Include page migration if the system is NUMA or having a memory model that
allows distinct areas of memory (SPARSEMEM, DISCONTIGMEM).
And:
- Only include lru_add_drain_per_cpu if building for an SMP system.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This adds the basic page migration function with a minimal implementation that
only allows the eviction of pages to swap space.
Page eviction and migration may be useful to migrate pages, to suspend
programs or for remapping single pages (useful for faulty pages or pages with
soft ECC failures)
The process is as follows:
The function wanting to migrate pages must first build a list of pages to be
migrated or evicted and take them off the lru lists via isolate_lru_page().
isolate_lru_page determines that a page is freeable based on the LRU bit set.
Then the actual migration or swapout can happen by calling migrate_pages().
migrate_pages does its best to migrate or swapout the pages and does multiple
passes over the list. Some pages may only be swappable if they are not dirty.
migrate_pages may start writing out dirty pages in the initial passes over
the pages. However, migrate_pages may not be able to migrate or evict all
pages for a variety of reasons.
The remaining pages may be returned to the LRU lists using putback_lru_pages().
Changelog V4->V5:
- Use the lru caches to return pages to the LRU
Changelog V3->V4:
- Restructure code so that applying patches to support full migration does
require minimal changes. Rename swapout_pages() to migrate_pages().
Changelog V2->V3:
- Extract common code from shrink_list() and swapout_pages()
Signed-off-by: Mike Kravetz <kravetz@us.ibm.com>
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: "Michael Kerrisk" <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add PF_SWAPWRITE to control a processes permission to write to swap.
- Use PF_SWAPWRITE in may_write_to_queue() instead of checking for kswapd
and pdflush
- Set PF_SWAPWRITE flag for kswapd and pdflush
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This is the start of the `swap migration' patch series.
Swap migration allows the moving of the physical location of pages between
nodes in a numa system while the process is running. This means that the
virtual addresses that the process sees do not change. However, the system
rearranges the physical location of those pages.
The main intent of page migration patches here is to reduce the latency of
memory access by moving pages near to the processor where the process
accessing that memory is running.
The patchset allows a process to manually relocate the node on which its
pages are located through the MF_MOVE and MF_MOVE_ALL options while
setting a new memory policy.
The pages of process can also be relocated from another process using the
sys_migrate_pages() function call. Requires CAP_SYS_ADMIN. The migrate_pages
function call takes two sets of nodes and moves pages of a process that are
located on the from nodes to the destination nodes.
Manual migration is very useful if for example the scheduler has relocated a
process to a processor on a distant node. A batch scheduler or an
administrator can detect the situation and move the pages of the process
nearer to the new processor.
sys_migrate_pages() could be used on non-numa machines as well, to force all
of a particualr process's pages out to swap, if someone thinks that's useful.
Larger installations usually partition the system using cpusets into sections
of nodes. Paul has equipped cpusets with the ability to move pages when a
task is moved to another cpuset. This allows automatic control over locality
of a process. If a task is moved to a new cpuset then also all its pages are
moved with it so that the performance of the process does not sink
dramatically (as is the case today).
Swap migration works by simply evicting the page. The pages must be faulted
back in. The pages are then typically reallocated by the system near the node
where the process is executing.
For swap migration the destination of the move is controlled by the allocation
policy. Cpusets set the allocation policy before calling sys_migrate_pages()
in order to move the pages as intended.
No allocation policy changes are performed for sys_migrate_pages(). This
means that the pages may not faulted in to the specified nodes if no
allocation policy was set by other means. The pages will just end up near the
node where the fault occurred.
There's another patch series in the pipeline which implements "direct
migration".
The direct migration patchset extends the migration functionality to avoid
going through swap. The destination node of the relation is controllable
during the actual moving of pages. The crutch of using the allocation policy
to relocate is not necessary and the pages are moved directly to the target.
Its also faster since swap is not used.
And sys_migrate_pages() can then move pages directly to the specified node.
Implement functions to isolate pages from the LRU and put them back later.
