Commit Graph

221 Commits

Author SHA1 Message Date
John Dyson
ca56715fd8 Fixed a sign reversal problem -- might have cause some Sig-11s that
people have been seeing.
1995-09-06 07:08:45 +00:00
John Dyson
ced399ee65 Minor performance improvements, additional prototype for additional
exported symbol.
1995-09-06 05:37:43 +00:00
John Dyson
170db9c63a Allow the fault code to use additional clustering info from both
bmap and the swap pager.  Improved fault clustering performance.
1995-09-04 04:44:26 +00:00
John Dyson
c83ebe7781 Added VOP_GETPAGES/VOP_PUTPAGES and also the "backwards" block count
for VOP_BMAP.  Updated affected filesystems...
1995-09-04 00:21:16 +00:00
John Dyson
f70f05f238 Machine independent changes to support pre-zeroed free pages. This
significantly improves demand-zero performance.
1995-09-03 20:40:43 +00:00
John Dyson
10ad4d483c Added prototype for new routine "vm_page_set_validclean" and initial
declarations for the prezeroed pages mechanism.
1995-09-03 20:11:26 +00:00
John Dyson
4589a4b5dc New subroutine "vm_page_set_validclean" for a vfs_bio improvement. 1995-09-03 19:57:25 +00:00
Julian Elischer
2b14f991e6 Reviewed by: julian with quick glances by bruce and others
Submitted by:	terry (terry lambert)
This is  a composite of 3 patch sets submitted by terry.
they are:
New low-level init code that supports loadbal modules better
some cleanups in the namei code to help terry in 16-bit character support
some changes to the mount-root code to make it a little more
modular..

NOTE: mounting root off cdrom or NFS MIGHT be broken as I haven't been able
to test those cases..

certainly mounting root of disk still works just fine..
mfs should work but is untested. (tomorrows task)

The low level init stuff includes a total rewrite of init_main.c
to make it possible for new modules to have an init phase by simply
adding an entry to a TEXT_SET (or is it DATA_SET) list. thus a new module can
be added to the kernel without editing any other files other than the
'files' file.
1995-08-28 09:19:25 +00:00
Bruce Evans
187f023877 Change vm_object_print() to have the correct number and type of args
for a ddb command.
1995-08-26 23:19:49 +00:00
Bruce Evans
914181e7de Change vm_map_print() to have the correct number and type of args for
a ddb command.
1995-08-26 23:18:38 +00:00
Bruce Evans
bf25be48a5 Make everything except the unsupported network sources compile cleanly
with -Wnested-externs.
1995-08-16 16:14:28 +00:00
Bruce Evans
28f8db1403 Eliminate sloppy common-style declarations. There should be none left for
the LINT configuation.
1995-07-29 11:44:31 +00:00
David Greenman
b367ddb191 #if 0'd one of the DIAGNOSTIC checks in vm_page_alloc(). It was too
expensive for "normal" use.
1995-07-20 05:28:07 +00:00
David Greenman
2a4895f4bb 1) Merged swpager structure into vm_object.
2) Changed swap_pager internal interfaces to cope w/#1.
3) Eliminated object->copy as we no longer have copy objects.
4) Minor stylistic changes.
1995-07-16 13:28:37 +00:00
David Greenman
588d138f56 Added a copyright to this file. 1995-07-13 10:29:34 +00:00
David Greenman
2541af0bba Oops, forgot to add the "default" pager files...
NOTE: libkvm, w, ps, 'top', and any other utility which depends on struct
      proc or any VM system structure will have to be rebuilt!!!

Much needed overhaul of the VM system. Included in this first round of
changes:

1) Improved pager interfaces: init, alloc, dealloc, getpages, putpages,
   haspage, and sync operations are supported. The haspage interface now
   provides information about clusterability. All pager routines now take
   struct vm_object's instead of "pagers".

