Commit Graph

657 Commits

Author SHA1 Message Date
yamt f8b7159909 unbusy a page after put it on the queue.
fix a panic with UVM_PAGE_TRKOWN when doing swapoff.
2003-04-12 14:36:43 +00:00
thorpej 03befad98b In uvm_map_clean(), only call pgo_put if the object has one.
From Quentin Garnier <quatriemek.com!netbsd>.
2003-04-09 21:39:29 +00:00
thorpej 7360657293 Tweak the way the pagesize-related variables are set:
* Remove DEFAULT_PAGE_SIZE.  We don't use PAGE_SIZE the way Mach did.
* In uvm_setpagesize(), if we are called with uvmexp.pagesize == 0,
  then assert that PAGE_SIZE != 0 (i.e. a constant), and set uvmexp.pagesize
  accordingly.
* Provide defaults for MIN_PAGE_SIZE and MAX_PAGE_SIZE if not defined
  by <machine/vmparam.h>.  If PAGE_SIZE is not a constant, MIN_PAGE_SIZE
  and MAX_PAGE_SIZE must be provided.
* If MIN_PAGE_SIZE and MAX_PAGE_SIZE are not equal (i.e. PAGE_SIZE may
  not be a constant in all configurations), then ensure that PAGE_SIZE
  and friends expand to variable references for LKMs.
2003-04-09 16:34:10 +00:00
matt 7876614463 Nuke mem_size global since nothing in the kernel actually refers to it.
(mmm lint).
2003-03-14 08:35:05 +00:00
thorpej 2d5e311009 Make PGALLOC_VERBOSE compile where size_t != int. 2003-03-10 19:52:24 +00:00
thorpej 2a493af5b0 For PMAP_CACHE_VIVT platforms, make UBC_RELEASE_UNMAP evaluate to TRUE,
and add a comment explaining why.

Reviewed by Chuq Silvers.
2003-03-10 15:07:17 +00:00
tsutsui 004ae00514 Use cpu_number() in UVMHIST_LOG() rather than non-public ci_cpuid member
in struct cpu_info.
2003-03-08 15:17:23 +00:00
matt 6074e25e08 Add support for mmap(2) to be able to return memory aligned on a 2^n
boundary.
2003-03-06 00:41:51 +00:00
thorpej 72dd57106c Implement a minimal pager for the uvm_loanzero_object, which simply has
a "put" method which reactivates or dequeues the page.

Need for pager pointed out by enami tsugutomo.
2003-03-05 01:52:41 +00:00
thorpej d3f54e81dd Fix the following pathological scanario:
* User allocates ZFOD region, but does not actually touch the buffer
  to fault in the pages.
* In a loop, user writes this buffer to a network socket, triggering
  sosend_loan().
* uvm_loan() calls uvm_loanzero() once for each page in the loaned
  region (since the pages have not yet faulted in).  This causes a
  page to be allocated and zero'd.  The result is the kernel spends
  a lot of time allocating and zero'ing pages.

This fixes creates a special object which owns a single zero'd page.
This single zero'd page is used to satisfy all loans of non-resident
ZFOD mappings.

Thanks to Allen Briggs for discovering the problem and for providing
an initial patch.
2003-03-04 06:18:54 +00:00
matt 76dd2c90fa In uvm_map_space, if the current entry is above the new space use the
previous entry.  (not if the current entry starts at the end of the new
space; that case doesn't take into account if the new space had a specified
alignment).
2003-03-02 08:57:49 +00:00
matt d6729b1f53 When finding an aligned block, we need to truncate in topdown, not roundup. 2003-03-02 02:55:03 +00:00
thorpej eb14e86676 Add a new BUF_INIT() macro which initializes b_dep and b_interlock, and
use it.  This fixes a few places where either b_dep or b_interlock were
not properly initialized.
2003-02-25 20:35:31 +00:00
simonb a2bdcc915e Cast result of pgo_put() to (void) as is the style with other calls to
pgo_put() in UVM.

Pointed out by Andrew Brown.
2003-02-25 00:22:20 +00:00
pk 2931081a79 Make updating a file's reference and use count MP-safe. 2003-02-23 14:37:32 +00:00
simonb 0b2b1cc0cc Remove assigned-to but not used variable. 2003-02-23 04:53:51 +00:00
matt 23b48be61f fix a tpyo in a comment. 2003-02-21 16:38:44 +00:00
atatat df0a9badc6 Introduce "top down" memory management for mmap()ed allocations. This
means that the dynamic linker gets mapped in at the top of available
user virtual memory (typically just below the stack), shared libraries
get mapped downwards from that point, and calls to mmap() that don't
specify a preferred address will get mapped in below those.

This means that the heap and the mmap()ed allocations will grow
towards each other, allowing one or the other to grow larger than
before.  Previously, the heap was limited to MAXDSIZ by the placement
of the dynamic linker (and the process's rlimits) and the space
available to mmap was hobbled by this reservation.

This is currently only enabled via an *option* for the i386 platform
(though other platforms are expected to follow).  Add "options
USE_TOPDOWN_VM" to your kernel config file, rerun config, and rebuild
your kernel to take advantage of this.