This patch:
An earlier implementation was provided by Hirokazu Takahashi
<taka@valinux.co.jp> and IWAMOTO Toshihiro <iwamoto@valinux.co.jp> for the
memory hotplug project.
From: Magnus
This breaks out isolate_lru_page() and putpack_lru_page(). Needed for swap
migration.
Signed-off-by: Magnus Damm <magnus.damm@gmail.com>
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
swap migration's isolate_lru_page() currently uses an IPI to notify other
processors that the lru caches need to be drained if the page cannot be
found on the LRU. The IPI interrupt may interrupt a processor that is just
processing lru requests and cause a race condition.
This patch introduces a new function run_on_each_cpu() that uses the
keventd() to run the LRU draining on each processor. Processors disable
preemption when dealing the LRU caches (these are per processor) and thus
executing LRU draining from another process is safe.
Thanks to Lee Schermerhorn <lee.schermerhorn@hp.com> for finding this race
condition.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Try to streamline free_pages_bulk by ensuring callers don't pass in a
'count' that exceeds the list size.
Some cleanups:
Rename __free_pages_bulk to __free_one_page.
Put the page list manipulation from __free_pages_ok into free_one_page.
Make __free_pages_ok static.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Use zone_pcp everywhere even though NUMA code "knows" the internal details
of the zone. Stop other people trying to copy, and it looks nicer.
Also, only print the pagesets of online cpus in zoneinfo.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: "Seth, Rohit" <rohit.seth@intel.com>
Cc: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
As recently there has been lot of traffic on the right values for batch and
high water marks for per_cpu_pagelists. This patch makes these two
variables configurable through /proc interface.
A new tunable /proc/sys/vm/percpu_pagelist_fraction is added. This entry
controls the fraction of pages at most in each zone that are allocated for
each per cpu page list. The min value for this is 8. It means that we
don't allow more than 1/8th of pages in each zone to be allocated in any
single per_cpu_pagelist.
The batch value of each per cpu pagelist is also updated as a result. It
is set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8)
Signed-off-by: Rohit Seth <rohit.seth@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add /proc/sys/vm/drop_caches. When written to, this will cause the kernel to
discard as much pagecache and/or reclaimable slab objects as it can. THis
operation requires root permissions.
It won't drop dirty data, so the user should run `sync' first.
Caveats:
a) Holds inode_lock for exorbitant amounts of time.
b) Needs to be taught about NUMA nodes: propagate these all the way through
so the discarding can be controlled on a per-node basis.
This is a debugging feature: useful for getting consistent results between
filesystem benchmarks. We could possibly put it under a config option, but
it's less than 300 bytes.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
For some reason there is an #ifdef CONFIG_NUMA within another #ifdef
CONFIG_NUMA in the page allocator. Remove innermost #ifdef CONFIG_NUMA
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The slab allocator code is inconsistent in coding style and messy. For this
patch, I ran Lindent for mm/slab.c and fixed up goofs by hand.
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch moves the ugly loop that determines the 'optimal' size (page order)
of cache slabs from kmem_cache_create() to a separate function and cleans it
up a bit.
Thanks to Matthew Wilcox for the help with this patch.
Signed-off-by: Matthew Dobson <colpatch@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch extracts slabinfo header printing to a separate function
print_slabinfo_header() to make s_start() more readable.
Signed-off-by: Matthew Dobson <colpatch@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
__alloc_percpu and alloc_percpu both take an 'align' argument which is
completely ignored. snmp6_mib_init() in net/ipv6/af_inet6.c attempts to use
it, but it will be ignored. Therefore, remove the 'align' argument and fixup
the lone caller.
Signed-off-by: Matthew Dobson <colpatch@us.ibm.com>
Acked-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Fix compilation with CONFIG_MEMORY_HOTPLUG=y and gcc41.
Also remove unneeded declations, add a public function.
drivers/base/memory.c:53: error: static declaration of 'register_memory_notifier' follows non-static declaration
include/linux/memory.h:85: error: previous declaration of 'register_memory_notifier' was here
drivers/base/memory.c:58: error: static declaration of 'unregister_memory_notifier' follows non-static declaration
include/linux/memory.h:86: error: previous declaration of 'unregister_memory_notifier' was here
drivers/base/memory.c:68: error: static declaration of 'register_memory' follows non-static declaration
include/linux/memory.h:73: error: previous declaration of 'register_memory' was here
Signed-off-by: Olaf Hering <olh@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Cleanup for the ARM-only watchdog driver wdt977.
