When we are out of memory of a suitable size we enter reclaim.  The current
reclaim algorithm targets pages in LRU order, which is great for fairness at
order-0 but highly unsuitable if you desire pages at higher orders.  To get
pages of higher order we must shoot down a very high proportion of memory;
>95% in a lot of cases.

This patch set adds a lumpy reclaim algorithm to the allocator.  It targets
groups of pages at the specified order anchored at the end of the active and
inactive lists.  This encourages groups of pages at the requested orders to
move from active to inactive, and active to free lists.  This behaviour is
only triggered out of direct reclaim when higher order pages have been
requested.

This patch set is particularly effective when utilised with an
anti-fragmentation scheme which groups pages of similar reclaimability
together.

This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms
the foundation.  Credit to Mel Gorman for sanitity checking.

Mel said:

  The patches have an application with hugepage pool resizing.

  When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can
  be resized with greater reliability.  Testing on a desktop machine with 2GB
  of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own
  was very slow as the success rate was quite low.  Without lumpy-reclaim,
  each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages.
  With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical.

[akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup]
[bunk@stusta.de: static declarations for internal functions]
[a.p.zijlstra@chello.nl: initial lumpy V2 implementation]
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This patch adds a new parameter for sizing ZONE_MOVABLE called
movablecore=.  While kernelcore= is used to specify the minimum amount of
memory that must be available for all allocation types, movablecore= is
used to specify the minimum amount of memory that is used for migratable
allocations.  The amount of memory used for migratable allocations
determines how large the huge page pool could be dynamically resized to at
runtime for example.

How movablecore is actually handled is that the total number of pages in
the system is calculated and a value is set for kernelcore that is

kernelcore == totalpages - movablecore

Both kernelcore= and movablecore= can be safely specified at the same time.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This patch adds the kernelcore= parameter for x86.

Once all patches are applied, a new command-line parameter exist and a new
sysctl.  This patch adds the necessary documentation.

From: Yasunori Goto <y-goto@jp.fujitsu.com>

  When "kernelcore" boot option is specified, kernel can't boot up on ia64
  because of an infinite loop.  In addition, the parsing code can be handled
  in an architecture-independent manner.

  This patch uses common code to handle the kernelcore= parameter.  It is
  only available to architectures that support arch-independent zone-sizing
  (i.e.  define CONFIG_ARCH_POPULATES_NODE_MAP).  Other architectures will
  ignore the boot parameter.

[bunk@stusta.de: make cmdline_parse_kernelcore() static]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Huge pages are not movable so are not allocated from ZONE_MOVABLE.  However,
as ZONE_MOVABLE will always have pages that can be migrated or reclaimed, it
can be used to satisfy hugepage allocations even when the system has been
running a long time.  This allows an administrator to resize the hugepage pool
at runtime depending on the size of ZONE_MOVABLE.

This patch adds a new sysctl called hugepages_treat_as_movable.  When a
non-zero value is written to it, future allocations for the huge page pool
will use ZONE_MOVABLE.  Despite huge pages being non-movable, we do not
introduce additional external fragmentation of note as huge pages are always
the largest contiguous block we care about.

[akpm@linux-foundation.org: various fixes]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

The following 8 patches against 2.6.20-mm2 create a zone called ZONE_MOVABLE
that is only usable by allocations that specify both __GFP_HIGHMEM and
__GFP_MOVABLE.  This has the effect of keeping all non-movable pages within a
single memory partition while allowing movable allocations to be satisfied
from either partition.  The patches may be applied with the list-based
anti-fragmentation patches that groups pages together based on mobility.

The size of the zone is determined by a kernelcore= parameter specified at
boot-time.  This specifies how much memory is usable by non-movable
allocations and the remainder is used for ZONE_MOVABLE.  Any range of pages
within ZONE_MOVABLE can be released by migrating the pages or by reclaiming.

When selecting a zone to take pages from for ZONE_MOVABLE, there are two
things to consider.  First, only memory from the highest populated zone is
used for ZONE_MOVABLE.  On the x86, this is probably going to be ZONE_HIGHMEM
but it would be ZONE_DMA on ppc64 or possibly ZONE_DMA32 on x86_64.  Second,
the amount of memory usable by the kernel will be spread evenly throughout
NUMA nodes where possible.  If the nodes are not of equal size, the amount of
memory usable by the kernel on some nodes may be greater than others.

By default, the zone is not as useful for hugetlb allocations because they are
pinned and non-migratable (currently at least).  A sysctl is provided that
allows huge pages to be allocated from that zone.  This means that the huge
page pool can be resized to the size of ZONE_MOVABLE during the lifetime of
the system assuming that pages are not mlocked.  Despite huge pages being
non-movable, we do not introduce additional external fragmentation of note as
huge pages are always the largest contiguous block we care about.

Credit goes to Andy Whitcroft for catching a large variety of problems during
review of the patches.

This patch creates an additional zone, ZONE_MOVABLE.  This zone is only usable
by allocations which specify both __GFP_HIGHMEM and __GFP_MOVABLE.  Hot-added
memory continues to be placed in their existing destination as there is no
mechanism to redirect them to a specific zone.