2) Improved data structures. In the previous paradigm, there is constant
   confusion caused by pagers being both a data structure ("allocate a
   pager") and a collection of routines. The idea of a pager structure has
   escentially been eliminated. Objects now have types, and this type is
   used to index the appropriate pager. In most cases, items in the pager
   structure were duplicated in the object data structure and thus were
   unnecessary. In the few cases that remained, a un_pager structure union
   was created in the object to contain these items.

3) Because of the cleanup of #1 & #2, a lot of unnecessary layering can now
   be removed. For instance, vm_object_enter(), vm_object_lookup(),
   vm_object_remove(), and the associated object hash list were some of the
   things that were removed.

4) simple_lock's removed. Discussion with several people reveals that the
   SMP locking primitives used in the VM system aren't likely the mechanism
   that we'll be adopting. Even if it were, the locking that was in the code
   was very inadequate and would have to be mostly re-done anyway. The
   locking in a uni-processor kernel was a no-op but went a long way toward
   making the code difficult to read and debug.

5) Places that attempted to kludge-up the fact that we don't have kernel
   thread support have been fixed to reflect the reality that we are really
   dealing with processes, not threads. The VM system didn't have complete
   thread support, so the comments and mis-named routines were just wrong.
   We now use tsleep and wakeup directly in the lock routines, for instance.

6) Where appropriate, the pagers have been improved, especially in the
   pager_alloc routines. Most of the pager_allocs have been rewritten and
   are now faster and easier to maintain.

7) The pagedaemon pageout clustering algorithm has been rewritten and
   now tries harder to output an even number of pages before and after
   the requested page. This is sort of the reverse of the ideal pagein
   algorithm and should provide better overall performance.

8) Unnecessary (incorrect) casts to caddr_t in calls to tsleep & wakeup
   have been removed. Some other unnecessary casts have also been removed.

9) Some almost useless debugging code removed.

10) Terminology of shadow objects vs. backing objects straightened out.
    The fact that the vm_object data structure escentially had this
    backwards really confused things. The use of "shadow" and "backing
    object" throughout the code is now internally consistent and correct
    in the Mach terminology.

11) Several minor bug fixes, including one in the vm daemon that caused
    0 RSS objects to not get purged as intended.

12) A "default pager" has now been created which cleans up the transition
    of objects to the "swap" type. The previous checks throughout the code
    for swp->pg_data != NULL were really ugly. This change also provides
    the rudiments for future backing of "anonymous" memory by something
    other than the swap pager (via the vnode pager, for example), and it
    allows the decision about which of these pagers to use to be made
    dynamically (although will need some additional decision code to do
    this, of course).

13) (dyson) MAP_COPY has been deprecated and the corresponding "copy
    object" code has been removed. MAP_COPY was undocumented and non-
    standard. It was furthermore broken in several ways which caused its
    behavior to degrade to MAP_PRIVATE. Binaries that use MAP_COPY will
    continue to work correctly, but via the slightly different semantics
    of MAP_PRIVATE.

14) (dyson) Sharing maps have been removed. It's marginal usefulness in a
    threads design can be worked around in other ways. Both #12 and #13
    were done to simplify the code and improve readability and maintain-
    ability. (As were most all of these changes)

TODO:

1) Rewrite most of the vnode pager to use VOP_GETPAGES/PUTPAGES. Doing
   this will reduce the vnode pager to a mere fraction of its current size.

2) Rewrite vm_fault and the swap/vnode pagers to use the clustering
   information provided by the new haspage pager interface. This will
   substantially reduce the overhead by eliminating a large number of
   VOP_BMAP() calls. The VOP_BMAP() filesystem interface should be
   improved to provide both a "behind" and "ahead" indication of
   contiguousness.

3) Implement the extended features of pager_haspage in swap_pager_haspage().
   It currently just says 0 pages ahead/behind.

4) Re-implement the swap device (swstrategy) in a more elegant way, perhaps
   via a much more general mechanism that could also be used for disk
   striping of regular filesystems.

