No need to duplicate all that code.

Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

msync() does a strange thing.  Essentially:

	vma = find_vma();
	for ( ; ; ) {
		if (!vma)
			return -ENOMEM;
		...
		vma = vma->vm_next;
	}

so an msync() request which starts within or before a valid VMA and which ends
within or beyond the final VMA will incorrectly return -ENOMEM.

Fix.

Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

It seems bad to hold mmap_sem while performing synchronous disk I/O.  Alter
the msync(MS_SYNC) code so that the lock is released while we sync the file.

Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

It seems sensible to perform dirty page throttling in msync: as the application
dirties pages we can kick off pdflush early, or even force the msync() caller
to perform writeout, or even throttle the msync() caller.

The main effect of this is to start disk writeback earlier if we've just
discovered that a large amount of pagecache has been dirtied.  (Otherwise it
wouldn't happen for up to five seconds, next time pdflush wakes up).

It also will cause the page-dirtying process to get panalised for dirtying
those pages rather than whacking someone else with the problem.

We should do this for munmap() and possibly even exit(), too.

We drop the mmap_sem while performing the dirty page balancing.  It doesn't
seem right to hold mmap_sem for that long.

Note that this patch only affects MS_ASYNC.  MS_SYNC will be syncing all the
dirty pages anyway.

We note that msync(MS_SYNC) does a full-file-sync inside mmap_sem, and always
has.  We can fix that up...

The patch also tightens up the mmap_sem coverage in sys_msync(): no point in
taking it while we perform the incoming arg checking.

Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

We need set_page_dirty() to return true if it actually transitioned the page
from a clean to dirty state.  This wasn't right in a couple of places.  Do a
kernel-wide audit, fix things up.

This leaves open the possibility of returning a negative errno from
set_page_dirty() sometime in the future.  But we don't do that at present.
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Modify balance_dirty_pages_ratelimited() so that it can take a
number-of-pages-which-I-just-dirtied argument.  For msync().
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Add two new linux-specific fadvise extensions():

LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file
offsets `offset' and `offset+len'.  Any pages which are currently under
writeout are skipped, whether or not they are dirty.

LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file
offsets `offset' and `offset+len'.

By combining these two operations the application may do several things:

LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk.

LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty
pages at the disk.

LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all
of the currently dirty pages at the disk, wait until they have been written.

It should be noted that none of these operations write out the file's
metadata.  So unless the application is strictly performing overwrites of
already-instantiated disk blocks, there are no guarantees here that the data
will be available after a crash.

To complete this suite of operations I guess we should have a "sync file
metadata only" operation.  This gives applications access to all the building
blocks needed for all sorts of sync operations.  But sync-metadata doesn't fit
well with the fadvise() interface.  Probably it should be a new syscall:
sys_fmetadatasync().

The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64().
It is made to represent that last affected byte in the file (ie: it is
inclusive).  Generally, all these byterange and pagerange functions are
inclusive so we can easily represent EOF with -1.

As Ulrich notes, these two functions are somewhat abusive of the fadvise()
concept, which appears to be "set the future policy for this fd".

But these commands are a perfect fit with the fadvise() impementation, and
several of the existing fadvise() commands are synchronous and don't affect
future policy either.   I think we can live with the slight incongruity.

Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

I had trouble understanding working out whether filemap_fdatawrite_range()'s
`end' parameter describes the last-byte-to-be-written or the last-plus-one.
Clarify that in comments.
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The hook in the slab cache allocation path to handle cpuset memory
spreading for tasks in cpusets with 'memory_spread_slab' enabled has a
modest performance bug.  The hook calls into the memory spreading handler
alternate_node_alloc() if either of 'memory_spread_slab' or
'memory_spread_page' is enabled, even though the handler does nothing
(albeit harmlessly) for the page case

Fix - drop PF_SPREAD_PAGE from the set of flag bits that are used to
trigger a call to alternate_node_alloc().