[y-goto@jp.fujitsu.com: Fix section mismatch of memory hotplug related code]
[akpm@linux-foundation.org: various fixes]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

It is often known at allocation time whether a page may be migrated or not.
This patch adds a flag called __GFP_MOVABLE and a new mask called
GFP_HIGH_MOVABLE.  Allocations using the __GFP_MOVABLE can be either migrated
using the page migration mechanism or reclaimed by syncing with backing
storage and discarding.

An API function very similar to alloc_zeroed_user_highpage() is added for
__GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable().  The
flags used by alloc_zeroed_user_highpage() are not changed because it would
change the semantics of an existing API.  After this patch is applied there
are no in-kernel users of alloc_zeroed_user_highpage() so it probably should
be marked deprecated if this patch is merged.

Note that this patch includes a minor cleanup to the use of __GFP_ZERO in
shmem.c to keep all flag modifications to inode->mapping in the
shmem_dir_alloc() helper function.  This clean-up suggestion is courtesy of
Hugh Dickens.

Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the
concept.  Credit to Hugh Dickens for catching issues with shmem swap vector
and ramfs allocations.

[akpm@linux-foundation.org: build fix]
[hugh@veritas.com: __GFP_ZERO cleanup]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

do_generic_mapping_read currently samples the i_size at the start and doesn't
do so again unless it needs to call ->readpage to load a page.  After
->readpage it has to re-sample i_size as a truncate may have caused that page
to be filled with zeros, and the read() call should not see these.

However there are other activities that might cause ->readpage to be called on
a page between the time that do_generic_mapping_read samples i_size and when
it finds that it has an uptodate page.  These include at least read-ahead and
possibly another thread performing a read.

So do_generic_mapping_read must sample i_size *after* it has an uptodate page.
 Thus the current sampling at the start and after a read can be replaced with
a sampling before the copy-out.

The same change applied to __generic_file_splice_read.

Note that this fixes any race with truncate_complete_page, but does not fix a
possible race with truncate_partial_page.  If a partial truncate happens after
do_generic_mapping_read samples i_size and before the copy_out, the nuls that
truncate_partial_page place in the page could be copied out incorrectly.

I think the best fix for that is to *not* zero out parts of the page in
truncate_partial_page, but rather to zero out the tail of a page when
increasing i_size.
Signed-off-by: Neil Brown <neilb@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Nobody is using ptep_test_and_clear_dirty and ptep_clear_flush_dirty.  Remove
the functions from all architectures.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

The last user of ptep_establish in mm/ is long gone.  Remove the architecture
primitive as well.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: Yoann Padioleau <padator@wanadoo.fr>
Cc: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

* 'drm-patches' of ssh://master.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  drm: add idr_init to drm_stub.c
  drm: fix problem with SiS typedef with sisfb enabled.

Brown paper bag for me this patch chunk didn't make it in the first application
Signed-off-by: Dave Airlie <airlied@linux.ie>

Reported by: Avuton Olrich <avuton@gmail.com>
Signed-off-by: Dave Airlie <airlied@linux.ie>

* 'drm-patches' of ssh://master.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  drm: convert drawable code to using idr
  drm: convert drm context code to use Linux idr

This converts the code for allocating drawables to the Linux idr,

Fixes from: Michel Dänzer <michel@tungstengraphics.com>, Kristian Høgsberg <krh@redhat.com>
Signed-off-by: Dave Airlie <airlied@linux.ie>

This converts the drm context allocator to an idr, using the new idr
interface features from Kristian.

Fixes from Kristian Hoegsberg <krh@redhat.com>
Signed-off-by: Dave Airlie <airlied@linux.ie>

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: (209 commits)
  [POWERPC] Create add_rtc() function to enable the RTC CMOS driver
  [POWERPC] Add H_ILLAN_ATTRIBUTES hcall number
  [POWERPC] xilinxfb: Parameterize xilinxfb platform device registration
  [POWERPC] Oprofile support for Power 5++
  [POWERPC] Enable arbitary speed tty ioctls and split input/output speed
  [POWERPC] Make drivers/char/hvc_console.c:khvcd() static
  [POWERPC] Remove dead code for preventing pread() and pwrite() calls
  [POWERPC] Remove unnecessary #undef printk from prom.c
  [POWERPC] Fix typo in Ebony default DTS
  [POWERPC] Check for NULL ppc_md.init_IRQ() before calling
  [POWERPC] Remove extra return statement
  [POWERPC] pasemi: Don't auto-select CONFIG_EMBEDDED
  [POWERPC] pasemi: Rename platform
  [POWERPC] arch/powerpc/kernel/sysfs.c: Move NUMA exports
  [POWERPC] Add __read_mostly support for powerpc
  [POWERPC] Modify sched_clock() to make CONFIG_PRINTK_TIME more sane
  [POWERPC] Create a dummy zImage if no valid platform has been selected
  [POWERPC] PS3: Bootwrapper support.
  [POWERPC] powermac i2c: Use mutex
  [POWERPC] Schedule removal of arch/ppc
  ...

