adulau/aha
1
0
Fork 0
mirror of https://github.com/adulau/aha.git synced 2024-12-27 11:16:11 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'x86/mm' into core/percpu

Browse source 
Conflicts:
	arch/x86/mm/fault.c
This commit is contained in:
Ingo Molnar 2009-01-21 10:39:51 +01:00
commit 198030782c
527 changed files with 8252 additions and 3743 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
CREDITS
View file

@ -3786,14 +3786,11 @@ S: The Netherlands
N: David Woodhouse
E: dwmw2@infradead.org
D: ARCnet stuff, Applicom board driver, SO_BINDTODEVICE,
D: some Alpha platform porting from 2.0, Memory Technology Devices,
D: Acquire watchdog timer, PC speaker driver maintenance,
D: JFFS2 file system, Memory Technology Device subsystem,
D: various other stuff that annoyed me by not working.
S: c/o Red Hat Engineering
S: Rustat House
S: 60 Clifton Road
S: Cambridge. CB1 7EG
S: c/o Intel Corporation
S: Pipers Way
S: Swindon. SN3 1RJ
S: England
N: Chris Wright

9
Documentation/DMA-API.txt
View file

@ -170,16 +170,15 @@ Returns: 0 if successful and a negative error if not.
u64
dma_get_required_mask(struct device *dev)
After setting the mask with dma_set_mask(), this API returns the
actual mask (within that already set) that the platform actually
requires to operate efficiently. Usually this means the returned mask
This API returns the mask that the platform requires to
operate efficiently. Usually this means the returned mask
is the minimum required to cover all of memory. Examining the
required mask gives drivers with variable descriptor sizes the
opportunity to use smaller descriptors as necessary.
Requesting the required mask does not alter the current mask. If you
wish to take advantage of it, you should issue another dma_set_mask()
call to lower the mask again.
wish to take advantage of it, you should issue a dma_set_mask()
call to set the mask to the value returned.
Part Id - Streaming DMA mappings

4
Documentation/accounting/getdelays.c
View file

@ -392,6 +392,10 @@ int main(int argc, char *argv[])
goto err;
}
}
if (!maskset && !tid && !containerset) {
usage();
goto err;
}
do {
int i;

5
Documentation/cgroups/cgroups.txt
View file

@ -1,7 +1,8 @@
CGROUPS
-------
Written by Paul Menage <menage@google.com> based on Documentation/cpusets.txt
Written by Paul Menage <menage@google.com> based on
Documentation/cgroups/cpusets.txt
Original copyright statements from cpusets.txt:
Portions Copyright (C) 2004 BULL SA.
@ -68,7 +69,7 @@ On their own, the only use for cgroups is for simple job
tracking. The intention is that other subsystems hook into the generic
cgroup support to provide new attributes for cgroups, such as
accounting/limiting the resources which processes in a cgroup can
access. For example, cpusets (see Documentation/cpusets.txt) allows
access. For example, cpusets (see Documentation/cgroups/cpusets.txt) allows
you to associate a set of CPUs and a set of memory nodes with the
tasks in each cgroup.

0
Documentation/controllers/cpuacct.txt → Documentation/cgroups/cpuacct.txt
View file

0
Documentation/cpusets.txt → Documentation/cgroups/cpusets.txt
View file

0
Documentation/controllers/devices.txt → Documentation/cgroups/devices.txt
View file

2
Documentation/controllers/memcg_test.txt → Documentation/cgroups/memcg_test.txt
View file

@ -6,7 +6,7 @@ Because VM is getting complex (one of reasons is memcg...), memcg's behavior
is complex. This is a document for memcg's internal behavior.
Please note that implementation details can be changed.
(*) Topics on API should be in Documentation/controllers/memory.txt)
(*) Topics on API should be in Documentation/cgroups/memory.txt)
0. How to record usage ?
2 objects are used.

0
Documentation/controllers/memory.txt → Documentation/cgroups/memory.txt
View file

0
Documentation/controllers/resource_counter.txt → Documentation/cgroups/resource_counter.txt
View file

288
Documentation/filesystems/proc.txt
View file

@ -1371,292 +1371,8 @@ auto_msgmni default value is 1.
2.4 /proc/sys/vm - The virtual memory subsystem
-----------------------------------------------
The files in this directory can be used to tune the operation of the virtual
memory (VM) subsystem of the Linux kernel.
vfs_cache_pressure
------------------
Controls the tendency of the kernel to reclaim the memory which is used for
caching of directory and inode objects.
At the default value of vfs_cache_pressure=100 the kernel will attempt to
reclaim dentries and inodes at a "fair" rate with respect to pagecache and
swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer
to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100
causes the kernel to prefer to reclaim dentries and inodes.
dirty_background_bytes
----------------------
Contains the amount of dirty memory at which the pdflush background writeback
daemon will start writeback.
If dirty_background_bytes is written, dirty_background_ratio becomes a function
of its value (dirty_background_bytes / the amount of dirtyable system memory).
dirty_background_ratio
----------------------
Contains, as a percentage of the dirtyable system memory (free pages + mapped
pages + file cache, not including locked pages and HugePages), the number of
pages at which the pdflush background writeback daemon will start writing out
dirty data.
If dirty_background_ratio is written, dirty_background_bytes becomes a function
of its value (dirty_background_ratio * the amount of dirtyable system memory).
dirty_bytes
-----------
Contains the amount of dirty memory at which a process generating disk writes
will itself start writeback.
If dirty_bytes is written, dirty_ratio becomes a function of its value
(dirty_bytes / the amount of dirtyable system memory).
dirty_ratio
-----------
Contains, as a percentage of the dirtyable system memory (free pages + mapped
pages + file cache, not including locked pages and HugePages), the number of
pages at which a process which is generating disk writes will itself start
writing out dirty data.
If dirty_ratio is written, dirty_bytes becomes a function of its value
(dirty_ratio * the amount of dirtyable system memory).
dirty_writeback_centisecs
-------------------------
The pdflush writeback daemons will periodically wake up and write `old' data
out to disk. This tunable expresses the interval between those wakeups, in
100'ths of a second.
Setting this to zero disables periodic writeback altogether.
dirty_expire_centisecs
----------------------
This tunable is used to define when dirty data is old enough to be eligible
for writeout by the pdflush daemons. It is expressed in 100'ths of a second.
Data which has been dirty in-memory for longer than this interval will be
written out next time a pdflush daemon wakes up.
highmem_is_dirtyable
--------------------
Only present if CONFIG_HIGHMEM is set.
This defaults to 0 (false), meaning that the ratios set above are calculated
as a percentage of lowmem only. This protects against excessive scanning
in page reclaim, swapping and general VM distress.
Setting this to 1 can be useful on 32 bit machines where you want to make
random changes within an MMAPed file that is larger than your available
lowmem without causing large quantities of random IO. Is is safe if the
behavior of all programs running on the machine is known and memory will
not be otherwise stressed.
legacy_va_layout
----------------
If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
will use the legacy (2.4) layout for all processes.
lowmem_reserve_ratio
---------------------
For some specialised workloads on highmem machines it is dangerous for
the kernel to allow process memory to be allocated from the "lowmem"
zone. This is because that memory could then be pinned via the mlock()
system call, or by unavailability of swapspace.
And on large highmem machines this lack of reclaimable lowmem memory
can be fatal.
So the Linux page allocator has a mechanism which prevents allocations
which _could_ use highmem from using too much lowmem. This means that
a certain amount of lowmem is defended from the possibility of being
captured into pinned user memory.
(The same argument applies to the old 16 megabyte ISA DMA region. This
mechanism will also defend that region from allocations which could use
highmem or lowmem).
The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
in defending these lower zones.
If you have a machine which uses highmem or ISA DMA and your
applications are using mlock(), or if you are running with no swap then
you probably should change the lowmem_reserve_ratio setting.
The lowmem_reserve_ratio is an array. You can see them by reading this file.
-
% cat /proc/sys/vm/lowmem_reserve_ratio
256 256 32
-
Note: # of this elements is one fewer than number of zones. Because the highest
zone's value is not necessary for following calculation.
But, these values are not used directly. The kernel calculates # of protection
pages for each zones from them. These are shown as array of protection pages
in /proc/zoneinfo like followings. (This is an example of x86-64 box).
Each zone has an array of protection pages like this.
-
Node 0, zone DMA
pages free 1355
min 3
low 3
high 4
:
:
numa_other 0
protection: (0, 2004, 2004, 2004)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pagesets
cpu: 0 pcp: 0
:
-
These protections are added to score to judge whether this zone should be used
for page allocation or should be reclaimed.
In this example, if normal pages (index=2) are required to this DMA zone and
pages_high is used for watermark, the kernel judges this zone should not be
used because pages_free(1355) is smaller than watermark + protection[2]
(4 + 2004 = 2008). If this protection value is 0, this zone would be used for
normal page requirement. If requirement is DMA zone(index=0), protection[0]
(=0) is used.
zone[i]'s protection[j] is calculated by following expression.
(i < j):
zone[i]->protection[j]
= (total sums of present_pages from zone[i+1] to zone[j] on the node)
/ lowmem_reserve_ratio[i];
(i = j):
(should not be protected. = 0;
(i > j):
(not necessary, but looks 0)
The default values of lowmem_reserve_ratio[i] are
256 (if zone[i] means DMA or DMA32 zone)
32 (others).
As above expression, they are reciprocal number of ratio.
256 means 1/256. # of protection pages becomes about "0.39%" of total present
pages of higher zones on the node.
If you would like to protect more pages, smaller values are effective.
The minimum value is 1 (1/1 -> 100%).
page-cluster
------------
page-cluster controls the number of pages which are written to swap in
a single attempt. The swap I/O size.
It is a logarithmic value - setting it to zero means "1 page", setting
it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
The default value is three (eight pages at a time). There may be some
small benefits in tuning this to a different value if your workload is
swap-intensive.
overcommit_memory
-----------------
Controls overcommit of system memory, possibly allowing processes
to allocate (but not use) more memory than is actually available.
0 - Heuristic overcommit handling. Obvious overcommits of
address space are refused. Used for a typical system. It
ensures a seriously wild allocation fails while allowing
overcommit to reduce swap usage. root is allowed to
allocate slightly more memory in this mode. This is the
default.
1 - Always overcommit. Appropriate for some scientific
applications.
2 - Don't overcommit. The total address space commit
for the system is not permitted to exceed swap plus a
configurable percentage (default is 50) of physical RAM.
Depending on the percentage you use, in most situations
this means a process will not be killed while attempting
to use already-allocated memory but will receive errors
on memory allocation as appropriate.
overcommit_ratio
----------------
Percentage of physical memory size to include in overcommit calculations
(see above.)
Memory allocation limit = swapspace + physmem * (overcommit_ratio / 100)
swapspace = total size of all swap areas
physmem = size of physical memory in system
nr_hugepages and hugetlb_shm_group
----------------------------------
nr_hugepages configures number of hugetlb page reserved for the system.
hugetlb_shm_group contains group id that is allowed to create SysV shared
memory segment using hugetlb page.
hugepages_treat_as_movable
--------------------------
This parameter is only useful when kernelcore= is specified at boot time to
create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
value written to hugepages_treat_as_movable allows huge pages to be allocated
from ZONE_MOVABLE.
Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
pages pool can easily grow or shrink within. Assuming that applications are
not running that mlock() a lot of memory, it is likely the huge pages pool
can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
into nr_hugepages and triggering page reclaim.
laptop_mode
-----------
laptop_mode is a knob that controls "laptop mode". All the things that are
controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
block_dump
----------
block_dump enables block I/O debugging when set to a nonzero value. More
information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
swap_token_timeout
------------------
This file contains valid hold time of swap out protection token. The Linux
VM has token based thrashing control mechanism and uses the token to prevent
unnecessary page faults in thrashing situation. The unit of the value is
second. The value would be useful to tune thrashing behavior.
drop_caches
-----------
Writing to this will cause the kernel to drop clean caches, dentries and
inodes from memory, causing that memory to become free.
To free pagecache:
echo 1 > /proc/sys/vm/drop_caches
To free dentries and inodes:
echo 2 > /proc/sys/vm/drop_caches
To free pagecache, dentries and inodes:
echo 3 > /proc/sys/vm/drop_caches
As this is a non-destructive operation and dirty objects are not freeable, the
user should run `sync' first.
Please see: Documentation/sysctls/vm.txt for a description of these
entries.
2.5 /proc/sys/dev - Device specific parameters