The page case is handled by separate hooks -- see the calls conditioned on
cpuset_do_page_mem_spread() in mm/filemap.c
Signed-off-by: NPaul Jackson <pj@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The hooks in the slab cache allocator code path for support of NUMA
mempolicies and cpuset memory spreading are in an important code path.  Many
systems will use neither feature.

This patch optimizes those hooks down to a single check of some bits in the
current tasks task_struct flags.  For non NUMA systems, this hook and related
code is already ifdef'd out.

The optimization is done by using another task flag, set if the task is using
a non-default NUMA mempolicy.  Taking this flag bit along with the
PF_SPREAD_PAGE and PF_SPREAD_SLAB flag bits added earlier in this 'cpuset
memory spreading' patch set, one can check for the combination of any of these
special case memory placement mechanisms with a single test of the current
tasks task_struct flags.

This patch also tightens up the code, to save a few bytes of kernel text
space, and moves some of it out of line.  Due to the nested inlines called
from multiple places, we were ending up with three copies of this code, which
once we get off the main code path (for local node allocation) seems a bit
wasteful of instruction memory.
Signed-off-by: NPaul Jackson <pj@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Provide the slab cache infrastructure to support cpuset memory spreading.

See the previous patches, cpuset_mem_spread, for an explanation of cpuset
memory spreading.

This patch provides a slab cache SLAB_MEM_SPREAD flag.  If set in the
kmem_cache_create() call defining a slab cache, then any task marked with the
process state flag PF_MEMSPREAD will spread memory page allocations for that
cache over all the allowed nodes, instead of preferring the local (faulting)
node.

On systems not configured with CONFIG_NUMA, this results in no change to the
page allocation code path for slab caches.

On systems with cpusets configured in the kernel, but the "memory_spread"
cpuset option not enabled for the current tasks cpuset, this adds a call to a
cpuset routine and failed bit test of the processor state flag PF_SPREAD_SLAB.

For tasks so marked, a second inline test is done for the slab cache flag
SLAB_MEM_SPREAD, and if that is set and if the allocation is not
in_interrupt(), this adds a call to to a cpuset routine that computes which of
the tasks mems_allowed nodes should be preferred for this allocation.

==> This patch adds another hook into the performance critical
    code path to allocating objects from the slab cache, in the
    ____cache_alloc() chunk, below.  The next patch optimizes this
    hook, reducing the impact of the combined mempolicy plus memory
    spreading hooks on this critical code path to a single check
    against the tasks task_struct flags word.

This patch provides the generic slab flags and logic needed to apply memory
spreading to a particular slab.

A subsequent patch will mark a few specific slab caches for this placement
policy.
Signed-off-by: NPaul Jackson <pj@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Change the page cache allocation calls to support cpuset memory spreading.

See the previous patch, cpuset_mem_spread, for an explanation of cpuset memory
spreading.

On systems without cpusets configured in the kernel, this is no change.

On systems with cpusets configured in the kernel, but the "memory_spread"
cpuset option not enabled for the current tasks cpuset, this adds a call to a
cpuset routine and failed bit test of the processor state flag PF_SPREAD_PAGE.

On tasks in cpusets with "memory_spread" enabled, this adds a call to a cpuset
routine that computes which of the tasks mems_allowed nodes should be
preferred for this allocation.

If memory spreading applies to a particular allocation, then any other NUMA
mempolicy does not apply.
Signed-off-by: NPaul Jackson <pj@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

If we get under some memory pressure in a cpuset (we only scan zones that
are in the cpuset for memory) then kswapd is woken up for all zones.  This
patch only wakes up kswapd in zones that are part of the current cpuset.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Acked-by: NPaul Jackson <pj@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Make that the internal value for /proc/sys/vm/laptop_mode is stored as
jiffies instead of seconds.  Let the sysctl interface do the conversions,
instead of doing on-the-fly conversions every time the value is used.

