Commit Graph

76 Commits

Author SHA1 Message Date
chs 76cacb8710 when processing PG_RDONLY, mask off VM_PROT_WRITE instead of hard-wiring
VM_PROT_READ (since we might have VM_PROT_EXEC too).  this fixes problems
running binaries out of NFS on macppc.  yet another fix courtesy of enami.
2002-03-25 01:56:48 +00:00
chs 87185156fd a vm_prot_t is a bit-mask, fix an assertion which was treating one
more like an enumerated type.
2002-03-09 04:29:03 +00:00
chs e9a82c88ce in uvm_fault_unwire_locked(), if we find that a pmap entry is missing,
just skip that page.  this situation can arise legitimately when a file
with a wired mapping is truncated so that a wired page is no longer
part of the file.
2002-01-02 01:10:36 +00:00
chs a7ec5b4144 redo part of the last commit. 2002-01-01 22:18:39 +00:00
chs 43973be0c5 introduce a new UVM fault type, VM_FAULT_WIREMAX. this is different
from VM_FAULT_WIRE in that when the pages being wired are faulted in,
the simulated fault is at the maximum protection allowed for the mapping
instead of the current protection.  use this in uvm_map_pageable{,_all}()
to fix the problem where writing via ptrace() to shared libraries that
are also mapped with wired mappings in another process causes a
diagnostic panic when the wired mapping is removed.

this is a really obscure problem so it deserves some more explanation.
ptrace() writing to another process ends up down in uvm_map_extract(),
which for MAP_PRIVATE mappings (such as shared libraries) will cause
the amap to be copied or created.  then the amap is made shared
(ie. the AMAP_SHARED flag is set) between the kernel and the ptrace()d
process so that the kernel can modify pages in the amap and have the
ptrace()d process see the changes.  then when the page being modified
is actually faulted on, the object pages (from the shared library vnode)
is copied to a new anon page and inserted into the shared amap.
to make all the processes sharing the amap actually see the new anon
page instead of the vnode page that was there before, we need to
invalidate all the pmap-level mappings of the vnode page in the pmaps
of the processes sharing the amap, but we don't have a good way of
doing this.  the amap doesn't keep track of the vm_maps which map it.
so all we can do at this point is to remove all the mappings of the
page with pmap_page_protect(), but this has the unfortunate side-effect
of removing wired mappings as well.  removing wired mappings with
pmap_page_protect() is a legitimate operation, it can happen when a file
with a wired mapping is truncated.  so the pmap has no way of knowing
whether a request to remove a wired mapping is normal or when it's due to
this weird situation.  so the pmap has to remove the weird mapping.
the process being ptrace()d goes away and life continues.  then,
much later when we go to unwire or remove the wired vm_map mapping,
we discover that the pmap mapping has been removed when it should
still be there, and we panic.

so where did we go wrong?  the problem is that we don't have any way
to update just the pmap mappings that need to be updated in this
scenario.  we could invent a mechanism to do this, but that is much
more complicated than this change and it doesn't seem like the right
way to go in the long run either.

the real underlying problem here is that wired pmap mappings just
aren't a good concept.  one of the original properties of the pmap
design was supposed to be that all the information in the pmap could
be thrown away at any time and the VM system could regenerate it all
through fault processing, but wired pmap mappings don't allow that.
a better design for UVM would not require wired pmap mappings,
and Chuck C. and I are talking about this, but it won't be done
anytime soon, so this change will do for now.

this change has the effect of causing MAP_PRIVATE mappings to be
copied to anonymous memory when they are mlock()d, so that uvm_fault()
doesn't need to copy these pages later when called from ptrace(), thus
avoiding the call to pmap_page_protect() and the panic that results
from this when the mlock()d region is unlocked or freed.  note that
this change doesn't help the case where the wired mapping is MAP_SHARED.