87
Documentation/hwmon/adt7475 Normal file
View file

@ -0,0 +1,87 @@
This describes the interface for the ADT7475 driver:
(there are 4 fans, numbered fan1 to fan4):
fanX_input Read the current speed of the fan (in RPMs)
fanX_min Read/write the minimum speed of the fan. Dropping
below this sets an alarm.
(there are three PWMs, numbered pwm1 to pwm3):
pwmX Read/write the current duty cycle of the PWM. Writes
only have effect when auto mode is turned off (see
below). Range is 0 - 255.
pwmX_enable Fan speed control method:
0 - No control (fan at full speed)
1 - Manual fan speed control (using pwm[1-*])
2 - Automatic fan speed control
pwmX_auto_channels_temp Select which channels affect this PWM
1 - TEMP1 controls PWM
2 - TEMP2 controls PWM
4 - TEMP3 controls PWM
6 - TEMP2 and TEMP3 control PWM
7 - All three inputs control PWM
pwmX_freq Read/write the PWM frequency in Hz. The number
should be one of the following:
11 Hz
14 Hz
22 Hz
29 Hz
35 Hz
44 Hz
58 Hz
88 Hz
pwmX_auto_point1_pwm Read/write the minimum PWM duty cycle in automatic mode
pwmX_auto_point2_pwm Read/write the maximum PWM duty cycle in automatic mode
(there are three temperature settings numbered temp1 to temp3):
tempX_input Read the current temperature. The value is in milli
degrees of Celsius.
tempX_max Read/write the upper temperature limit - exceeding this
will cause an alarm.
tempX_min Read/write the lower temperature limit - exceeding this
will cause an alarm.
tempX_offset Read/write the temperature adjustment offset
tempX_crit Read/write the THERM limit for remote1.
tempX_crit_hyst Set the temperature value below crit where the
fans will stay on - this helps drive the temperature
low enough so it doesn't stay near the edge and
cause THERM to keep tripping.
tempX_auto_point1_temp Read/write the minimum temperature where the fans will
turn on in automatic mode.
tempX_auto_point2_temp Read/write the maximum temperature over which the fans
will run in automatic mode. tempX_auto_point1_temp
and tempX_auto_point2_temp together define the
range of automatic control.
tempX_alarm Read a 1 if the max/min alarm is set
tempX_fault Read a 1 if either temp1 or temp3 diode has a fault
(There are two voltage settings, in1 and in2):
inX_input Read the current voltage on VCC. Value is in
millivolts.
inX_min read/write the minimum voltage limit.
Dropping below this causes an alarm.
inX_max read/write the maximum voltage limit.
Exceeding this causes an alarm.
inX_alarm Read a 1 if the max/min alarm is set.

30
Documentation/hwmon/lis3lv02d
View file

@ -13,18 +13,21 @@ Author:
Description
-----------
This driver provides support for the accelerometer found in various HP laptops
sporting the feature officially called "HP Mobile Data Protection System 3D" or
"HP 3D DriveGuard". It detect automatically laptops with this sensor. Known models
(for now the HP 2133, nc6420, nc2510, nc8510, nc84x0, nw9440 and nx9420) will
have their axis automatically oriented on standard way (eg: you can directly
play neverball). The accelerometer data is readable via
This driver provides support for the accelerometer found in various HP
laptops sporting the feature officially called "HP Mobile Data
Protection System 3D" or "HP 3D DriveGuard". It detect automatically
laptops with this sensor. Known models (for now the HP 2133, nc6420,
nc2510, nc8510, nc84x0, nw9440 and nx9420) will have their axis
automatically oriented on standard way (eg: you can directly play
neverball). The accelerometer data is readable via
/sys/devices/platform/lis3lv02d.
Sysfs attributes under /sys/devices/platform/lis3lv02d/:
position - 3D position that the accelerometer reports. Format: "(x,y,z)"
calibrate - read: values (x, y, z) that are used as the base for input class device operation.
write: forces the base to be recalibrated with the current position.
calibrate - read: values (x, y, z) that are used as the base for input
class device operation.
write: forces the base to be recalibrated with the current
position.
rate - reports the sampling rate of the accelerometer device in HZ
This driver also provides an absolute input class device, allowing
@ -39,11 +42,12 @@ the accelerometer are converted into a "standard" organisation of the axes
* When the laptop is horizontal the position reported is about 0 for X and Y
and a positive value for Z
* If the left side is elevated, X increases (becomes positive)
* If the front side (where the touchpad is) is elevated, Y decreases (becomes negative)
* If the front side (where the touchpad is) is elevated, Y decreases
(becomes negative)
* If the laptop is put upside-down, Z becomes negative
If your laptop model is not recognized (cf "dmesg"), you can send an email to the
authors to add it to the database. When reporting a new laptop, please include
the output of "dmidecode" plus the value of /sys/devices/platform/lis3lv02d/position
in these four cases.
If your laptop model is not recognized (cf "dmesg"), you can send an
email to the authors to add it to the database. When reporting a new
laptop, please include the output of "dmidecode" plus the value of
/sys/devices/platform/lis3lv02d/position in these four cases.