Add a description of the fact that laptop_mode doubles as a flag and a
timeout to the comment above the laptop_mode variable.
Signed-off-by: NBart Samwel <bart@samwel.tk>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Make that the internal values for:

/proc/sys/vm/dirty_writeback_centisecs
/proc/sys/vm/dirty_expire_centisecs

are stored as jiffies instead of centiseconds.  Let the sysctl interface do
the conversions with full precision using clock_t_to_jiffies, instead of
doing overflow-sensitive on-the-fly conversions every time the values are
used.

Cons: apparent precision loss if HZ is not a multiple of 100, because of
conversion back and forth.  This is a common problem for all sysctl values
that use proc_dointvec_userhz_jiffies.  (There is only one other in-tree
use, in net/core/neighbour.c.)
Signed-off-by: NBart Samwel <bart@samwel.tk>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Signed-off-by: NJens Axboe <axboe@suse.de>

Linus points out that ext3_readdir's readahead only cuts in when
ext3_readdir() is operating at the very start of the directory.  So for large
directories we end up performing no readahead at all and we suck.

So take it all out and use the core VM's page_cache_readahead().  This means
that ext3 directory reads will use all of readahead's dynamic sizing goop.

Note that we're using the directory's filp->f_ra to hold the readahead state,
but readahead is actually being performed against the underlying blockdev's
address_space.  Fortunately the readahead code is all set up to handle this.

Tested with printk.  It works.  I was struggling to find a real workload which
actually cared.

(The patch also exports page_cache_readahead() to GPL modules)

Cc: "Stephen C. Tweedie" <sct@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch introduces a user space interface for swsusp.

The interface is based on a special character device, called the snapshot
device, that allows user space processes to perform suspend and resume-related
operations with the help of some ioctls and the read()/write() functions.
 Additionally it allows these processes to allocate free swap pages from a
selected swap partition, called the resume partition, so that they know which
sectors of the resume partition are available to them.

The interface uses the same low-level system memory snapshot-handling
functions that are used by the built-it swap-writing/reading code of swsusp.

The interface documentation is included in the patch.

The patch assumes that the major and minor numbers of the snapshot device will
be 10 (ie.  misc device) and 231, the registration of which has already been
requested.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Introduce the low level interface that can be used for handling the
snapshot of the system memory by the in-kernel swap-writing/reading code of
swsusp and the userland interface code (to be introduced shortly).

Also change the way in which swsusp records the allocated swap pages and,
consequently, simplifies the in-kernel swap-writing/reading code (this is
necessary for the userland interface too).  To this end, it introduces two
helper functions in mm/swapfile.c, so that the swsusp code does not refer
directly to the swap internals.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Centralize the page migration functions in anticipation of additional
tinkering.  Creates a new file mm/migrate.c

1. Extract buffer_migrate_page() from fs/buffer.c

2. Extract central migration code from vmscan.c

3. Extract some components from mempolicy.c

4. Export pageout() and remove_from_swap() from vmscan.c

5. Make it possible to configure NUMA systems without page migration
   and non-NUMA systems with page migration.

I had to so some #ifdeffing in mempolicy.c that may need a cleanup.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The alien cache rotor in mm/slab.c assumes that the first online node is
node 0.  Eventually for some archs, especially with hotplug, this will no
longer be true.

Fix the interleave rotor to handle the general case of node numbering.
Signed-off-by: NPaul Jackson <pj@sgi.com>
Acked-by: NChristoph Lameter <clameter@engr.sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Fix bogus node loop in hugetlb.c alloc_fresh_huge_page(), which was
assuming that nodes are numbered contiguously from 0 to num_online_nodes().
Once the hotplug folks get this far, that will be false.
Signed-off-by: NPaul Jackson <pj@sgi.com>
Acked-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

When we've allocated SWAPFILE_CLUSTER pages, ->cluster_next should be the
first index of swap cluster.  But current code probably sets it wrong offset.
Signed-off-by: NAkinobu Mita <mita@miraclelinux.com>
Acked-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

1. Only disable interrupts if there is actually something to free

2. Only dirty the pcp cacheline if we actually freed something.

3. Disable interrupts for each single pcp and not for cleaning
  all the pcps in all zones of a node.

drain_node_pages is called every 2 seconds from cache_reap. This
fix should avoid most disabling of interrupts.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The list_lock also protects the shared array and we call drain_array() with
the shared array.  Therefore we cannot go as far as I wanted to but have to
take the lock in a way so that it also protects the array_cache in
drain_pages.