discussed at great length with Chuck Cranor.
fixes PRs 10363, 12554, 12604, 13041, 13487, 14580 and 14853.
2001-12-31 22:34:39 +00:00
lukem b616d1ca1d add RCSIDs, and in some cases, slightly cleanup #include order 2001-11-10 07:36:59 +00:00
chs 3aea6d69ad skip the MADV_SEQUENTIAL processing if we refault. fixes PR 14060. 2001-10-03 05:17:58 +00:00
chs 64c6d1d2dc a whole bunch of changes to improve performance and robustness under load:
- remove special treatment of pager_map mappings in pmaps.  this is
   required now, since I've removed the globals that expose the address range.
   pager_map now uses pmap_kenter_pa() instead of pmap_enter(), so there's
   no longer any need to special-case it.
 - eliminate struct uvm_vnode by moving its fields into struct vnode.
 - rewrite the pageout path.  the pager is now responsible for handling the
   high-level requests instead of only getting control after a bunch of work
   has already been done on its behalf.  this will allow us to UBCify LFS,
   which needs tighter control over its pages than other filesystems do.
   writing a page to disk no longer requires making it read-only, which
   allows us to write wired pages without causing all kinds of havoc.
 - use a new PG_PAGEOUT flag to indicate that a page should be freed
   on behalf of the pagedaemon when it's unlocked.  this flag is very similar
   to PG_RELEASED, but unlike PG_RELEASED, PG_PAGEOUT can be cleared if the
   pageout fails due to eg. an indirect-block buffer being locked.
   this allows us to remove the "version" field from struct vm_page,
   and together with shrinking "loan_count" from 32 bits to 16,
   struct vm_page is now 4 bytes smaller.
 - no longer use PG_RELEASED for swap-backed pages.  if the page is busy
   because it's being paged out, we can't release the swap slot to be
   reallocated until that write is complete, but unlike with vnodes we
   don't keep a count of in-progress writes so there's no good way to
   know when the write is done.  instead, when we need to free a busy
   swap-backed page, just sleep until we can get it busy ourselves.
 - implement a fast-path for extending writes which allows us to avoid
   zeroing new pages.  this substantially reduces cpu usage.
 - encapsulate the data used by the genfs code in a struct genfs_node,
   which must be the first element of the filesystem-specific vnode data
   for filesystems which use genfs_{get,put}pages().
 - eliminate many of the UVM pagerops, since they aren't needed anymore
   now that the pager "put" operation is a higher-level operation.
 - enhance the genfs code to allow NFS to use the genfs_{get,put}pages
   instead of a modified copy.
 - clean up struct vnode by removing all the fields that used to be used by
   the vfs_cluster.c code (which we don't use anymore with UBC).
 - remove kmem_object and mb_object since they were useless.
   instead of allocating pages to these objects, we now just allocate
   pages with no object.  such pages are mapped in the kernel until they
   are freed, so we can use the mapping to find the page to free it.
   this allows us to remove splvm() protection in several places.

The sum of all these changes improves write throughput on my
decstation 5000/200 to within 1% of the rate of NetBSD 1.5
and reduces the elapsed time for "make release" of a NetBSD 1.5
source tree on my 128MB pc to 10% less than a 1.5 kernel took.
2001-09-15 20:36:31 +00:00
chris 0e7661f023 Update pmap_update to now take the updated pmap as an argument.
This will allow improvements to the pmaps so that they can more easily defer expensive operations, eg tlb/cache flush, til the last possible moment.

Currently this is a no-op on most platforms, so they should see no difference.

Reviewed by Jason.
2001-09-10 21:19:08 +00:00
thorpej a279b0973b Reduce some complexity in the fault path -- Rather than maintaining
an spl-protected "interrupt safe map" list, simply require that callers
of uvm_fault() never call us in interrupt context (MD code must make
the assertion), and check for interrupt-safe maps in uvmfault_lookup()
before we lock the map.
2001-06-26 17:55:14 +00:00
thorpej 78ae4127bb Note that uvm_fault() must NEVER EVER EVER be called in interrupt
context.
2001-06-26 17:27:31 +00:00
chs 7e00a527ea work around an overflow problem in uvm_fault_wire().
from Eduardo Horvath and Simon Burge.
2001-06-14 05:12:56 +00:00
chs 821ec03ed9 replace vm_map{,_entry}_t with struct vm_map{,_entry} *. 2001-06-02 18:09:08 +00:00
chs 3845302904 remove trailing whitespace. 2001-05-25 04:06:11 +00:00
thorpej 773ed79e5b Add a comment describing a problem. 2001-04-25 14:59:44 +00:00
thorpej 1c3a62e066 Sprinkle pmap_update() calls after calls to:
- pmap_enter()
- pmap_remove()
- pmap_protect()
- pmap_kenter_pa()
- pmap_kremove()
as described in pmap(9).