25
Documentation/laptops/thinkpad-acpi.txt
View file

@ -1,7 +1,7 @@
ThinkPad ACPI Extras Driver
Version 0.21
May 29th, 2008
Version 0.22
November 23rd, 2008
Borislav Deianov <borislav@users.sf.net>
Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@ -16,7 +16,8 @@ supported by the generic Linux ACPI drivers.
This driver used to be named ibm-acpi until kernel 2.6.21 and release
0.13-20070314. It used to be in the drivers/acpi tree, but it was
moved to the drivers/misc tree and renamed to thinkpad-acpi for kernel
2.6.22, and release 0.14.
2.6.22, and release 0.14. It was moved to drivers/platform/x86 for
kernel 2.6.29 and release 0.22.
The driver is named "thinkpad-acpi". In some places, like module
names, "thinkpad_acpi" is used because of userspace issues.
@ -1412,6 +1413,24 @@ Sysfs notes:
rfkill controller switch "tpacpi_wwan_sw": refer to
Documentation/rfkill.txt for details.
EXPERIMENTAL: UWB
-----------------
This feature is marked EXPERIMENTAL because it has not been extensively
tested and validated in various ThinkPad models yet. The feature may not
work as expected. USE WITH CAUTION! To use this feature, you need to supply
the experimental=1 parameter when loading the module.
sysfs rfkill class: switch "tpacpi_uwb_sw"
This feature exports an rfkill controller for the UWB device, if one is
present and enabled in the BIOS.
Sysfs notes:
rfkill controller switch "tpacpi_uwb_sw": refer to
Documentation/rfkill.txt for details.
Multiple Commands, Module Parameters
------------------------------------

6
Documentation/mips/AU1xxx_IDE.README
View file

@ -52,14 +52,12 @@ Two files are introduced:
b) 'drivers/ide/mips/au1xxx-ide.c'
contains the functionality of the AU1XXX IDE driver
Four configs variables are introduced:
Following extra configs variables are introduced:
CONFIG_BLK_DEV_IDE_AU1XXX_PIO_DBDMA - enable the PIO+DBDMA mode
CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA - enable the MWDMA mode
CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON - set Burstable FIFO in DBDMA
controller
CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ - maximum transfer size
per descriptor
SUPPORTED IDE MODES
@ -87,7 +85,6 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y
CONFIG_IDEDMA_PCI_AUTO=y
CONFIG_BLK_DEV_IDE_AU1XXX=y
CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y
CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128
CONFIG_BLK_DEV_IDEDMA=y
CONFIG_IDEDMA_AUTO=y
@ -105,7 +102,6 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y
CONFIG_IDEDMA_PCI_AUTO=y
CONFIG_BLK_DEV_IDE_AU1XXX=y
CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y
CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ=128
CONFIG_BLK_DEV_IDEDMA=y
CONFIG_IDEDMA_AUTO=y

2
Documentation/scheduler/sched-design-CFS.txt
View file

@ -231,7 +231,7 @@ CPU bandwidth control purposes:
This options needs CONFIG_CGROUPS to be defined, and lets the administrator
create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See
Documentation/cgroups.txt for more information about this filesystem.
Documentation/cgroups/cgroups.txt for more information about this filesystem.
Only one of these options to group tasks can be chosen and not both.

12
Documentation/sound/alsa/HD-Audio-Models.txt
View file

@ -275,7 +275,8 @@ STAC9200
dell-m25 Dell Inspiron E1505n
dell-m26 Dell Inspiron 1501
dell-m27 Dell Inspiron E1705/9400
gateway Gateway laptops with EAPD control
gateway-m4 Gateway laptops with EAPD control
gateway-m4-2 Gateway laptops with EAPD control
panasonic Panasonic CF-74
STAC9205/9254
@ -302,6 +303,7 @@ STAC9220/9221
macbook-pro Intel Mac Book Pro 2nd generation (eq. type 3)
imac-intel Intel iMac (eq. type 2)
imac-intel-20 Intel iMac (newer version) (eq. type 3)
ecs202 ECS/PC chips
dell-d81 Dell (unknown)
dell-d82 Dell (unknown)
dell-m81 Dell (unknown)
@ -310,9 +312,13 @@ STAC9220/9221
STAC9202/9250/9251
==================
ref Reference board, base config
m1 Some Gateway MX series laptops (NX560XL)
m1-2 Some Gateway MX series laptops (MX6453)
m2 Some Gateway MX series laptops (M255)
m2-2 Some Gateway MX series laptops
m3 Some Gateway MX series laptops
m5 Some Gateway MX series laptops (MP6954)
m6 Some Gateway NX series laptops
pa6 Gateway NX860 series
STAC9227/9228/9229/927x
=======================
@ -329,6 +335,7 @@ STAC92HD71B*
dell-m4-1 Dell desktops
dell-m4-2 Dell desktops
dell-m4-3 Dell desktops
hp-m4 HP dv laptops
STAC92HD73*
===========
@ -337,6 +344,7 @@ STAC92HD73*
dell-m6-amic Dell desktops/laptops with analog mics
dell-m6-dmic Dell desktops/laptops with digital mics
dell-m6 Dell desktops/laptops with both type of mics
dell-eq Dell desktops/laptops
STAC92HD83*
===========

