Граф коммитов

7358 Коммитов

Автор SHA1 Сообщение Дата
Christoph Lameter ce866b34ae [PATCH] zoned vm counters: conversion of nr_writeback to per zone counter
Conversion of nr_writeback to per zone counter.

This removes the last page_state counter from arch/i386/mm/pgtable.c so we
drop the page_state from there.

[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:35 -07:00
Christoph Lameter b1e7a8fd85 [PATCH] zoned vm counters: conversion of nr_dirty to per zone counter
This makes nr_dirty a per zone counter.  Looping over all processors is
avoided during writeback state determination.

The counter aggregation for nr_dirty had to be undone in the NFS layer since
we summed up the page counts from multiple zones.  Someone more familiar with
NFS should probably review what I have done.

[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:35 -07:00
Christoph Lameter df849a1529 [PATCH] zoned vm counters: conversion of nr_pagetables to per zone counter
Conversion of nr_page_table_pages to a per zone counter

[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:35 -07:00
Christoph Lameter 9a865ffa34 [PATCH] zoned vm counters: conversion of nr_slab to per zone counter
- Allows reclaim to access counter without looping over processor counts.

- Allows accurate statistics on how many pages are used in a zone by
  the slab. This may become useful to balance slab allocations over
  various zones.

[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:35 -07:00
Christoph Lameter 347ce434d5 [PATCH] zoned vm counters: conversion of nr_pagecache to per zone counter
Currently a single atomic variable is used to establish the size of the page
cache in the whole machine.  The zoned VM counters have the same method of
implementation as the nr_pagecache code but also allow the determination of
the pagecache size per zone.

Remove the special implementation for nr_pagecache and make it a zoned counter
named NR_FILE_PAGES.

Updates of the page cache counters are always performed with interrupts off.
We can therefore use the __ variant here.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:34 -07:00
Christoph Lameter 65ba55f500 [PATCH] zoned vm counters: convert nr_mapped to per zone counter
nr_mapped is important because it allows a determination of how many pages of
a zone are not mapped, which would allow a more efficient means of determining
when we need to reclaim memory in a zone.

We take the nr_mapped field out of the page state structure and define a new
per zone counter named NR_FILE_MAPPED (the anonymous pages will be split off
from NR_MAPPED in the next patch).

We replace the use of nr_mapped in various kernel locations.  This avoids the
looping over all processors in try_to_free_pages(), writeback, reclaim (swap +
zone reclaim).

[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:34 -07:00
Christoph Lameter 2244b95a7b [PATCH] zoned vm counters: basic ZVC (zoned vm counter) implementation
Per zone counter infrastructure

The counters that we currently have for the VM are split per processor.  The
processor however has not much to do with the zone these pages belong to.  We
cannot tell f.e.  how many ZONE_DMA pages are dirty.

So we are blind to potentially inbalances in the usage of memory in various
zones.  F.e.  in a NUMA system we cannot tell how many pages are dirty on a
particular node.  If we knew then we could put measures into the VM to balance
the use of memory between different zones and different nodes in a NUMA
system.  For example it would be possible to limit the dirty pages per node so
that fast local memory is kept available even if a process is dirtying huge
amounts of pages.

Another example is zone reclaim.  We do not know how many unmapped pages exist
per zone.  So we just have to try to reclaim.  If it is not working then we
pause and try again later.  It would be better if we knew when it makes sense
to reclaim unmapped pages from a zone.  This patchset allows the determination
of the number of unmapped pages per zone.  We can remove the zone reclaim
interval with the counters introduced here.

Futhermore the ability to have various usage statistics available will allow
the development of new NUMA balancing algorithms that may be able to improve
the decision making in the scheduler of when to move a process to another node
and hopefully will also enable automatic page migration through a user space
program that can analyse the memory load distribution and then rebalance
memory use in order to increase performance.

The counter framework here implements differential counters for each processor
in struct zone.  The differential counters are consolidated when a threshold
is exceeded (like done in the current implementation for nr_pageache), when
slab reaping occurs or when a consolidation function is called.

Consolidation uses atomic operations and accumulates counters per zone in the
zone structure and also globally in the vm_stat array.  VM functions can
access the counts by simply indexing a global or zone specific array.

The arrangement of counters in an array also simplifies processing when output
has to be generated for /proc/*.