These calls are relatively conservative.  It may be possible to
optimize these a little more.
2001-04-24 04:30:50 +00:00
chs 088989a557 undo the part of a previous commit which turned a check for faulting
on an "intrsafe" map into a KASSERT.  this situation can be caused by
an application accessing /dev/kmem.
2001-04-01 16:45:53 +00:00
chs edb041f0d1 return the real error from pgo_fault(). 2001-03-17 04:01:24 +00:00
chs ac3bc537bd eliminate the KERN_* error codes in favor of the traditional E* codes.
the mapping is:

KERN_SUCCESS			0
KERN_INVALID_ADDRESS		EFAULT
KERN_PROTECTION_FAILURE		EACCES
KERN_NO_SPACE			ENOMEM
KERN_INVALID_ARGUMENT		EINVAL
KERN_FAILURE			various, mostly turn into KASSERTs
KERN_RESOURCE_SHORTAGE		ENOMEM
KERN_NOT_RECEIVER		<unused>
KERN_NO_ACCESS			<unused>
KERN_PAGES_LOCKED		<unused>
2001-03-15 06:10:32 +00:00
chs dd82ad8e2c eliminate the VM_PAGER_* error codes in favor of the traditional E* codes.
the mapping is:

VM_PAGER_OK		        0
VM_PAGER_BAD		        <unused>
VM_PAGER_FAIL		        <unused>
VM_PAGER_PEND		        0 (see below)
VM_PAGER_ERROR		        EIO
VM_PAGER_AGAIN		        EAGAIN
VM_PAGER_UNLOCK		        EBUSY
VM_PAGER_REFAULT	        ERESTART

for async i/o requests, it used to be possible for the request to
be convert to sync, and the pager would return VM_PAGER_OK or VM_PAGER_PEND
to indicate whether the caller should perform post-i/o cleanup.
this is no longer allowed; pagers must now return 0 to indicate that
the async i/o was successfully started, and the caller never needs to
worry about doing the post-i/o cleanup.
2001-03-10 22:46:45 +00:00
chs 19b7b64642 clean up DIAGNOSTIC checks, use KASSERT(). 2001-02-18 21:19:08 +00:00
thorpej 1779f8f71b Page scanner improvements, behavior is actually a bit more like
Mach VM's now.  Specific changes:
- Pages now need not have all of their mappings removed before being
  put on the inactive list.  They only need to have the "referenced"
  attribute cleared.  This makes putting pages onto the inactive list
  much more efficient.  In order to eliminate redundant clearings of
  "refrenced", callers of uvm_pagedeactivate() must now do this
  themselves.
- When checking the "modified" attribute for a page (for clearing
  PG_CLEAN), make sure to only do it if PG_CLEAN is currently set on
  the page (saves a potentially expensive pmap operation).
- When scanning the inactive list, if a page is referenced, reactivate
  it (this part was actually added in uvm_pdaemon.c,v 1.27).  This
  now works properly now that pages on the inactive list are allowed to
  have mappings.
- When scanning the inactive list and considering a page for freeing,
  remove all mappings, and then check the "modified" attribute if the
  page is marked PG_CLEAN.
- When scanning the active list, if the page was referenced since its
  last sweep by the scanner, don't deactivate it.  (This part was
  actually added in uvm_pdaemon.c,v 1.28.)

