for now.
2001-05-23 22:09:18 +00:00
John Baldwin
c52f090cfb Set the phys_pager_alloc_lock to 1 when it is acquired so that it is
actually locked.
2001-05-23 19:52:23 +00:00
Alfred Perlstein
c5e62505ad aquire Giant when playing with the buffercache and doing IO.
use msleep against the vm mutex while waiting for a page IO to complete.
2001-05-23 10:28:11 +00:00
Alfred Perlstein
240e0fdd93 aquire vm mutex in swp_pager_async_iodone. Don't call swp_pager_async_iodone
with the mutex held.
2001-05-22 19:01:26 +00:00
John Baldwin
86e92ee7e1 Remove duplicate include and sort includes. 2001-05-22 07:21:46 +00:00
John Baldwin
7d4ad42de5 Sort includes. 2001-05-22 07:01:11 +00:00
John Baldwin
12635f9c89 Unlock the VM lock at the end of munlock() instead of locking it again. 2001-05-22 06:07:36 +00:00
John Baldwin
874468957d Sort includes from previous commit. 2001-05-22 05:35:45 +00:00
John Baldwin
4edf4a58e6 Sort includes. 2001-05-22 00:56:25 +00:00
Alfred Perlstein
2395531439 Introduce a global lock for the vm subsystem (vm_mtx).
vm_mtx does not recurse and is required for most low level
vm operations.

faults can not be taken without holding Giant.

Memory subsystems can now call the base page allocators safely.

Almost all atomic ops were removed as they are covered under the
vm mutex.

Alpha and ia64 now need to catch up to i386's trap handlers.

FFS and NFS have been tested, other filesystems will need minor
changes (grabbing the vm lock when twiddling page properties).

Reviewed (partially) by: jake, jhb
2001-05-19 01:28:09 +00:00
John Baldwin
ea7549540f - Use a timeout for the tsleep in scheduler() instead of having vmmeter()
wakeup proc0 by hand to enforce the timeout.
- When swapping out a process, keep the process locked via the proc lock
  from the first checks up until we clear PS_INMEM and set PS_SWAPPING in
  swapout().  The swapout() function now must be called with the proc lock
  held and releases it before returning.
- Comment out the code to attempt to lock a process' VM structures before
  swapping out.  It is broken in that it releases the lock after obtaining
  it.  If it does grab the lock, it needs to hand it off to swapout()
  instead of releasing it.  This can be revisisted when the VM is locked
  as this is a valid test to perform.  It also causes a lock order reversal
  for the time being, which is the immediate cause for temporarily
  disabling it.
2001-05-18 00:08:38 +00:00
John Baldwin
1c58e4e550 During the code to pick a process to kill when memory is exhausted, keep
the process in question locked as soon as we find it and determine it to
be eligible until we actually kill it.  To avoid deadlock, we don't block
on the process lock but skip any process that is already locked during our
search.
2001-05-17 22:49:03 +00:00
John Baldwin
c96d52a913 - Use PROC_LOCK_ASSERT instead of a direct mtx_assert.
- Don't hold Giant in the swapper daemon while we walk the list of
  processes looking for a process to swap back in.
- Don't bother grabbing the sched_lock while checking a process' sleep
  time in swapout_procs() to ensure that a process has been idle for at
  least swap_idle_threshold2 before swapping it out.  If we lose the race
  we just let a process stay in memory until the next call of
  swapout_procs().
- Remove some unneeded spl's, sched_lock does all the locking needed in
  this case.
2001-05-15 22:20:44 +00:00
Poul-Henning Kamp
a468031ce8 Actually biofinish(struct bio *, struct devstat *, int error) is more general
than the bioerror().

Most of this patch is generated by scripts.
2001-05-06 20:00:03 +00:00
Mark Murray
559034b748 Putting sys/lockmgr.h in here allows us to depollute userland includes
a bit.
OK'ed by:	bde
2001-05-03 11:33:51 +00:00