(Note: maybe we should make the array_cache locking more consistent?  I.e.
always take the array cache lock for shared arrays and disable interrupts
for the per cpu arrays?)
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Remove drain_array_locked and use that opportunity to limit the time the l3
lock is taken further.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

And a parameter to drain_array to control the freeing of all objects and
then use drain_array() to replace instances of drain_array_locked with
drain_array.  Doing so will avoid taking locks in those locations if the
arrays are empty.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

cache_reap takes the l3->list_lock (disabling interrupts) unconditionally
and then does a few checks and maybe does some cleanup.  This patch makes
cache_reap() only take the lock if there is work to do and then the lock is
taken and released for each cleaning action.

The checking of when to do the next reaping is done without any locking and
becomes racy.  Should not matter since reaping can also be skipped if the
slab mutex cannot be acquired.

The same is true for the touched processing.  If we get this wrong once in
awhile then we will mistakenly clean or not clean the shared cache.  This
will impact performance slightly.

Note that the additional drain_array() function introduced here will fall
out in a subsequent patch since array cleaning will now be very similar
from all callers.
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Make shrink_all_memory() repeat the attempts to free more memory if there
seems to be no pages to free.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

follow_hugetlb_page() walks a range of user virtual address and then fills
in list of struct page * into an array that is passed from the argument
list.  It also gets a reference count via get_page().  For compound page,
get_page() actually traverse back to head page via page_private() macro and
then adds a reference count to the head page.  Since we are doing a virt to
pte look up, kernel already has a struct page pointer into the head page.
So instead of traverse into the small unit page struct and then follow a
link back to the head page, optimize that with incrementing the reference
count directly on the head page.

The benefit is that we don't take a cache miss on accessing page struct for
the corresponding user address and more importantly, not to pollute the
cache with a "not very useful" round trip of pointer chasing.  This adds a
moderate performance gain on an I/O intensive database transaction
workload.
Signed-off-by: NKen Chen <kenneth.w.chen@intel.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Turns out the hugepage logic in free_pgtables() was doubly broken.  The
loop coalescing multiple normal page VMAs into one call to free_pgd_range()
had an off by one error, which could mean it would coalesce one hugepage
VMA into the same bundle (checking 'vma' not 'next' in the loop).  I
transferred this bug into the new is_vm_hugetlb_page() based version.
Here's the fix.

This one didn't bite on powerpc previously for the same reason the
is_hugepage_only_range() problem didn't: powerpc's hugetlb_free_pgd_range()
is identical to free_pgd_range().  It didn't bite on ia64 because the
hugepage region is distant enough from any other region that the separated
PMD_SIZE distance test would always prevent coalescing the two together.

No libhugetlbfs testsuite regressions (ppc64, POWER5).
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

free_pgtables() has special logic to call hugetlb_free_pgd_range() instead
of the normal free_pgd_range() on hugepage VMAs.  However, the test it uses
to do so is incorrect: it calls is_hugepage_only_range on a hugepage sized
range at the start of the vma.  is_hugepage_only_range() will return true
if the given range has any intersection with a hugepage address region, and
in this case the given region need not be hugepage aligned.  So, for
example, this test can return true if called on, say, a 4k VMA immediately
preceding a (nicely aligned) hugepage VMA.

At present we get away with this because the powerpc version of
hugetlb_free_pgd_range() is just a call to free_pgd_range().  On ia64 (the
only other arch with a non-trivial is_hugepage_only_range()) we get away
with it for a different reason; the hugepage area is not contiguous with
the rest of the user address space, and VMAs are not permitted in between,
so the test can't return a false positive there.