Fixed up conflicts manually in:

	Documentation/feature-removal-schedule.txt
	arch/powerpc/kernel/pci_32.c
	arch/powerpc/kernel/pci_64.c
	include/asm-powerpc/pci.h

and asked the powerpc people to double-check the result..

* 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6: (37 commits)
  forcedeth bug fix: realtek phy
  forcedeth bug fix: vitesse phy
  forcedeth bug fix: cicada phy
  atl1: reorder atl1_main functions
  atl1: fix excessively indented code
  atl1: cleanup atl1_main
  atl1: header file cleanup
  atl1: remove irq_sem
  cdc-subset to support new vendor/product ID
  8139cp: implement the missing dev->tx_timeout
  myri10ge: Remove nonsensical limit in the tx done routine
  gianfar: kill unused header
  EP93XX_ETH must select MII
  macb: Add multicast capability
  macb: Use generic PHY layer
  s390: add barriers to qeth driver
  s390: scatter-gather for inbound traffic in qeth driver
  eHEA: Introducing support vor DLPAR memory add
  Fix a potential NULL pointer dereference in free_shared_mem() in drivers/net/s2io.c
  [PATCH] softmac: Fix ESSID problem
  ...

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6:
  [SERIAL] SUNHV: Fix jerky console on LDOM guests.
  [SPARC64]: Fix race between MD update and dr-cpu add.
  [SPARC64]: SMP build fix.

All of the clockevent notifiers expect a pointer to
an "unsigned int" cpu argument, but hrtimer_cpu_notify()
passes in a pointer to a long.

[ Discussed with and ok by Thomas Gleixner ]
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Mixing putchar() and write() hvcalls does not work %100
correctly.  But we should be using write() all the time
if we can, even from ->start_tx(), anyways.
Signed-off-by: David S. Miller <davem@davemloft.net>

We need to make sure the MD update occurs before we try to
process dr-cpu configure requests.  MD update and dr-cpu
were being processed by seperate threads so that did not
happen occaisionally.

Fix this by executing all domain services data packets from
a single thread, in order.

This will help simplify some other things as well.
Signed-off-by: David S. Miller <davem@davemloft.net>

The UP build fix had some unintended consequences.
Signed-off-by: David S. Miller <davem@davemloft.net>

The SCSI code can be compiled modular, but BLK_DEV_BSG currently cannot,
and depends on the SCSI layer.  So make sure that it depends on the SCSI
layer being compiled in, not just available as a module.

Noticed by Jeff Garzik and S.Çağlar Onur.

Cc: Jeff Garzik <jeff@garzik.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: S.Çağlar Onur <caglar@pardus.org.tr>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This should avoid build problems on architectures without a "readb()",
that got bitten by check_signature() being uninlined.

Noted by Heiko Carstens.

Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

This patch contains errata fixes for the realtek phy.
Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

This patch contains errata fixes for the vitesse phy.
Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

This patch contains errata fixes for the cicada phy. It only renamed the
defines to be phy specific.
Signed-off-by: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Reorder functions in atl1_main into more logical groupings to make the
code easier to follow. This patch is large, but it's harmless; it neither
adds nor removes any functionality whatsoever.
Signed-off-by: Jay Cliburn <jacliburn@bellsouth.net>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Move excessively indented code to separate functions.  Also move ring
pointer initialization to its own function.
Signed-off-by: Jay Cliburn <jacliburn@bellsouth.net>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Fix indentation, remove dead code, improve some comments, change dev_dbg to
dev_printk.
Signed-off-by: Jay Cliburn <jacliburn@bellsouth.net>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Remove unused structure members, improve comments, break long comment lines,
rename a constant to be consistent with others in the file.
Signed-off-by: Jay Cliburn <jacliburn@bellsouth.net>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Remove unnecessary irq_sem code.
Signed-off-by: Chris Snook <csnook@redhat.com>
Signed-off-by: Jay Cliburn <jacliburn@bellsouth.net>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

This patch is for cdc subset to support Mavell vendor/product ID.
Signed-off-by: Jing Xiang <everxiang@gmail.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Signed-off-by: Mika Lansirinne <mika.lansirinne@stonesoft.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Remove nonsensical limit in the tx done routine. Specifically,
the loop will always terminate after processing <= 1 rings worth
of frames, as the mcp index is not refetched, so the removed
conditional could never be true.
Signed-off-by: Brice Goglin <brice@myri.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

A long time ago we used OCP with the gianfar driver.  Eventually when
we kill arch/ppc including this will cause issues so lets just kill it now.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

CONFIG_EP93XX_ETH=y, CONFIG_MII=n results in an obvious link error.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Add multicast capability to Atmel ethernet macb driver.
Signed-off-by: Patrice Vilchez <patrice.vilchez@rfo.atmel.com>
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

Convert the macb driver to use the generic PHY layer in
drivers/net/phy.
Signed-off-by: Frederic RODO <f.rodo@til-technologies.fr>
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>