Note that the pmap_prefer() interface has not yet been modified to
play nicely with this, so those platforms require a bit more work
(most notably the sparc) before they can use this new memory
arrangement.

This change also introduces a VM_DEFAULT_ADDRESS() macro that picks
the appropriate default address based on the size of the allocation or
the size of the process's text segment accordingly.  Several drivers
and the SYSV SHM address assignment were changed to use this instead
of each one picking their own "default".
2003-02-20 22:16:05 +00:00
perseant b397c875ae Add code to UBCify LFS. This is still behind "#ifdef LFS_UBC" for now
(there are still some details to work out) but expect that to go
away soon.  To support these basic changes (creation of lfs_putpages,
lfs_gop_write, mods to lfs_balloc) several other changes were made, to
wit:

* Create a writer daemon kernel thread whose purpose is to handle page
  writes for the pagedaemon, but which also takes over some of the
  functions of lfs_check().  This thread is started the first time an
  LFS is mounted.

* Add a "flags" parameter to GOP_SIZE.  Current values are
  GOP_SIZE_READ, meaning that the call should return the size of the
  in-core version of the file, and GOP_SIZE_WRITE, meaning that it
  should return the on-disk size.  One of GOP_SIZE_READ or
  GOP_SIZE_WRITE must be specified.

* Instead of using malloc(...M_WAITOK) for everything, reserve enough
  resources to get by and use malloc(...M_NOWAIT), using the reserves if
  necessary.  Use the pool subsystem for structures small enough that
  this is feasible.  This also obsoletes LFS_THROTTLE.

And a few that are not strictly necessary:

* Moves the LFS inode extensions off onto a separately allocated
  structure; getting closer to LFS as an LKM.  "Welcome to 1.6O."

* Unified GOP_ALLOC between FFS and LFS.

* Update LFS copyright headers to correct values.

* Actually cast to unsigned in lfs_shellsort, like the comment says.

* Keep track of which segments were empty before the previous
  checkpoint; any segments that pass two checkpoints both dirty and
  empty can be summarily cleaned.  Do this.  Right now lfs_segclean
  still works, but this should be turned into an effectless
  compatibility syscall.
2003-02-17 23:48:08 +00:00
atatat a57bcda26a Rework the way in which the map is traversed when dumping core. Now
we read-lock the map and call uvm_map_lookup_entry() instead of simply
walking from the header to the next and to the next, etc.

Dumping from sparsely populated amaps could cause faults that would
result in amaps being split, which (in turn) resulted in the core
dumping routines dumping some regions of memory twice.  This makes the
core file too large, the headers not match, gdb not work properly,
and so on.

Addresses PR 19260.
2003-02-14 16:25:12 +00:00
pk ff65229410 Include CPU number in UVM history logs. 2003-02-09 22:33:18 +00:00
pk c7cbbfeead uvm_fault: case 1B: lock page queue before calling uvm_pageactivate(). 2003-02-09 22:32:21 +00:00
pk 9d4b10800c uao_put: release uvm object's lock only after we're done with its page list. 2003-02-09 22:28:40 +00:00
pk 338f31f581 Make the buffer cache code MP-safe. 2003-02-05 21:38:38 +00:00
thorpej b193480908 Add extensible malloc types, adapted from FreeBSD. This turns
malloc types into a structure, a pointer to which is passed around,
instead of an int constant.  Allow the limit to be adjusted when the
malloc type is defined, or with a function call, as suggested by
Jonathan Stone.
2003-02-01 06:23:35 +00:00
pk ac1bea60c1 amap_copy: remove stray amap_unlock(). 2003-01-27 22:14:48 +00:00
enami c3d0a7a93b uvm_page_unbusy should skip PGO_DONTCARE page; e.g., locked pgo_getpages
request may contain PGO_DONTCARE and nfs_getpages may unbusy them on error.

Fix is provided in PR#20028 by YAMAMOTO Takashi.  (and same one is approved
by chuq while ago in private mail).  It was my fault to forget to commit.
2003-01-27 02:10:20 +00:00
yamt 41ad61ee76 make KSTACK_CHECK_* compile after sa merge. 2003-01-22 12:52:14 +00:00
christos 5c729d909f finally: step 5: disable a KASSERT() if we are doing_shutdown.
now sync from ddb should work as badly as before the nathanw_sa merge.
2003-01-21 00:03:07 +00:00
thorpej b78f59b443 Merge the nathanw_sa branch. 2003-01-18 08:51:40 +00:00
atatat 84a6247a30 Properly set page references counts at the start of the newly
allocated ppref data to zero in the case of an amap that has empty
space at the front.

Don't set anything in the ppref array if "len" is zero.

Many thanks to Sami Kantoluoto for providing gdb access to a machine
that would reliably crash with problems related to the above, and to
Stephan Thesing for corroborating that the patch properly addressed
the problem.