Nonetheless this should be fixed.  We do that in the patch below by
replacing the is_hugepage_only_range() test with an explicit test of the
VMA using is_vm_hugetlb_page().

This in turn changes behaviour for platforms where is_hugepage_only_range()
returns false always (everything except powerpc and ia64).  We address this
by ensuring that hugetlb_free_pgd_range() is defined to be identical to
free_pgd_range() (instead of a no-op) on everything except ia64.  Even so,
it will prevent some otherwise possible coalescing of calls down to
free_pgd_range().  Since this only happens for hugepage VMAs, removing this
small optimization seems unlikely to cause any trouble.

This patch causes no regressions on the libhugetlbfs testsuite - ppc64
POWER5 (8-way), ppc64 G5 (2-way) and i386 Pentium M (UP).
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Acked-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Originally, mm/hugetlb.c just handled the hugepage physical allocation path
and its {alloc,free}_huge_page() functions were used from the arch specific
hugepage code.  These days those functions are only used with mm/hugetlb.c
itself.  Therefore, this patch makes them static and removes their
prototypes from hugetlb.h.  This requires a small rearrangement of code in
mm/hugetlb.c to avoid a forward declaration.

This patch causes no regressions on the libhugetlbfs testsuite (ppc64,
POWER5).
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

These days, hugepages are demand-allocated at first fault time.  There's a
somewhat dubious (and racy) heuristic when making a new mmap() to check if
there are enough available hugepages to fully satisfy that mapping.

A particularly obvious case where the heuristic breaks down is where a
process maps its hugepages not as a single chunk, but as a bunch of
individually mmap()ed (or shmat()ed) blocks without touching and
instantiating the pages in between allocations.  In this case the size of
each block is compared against the total number of available hugepages.
It's thus easy for the process to become overcommitted, because each block
mapping will succeed, although the total number of hugepages required by
all blocks exceeds the number available.  In particular, this defeats such
a program which will detect a mapping failure and adjust its hugepage usage
downward accordingly.

The patch below addresses this problem, by strictly reserving a number of
physical hugepages for hugepage inodes which have been mapped, but not
instatiated.  MAP_SHARED mappings are thus "safe" - they will fail on
mmap(), not later with an OOM SIGKILL.  MAP_PRIVATE mappings can still
trigger an OOM.  (Actually SHARED mappings can technically still OOM, but
only if the sysadmin explicitly reduces the hugepage pool between mapping
and instantiation)

This patch appears to address the problem at hand - it allows DB2 to start
correctly, for instance, which previously suffered the failure described
above.

This patch causes no regressions on the libhugetblfs testsuite, and makes a
test (designed to catch this problem) pass which previously failed (ppc64,
POWER5).
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Currently, no lock or mutex is held between allocating a hugepage and
inserting it into the pagetables / page cache.  When we do go to insert the
page into pagetables or page cache, we recheck and may free the newly
allocated hugepage.  However, since the number of hugepages in the system
is strictly limited, and it's usualy to want to use all of them, this can
still lead to spurious allocation failures.

For example, suppose two processes are both mapping (MAP_SHARED) the same
hugepage file, large enough to consume the entire available hugepage pool.
If they race instantiating the last page in the mapping, they will both
attempt to allocate the last available hugepage.  One will fail, of course,
returning OOM from the fault and thus causing the process to be killed,
despite the fact that the entire mapping can, in fact, be instantiated.

The patch fixes this race by the simple method of adding a (sleeping) mutex
to serialize the hugepage fault path between allocation and insertion into
pagetables and/or page cache.  It would be possible to avoid the
serialization by catching the allocation failures, waiting on some
condition, then rechecking to see if someone else has instantiated the page
for us.  Given the likely frequency of hugepage instantiations, it seems
very doubtful it's worth the extra complexity.

This patch causes no regression on the libhugetlbfs testsuite, and one
test, which can trigger this race now passes where it previously failed.