647
Documentation/sysctl/vm.txt
View file

@ -1,12 +1,13 @@
Documentation for /proc/sys/vm/* kernel version 2.2.10
Documentation for /proc/sys/vm/* kernel version 2.6.29
(c) 1998, 1999, Rik van Riel <riel@nl.linux.org>
(c) 2008 Peter W. Morreale <pmorreale@novell.com>
For general info and legal blurb, please look in README.
==============================================================
This file contains the documentation for the sysctl files in
/proc/sys/vm and is valid for Linux kernel version 2.2.
/proc/sys/vm and is valid for Linux kernel version 2.6.29.
The files in this directory can be used to tune the operation
of the virtual memory (VM) subsystem of the Linux kernel and
@ -16,83 +17,244 @@ Default values and initialization routines for most of these
files can be found in mm/swap.c.
Currently, these files are in /proc/sys/vm:
- overcommit_memory
- page-cluster
- dirty_ratio
- block_dump
- dirty_background_bytes
- dirty_background_ratio
- dirty_bytes
- dirty_expire_centisecs
- dirty_ratio
- dirty_writeback_centisecs
- highmem_is_dirtyable (only if CONFIG_HIGHMEM set)
- drop_caches
- hugepages_treat_as_movable
- hugetlb_shm_group
- laptop_mode
- legacy_va_layout
- lowmem_reserve_ratio
- max_map_count
- min_free_kbytes
- laptop_mode
- block_dump
- drop-caches
- zone_reclaim_mode
- min_unmapped_ratio
- min_slab_ratio
- panic_on_oom
- oom_dump_tasks
- oom_kill_allocating_task
- mmap_min_address
- numa_zonelist_order
- min_unmapped_ratio
- mmap_min_addr
- nr_hugepages
- nr_overcommit_hugepages
- nr_trim_pages (only if CONFIG_MMU=n)
- nr_pdflush_threads
- nr_trim_pages (only if CONFIG_MMU=n)
- numa_zonelist_order
- oom_dump_tasks
- oom_kill_allocating_task
- overcommit_memory
- overcommit_ratio
- page-cluster
- panic_on_oom
- percpu_pagelist_fraction
- stat_interval
- swappiness
- vfs_cache_pressure
- zone_reclaim_mode
==============================================================
dirty_bytes, dirty_ratio, dirty_background_bytes,
dirty_background_ratio, dirty_expire_centisecs,
dirty_writeback_centisecs, highmem_is_dirtyable,
vfs_cache_pressure, laptop_mode, block_dump, swap_token_timeout,
drop-caches, hugepages_treat_as_movable:
block_dump
See Documentation/filesystems/proc.txt
block_dump enables block I/O debugging when set to a nonzero value. More
information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
==============================================================
overcommit_memory:
dirty_background_bytes
This value contains a flag that enables memory overcommitment.
Contains the amount of dirty memory at which the pdflush background writeback
daemon will start writeback.
When this flag is 0, the kernel attempts to estimate the amount
of free memory left when userspace requests more memory.
When this flag is 1, the kernel pretends there is always enough
memory until it actually runs out.
When this flag is 2, the kernel uses a "never overcommit"
policy that attempts to prevent any overcommit of memory.
This feature can be very useful because there are a lot of
programs that malloc() huge amounts of memory "just-in-case"
and don't use much of it.
The default value is 0.
See Documentation/vm/overcommit-accounting and
security/commoncap.c::cap_vm_enough_memory() for more information.
If dirty_background_bytes is written, dirty_background_ratio becomes a function
of its value (dirty_background_bytes / the amount of dirtyable system memory).
==============================================================
overcommit_ratio:
dirty_background_ratio
When overcommit_memory is set to 2, the committed address
space is not permitted to exceed swap plus this percentage
of physical RAM. See above.
Contains, as a percentage of total system memory, the number of pages at which
the pdflush background writeback daemon will start writing out dirty data.
==============================================================
page-cluster:
dirty_bytes
The Linux VM subsystem avoids excessive disk seeks by reading
multiple pages on a page fault. The number of pages it reads
is dependent on the amount of memory in your machine.
Contains the amount of dirty memory at which a process generating disk writes
will itself start writeback.
The number of pages the kernel reads in at once is equal to
2 ^ page-cluster. Values above 2 ^ 5 don't make much sense
for swap because we only cluster swap data in 32-page groups.
If dirty_bytes is written, dirty_ratio becomes a function of its value
(dirty_bytes / the amount of dirtyable system memory).
==============================================================
dirty_expire_centisecs
This tunable is used to define when dirty data is old enough to be eligible
for writeout by the pdflush daemons. It is expressed in 100'ths of a second.
Data which has been dirty in-memory for longer than this interval will be
written out next time a pdflush daemon wakes up.
==============================================================
dirty_ratio
Contains, as a percentage of total system memory, the number of pages at which
a process which is generating disk writes will itself start writing out dirty
data.
==============================================================
dirty_writeback_centisecs
The pdflush writeback daemons will periodically wake up and write `old' data
out to disk. This tunable expresses the interval between those wakeups, in
100'ths of a second.
Setting this to zero disables periodic writeback altogether.
==============================================================
drop_caches
Writing to this will cause the kernel to drop clean caches, dentries and
inodes from memory, causing that memory to become free.
To free pagecache:
echo 1 > /proc/sys/vm/drop_caches
To free dentries and inodes:
echo 2 > /proc/sys/vm/drop_caches
To free pagecache, dentries and inodes:
echo 3 > /proc/sys/vm/drop_caches
As this is a non-destructive operation and dirty objects are not freeable, the
user should run `sync' first.
==============================================================
hugepages_treat_as_movable
This parameter is only useful when kernelcore= is specified at boot time to
create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
value written to hugepages_treat_as_movable allows huge pages to be allocated
from ZONE_MOVABLE.
Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
pages pool can easily grow or shrink within. Assuming that applications are
not running that mlock() a lot of memory, it is likely the huge pages pool
can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
into nr_hugepages and triggering page reclaim.
==============================================================
hugetlb_shm_group
hugetlb_shm_group contains group id that is allowed to create SysV
shared memory segment using hugetlb page.
==============================================================
laptop_mode
laptop_mode is a knob that controls "laptop mode". All the things that are
controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
==============================================================
legacy_va_layout
If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
will use the legacy (2.4) layout for all processes.
==============================================================
lowmem_reserve_ratio
For some specialised workloads on highmem machines it is dangerous for
the kernel to allow process memory to be allocated from the "lowmem"
zone. This is because that memory could then be pinned via the mlock()
system call, or by unavailability of swapspace.
And on large highmem machines this lack of reclaimable lowmem memory
can be fatal.
So the Linux page allocator has a mechanism which prevents allocations
which _could_ use highmem from using too much lowmem. This means that
a certain amount of lowmem is defended from the possibility of being
captured into pinned user memory.
(The same argument applies to the old 16 megabyte ISA DMA region. This
mechanism will also defend that region from allocations which could use
highmem or lowmem).
The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
in defending these lower zones.
If you have a machine which uses highmem or ISA DMA and your
applications are using mlock(), or if you are running with no swap then
you probably should change the lowmem_reserve_ratio setting.
The lowmem_reserve_ratio is an array. You can see them by reading this file.
-
% cat /proc/sys/vm/lowmem_reserve_ratio
256 256 32
-
Note: # of this elements is one fewer than number of zones. Because the highest
zone's value is not necessary for following calculation.
But, these values are not used directly. The kernel calculates # of protection
pages for each zones from them. These are shown as array of protection pages
in /proc/zoneinfo like followings. (This is an example of x86-64 box).
Each zone has an array of protection pages like this.
-
Node 0, zone DMA
pages free 1355
min 3
low 3
high 4
:
:
numa_other 0
protection: (0, 2004, 2004, 2004)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pagesets
cpu: 0 pcp: 0
:
-
These protections are added to score to judge whether this zone should be used
for page allocation or should be reclaimed.
In this example, if normal pages (index=2) are required to this DMA zone and
pages_high is used for watermark, the kernel judges this zone should not be
used because pages_free(1355) is smaller than watermark + protection[2]
(4 + 2004 = 2008). If this protection value is 0, this zone would be used for
normal page requirement. If requirement is DMA zone(index=0), protection[0]
(=0) is used.
zone[i]'s protection[j] is calculated by following expression.
(i < j):
zone[i]->protection[j]
= (total sums of present_pages from zone[i+1] to zone[j] on the node)
/ lowmem_reserve_ratio[i];
(i = j):
(should not be protected. = 0;
(i > j):
(not necessary, but looks 0)
The default values of lowmem_reserve_ratio[i] are
256 (if zone[i] means DMA or DMA32 zone)
32 (others).
As above expression, they are reciprocal number of ratio.
256 means 1/256. # of protection pages becomes about "0.39%" of total present
pages of higher zones on the node.
If you would like to protect more pages, smaller values are effective.
The minimum value is 1 (1/1 -> 100%).
==============================================================
@ -113,9 +275,9 @@ The default value is 65536.
min_free_kbytes:
This is used to force the Linux VM to keep a minimum number
This is used to force the Linux VM to keep a minimum number
of kilobytes free. The VM uses this number to compute a pages_min
value for each lowmem zone in the system. Each lowmem zone gets
value for each lowmem zone in the system. Each lowmem zone gets
a number of reserved free pages based proportionally on its size.
Some minimal amount of memory is needed to satisfy PF_MEMALLOC
@ -124,73 +286,6 @@ become subtly broken, and prone to deadlock under high loads.
Setting this too high will OOM your machine instantly.
==============================================================
percpu_pagelist_fraction
This is the fraction of pages at most (high mark pcp->high) 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. This entry only changes the value
of hot per cpu pagelists. User can specify a number like 100 to allocate
1/100th of each zone to each per cpu page list.
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)
The initial value is zero. Kernel does not use this value at boot time to set
the high water marks for each per cpu page list.
===============================================================
zone_reclaim_mode:
Zone_reclaim_mode allows someone to set more or less aggressive approaches to
reclaim memory when a zone runs out of memory. If it is set to zero then no
zone reclaim occurs. Allocations will be satisfied from other zones / nodes
in the system.
This is value ORed together of
1 = Zone reclaim on
2 = Zone reclaim writes dirty pages out
4 = Zone reclaim swaps pages
zone_reclaim_mode is set during bootup to 1 if it is determined that pages
from remote zones will cause a measurable performance reduction. The
page allocator will then reclaim easily reusable pages (those page
cache pages that are currently not used) before allocating off node pages.
It may be beneficial to switch off zone reclaim if the system is
used for a file server and all of memory should be used for caching files
from disk. In that case the caching effect is more important than
data locality.
Allowing zone reclaim to write out pages stops processes that are
writing large amounts of data from dirtying pages on other nodes. Zone
reclaim will write out dirty pages if a zone fills up and so effectively
throttle the process. This may decrease the performance of a single process
since it cannot use all of system memory to buffer the outgoing writes