These changes greatly improve interactive performance during
moderate to high memory and I/O load.
2001-01-28 23:30:42 +00:00
thorpej ad7259d7c6 Change uvm_analloc() to return a locked anon, update all callers,
and fix an anon locking protocol error in uvm_loanzero().
2001-01-23 02:27:39 +00:00
thorpej 13759f5310 Sprinkle some assertions:
amap_free(): Assert that the amap is locked.
amap_share_protect(): Assert that the amap is locked.
amap_wipeout(): Assert that the amap is locked.
uvm_anfree(): Assert that the anon has a reference count of 0 and is
              not locked.
uvm_anon_lockloanpg(): Assert that the anon is locked.
anon_pagein(): Assert that the anon is locked.
uvmfault_anonget(): Assert that the anon is locked.
uvm_pagealloc_strat(): Assert that the uobj or the anon is locked

And fix the problems these have uncovered:
amap_cow_now(): Lock the new anon after allocating it, and unref and
                unlock it (rather than lock!) before freeing it in case
                of an error condition.  This should fix a problem reported
		by Dan Carosone using cdrecord on an i386 MP kernel.
uvm_fault(): Case1B -- Lock the new anon afer allocating it, and unlock
             it later when we unlock the old anon.
	     Case2 -- Lock the new anon after allocating it, and unlock
	     it later by passing it to uvmfault_unlockall() (we set anon
	     to NULL if we're not doing a promote fault).
2001-01-23 01:56:16 +00:00
chs aeda8d3b77 Initial integration of the Unified Buffer Cache project. 2000-11-27 08:39:39 +00:00
thorpej 6eb78dcb4e Update a comment in uvmfault_anonget() to reflect reality, and
make uvm_fault() handle uvmfault_anonget() failure properly (i.e.
don't unlock a lock that's already unlocked).
2000-08-06 00:22:53 +00:00
mrg dea44a9ec4 remove include of <vm/vm.h> 2000-06-27 17:29:17 +00:00
mrg 2f159a1bac remove/move more mach vm header files:
<vm/pglist.h> -> <uvm/uvm_pglist.h>
	<vm/vm_inherit.h> -> <uvm/uvm_inherit.h>
	<vm/vm_kern.h> -> into <uvm/uvm_extern.h>
	<vm/vm_object.h> -> nothing
	<vm/vm_pager.h> -> into <uvm/uvm_pager.h>

also includes a bunch of <vm/vm_page.h> include removals (due to redudancy
with <vm/vm.h>), and a scattering of other similar headers.
2000-06-26 14:20:25 +00:00
thorpej eeb3a38cfc Use UVM_PGA_ZERO in the promote-zero-fault case of uvm_fault(). 2000-04-10 01:17:41 +00:00
chs 16f0ca3612 add support for ``swapctl -d'' (removing swap space).
improve handling of i/o errors in swap space.

reviewed by:  Chuck Cranor
2000-01-11 06:57:49 +00:00
thorpej 1da427a80a Change the pmap_enter() API slightly; pmap_enter() now returns an error
value (KERN_SUCCESS or KERN_RESOURCE_SHORTAGE) indicating if it succeeded
or failed.  Change the `wired' and `access_type' arguments to a single
`flags' argument, which includes the access type, and flags:

	PMAP_WIRED	the old `wired' boolean
	PMAP_CANFAIL	pmap_enter() is allowed to fail

If PMAP_CANFAIL is not specified, the pmap should behave as it always
has in the face of a drastic resource shortage: fall over dead.

Change the fault handler to deal with failure (which indicates resource
shortage) by unlocking everything, waiting for the pagedaemon to free
more memory, then retrying the fault.
1999-11-13 00:24:38 +00:00
chs f3a668ed84 eliminate the PMAP_NEW option by making it required for all ports.
ports which previously had no support for PMAP_NEW now implement
the pmap_k* interfaces as wrappers around the non-k versions.
1999-09-12 01:16:55 +00:00
thorpej 3f176180d5 Garbage collect thread_sleep()/thread_wakeup() left over from the old
Mach VM code.  Also nuke iprintf(), which was no longer used anywhere.