Note that the ar_pageoff (and related variables) types must be changed
soon.  The use of "int" here is not theoretically sufficient.
2002-12-20 18:21:13 +00:00
thorpej 130e5c278b UVM_KMF_NOWAIT -> UVM_FLAG_NOWAIT 2002-12-11 07:14:28 +00:00
thorpej 8ae922d8a7 Define a UVM_FLAG_NOWAIT, which indicates that we're not allowed
to sleep.  Define UVM_KMF_NOWAIT in terms of UVM_FLAG_NOWAIT.

From Manuel Bouyer.  Fixes a problem where any mapping with
read protection was created in a "nowait" context, causing
spurious failures.
2002-12-11 07:10:20 +00:00
matt 00ed0b8fb8 Reorder things so that with multiple inclusion protection that optional
definitions are outside the protection checks.
2002-12-01 22:58:43 +00:00
bouyer d986226518 Change uvm_km_kmemalloc() to accept flag UVM_KMF_NOWAIT and pass it to
uvm_map(). Change uvm_map() to honnor UVM_KMF_NOWAIT. For this, change
amap_extend() to take a flags parameter instead of just boolean for
direction, and introduce AMAP_EXTEND_FORWARDS and AMAP_EXTEND_NOWAIT flags
(AMAP_EXTEND_BACKWARDS is still defined as 0x0, to keep the code easier to
read).
Add a flag parameter to uvm_mapent_alloc().
This solves a problem a pool_get(PR_NOWAIT) could trigger a pool_get(PR_WAITOK)
in uvm_mapent_alloc().
Thanks to Chuck Silvers, enami tsugutomo, Andrew Brown and Jason R Thorpe
for feedback.
2002-11-30 18:28:04 +00:00
lukem 0635de35a3 Remove KDIR=, since SYS_INCLUDE=symlinks and KDIR are not supported any more. 2002-11-26 23:30:07 +00:00
scw e591e98c92 Quell uninitialised variable warnings. 2002-11-24 11:50:32 +00:00
chs 4b2625143d change uvm_uarea_alloc() to indicate whether the returned uarea is already
backed by physical pages (ie. because it reused a previously-freed one),
so that we can skip a bunch of useless work in that case.
this fixes the underlying problem behind PR 18543, and also speeds up fork()
quite a bit (eg. 7% on my pc, 1% on my ultra2) when we get a cache hit.
2002-11-17 08:32:43 +00:00
atatat 966f9caaed Properly free "newppref", instead of "amap->am_ppref" (oops), and
delay freeing the old am_ppref so that if we bail early due to
malloc() failures, valid ppref data hasn't been freed for no reason.

Based on comments from enami.
2002-11-15 17:30:35 +00:00
atatat 42c2fe641b Implement backwards extension of amaps. There are three cases to deal
with:

Case #1 -- adjust offset: The slot offset in the aref can be
decremented to cover the required size addition.

Case #2 -- move pages and adjust offset: The slot offset is not large
enough, but the amap contains enough inactive space *after* the mapped
pages to make up the difference, so active slots are slid to the "end"
of the amap, and the slot offset is, again, adjusted to cover the
required size addition.  This optimizes for hitting case #1 again on
the next small extension.

Case #3 -- reallocate, move pages, and adjust offset: There is not
enough inactive space in the amap, so the arrays are reallocated, and
the active pages are copied again to the "end" of the amap, and the
slot offset is adjusted to cover the required size.  This also
optimizes for hitting case #1 on the next backwards extension.

This provides the missing piece in the "forward extension of
vm_map_entries" logic, so the merge failure counters have been
removed.

Not many applications will make any use of this at this time (except
for jvms and perhaps gcc3), but a "top-down" memory allocator will use
it extensively.
2002-11-14 17:58:48 +00:00
thorpej ff114c4a59 Fix signed/unsigned comparison warnings. 2002-11-09 20:06:07 +00:00
enami b7ac697dae s/than than/than/. 2002-11-08 02:05:16 +00:00
perry fbf4988104 gah. reversed a test. 2002-11-02 16:50:18 +00:00
perry bbad42171f /*CONTCOND*/ while (0)'ed macros 2002-11-02 07:40:47 +00:00
perry e6873029ee /*CONSTCOND*/ 2002-11-02 07:38:42 +00:00
perry dd07fed86d /*CONTCOND*/, and protect UVMHIST_DECL with #ifdef UVMHIST 2002-11-02 07:37:14 +00:00
yamt 3a7bfaf54e change "uoff" to voff_t from vaddr_t as it's offset within uvm object.
fix PR/18855.
2002-10-30 05:24:33 +00:00
simonb a426ccb272 Fix whitespace bogon. 2002-10-30 02:48:28 +00:00
chs e60ad901b2 examine the B_ERROR flag instead of the b_error field to determine
whether or not an error has occured.  pointed out by Stephan Uphoff.
2002-10-27 16:53:20 +00:00
atatat 68277bb301 In the case of a double amap_extend() (during a forward merge after a
back merge), don't abort the allocation if the second extend fails,
just abort the forward merge and finish the allocation.

Code reviewed by thorpej.
2002-10-24 22:22:28 +00:00