anymore but it preserve the memory on other nodes so that the performance
of other processes running on other nodes will not be affected.
Allowing regular swap effectively restricts allocations to the local
node unless explicitly overridden by memory policies or cpuset
configurations.
=============================================================
min_unmapped_ratio:
This is available only on NUMA kernels.
A percentage of the total pages in each zone. Zone reclaim will only
occur if more than this percentage of pages are file backed and unmapped.
This is to insure that a minimal amount of local pages is still available for
file I/O even if the node is overallocated.
The default is 1 percent.
=============================================================
min_slab_ratio:
@ -211,69 +306,16 @@ and may not be fast.
=============================================================
panic_on_oom
min_unmapped_ratio:
This enables or disables panic on out-of-memory feature.
This is available only on NUMA kernels.
If this is set to 0, the kernel will kill some rogue process,
called oom_killer. Usually, oom_killer can kill rogue processes and
system will survive.
A percentage of the total pages in each zone. Zone reclaim will only
occur if more than this percentage of pages are file backed and unmapped.
This is to insure that a minimal amount of local pages is still available for
file I/O even if the node is overallocated.
If this is set to 1, the kernel panics when out-of-memory happens.
However, if a process limits using nodes by mempolicy/cpusets,
and those nodes become memory exhaustion status, one process
may be killed by oom-killer. No panic occurs in this case.
Because other nodes' memory may be free. This means system total status
may be not fatal yet.
If this is set to 2, the kernel panics compulsorily even on the
above-mentioned.
The default value is 0.
1 and 2 are for failover of clustering. Please select either
according to your policy of failover.
=============================================================
oom_dump_tasks
Enables a system-wide task dump (excluding kernel threads) to be
produced when the kernel performs an OOM-killing and includes such
information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and
name. This is helpful to determine why the OOM killer was invoked
and to identify the rogue task that caused it.
If this is set to zero, this information is suppressed. On very
large systems with thousands of tasks it may not be feasible to dump
the memory state information for each one. Such systems should not
be forced to incur a performance penalty in OOM conditions when the
information may not be desired.
If this is set to non-zero, this information is shown whenever the
OOM killer actually kills a memory-hogging task.
The default value is 0.
=============================================================
oom_kill_allocating_task
This enables or disables killing the OOM-triggering task in
out-of-memory situations.
If this is set to zero, the OOM killer will scan through the entire
tasklist and select a task based on heuristics to kill. This normally
selects a rogue memory-hogging task that frees up a large amount of
memory when killed.
If this is set to non-zero, the OOM killer simply kills the task that
triggered the out-of-memory condition. This avoids the expensive
tasklist scan.
If panic_on_oom is selected, it takes precedence over whatever value
is used in oom_kill_allocating_task.
The default value is 0.
The default is 1 percent.
==============================================================
@ -290,6 +332,50 @@ against future potential kernel bugs.
==============================================================
nr_hugepages
Change the minimum size of the hugepage pool.
See Documentation/vm/hugetlbpage.txt
==============================================================
nr_overcommit_hugepages
Change the maximum size of the hugepage pool. The maximum is
nr_hugepages + nr_overcommit_hugepages.
See Documentation/vm/hugetlbpage.txt
==============================================================
nr_pdflush_threads
The current number of pdflush threads. This value is read-only.
The value changes according to the number of dirty pages in the system.
When neccessary, additional pdflush threads are created, one per second, up to
nr_pdflush_threads_max.
==============================================================
nr_trim_pages
This is available only on NOMMU kernels.
This value adjusts the excess page trimming behaviour of power-of-2 aligned
NOMMU mmap allocations.
A value of 0 disables trimming of allocations entirely, while a value of 1
trims excess pages aggressively. Any value >= 1 acts as the watermark where
trimming of allocations is initiated.
The default value is 1.
See Documentation/nommu-mmap.txt for more information.
==============================================================
numa_zonelist_order
This sysctl is only for NUMA.
@ -335,34 +421,199 @@ this is causing problems for your system/application.
==============================================================
nr_hugepages
oom_dump_tasks
Change the minimum size of the hugepage pool.
Enables a system-wide task dump (excluding kernel threads) to be
produced when the kernel performs an OOM-killing and includes such
information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and
name. This is helpful to determine why the OOM killer was invoked
and to identify the rogue task that caused it.
See Documentation/vm/hugetlbpage.txt
If this is set to zero, this information is suppressed. On very
large systems with thousands of tasks it may not be feasible to dump
the memory state information for each one. Such systems should not
be forced to incur a performance penalty in OOM conditions when the
information may not be desired.
If this is set to non-zero, this information is shown whenever the
OOM killer actually kills a memory-hogging task.
The default value is 0.
==============================================================
nr_overcommit_hugepages
oom_kill_allocating_task
Change the maximum size of the hugepage pool. The maximum is
nr_hugepages + nr_overcommit_hugepages.
This enables or disables killing the OOM-triggering task in
out-of-memory situations.
See Documentation/vm/hugetlbpage.txt
If this is set to zero, the OOM killer will scan through the entire
tasklist and select a task based on heuristics to kill. This normally
selects a rogue memory-hogging task that frees up a large amount of
memory when killed.
If this is set to non-zero, the OOM killer simply kills the task that
triggered the out-of-memory condition. This avoids the expensive
tasklist scan.
If panic_on_oom is selected, it takes precedence over whatever value
is used in oom_kill_allocating_task.
The default value is 0.
==============================================================
nr_trim_pages
overcommit_memory:
This is available only on NOMMU kernels.
This value contains a flag that enables memory overcommitment.
This value adjusts the excess page trimming behaviour of power-of-2 aligned
NOMMU mmap allocations.
When this flag is 0, the kernel attempts to estimate the amount
of free memory left when userspace requests more memory.
A value of 0 disables trimming of allocations entirely, while a value of 1
trims excess pages aggressively. Any value >= 1 acts as the watermark where
trimming of allocations is initiated.
When this flag is 1, the kernel pretends there is always enough
memory until it actually runs out.
The default value is 1.
When this flag is 2, the kernel uses a "never overcommit"
policy that attempts to prevent any overcommit of memory.
See Documentation/nommu-mmap.txt for more information.
This feature can be very useful because there are a lot of
programs that malloc() huge amounts of memory "just-in-case"
and don't use much of it.
The default value is 0.
See Documentation/vm/overcommit-accounting and
security/commoncap.c::cap_vm_enough_memory() for more information.
==============================================================
overcommit_ratio:
When overcommit_memory is set to 2, the committed address
space is not permitted to exceed swap plus this percentage
of physical RAM. See above.
==============================================================
page-cluster
page-cluster controls the number of pages which are written to swap in
a single attempt. The swap I/O size.
It is a logarithmic value - setting it to zero means "1 page", setting
it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
The default value is three (eight pages at a time). There may be some
small benefits in tuning this to a different value if your workload is
swap-intensive.
=============================================================
panic_on_oom
This enables or disables panic on out-of-memory feature.
If this is set to 0, the kernel will kill some rogue process,
called oom_killer. Usually, oom_killer can kill rogue processes and
system will survive.
If this is set to 1, the kernel panics when out-of-memory happens.
However, if a process limits using nodes by mempolicy/cpusets,
and those nodes become memory exhaustion status, one process
may be killed by oom-killer. No panic occurs in this case.
Because other nodes' memory may be free. This means system total status
may be not fatal yet.
If this is set to 2, the kernel panics compulsorily even on the
above-mentioned.
The default value is 0.
1 and 2 are for failover of clustering. Please select either
according to your policy of failover.
=============================================================
percpu_pagelist_fraction
This is the fraction of pages at most (high mark pcp->high) 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. This entry only changes the value
of hot per cpu pagelists. User can specify a number like 100 to allocate
1/100th of each zone to each per cpu page list.
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)
The initial value is zero. Kernel does not use this value at boot time to set
the high water marks for each per cpu page list.
==============================================================
stat_interval
The time interval between which vm statistics are updated. The default
is 1 second.
==============================================================
swappiness
This control is used to define how aggressive the kernel will swap
memory pages. Higher values will increase agressiveness, lower values
descrease the amount of swap.
The default value is 60.
==============================================================
vfs_cache_pressure
------------------
Controls the tendency of the kernel to reclaim the memory which is used for
caching of directory and inode objects.
At the default value of vfs_cache_pressure=100 the kernel will attempt to
reclaim dentries and inodes at a "fair" rate with respect to pagecache and
swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer
to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100
causes the kernel to prefer to reclaim dentries and inodes.
==============================================================
zone_reclaim_mode:
Zone_reclaim_mode allows someone to set more or less aggressive approaches to
reclaim memory when a zone runs out of memory. If it is set to zero then no
zone reclaim occurs. Allocations will be satisfied from other zones / nodes
in the system.
This is value ORed together of
1 = Zone reclaim on
2 = Zone reclaim writes dirty pages out
4 = Zone reclaim swaps pages
zone_reclaim_mode is set during bootup to 1 if it is determined that pages
from remote zones will cause a measurable performance reduction. The
page allocator will then reclaim easily reusable pages (those page
cache pages that are currently not used) before allocating off node pages.
It may be beneficial to switch off zone reclaim if the system is
used for a file server and all of memory should be used for caching files
from disk. In that case the caching effect is more important than
data locality.
Allowing zone reclaim to write out pages stops processes that are
writing large amounts of data from dirtying pages on other nodes. Zone
reclaim will write out dirty pages if a zone fills up and so effectively
throttle the process. This may decrease the performance of a single process
since it cannot use all of system memory to buffer the outgoing writes
anymore but it preserve the memory on other nodes so that the performance
of other processes running on other nodes will not be affected.
Allowing regular swap effectively restricts allocations to the local
node unless explicitly overridden by memory policies or cpuset
configurations.
============ End of Document =================================