5) Do something to improve the architecture of vm_object_collapse(). The
   fact that it makes calls into the swap pager and knows too much about
   how the swap pager operates really bothers me. It also doesn't allow
   for collapsing of non-swap pager objects ("unnamed" objects backed by
   other pagers).
1995-07-13 10:15:03 +00:00
David Greenman
24a1cce34f NOTE: libkvm, w, ps, 'top', and any other utility which depends on struct
proc or any VM system structure will have to be rebuilt!!!

Much needed overhaul of the VM system. Included in this first round of
changes:

1) Improved pager interfaces: init, alloc, dealloc, getpages, putpages,
   haspage, and sync operations are supported. The haspage interface now
   provides information about clusterability. All pager routines now take
   struct vm_object's instead of "pagers".

2) Improved data structures. In the previous paradigm, there is constant
   confusion caused by pagers being both a data structure ("allocate a
   pager") and a collection of routines. The idea of a pager structure has
   escentially been eliminated. Objects now have types, and this type is
   used to index the appropriate pager. In most cases, items in the pager
   structure were duplicated in the object data structure and thus were
   unnecessary. In the few cases that remained, a un_pager structure union
   was created in the object to contain these items.

3) Because of the cleanup of #1 & #2, a lot of unnecessary layering can now
   be removed. For instance, vm_object_enter(), vm_object_lookup(),
   vm_object_remove(), and the associated object hash list were some of the
   things that were removed.

4) simple_lock's removed. Discussion with several people reveals that the
   SMP locking primitives used in the VM system aren't likely the mechanism
   that we'll be adopting. Even if it were, the locking that was in the code
   was very inadequate and would have to be mostly re-done anyway. The
   locking in a uni-processor kernel was a no-op but went a long way toward
   making the code difficult to read and debug.

5) Places that attempted to kludge-up the fact that we don't have kernel
   thread support have been fixed to reflect the reality that we are really
   dealing with processes, not threads. The VM system didn't have complete
   thread support, so the comments and mis-named routines were just wrong.
   We now use tsleep and wakeup directly in the lock routines, for instance.

6) Where appropriate, the pagers have been improved, especially in the
   pager_alloc routines. Most of the pager_allocs have been rewritten and
   are now faster and easier to maintain.

7) The pagedaemon pageout clustering algorithm has been rewritten and
   now tries harder to output an even number of pages before and after
   the requested page. This is sort of the reverse of the ideal pagein
   algorithm and should provide better overall performance.

8) Unnecessary (incorrect) casts to caddr_t in calls to tsleep & wakeup
   have been removed. Some other unnecessary casts have also been removed.

9) Some almost useless debugging code removed.

10) Terminology of shadow objects vs. backing objects straightened out.
    The fact that the vm_object data structure escentially had this
    backwards really confused things. The use of "shadow" and "backing
    object" throughout the code is now internally consistent and correct
    in the Mach terminology.

11) Several minor bug fixes, including one in the vm daemon that caused
    0 RSS objects to not get purged as intended.

12) A "default pager" has now been created which cleans up the transition
    of objects to the "swap" type. The previous checks throughout the code
    for swp->pg_data != NULL were really ugly. This change also provides
    the rudiments for future backing of "anonymous" memory by something
    other than the swap pager (via the vnode pager, for example), and it
    allows the decision about which of these pagers to use to be made
    dynamically (although will need some additional decision code to do
    this, of course).

13) (dyson) MAP_COPY has been deprecated and the corresponding "copy
    object" code has been removed. MAP_COPY was undocumented and non-
    standard. It was furthermore broken in several ways which caused its
    behavior to degrade to MAP_PRIVATE. Binaries that use MAP_COPY will
    continue to work correctly, but via the slightly different semantics
    of MAP_PRIVATE.