Counters can be updated by calling inc/dec_zone_page_state or
_inc/dec_zone_page_state analogous to *_page_state.  The second group of
functions can be called if it is known that interrupts are disabled.

Special optimized increment and decrement functions are provided.  These can
avoid certain checks and use increment or decrement instructions that an
architecture may provide.

We also add a new CONFIG_DMA_IS_NORMAL that signifies that an architecture can
do DMA to all memory and therefore ZONE_NORMAL will not be populated.  This is
only currently set for IA64 SGI SN2 and currently only affects
node_page_state().  In the best case node_page_state can be reduced to
retrieving a single counter for the one zone on the node.

[akpm@osdl.org: cleanups]
[akpm@osdl.org: export vm_stat[] for filesystems]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:34 -07:00
Andrew Morton e09793bb91 [PATCH] msr.c: use register_hotcpu_notifier()
register_cpu_notifier() cannot do anything in a module, in a
!CONFIG_HOTPLUG_CPU kernel.

Cc: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 11:25:34 -07:00
Linus Torvalds 74e651f0aa Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (30 commits)
  [TIPC]: Initial activation message now includes TIPC version number
  [TIPC]: Improve response to requests for node/link information
  [TIPC]: Fixed skb_under_panic caused by tipc_link_bundle_buf
  [IrDA]: Fix the AU1000 FIR dependencies
  [IrDA]: Fix RCU lock pairing on error path
  [XFRM]: unexport xfrm_state_mtu
  [NET]: make skb_release_data() static
  [NETFILTE] ipv4: Fix typo (Bugzilla #6753)
  [IrDA]: MCS7780 usb_driver struct should be static
  [BNX2]: Turn off link during shutdown
  [BNX2]: Use dev_kfree_skb() instead of the _irq version
  [ATM]: basic sysfs support for ATM devices
  [ATM]: [suni] change suni_init to __devinit
  [ATM]: [iphase] should be __devinit not __init
  [ATM]: [idt77105] should be __devinit not __init
  [BNX2]: Add NETIF_F_TSO_ECN
  [NET]: Add ECN support for TSO
  [AF_UNIX]: Datagram getpeersec
  [NET]: Fix logical error in skb_gso_ok
  [PKT_SCHED]: PSCHED_TADD() and PSCHED_TADD2() can result,tv_usec >= 1000000
  ...
2006-06-29 17:43:43 -07:00
Adrian Bunk 5bba17127e [NET]: make skb_release_data() static
skb_release_data() no longer has any users in other files.

Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:58:30 -07:00
David S. Miller 675f740e55 [SPARC64]: Print symbol name of regs->tpc on kernel unaligned accesses.
This makes things easier to track down, especially in modules.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:38:03 -07:00
David S. Miller ff0d2fc6a6 [SPARC64]: time: Kill unnecessary asm/{fhc,sbus,ebus,isa}.h includes.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:59 -07:00
David S. Miller abbce6e2fd [SPARC64] power: Convert to of_driver.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:57 -07:00
David S. Miller f2ad06a201 [SPARC64] auxio: Remove asm/{sbus,ebus}.h includes.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:55 -07:00
David S. Miller 8f96cd1a69 [SPARC]: sparc32 side of of_device layer IRQ resolution.
Happily, life is much simpler on 32-bit sparc systems.
The "intr" property, preferred over the "interrupts"
property is used-as.  Some minor translations of this
value happen on sun4d systems.

The stage is now set to rewrite the sparc serial driver
probing to use the of_driver framework, and then to convert
all SBUS, EBUS, and ISA drivers in-kind so that we can nuke
all those special bus frameworks.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:40 -07:00
David S. Miller 2b1e597871 [SPARC64]: of_device layer IRQ resolution
Do IRQ determination generically by parsing the PROM properties,
and using IRQ controller drivers for final resolution.

One immediate positive effect is that all of the IRQ frobbing
in the EBUS, ISA, and PCI controller layers has been eliminated.
We just look up the of_device and use the properly computed
value.