Add proclist locking where appropriate.
1999-07-22 22:58:38 +00:00
cgd 4eb46531af make sure 'wide' fault handling is actually done only once per fault.
('narrow' was mistakenly set to FALSE instead of TRUE.)  Committed after
discussion with chuq.
1999-07-19 19:02:22 +00:00
thorpej ff05773b4a Back out the change I made yesterday. It seems to cause some trouble
for some folks.
1999-07-11 17:47:12 +00:00
thorpej a0555db3e0 Simplify uvm_fault_unwire_locked() a little. 1999-07-10 21:46:56 +00:00
thorpej 3ebbe095e0 Change the pmap_extract() interface to:
boolean_t pmap_extract(pmap_t, vaddr_t, paddr_t *);
This makes it possible for the pmap to map physical address 0.
1999-07-08 18:05:21 +00:00
thorpej 0288ffb53a pmap_change_wiring() -> pmap_unwire(). 1999-06-17 19:23:20 +00:00
thorpej f5a527bb4e Remove pmap_pageable(); no pmap implements it, and it is not really useful,
because pmap_enter()/pmap_change_wiring() (soon to be pmap_unwire())
communicate the information in greater detail.
1999-06-17 18:21:21 +00:00
thorpej d1d9b366cd When unwiring a range in uvm_fault_unwire_locked(), don't call
pmap_change_wiring(...,FALSE) unless the map entry claims the address
is unwired.  This fixes the following scenario, as described on
tech-kern@netbsd.org on Wed 6/16/1999 12:25:23:

	- User mlock(2)'s a buffer, to guarantee it will never become
	  non-resident while he is using it.

	- User then does physio to that buffer.  Physio calls uvm_vslock()
	  to lock down the pages and ensure that page faults do not happen
	  while the I/O is in progress (possibly in interrupt context).

	- Physio does the I/O.

	- Physio calls uvm_vsunlock().  This calls uvm_fault_unwire().

	  >>> HERE IS WHERE THE PROBLEM OCCURS <<<

	  uvm_fault_unwire() calls pmap_change_wiring(..., FALSE),
	  which now gives the pmap free reign to recycle the mapping
	  information for that page, which is illegal; the mapping is
	  still wired (due to the mlock(2)), but now access of the
	  page could cause a non-protection page fault (disallowed).

	  NOTE: This could eventually lead to a panic when the user
	  subsequently munlock(2)'s the buffer and the mapping info
	  has been recycled for use by another mapping!
1999-06-16 23:02:40 +00:00
thorpej b861180119 * Rename uvm_fault_unwire() to uvm_fault_unwire_locked(), and require that
the map be at least read-locked to call this function.  This requirement
  will be taken advantage of in a future commit.
* Write a uvm_fault_unwire() wrapper which read-locks the map and calls
  uvm_fault_unwire_locked().
* Update the comments describing the locking contraints of uvm_fault_wire()
  and uvm_fault_unwire().
1999-06-16 22:11:23 +00:00
thorpej 23c6eb95d3 Remove a incorrect-and-no-longer-relevant comment. 1999-06-16 18:43:28 +00:00
thorpej ee9703dea9 Add a macro to test if a map entry is wired. 1999-06-16 00:29:04 +00:00
thorpej 2c3dc83a64 Keep interrupt-safe maps on an additional queue. In uvm_fault(), if we're
looking up a kernel address, check to see if the address is on this
"interrupt-safe" list.  If so, return failure immediately.  This prevents
a locking screw if a page fault is taken on an interrupt-safe map in or
out of interrupt context.
1999-06-04 23:38:41 +00:00
thorpej acf81da21e A page fault on a non-pageable map is always fatal. 1999-06-02 23:26:21 +00:00
thorpej 8d8badbd8f Make uvm_fault_unwire() take a vm_map_t, rather than a pmap_t, for
consistency.  Use this opportunity for checking for intrsafe map use
in this routine (which is illegal).
1999-05-28 20:49:51 +00:00
thorpej 195c1a2741 Pass an access_type to uvm_fault_wire(), which it forwards on to
uvm_fault().
1999-05-26 00:32:42 +00:00
chs a5d3e8dae9 when wiring swap-backed pages, clear the PG_CLEAN flag before
releasing any swap resources.  if we don't do this, we can
end up with a clean, swap-backed page, which is illegal.
tracked down by Bill Sommerfeld, fixes PR 7578.
1999-05-19 06:14:15 +00:00
chs f455dd6596 add a `flags' argument to uvm_pagealloc_strat().
define a flag UVM_PGA_USERESERVE to allow non-kernel object
allocations to use pages from the reserve.
use the new flag for allocations in pmap modules.
1999-04-11 04:04:04 +00:00
mycroft 671c65c6da Duuuh. Back and front pages should have an access_type of 0, since we don't
know they're going to be used.  What was I thinking??
1999-03-29 05:43:31 +00:00