This is probably the last update, since we want to merge with w83977f_wdt.
Jose Goncalves has ported this driver to i386, so probably we can iron out
configuration differences.
Signed-off-by: Woody Suwalski <woodys@xandros.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Hugh says:
page_alloc_cpu_notify() specifically contains code to
/* Add dead cpu's page_states to our own. */
which handles this more efficiently.
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Oops, forgot to compile the VMALLOCBASE/VMALLOC_START patch on
iSeries. VMALLOC_START is defined in pgtable.h whereas previously
VMALLOCBASE was previously defined in page.h. lparmap.c needs to be
updated appropriately.
Booted on iSeries RS64 (now).
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch adds oprofile support for the 7450 and all its multitudinous
derivatives.
* Added 7450 (and derivatives) support for oprofile
* Changed e500 cputable to have oprofile model and cpu_type fields
* Added support for classic 32-bit performance monitor interrupt
* Cleaned up common powerpc oprofile code to be as common as possible
* Cleaned up oprofile_impl.h to reflect 32 bit classic code
* Added 32-bit MMCRx bitfield definitions and SPR numbers
Signed-off-by: Andy Fleming <afleming@freescale.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
pci_address_to_pio is missing a closing curly brace
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This fixes pci_address_to_pio() to return an unsigned long (to be safe)
and fixes a bug in the implementation that caused it to return a bogus
IO port number
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
On ppc64, we independently define VMALLOCBASE and VMALLOC_START to be
the same thing: the start of the vmalloc() area at 0xd000000000000000.
VMALLOC_START is used much more widely, including in generic code, so
this patch gets rid of the extraneous VMALLOCBASE.
This does require moving the definitions of region IDs from page_64.h
to pgtable.h, but they don't clearly belong in the former rather than
the latter, anyway. While we're moving them, clean up the definitions
of the REGION_IDs:
- Abolish REGION_SIZE, it was only used once, to define
REGION_MASK anyway
- Define the specific region ids in terms of the REGION_ID()
macro.
- Define KERNEL_REGION_ID in terms of PAGE_OFFSET rather than
KERNELBASE. It amounts to the same thing, but conceptually this is
about the region of the linear mapping (which starts at PAGE_OFFSET)
rather than of the kernel text itself (which is at KERNELBASE).
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The patch enabling the new G5's with U4 broke initialization of the DART
driver, causing it to trigger a BUG_ON for a case that is actually
valid. This patch fixes it:
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds some very basic support for the new machines, including the
Quad G5 (tested), and other new dual core based machines and iMac G5
iSight (untested). This is still experimental ! There is no thermal
control yet, there is no proper handing of MSIs, etc.. but it
boots, I have all 4 cores up on my machine. Compared to the previous
version of this patch, this one adds DART IOMMU support for the U4
chipset and thus should work fine on setups with more than 2Gb of RAM.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Added the ability to determine if an outbound window in the PCI host
controller is for prefetchable memory and report it as such.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
There is code in the RPAPHP directory that is identical to this routine;
I'll be removing that code in an upcoming patch, but this patch is needed
to expose the function to make it callable.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Cleanup the MPIC IO-APIC workarounds, make them a bit more generic,
smaller and faster.
Signed-off-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The pre-parsed addrs/n_addrs fields in struct device_node are finally
gone. Remove the dodgy heuristics that did that parsing at boot and
remove the fields themselves since we now have a good replacement with
the new OF parsing code. This patch also fixes a bunch of drivers to use
the new code instead, so that at least pmac32, pseries, iseries and g5
defconfigs build.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The platinumfb driver used only on some powermacs has an issue with some
video modes & limited VRAM. This patch fixes it.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds a defconfig for PowerMac with ARCH=powerpc
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Remove a comment in head.S which is no longer relevant.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Milton and I were looking at the cputable code and it looks like we can
set spurious bits on 64bit.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
We used to print a NUMA cpu summary at boot before the hotplug cpu code
was added. This has been useful for catching machine configuration as
well as firmware bugs in the past.