14) (dyson) Sharing maps have been removed. It's marginal usefulness in a
    threads design can be worked around in other ways. Both #12 and #13
    were done to simplify the code and improve readability and maintain-
    ability. (As were most all of these changes)

TODO:

1) Rewrite most of the vnode pager to use VOP_GETPAGES/PUTPAGES. Doing
   this will reduce the vnode pager to a mere fraction of its current size.

2) Rewrite vm_fault and the swap/vnode pagers to use the clustering
   information provided by the new haspage pager interface. This will
   substantially reduce the overhead by eliminating a large number of
   VOP_BMAP() calls. The VOP_BMAP() filesystem interface should be
   improved to provide both a "behind" and "ahead" indication of
   contiguousness.

3) Implement the extended features of pager_haspage in swap_pager_haspage().
   It currently just says 0 pages ahead/behind.

4) Re-implement the swap device (swstrategy) in a more elegant way, perhaps
   via a much more general mechanism that could also be used for disk
   striping of regular filesystems.

5) Do something to improve the architecture of vm_object_collapse(). The
   fact that it makes calls into the swap pager and knows too much about
   how the swap pager operates really bothers me. It also doesn't allow
   for collapsing of non-swap pager objects ("unnamed" objects backed by
   other pagers).
1995-07-13 08:48:48 +00:00
David Greenman
6306c897b5 swapout_threads() -> swapout_procs(). 1995-07-10 08:53:22 +00:00
David Greenman
f2daac0c69 Increased global RSS limit to total RAM. 1995-07-10 08:48:58 +00:00
David Greenman
06cb725951 Moved call to VOP_GETATTR() out of vnode_pager_alloc() and into the places
that call vnode_pager_alloc() so that a failure return can be dealt with.
This fixes a panic seen on NFS clients when a file being opened is deleted
on the server before the open completes.
1995-07-09 06:58:03 +00:00
David Greenman
39d38f93e2 Fixed an object allocation race condition that was causing a "object
deallocated too many times" panic when using NFS.

Reviewed by:	John Dyson
1995-07-06 11:48:48 +00:00
David Greenman
aa2cabb958 1) Converted v_vmdata to v_object.
2) Removed unnecessary vm_object_lookup()/pager_cache(object, TRUE) pairs
   after vnode_pager_alloc() calls - the object is already guaranteed to be
   persistent.
3) Removed some gratuitous casts.
1995-06-28 12:01:13 +00:00
Rodney W. Grimes
d3628763db Merge RELENG_2_0_5 into HEAD 1995-06-11 19:33:05 +00:00
Rodney W. Grimes
9b2e535452 Remove trailing whitespace. 1995-05-30 08:16:23 +00:00
David Greenman
956e9ca5a0 Removed check for sw_dev == NODEV; this is a normal condition for swap
over NFS and was gratuitously panicing when it happens.

Reviewed by:	John Dyson
Submitted by:	Pierre Beyssac via Poul-Henning Kamp
1995-05-25 03:38:11 +00:00
David Greenman
61f5d51062 Changes to fix the following bugs:
1) Files weren't properly synced on filesystems other than UFS. In some
   cases, this lead to lost data. Most likely would be noticed on NFS.
   The fix is to make the VM page sync/object_clean general rather than
   in each filesystem.
2) Mixing regular and mmaped file I/O on NFS was very broken. It caused
   chunks of files to end up as zeroes rather than the intended contents.
   The fix was to fix several race conditions and to kludge up the
   "b_dirtyoff" and "b_dirtyend" that NFS relies upon - paying attention
   to page modifications that occurred via the mmapping.

Reviewed by:	David Greenman
Submitted by:	John Dyson
1995-05-21 21:39:31 +00:00
David Greenman
2976b7f19f NFS diskless operation was broken because swapdev_vp wasn't initialized.
These changes solve the problem in a general way by moving the
initialization out of the individual fs_mountroot's and into swaponvp().