The PCI controller irq_build() routines are gone and no longer
used.  Unfortunately sbus_build_irq() has to remain as there is
a direct reference to this in the sunzilog driver.  That can be
killed off once the sparc32 side of this is written and the
sunzilog driver is transformed into an "of" bus driver.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:38 -07:00
David S. Miller c3a8b85f5a [SPARC64]: Fix typo in clock_probe().
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:35 -07:00
David S. Miller 915214853d [SPARC64] clock: Only probe central fhc clock on Enterprise boxes.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:33 -07:00
David S. Miller 00cde67482 [SPARC64] power: Do not pass SA_SHIRQ to request_irq().
This needs to be a unique interrupt source because we do
not have a register or similar to poll to make sure the
IRQ is really for us.  We do not have any dev_id to pass
in anyways, and the generic IRQ layer is now enforcing
that when SA_SHIRQ is specified, dev_id must be non-NULL.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:31 -07:00
David S. Miller d44b3be88e [SPARC64]: Fix typo in isa_dev_get_irq_using_imap().
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:29 -07:00
David S. Miller 24ac26d425 [SPARC64]: Let irq_install_pre_handler() get called multiple times.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:27 -07:00
David S. Miller ee5caf0ee1 [SPARC]: Convert clock drivers to of_driver framework.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:23 -07:00
David S. Miller 36a59bd89c [SPARC64] auxio: Convert to pure of_device driver.
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:21 -07:00
David S. Miller 3ca9fab410 [SPARC]: Add of_io{remap,unmap}().
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:16 -07:00
David S. Miller 95714e12df [SPARC]: Encode I/O space into resource flags on sparc32.
On sparc64 we don't need to do this because the resource
values are large enough to encode the full physical address.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:14 -07:00
David S. Miller cf44bbc26c [SPARC]: Beginnings of generic of_device framework.
The idea is to fully construct the device register and
interrupt values into these of_device objects, and convert
all of SBUS, EBUS, ISA drivers to use this new stuff.

Much ideas and code taken from Ben H.'s powerpc work.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:12 -07:00
David S. Miller 3ae9a3489a [SPARC]: Add of_n_{addr,size}_cells().
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:10 -07:00
David S. Miller 286bbe87c1 [SPARC64]: Kill starfire_cookie from SBUS/PCI.
Totally unused.

We need to traverse the list of global IRQ translaters,
so storing it in the per-bus structures was useless.

Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 16:37:08 -07:00
Linus Torvalds 602cada851 Merge git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/devfs-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/devfs-2.6: (22 commits)
  [PATCH] devfs: Remove it from the feature_removal.txt file
  [PATCH] devfs: Last little devfs cleanups throughout the kernel tree.
  [PATCH] devfs: Rename TTY_DRIVER_NO_DEVFS to TTY_DRIVER_DYNAMIC_DEV
  [PATCH] devfs: Remove the tty_driver devfs_name field as it's no longer needed
  [PATCH] devfs: Remove the line_driver devfs_name field as it's no longer needed
  [PATCH] devfs: Remove the videodevice devfs_name field as it's no longer needed
  [PATCH] devfs: Remove the gendisk devfs_name field as it's no longer needed
  [PATCH] devfs: Remove the miscdevice devfs_name field as it's no longer needed
  [PATCH] devfs: Remove the devfs_fs_kernel.h file from the tree
  [PATCH] devfs: Remove devfs_remove() function from the kernel tree
  [PATCH] devfs: Remove devfs_mk_cdev() function from the kernel tree
  [PATCH] devfs: Remove devfs_mk_bdev() function from the kernel tree
  [PATCH] devfs: Remove devfs_mk_symlink() function from the kernel tree
  [PATCH] devfs: Remove devfs_mk_dir() function from the kernel tree
  [PATCH] devfs: Remove devfs_*_tape() functions from the kernel tree
  [PATCH] devfs: Remove devfs support from the sound subsystem
  [PATCH] devfs: Remove devfs support from the ide subsystem.
  [PATCH] devfs: Remove devfs support from the serial subsystem
  [PATCH] devfs: Remove devfs from the init code
  [PATCH] devfs: Remove devfs from the partition code
  ...
2006-06-29 14:19:21 -07:00
Linus Torvalds 8d231c11fd Merge branch 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus
* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus: (33 commits)
  [MIPS] Add missing backslashes to macro definitions.
  [MIPS] Death list of board support to be removed after 2.6.18.
  [MIPS] Remove BSD and Sys V compat data types.
  [MIPS] ioc3.h: Uses u8, so include <linux/types.h>.
  [MIPS] 74K: Assume it will also have an AR bit in config7
  [MIPS] Treat CPUs with AR bit as physically indexed.
  [MIPS] Oprofile: Support VSMP on 34K.
  [MIPS] MIPS32/MIPS64 S-cache fix and cleanup
  [MIPS] excite: PCI makefile needs to use += if it wants a chance to work.
  [MIPS] excite: plat_setup -> plat_mem_setup.
  [MIPS] au1xxx: export dbdma functions
  [MIPS] au1xxx: dbdma, no sleeping under spin_lock
  [MIPS] au1xxx: fix PSC_SMBTXRX_RSR.
  [MIPS] Early printk for IP27.
  [MIPS] Fix handling of 0 length I & D caches.
  [MIPS] Typo fixes.
  [MIPS] MIPS32/MIPS64 secondary cache management
  [MIPS] Fix FIXADDR_TOP for TX39/TX49.
  [MIPS] Remove first timer interrupt setup in wrppmc_timer_setup()
  [MIPS] Fix configuration of R2 CPU features and multithreading.
  ...
2006-06-29 13:44:45 -07:00
Ralf Baechle fc103349bb [MIPS] Remove BSD and Sys V compat data types.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Ralf Baechle 2e78ae3f48 [MIPS] 74K: Assume it will also have an AR bit in config7
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Ralf Baechle beab375a48 [MIPS] Treat CPUs with AR bit as physically indexed.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Ralf Baechle 92c7b62fd1 [MIPS] Oprofile: Support VSMP on 34K.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Atsushi Nemoto a2c2bc4b26 [MIPS] MIPS32/MIPS64 S-cache fix and cleanup
Use blast_scache_range, blast_inv_scache_range for mips32/mips64 scache
routine.  Also initialize waybit for MIPS32/MIPS64 S-cache.

Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Ralf Baechle 86165879a2 [MIPS] excite: PCI makefile needs to use += if it wants a chance to work.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Ralf Baechle ec52d7bff0 [MIPS] excite: plat_setup -> plat_mem_setup.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:54 +01:00
Domen Puncer 3e2c6ef3c6 [MIPS] au1xxx: export dbdma functions
These are needed for au1550_ac97 module.

Signed-off-by: Domen Puncer <domen.puncer@ultra.si>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:53 +01:00
Domen Puncer c06138941c [MIPS] au1xxx: dbdma, no sleeping under spin_lock
kmalloc under spin_lock can't sleep.

Signed-off-by: Domen Puncer <domen.puncer@ultra.si>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:53 +01:00
Ralf Baechle a3d4539186 [MIPS] Early printk for IP27.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:53 +01:00
Chris Dearman 73f403527b [MIPS] Fix handling of 0 length I & D caches.
Don't ask.

Signed-off-by: Chris Dearman <chris@mips.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:53 +01:00
Chris Dearman c09b47d8a9 [MIPS] Typo fixes.
Signed-off-by: Chris Dearman <chris@mips.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:52 +01:00
Chris Dearman 9318c51acd [MIPS] MIPS32/MIPS64 secondary cache management
Signed-off-by: Chris Dearman <chris@mips.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:52 +01:00
Yoichi Yuasa 6feb6efaec [MIPS] Remove first timer interrupt setup in wrppmc_timer_setup()
The first timer interrupt setup already happens in time_init().

Signed-off-by: Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:52 +01:00
Ralf Baechle f41ae0b2b9 [MIPS] Fix configuration of R2 CPU features and multithreading.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:51 +01:00
Ralf Baechle e73ea273ef [MIPS] Fix build error: don't offer SMP on systems that don't have SMP.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:51 +01:00
Ralf Baechle a620dbe378 [MIPS] Limit MIPS_MT to MIPS32R2 only.
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:51 +01:00
Yoichi Yuasa 08aecfb9ea [MIPS] Remove set_c0_status(ST0_IM) from wrppmc's irq.c.
mips_cpu_irq_init() does clear_c0_status(ST0_IM) first, so
set_c0_status(ST0_IM) isn't necessary.

Signed-off-by: Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:51 +01:00
Yoichi Yuasa 1500b9a0f4 [MIPS] Remove unused system type name for DDB5074 and DDB5476.
This patch removes unused system type name.
DDB5074 and DDB5476 were already removed.

Signed-off-by: Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:50 +01:00
Yoichi Yuasa 0ef831b1ff [MIPS] Removes unused functions for GT64120
Signed-off-by: Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2006-06-29 21:10:49 +01:00