This patch restores that functionality. An example of the output is:
Node 0 CPUs: 0-7
Node 1 CPUs: 8-15
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Add three files not mentioned in Documentation/powerpc/00-INDEX.
Sort alphabetically.
Signed-off-by: Nicolas Kaiser <nikai@nikai.net>
Signed-off-by: Paul Mackerras <paulus@samba.org>
/dev/nvram uses the user-provided read/write size
for kmalloc, which fails, if a large number is passed.
This will always use a single page at most, which
can be expected to succeed.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
We currently crash in the fedora installer because the keyboard
driver tries to access I/O space that is not there on our hardware.
This uses the same solution as powermac by just marking all
legacy i/o as invalid.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
So far, the iommu code was hardwired to a linear mapping
between 0x20000000 and 0x40000000, so it could only support
512MB of RAM.
This patch still keeps the linear mapping, but looks for
proper ibm,dma-window properties to set up larger windows,
this makes the maximum supported RAM size 2GB.
If there is anything unusual about the dma-window properties,
we fall back to the old behavior.
We also support switching off the iommu completely now
with the regular iommu=off command line option.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Output from hexdump with "%08x" depends on HOST platform's endian.
When building linux by cross toolchain, that difference makes errors.
Signed-off-by: Masato Noguchi <Masato.Noguchi@jp.sony.com>
Signed-off-by: Geoff Levand <geoff.levand@am.sony.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
One of my last patches contained a broken line
from splitting out some other changes, this
restores a working version.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
One of the two users of spufs_calls.owner still has a race
when calling try_module_get while the module is removed.
This makes it use the correct instance of owner.
Noticed by Milton Miller.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch adds support for the TQ Components TQM85xx modules. Currently the
modules TQM8540/8541/8555/8560 are supported.
Signed-off-by: Stefan Roese <sr@denx.de>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
I can't really get a conclusive answer from the firmware
people what to check for, so I just try scanning for
anything that starts with "IBM,CPB", which should be
correct for all hardware produced so far and for
systemsim.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Handling mailbox interrupts was broken in multiple respects,
the combination of which was hiding the bugs most of the time.
- The ibox interrupt mask was open initially even though there
are no waiters on a newly created SPU.
- Acknowledging the mailbox interrupt did not work because
it is level triggered and the mailbox data is never retrieved
from inside the interrupt handler.
- The interrupt handler delivered interrupts with a disabled
mask if another interrupt is triggered for the same class
but a different mask.
- The poll function did not enable the interrupt if it had not
been enabled, so we might run into the poll timeout if none of
the other bugs saved us and no signal was delivered.
We probably still have a similar problem with blocking
read/write on mailbox files, but that will result in extra
wakeup in the worst case, not in incorrect behaviour.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch reduces lock complexity of SPU scheduler, particularly
for involuntary preemptive switches. As a result the new code
does a better job of mapping the highest priority tasks to SPUs.
Lock complexity is reduced by using the system default workqueue
to perform involuntary saves. In this way we avoid nasty lock
ordering problems that the previous code had. A "minimum timeslice"
for SPU contexts is also introduced. The intent here is to avoid
thrashing.
While the new scheduler does a better job at prioritization it
still does nothing for fairness.
From: Mark Nutter <mnutter@us.ibm.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch makes it easier to preempt an SPU context by
having the scheduler hold ctx->state_sema for much shorter
periods of time.
As part of this restructuring, the control logic for the "run"
operation is moved from arch/ppc64/kernel/spu_base.c to
fs/spufs/file.c. Of course the base retains "bottom half"
handlers for class{0,1} irqs. The new run loop will re-acquire
an SPU if preempted.
From: Mark Nutter <mnutter@us.ibm.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
spufs is rather noisy when debugging is enabled, this
turns off the messages for production use.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Christoph Lameter