Submitted by:	Poul-Henning Kamp
1995-05-19 03:27:08 +00:00
David Greenman
0e5b52868f Fixed a bug that managed to slip in during Poul's dynamic swap partition
changes. The check for nswap was bogus, but the code was so convoluted
that it was difficult to tell. It's better now. :-)

Reviewed by:	David Greenman (extensively), and John Dyson
Submitted by:	Poul-Henning Kamp, w/tweaks by me.
1995-05-18 05:09:54 +00:00
David Greenman
5f55e84104 Accessing pages beyond the end of a mapped file results in internal
inconsistencies in the VM system that eventually lead to a panic. These
changes fix the behavior to conform to the behavior in SunOS, which is
to deny faults to pages beyond the EOF (returning SIGBUS). Internally,
this is implemented by requiring faults to be within the object size
boundaries. These changes exposed another bug, namely that passing in
an offset to mmap when trying to map an unnamed anonymous region also
results in internal inconsistencies. In this case, the offset is forced
to zero.

Reviewed by:	John Dyson and others
1995-05-18 02:59:26 +00:00
David Greenman
a401ebbe32 Changed swap partition handling/allocation so that it doesn't
require specific partitions be mentioned in the kernel config
file ("swap on foo" is now obsolete).

From Poul-Henning:

The visible effect is this:

As default, unless
        options "NSWAPDEV=23"
is in your config, you will have four swap-devices.
You can swapon(2) any block device you feel like, it doesn't have
to be in the kernel config.

There is a performance/resource win available by getting the NSWAPDEV right
(but only if you have just one swap-device ??), but using that as default
would be too restrictive.

The invisible effect is that:

Swap-handling disappears from the $arch part of the kernel.
It gets a lot simpler (-145 lines) and cleaner.

Reviewed by:	John Dyson, David Greenman
Submitted by:	Poul-Henning Kamp, with minor changes by me.
1995-05-14 03:00:10 +00:00
Poul-Henning Kamp
8af2296bcb I'm about to jump on the swap-initialization, and having talked
with davidg about it, I hereby kill two undocumented misfeatures:
The code to skip a miniroot in the swapdev is not particular useful, and
if we need it we need it to be done properly, ie size the fs and skip all
of it not some hardcoded size, and subtract what we skip from the length
in the first place.
The SEQSWAP dies too.  It's not the way to do it, it doesn't work, and
nobody have expressed any great desire for it to work.  The way to
implement it correctly would be a second argument to swapon(2) to give
a priority/policy information.  Low priority swapdevs can be made so
by adding them at a far offset (0x80000000 kind of thing), with almost no
modification to the strategy routine (in particular a offset per swapdev).
But until the need is obvious, it will not be done.
1995-05-12 03:54:59 +00:00
David Greenman
ee3a64c992 Changed "handle" from type caddr_t to void *; "handle" is several different
types of pointers, and "char *" is a bad choice for the type.
1995-05-10 18:56:09 +00:00
John Dyson
11fda60b40 Another error in the correction for trimming swap allocation for
small objects.  (This code needs to be revisited.)
1995-05-07 06:36:59 +00:00
John Dyson
85b67b98fd Fixed a calculation that would once-in-a-while cause the swap_pager
to emit spurious page outside of object type messages.  It is not
a fatal condition anyway, so the message will be omitted for
release.  Also, the code that "clips" the allocation size, associated
with the above problem, was fixed.
1995-05-07 03:48:54 +00:00
David Greenman
f325917a65 Changed object hash list to be a list rather than a tailq. This saves
space for the hash list buckets and is a little faster. The features
of tailq aren't needed. Increased the size of the object hash table
to improve performance. In the future, this will be changed so that
the table is sized dynamically.
1995-05-02 05:57:11 +00:00
David Greenman
3fc3004e03 Fixed a "bswbuf" hang caused by the wakeup in relpbuf() waking up the
wrong thing.
1995-04-25 06:22:47 +00:00
Bruce Evans
7666fb4753 inline -> __inline.
Headers should always use `__inline' for inline functions to avoid
syntax errors when modules that don't even use the offending functions
are compiled with `gcc -ansi'.
1995-04-23 08:05:49 +00:00
John Dyson
7e15fd2757 Fixed a problem in _vm_object_page_clean that could cause an
infinite loop.
1995-04-21 02:48:40 +00:00
David Greenman
aba8f38eb9 New flag: B_PAGING. Added as part of the vn driver hack. 1995-04-19 10:32:11 +00:00
David Greenman
4c1f8ee9b8 Fixed a logic bug that caused the vmdaemon to not wake up when intended.
Submitted by:	John Dyson
1995-04-17 10:00:55 +00:00
David Greenman
7c0414d074 Removed obsolete/unused variable declarations. Killed externs and included
appropriate include files.
1995-04-16 14:12:15 +00:00
David Greenman
64abb5a522 Removed obsolete/unused variable declarations.
Removed some extern declarations and included the correct include files.
1995-04-16 13:58:42 +00:00
David Greenman
c3cb3e12f5 Moved some zero-initialized variables into .bss. Made code intended to be
called only from DDB #ifdef DDB. Removed some completely unused globals.
1995-04-16 12:56:22 +00:00
David Greenman
8c3d9c403c Removed gratuitous m->blah=0 assignments when initializing the vm_page
structs in vm_page_startup(). The vm_page structs are already completely
zeroed.
1995-04-16 11:50:45 +00:00
David Greenman
2fdccd5e8c Make "print_page_info" #ifdef DDB. 1995-04-16 09:59:16 +00:00
David Greenman
ec4f9fb0ee Fixed a few bugs in vm_object_page_clean, mostly related to not syncing
pages that are in FS buffers. This fixes the (believed to already have been
fixed) problem with msync() not doing it's job...in other words, the
stuff that Andrew has continuously been complaining about.