19
Documentation/sysrq.txt
View file

@ -1,6 +1,5 @@
Linux Magic System Request Key Hacks
Documentation for sysrq.c
Last update: 2007-AUG-04
* What is the magic SysRq key?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@ -211,6 +210,24 @@ within a function called by handle_sysrq, you must be aware that you are in
a lock (you are also in an interrupt handler, which means don't sleep!), so
you must call __handle_sysrq_nolock instead.
* When I hit a SysRq key combination only the header appears on the console?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Sysrq output is subject to the same console loglevel control as all
other console output. This means that if the kernel was booted 'quiet'
as is common on distro kernels the output may not appear on the actual
console, even though it will appear in the dmesg buffer, and be accessible
via the dmesg command and to the consumers of /proc/kmsg. As a specific
exception the header line from the sysrq command is passed to all console
consumers as if the current loglevel was maximum. If only the header
is emitted it is almost certain that the kernel loglevel is too low.
Should you require the output on the console channel then you will need
to temporarily up the console loglevel using alt-sysrq-8 or:
echo 8 > /proc/sysrq-trigger
Remember to return the loglevel to normal after triggering the sysrq
command you are interested in.
* I have more questions, who can I ask?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
And I'll answer any questions about the registration system you got, also

19
MAINTAINERS
View file

@ -1581,6 +1581,13 @@ L: bluesmoke-devel@lists.sourceforge.net
W: bluesmoke.sourceforge.net
S: Maintained
EDAC-I5400
P: Mauro Carvalho Chehab
M: mchehab@redhat.com
L: bluesmoke-devel@lists.sourceforge.net
W: bluesmoke.sourceforge.net
S: Maintained
EDAC-I82975X
P: Ranganathan Desikan
P: Arvind R.
@ -1814,6 +1821,14 @@ M: hch@infradead.org
W: ftp://ftp.openlinux.org/pub/people/hch/vxfs
S: Maintained
FREEZER
P: Pavel Machek
M: pavel@suse.cz
P: Rafael J. Wysocki
M: rjw@sisk.pl
L: linux-pm@lists.linux-foundation.org
S: Supported
FTRACE
P: Steven Rostedt
M: rostedt@goodmis.org
@ -4842,11 +4857,11 @@ S: Supported
XFS FILESYSTEM
P: Silicon Graphics Inc
P: Tim Shimmin
P: Bill O'Donnell
M: xfs-masters@oss.sgi.com
L: xfs@oss.sgi.com
W: http://oss.sgi.com/projects/xfs
T: git git://oss.sgi.com:8090/xfs/xfs-2.6.git
T: git://oss.sgi.com/xfs/xfs.git
S: Supported
XILINX SYSTEMACE DRIVER

2
Makefile
View file

@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 29
EXTRAVERSION = -rc1
EXTRAVERSION = -rc2
NAME = Erotic Pickled Herring
# *DOCUMENTATION*

3
arch/Kconfig
View file

@ -62,6 +62,9 @@ config HAVE_EFFICIENT_UNALIGNED_ACCESS
See Documentation/unaligned-memory-access.txt for more
information on the topic of unaligned memory accesses.
config HAVE_SYSCALL_WRAPPERS
bool
config KRETPROBES
def_bool y
depends on KPROBES && HAVE_KRETPROBES

1
arch/alpha/include/asm/Kbuild
View file

@ -9,4 +9,3 @@ unifdef-y += console.h
unifdef-y += fpu.h
unifdef-y += sysinfo.h
unifdef-y += compiler.h
unifdef-y += swab.h

1
arch/alpha/include/asm/byteorder.h
View file

@ -1,7 +1,6 @@
#ifndef _ALPHA_BYTEORDER_H
#define _ALPHA_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/little_endian.h>
#endif /* _ALPHA_BYTEORDER_H */

4
arch/alpha/include/asm/machvec.h
View file

@ -21,6 +21,7 @@ struct pci_dev;
struct pci_ops;
struct pci_controller;
struct _alpha_agp_info;
struct rtc_time;
struct alpha_machine_vector
{
@ -94,6 +95,9 @@ struct alpha_machine_vector
struct _alpha_agp_info *(*agp_info)(void);
unsigned int (*rtc_get_time)(struct rtc_time *);
int (*rtc_set_time)(struct rtc_time *);
const char *vector_name;
/* NUMA information */

7
arch/alpha/include/asm/pgalloc.h
View file

@ -50,7 +50,12 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd)
free_page((unsigned long)pmd);
}
extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
static inline pte_t *
pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
return pte;
}
static inline void
pte_free_kernel(struct mm_struct *mm, pte_t *pte)

12
arch/alpha/include/asm/rtc.h
View file

@ -1,9 +1,15 @@
#ifndef _ALPHA_RTC_H
#define _ALPHA_RTC_H
/*
* Alpha uses the default access methods for the RTC.
*/
#if defined(CONFIG_ALPHA_GENERIC)
# define get_rtc_time alpha_mv.rtc_get_time
# define set_rtc_time alpha_mv.rtc_set_time
#else
# if defined(CONFIG_ALPHA_MARVEL) && defined(CONFIG_SMP)
# define get_rtc_time marvel_get_rtc_time
# define set_rtc_time marvel_set_rtc_time
# endif
#endif
#include <asm-generic/rtc.h>

1
arch/alpha/kernel/.gitignore vendored Normal file
View file

@ -0,0 +1 @@
vmlinux.lds

10
arch/alpha/kernel/core_marvel.c
View file

@ -658,16 +658,8 @@ __marvel_rtc_io(u8 b, unsigned long addr, int write)
rtc_access.data = bcd2bin(b);
rtc_access.function = 0x48 + !write; /* GET/PUT_TOY */
#ifdef CONFIG_SMP
if (smp_processor_id() != boot_cpuid)
smp_call_function_single(boot_cpuid,
__marvel_access_rtc,
&rtc_access, 1);
else
__marvel_access_rtc(&rtc_access);
#else
__marvel_access_rtc(&rtc_access);
#endif
ret = bin2bcd(rtc_access.data);
break;

8
arch/alpha/kernel/entry.S
View file

@ -896,9 +896,9 @@ sys_getxpid:
.end sys_getxpid
.align 4
.globl sys_pipe
.ent sys_pipe
sys_pipe:
.globl sys_alpha_pipe
.ent sys_alpha_pipe
sys_alpha_pipe:
lda $sp, -16($sp)
stq $26, 0($sp)
.prologue 0
@ -916,7 +916,7 @@ sys_pipe:
stq $1, 80+16($sp)
1: lda $sp, 16($sp)
ret
.end sys_pipe
.end sys_alpha_pipe
.align 4
.globl sys_execve

2
arch/alpha/kernel/irq_srm.c
View file

@ -63,6 +63,8 @@ init_srm_irqs(long max, unsigned long ignore_mask)
{
long i;
if (NR_IRQS <= 16)
return;
for (i = 16; i < max; ++i) {
if (i < 64 && ((ignore_mask >> i) & 1))
continue;

5
arch/alpha/kernel/machvec_impl.h
View file

@ -40,7 +40,10 @@
#define CAT1(x,y) x##y
#define CAT(x,y) CAT1(x,y)
#define DO_DEFAULT_RTC .rtc_port = 0x70
#define DO_DEFAULT_RTC \
.rtc_port = 0x70, \
.rtc_get_time = common_get_rtc_time, \
.rtc_set_time = common_set_rtc_time
#define DO_EV4_MMU \
.max_asn = EV4_MAX_ASN, \

2
arch/alpha/kernel/proto.h
View file

@ -145,6 +145,8 @@ extern void smp_percpu_timer_interrupt(struct pt_regs *);
extern irqreturn_t timer_interrupt(int irq, void *dev);
extern void common_init_rtc(void);
extern unsigned long est_cycle_freq;
extern unsigned int common_get_rtc_time(struct rtc_time *time);
extern int common_set_rtc_time(struct rtc_time *time);
/* smc37c93x.c */
extern void SMC93x_Init(void);

2
arch/alpha/kernel/sys_jensen.c
View file

@ -261,6 +261,8 @@ struct alpha_machine_vector jensen_mv __initmv = {
.machine_check = jensen_machine_check,
.max_isa_dma_address = ALPHA_MAX_ISA_DMA_ADDRESS,
.rtc_port = 0x170,
.rtc_get_time = common_get_rtc_time,
.rtc_set_time = common_set_rtc_time,
.nr_irqs = 16,
.device_interrupt = jensen_device_interrupt,