Actually, the test still sometimes fails, though less often and only as a
shmat() failure, rather processes getting OOM killed by the VM.  The dodgy
heuristic tests in fs/hugetlbfs/inode.c for whether there's enough hugepage
space aren't protected by the new mutex, and would be ugly to do so, so
there's still a race there.  Another patch to replace those tests with
something saner for this reason as well as others coming...
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Move the loops used in mm/hugetlb.c to clear and copy hugepages to their
own functions for clarity.  As we do so, we add some checks of need_resched
- we are, after all copying megabytes of memory here.  We also add
might_sleep() accordingly.  We generally dropped locks around the clear and
copy, already but not everyone has PREEMPT enabled, so we should still be
checking explicitly.

For this to work, we need to remove the clear_huge_page() from
alloc_huge_page(), which is called with the page_table_lock held in the COW
path.  We move the clear_huge_page() to just after the alloc_huge_page() in
the hugepage no-page path.  In the COW path, the new page is about to be
copied over, so clearing it was just a waste of time anyway.  So as a side
effect we also fix the fact that we held the page_table_lock for far too
long in this path by calling alloc_huge_page() under it.

It causes no regressions on the libhugetlbfs testsuite (ppc64, POWER5).
Signed-off-by: NDavid Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

2.6.16-rc3 uses hugetlb on-demand paging, but it doesn_t support hugetlb
mprotect.

From: David Gibson <david@gibson.dropbear.id.au>

  Remove a test from the mprotect() path which checks that the mprotect()ed
  range on a hugepage VMA is hugepage aligned (yes, really, the sense of
  is_aligned_hugepage_range() is the opposite of what you'd guess :-/).

  In fact, we don't need this test.  If the given addresses match the
  beginning/end of a hugepage VMA they must already be suitably aligned.  If
  they don't, then mprotect_fixup() will attempt to split the VMA.  The very
  first test in split_vma() will check for a badly aligned address on a
  hugepage VMA and return -EINVAL if necessary.

From: "Chen, Kenneth W" <kenneth.w.chen@intel.com>

  On i386 and x86-64, pte flag _PAGE_PSE collides with _PAGE_PROTNONE.  The
  identify of hugetlb pte is lost when changing page protection via mprotect.
  A page fault occurs later will trigger a bug check in huge_pte_alloc().

  The fix is to always make new pte a hugetlb pte and also to clean up
  legacy code where _PAGE_PRESENT is forced on in the pre-faulting day.
Signed-off-by: NZhang Yanmin <yanmin.zhang@intel.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: NKen Chen <kenneth.w.chen@intel.com>
Signed-off-by: NNishanth Aravamudan <nacc@us.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The current current get_init_ra_size is not optimal across different IO
sizes and max_readahead values.  Here is a quick summary of sizes computed
under current design and under the attached patch.  All of these assume 1st
IO at offset 0, or 1st detected sequential IO.

	32k max, 4k request

	old         new
	-----------------
	 8k        8k
	16k       16k
	32k       32k

	128k max, 4k request
	old         new
	-----------------
	32k         16k
	64k         32k
	128k        64k
	128k       128k

	128k max, 32k request
	old         new
	-----------------
	32k         64k    <-----
	64k        128k
	128k       128k

	512k max, 4k request
	old         new
	-----------------
	4k         32k     <----
	16k        64k
	64k       128k
	128k      256k
	512k      512k

Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Steven Pratt <slpratt@austin.ibm.com>
Cc: Ram Pai <linuxram@us.ibm.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

If get_next_ra_size() does not grow fast enough, ->prev_page can overrun
the ahead window.  This means the caller will read the pages from
->ahead_start + ->ahead_size to ->prev_page synchronously.
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>
Cc: Steven Pratt <slpratt@austin.ibm.com>
Cc: Ram Pai <linuxram@us.ibm.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

shmem.c was named and shamed in Jesper's "Building 100 kernels" warnings:
shmem_parse_mpol is only used when CONFIG_TMPFS parses mount options; and
only called from that one site, so mark it inline like its non-NUMA stub.
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>