Submitted by:	John Dyson, w/minor changes by me.
1995-04-16 03:11:28 +00:00
David Greenman
f6b04d2bfb Changes from John Dyson and myself:
Fixed remaining known bugs in the buffer IO and VM system.

vfs_bio.c:
Fixed some race conditions and locking bugs. Improved performance
by removing some (now) unnecessary code and fixing some broken
logic.
Fixed process accounting of # of FS outputs.
Properly handle NFS interrupts (B_EINTR).

(various)
Replaced calls to clrbuf() with calls to an optimized routine
called vfs_bio_clrbuf().

(various FS sync)
Sync out modified vnode_pager backed pages.

ffs_vnops.c:
Do two passes: Sync out file data first, then indirect blocks.

vm_fault.c:
Fixed deadly embrace caused by acquiring locks in the wrong order.

vnode_pager.c:
Changed to use buffer I/O system for writing out modified pages. This
should fix the problem with the modification date previous not getting
updated. Also dramatically simplifies the code. Note that this is
going to change in the future and be implemented via VOP_PUTPAGES().

vm_object.c:
Fixed a pile of bugs related to cleaning (vnode) objects. The performance
of vm_object_page_clean() is terrible when dealing with huge objects,
but this will change when we implement a binary tree to keep the object
pages sorted.

vm_pageout.c:
Fixed broken clustering of pageouts. Fixed race conditions and other
lockup style bugs in the scanning of pages. Improved performance.
1995-04-09 06:03:56 +00:00
Bruce Evans
3aa12267a5 Add and move declarations to fix all of the warnings from `gcc -Wimplicit'
(except in netccitt, netiso and netns) that I didn't notice when I fixed
"all" such warnings before.
1995-03-28 07:58:53 +00:00
David Greenman
17c4c40800 Fixed typo...using wrong variable in page_shortage calculation. 1995-03-28 05:58:35 +00:00
David Greenman
0bb3a0d2f4 Fixed "pages freed by daemon" statistic (again). 1995-03-28 05:35:29 +00:00