56
arch/alpha/kernel/sys_marvel.c
View file

@ -23,6 +23,7 @@
#include <asm/hwrpb.h>
#include <asm/tlbflush.h>
#include <asm/vga.h>
#include <asm/rtc.h>
#include "proto.h"
#include "err_impl.h"
@ -426,6 +427,57 @@ marvel_init_rtc(void)
init_rtc_irq();
}
struct marvel_rtc_time {
struct rtc_time *time;
int retval;
};
#ifdef CONFIG_SMP
static void
smp_get_rtc_time(void *data)
{
struct marvel_rtc_time *mrt = data;
mrt->retval = __get_rtc_time(mrt->time);
}
static void
smp_set_rtc_time(void *data)
{
struct marvel_rtc_time *mrt = data;
mrt->retval = __set_rtc_time(mrt->time);
}
#endif
static unsigned int
marvel_get_rtc_time(struct rtc_time *time)
{
#ifdef CONFIG_SMP
struct marvel_rtc_time mrt;
if (smp_processor_id() != boot_cpuid) {
mrt.time = time;
smp_call_function_single(boot_cpuid, smp_get_rtc_time, &mrt, 1);
return mrt.retval;
}
#endif
return __get_rtc_time(time);
}
static int
marvel_set_rtc_time(struct rtc_time *time)
{
#ifdef CONFIG_SMP
struct marvel_rtc_time mrt;
if (smp_processor_id() != boot_cpuid) {
mrt.time = time;
smp_call_function_single(boot_cpuid, smp_set_rtc_time, &mrt, 1);
return mrt.retval;
}
#endif
return __set_rtc_time(time);
}
static void
marvel_smp_callin(void)
{
@ -466,7 +518,9 @@ marvel_smp_callin(void)
struct alpha_machine_vector marvel_ev7_mv __initmv = {
.vector_name = "MARVEL/EV7",
DO_EV7_MMU,
DO_DEFAULT_RTC,
.rtc_port = 0x70,
.rtc_get_time = marvel_get_rtc_time,
.rtc_set_time = marvel_set_rtc_time,
DO_MARVEL_IO,
.machine_check = marvel_machine_check,
.max_isa_dma_address = ALPHA_MAX_ISA_DMA_ADDRESS,

4
arch/alpha/kernel/sys_nautilus.c
View file

@ -245,6 +245,10 @@ nautilus_init_pci(void)
IRONGATE0->pci_mem = pci_mem;
pci_bus_assign_resources(bus);
/* pci_common_swizzle() relies on bus->self being NULL
for the root bus, so just clear it. */
bus->self = NULL;
pci_fixup_irqs(alpha_mv.pci_swizzle, alpha_mv.pci_map_irq);
}

2
arch/alpha/kernel/systbls.S
View file

@ -52,7 +52,7 @@ sys_call_table:
.quad sys_setpgid
.quad alpha_ni_syscall /* 40 */
.quad sys_dup
.quad sys_pipe
.quad sys_alpha_pipe
.quad osf_set_program_attributes
.quad alpha_ni_syscall
.quad sys_open /* 45 */

10
arch/alpha/kernel/time.c
View file

@ -46,6 +46,7 @@
#include <asm/io.h>
#include <asm/hwrpb.h>
#include <asm/8253pit.h>
#include <asm/rtc.h>
#include <linux/mc146818rtc.h>
#include <linux/time.h>
@ -180,6 +181,15 @@ common_init_rtc(void)
init_rtc_irq();
}
unsigned int common_get_rtc_time(struct rtc_time *time)
{
return __get_rtc_time(time);
}
int common_set_rtc_time(struct rtc_time *time)
{
return __set_rtc_time(time);
}
/* Validate a computed cycle counter result against the known bounds for
the given processor core. There's too much brokenness in the way of

7
arch/alpha/mm/init.c
View file

@ -59,13 +59,6 @@ pgd_alloc(struct mm_struct *mm)
return ret;
}
pte_t *
pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
return pte;
}
/*
* BAD_PAGE is the page that is used for page faults when linux

1
arch/arm/include/asm/Kbuild
View file

@ -1,4 +1,3 @@
include include/asm-generic/Kbuild.asm
unifdef-y += hwcap.h
unifdef-y += swab.h

2
arch/arm/include/asm/byteorder.h
View file

@ -15,8 +15,6 @@
#ifndef __ASM_ARM_BYTEORDER_H
#define __ASM_ARM_BYTEORDER_H
#include <asm/swab.h>
#ifdef __ARMEB__
#include <linux/byteorder/big_endian.h>
#else

2
arch/arm/kernel/calls.S
View file

@ -98,7 +98,7 @@
CALL(sys_uselib)
CALL(sys_swapon)
CALL(sys_reboot)
CALL(OBSOLETE(old_readdir)) /* used by libc4 */
CALL(OBSOLETE(sys_old_readdir)) /* used by libc4 */
/* 90 */ CALL(OBSOLETE(old_mmap)) /* used by libc4 */
CALL(sys_munmap)
CALL(sys_truncate)

1
arch/avr32/include/asm/Kbuild
View file

@ -1,4 +1,3 @@
include include/asm-generic/Kbuild.asm
header-y += swab.h
header-y += cachectl.h

1
arch/avr32/include/asm/byteorder.h
View file

@ -4,7 +4,6 @@
#ifndef __ASM_AVR32_BYTEORDER_H
#define __ASM_AVR32_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/big_endian.h>
#endif /* __ASM_AVR32_BYTEORDER_H */

1
arch/blackfin/include/asm/Kbuild
View file

@ -1,4 +1,3 @@
include include/asm-generic/Kbuild.asm
unifdef-y += fixed_code.h
unifdef-y += swab.h

1
arch/blackfin/include/asm/byteorder.h
View file

@ -1,7 +1,6 @@
#ifndef _BLACKFIN_BYTEORDER_H
#define _BLACKFIN_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/little_endian.h>
#endif /* _BLACKFIN_BYTEORDER_H */

2
arch/cris/arch-v10/kernel/entry.S
View file

@ -691,7 +691,7 @@ sys_call_table:
.long sys_uselib
.long sys_swapon
.long sys_reboot
.long old_readdir
.long sys_old_readdir
.long old_mmap /* 90 */
.long sys_munmap
.long sys_truncate

2
arch/cris/arch-v32/kernel/entry.S
View file

@ -614,7 +614,7 @@ sys_call_table:
.long sys_uselib
.long sys_swapon
.long sys_reboot
.long old_readdir
.long sys_old_readdir
.long old_mmap /* 90 */
.long sys_munmap
.long sys_truncate

16
arch/cris/include/arch-v10/arch/byteorder.h → arch/cris/include/arch-v10/arch/swab.h
View file

@ -1,26 +1,30 @@
#ifndef _CRIS_ARCH_BYTEORDER_H
#define _CRIS_ARCH_BYTEORDER_H
#ifndef _CRIS_ARCH_SWAB_H
#define _CRIS_ARCH_SWAB_H
#include <asm/types.h>
#include <linux/compiler.h>
#define __SWAB_64_THRU_32__
/* we just define these two (as we can do the swap in a single
* asm instruction in CRIS) and the arch-independent files will put
* them together into ntohl etc.
*/
static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
{
__asm__ ("swapwb %0" : "=r" (x) : "0" (x));
return(x);
}
#define __arch_swab32 __arch_swab32
static inline __attribute_const__ __u16 ___arch__swab16(__u16 x)
static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
{
__asm__ ("swapb %0" : "=r" (x) : "0" (x));
return(x);
}
#define __arch_swab16 __arch_swab16
#endif

20
arch/cris/include/arch-v32/arch/byteorder.h
View file

@ -1,20 +0,0 @@
#ifndef _ASM_CRIS_ARCH_BYTEORDER_H
#define _ASM_CRIS_ARCH_BYTEORDER_H
#include <asm/types.h>
static inline __const__ __u32
___arch__swab32(__u32 x)
{
__asm__ __volatile__ ("swapwb %0" : "=r" (x) : "0" (x));
return (x);
}
static inline __const__ __u16
___arch__swab16(__u16 x)
{
__asm__ __volatile__ ("swapb %0" : "=r" (x) : "0" (x));
return (x);
}
#endif /* _ASM_CRIS_ARCH_BYTEORDER_H */

24
arch/cris/include/arch-v32/arch/swab.h Normal file
View file

@ -0,0 +1,24 @@
#ifndef _ASM_CRIS_ARCH_SWAB_H
#define _ASM_CRIS_ARCH_SWAB_H
#include <asm/types.h>
#define __SWAB_64_THRU_32__
static inline __const__ __u32
__arch_swab32(__u32 x)
{
__asm__ __volatile__ ("swapwb %0" : "=r" (x) : "0" (x));
return (x);
}
#define __arch_swab32 __arch_swab32
static inline __const__ __u16
__arch_swab16(__u16 x)
{
__asm__ __volatile__ ("swapb %0" : "=r" (x) : "0" (x));
return (x);
}
#define __arch_swab16 __arch_swab16
#endif /* _ASM_CRIS_ARCH_SWAB_H */

19
arch/cris/include/asm/byteorder.h
View file

@ -1,25 +1,6 @@
#ifndef _CRIS_BYTEORDER_H
#define _CRIS_BYTEORDER_H
#ifdef __GNUC__
#ifdef __KERNEL__
#include <arch/byteorder.h>
/* defines are necessary because the other files detect the presence
* of a defined __arch_swab32, not an inline
*/
#define __arch__swab32(x) ___arch__swab32(x)
#define __arch__swab16(x) ___arch__swab16(x)
#endif /* __KERNEL__ */
#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
# define __BYTEORDER_HAS_U64__
# define __SWAB_64_THRU_32__
#endif
#endif /* __GNUC__ */
#include <linux/byteorder/little_endian.h>
#endif

8
arch/cris/include/asm/swab.h Normal file
View file

@ -0,0 +1,8 @@
#ifndef _CRIS_SWAB_H
#define _CRIS_SWAB_H
#ifdef __KERNEL__
#include <arch/swab.h>
#endif /* __KERNEL__ */
#endif /* _CRIS_SWAB_H */

1
arch/h8300/include/asm/Kbuild
View file

@ -1,2 +1 @@
include include/asm-generic/Kbuild.asm
unifdef-y += swab.h

1
arch/h8300/include/asm/byteorder.h
View file

@ -1,7 +1,6 @@
#ifndef _H8300_BYTEORDER_H
#define _H8300_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/big_endian.h>
#endif /* _H8300_BYTEORDER_H */

2
arch/h8300/kernel/syscalls.S
View file

@ -103,7 +103,7 @@ SYMBOL_NAME_LABEL(sys_call_table)
.long SYMBOL_NAME(sys_uselib)
.long SYMBOL_NAME(sys_swapon)
.long SYMBOL_NAME(sys_reboot)
.long SYMBOL_NAME(old_readdir)
.long SYMBOL_NAME(sys_old_readdir)
.long SYMBOL_NAME(old_mmap) /* 90 */
.long SYMBOL_NAME(sys_munmap)
.long SYMBOL_NAME(sys_truncate)

1
arch/ia64/Kconfig
View file

@ -17,6 +17,7 @@ config IA64
select ACPI if (!IA64_HP_SIM)
select PM if (!IA64_HP_SIM)
select ARCH_SUPPORTS_MSI
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_IDE
select HAVE_OPROFILE
select HAVE_KPROBES

2
arch/ia64/configs/generic_defconfig
View file

@ -578,7 +578,7 @@ CONFIG_ATA_PIIX=y
# CONFIG_SATA_SIS is not set
# CONFIG_SATA_ULI is not set
# CONFIG_SATA_VIA is not set
# CONFIG_SATA_VITESSE is not set
CONFIG_SATA_VITESSE=y
# CONFIG_SATA_INIC162X is not set
# CONFIG_PATA_ACPI is not set
# CONFIG_PATA_ALI is not set

2
arch/ia64/ia32/ia32_entry.S
View file

@ -220,7 +220,7 @@ ia32_syscall_table:
data8 sys_mkdir
data8 sys_rmdir /* 40 */
data8 sys_dup
data8 sys_pipe
data8 sys_ia64_pipe
data8 compat_sys_times
data8 sys_ni_syscall /* old prof syscall holder */
data8 sys32_brk /* 45 */

1
arch/ia64/include/asm/Kbuild
View file

@ -14,4 +14,3 @@ unifdef-y += gcc_intrin.h
unifdef-y += intrinsics.h
unifdef-y += perfmon.h
unifdef-y += ustack.h
unifdef-y += swab.h

1
arch/ia64/include/asm/byteorder.h
View file

@ -1,7 +1,6 @@
#ifndef _ASM_IA64_BYTEORDER_H
#define _ASM_IA64_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/little_endian.h>
#endif /* _ASM_IA64_BYTEORDER_H */

2
arch/ia64/include/asm/dma-mapping.h
View file

@ -9,6 +9,8 @@
#include <linux/scatterlist.h>
#include <asm/swiotlb.h>
#define ARCH_HAS_DMA_GET_REQUIRED_MASK
struct dma_mapping_ops {
int (*mapping_error)(struct device *dev,
dma_addr_t dma_addr);

7
arch/ia64/include/asm/machvec.h
View file

@ -62,6 +62,7 @@ typedef dma_addr_t ia64_mv_dma_map_single_attrs (struct device *, void *, size_t
typedef void ia64_mv_dma_unmap_single_attrs (struct device *, dma_addr_t, size_t, int, struct dma_attrs *);
typedef int ia64_mv_dma_map_sg_attrs (struct device *, struct scatterlist *, int, int, struct dma_attrs *);
typedef void ia64_mv_dma_unmap_sg_attrs (struct device *, struct scatterlist *, int, int, struct dma_attrs *);
typedef u64 ia64_mv_dma_get_required_mask (struct device *);
/*
* WARNING: The legacy I/O space is _architected_. Platforms are
@ -159,6 +160,7 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
# define platform_dma_sync_sg_for_device ia64_mv.dma_sync_sg_for_device
# define platform_dma_mapping_error ia64_mv.dma_mapping_error
# define platform_dma_supported ia64_mv.dma_supported
# define platform_dma_get_required_mask ia64_mv.dma_get_required_mask
# define platform_irq_to_vector ia64_mv.irq_to_vector
# define platform_local_vector_to_irq ia64_mv.local_vector_to_irq
# define platform_pci_get_legacy_mem ia64_mv.pci_get_legacy_mem
@ -213,6 +215,7 @@ struct ia64_machine_vector {
ia64_mv_dma_sync_sg_for_device *dma_sync_sg_for_device;
ia64_mv_dma_mapping_error *dma_mapping_error;
ia64_mv_dma_supported *dma_supported;
ia64_mv_dma_get_required_mask *dma_get_required_mask;
ia64_mv_irq_to_vector *irq_to_vector;
ia64_mv_local_vector_to_irq *local_vector_to_irq;
ia64_mv_pci_get_legacy_mem_t *pci_get_legacy_mem;
@ -263,6 +266,7 @@ struct ia64_machine_vector {
platform_dma_sync_sg_for_device, \
platform_dma_mapping_error, \
platform_dma_supported, \
platform_dma_get_required_mask, \
platform_irq_to_vector, \
platform_local_vector_to_irq, \
platform_pci_get_legacy_mem, \
@ -366,6 +370,9 @@ extern void machvec_init_from_cmdline(const char *cmdline);
#ifndef platform_dma_supported
# define platform_dma_supported swiotlb_dma_supported
#endif
#ifndef platform_dma_get_required_mask
# define platform_dma_get_required_mask ia64_dma_get_required_mask
#endif
#ifndef platform_irq_to_vector
# define platform_irq_to_vector __ia64_irq_to_vector
#endif

1
arch/ia64/include/asm/machvec_init.h
View file

@ -3,6 +3,7 @@
extern ia64_mv_send_ipi_t ia64_send_ipi;
extern ia64_mv_global_tlb_purge_t ia64_global_tlb_purge;
extern ia64_mv_dma_get_required_mask ia64_dma_get_required_mask;
extern ia64_mv_irq_to_vector __ia64_irq_to_vector;
extern ia64_mv_local_vector_to_irq __ia64_local_vector_to_irq;
extern ia64_mv_pci_get_legacy_mem_t ia64_pci_get_legacy_mem;

2
arch/ia64/include/asm/machvec_sn2.h
View file

@ -67,6 +67,7 @@ extern ia64_mv_dma_sync_single_for_device sn_dma_sync_single_for_device;
extern ia64_mv_dma_sync_sg_for_device sn_dma_sync_sg_for_device;
extern ia64_mv_dma_mapping_error sn_dma_mapping_error;
extern ia64_mv_dma_supported sn_dma_supported;
extern ia64_mv_dma_get_required_mask sn_dma_get_required_mask;
extern ia64_mv_migrate_t sn_migrate;
extern ia64_mv_kernel_launch_event_t sn_kernel_launch_event;
extern ia64_mv_setup_msi_irq_t sn_setup_msi_irq;
@ -123,6 +124,7 @@ extern ia64_mv_pci_fixup_bus_t sn_pci_fixup_bus;
#define platform_dma_sync_sg_for_device sn_dma_sync_sg_for_device
#define platform_dma_mapping_error sn_dma_mapping_error
#define platform_dma_supported sn_dma_supported
#define platform_dma_get_required_mask sn_dma_get_required_mask
#define platform_migrate sn_migrate
#define platform_kernel_launch_event sn_kernel_launch_event
#ifdef CONFIG_PCI_MSI

2
arch/ia64/include/asm/unistd.h
View file

@ -364,7 +364,7 @@ struct pt_regs;
struct sigaction;
long sys_execve(char __user *filename, char __user * __user *argv,
char __user * __user *envp, struct pt_regs *regs);
asmlinkage long sys_pipe(void);
asmlinkage long sys_ia64_pipe(void);
asmlinkage long sys_rt_sigaction(int sig,
const struct sigaction __user *act,
struct sigaction __user *oact,

2
arch/ia64/kernel/entry.S
View file

@ -1442,7 +1442,7 @@ sys_call_table:
data8 sys_mkdir // 1055
data8 sys_rmdir
data8 sys_dup
data8 sys_pipe
data8 sys_ia64_pipe
data8 sys_times
data8 ia64_brk // 1060
data8 sys_setgid

2
arch/ia64/kernel/kprobes.c
View file

@ -870,7 +870,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
return 1;
ss_probe:
#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM)
#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
/* Boost up -- we can execute copied instructions directly */
ia64_psr(regs)->ri = p->ainsn.slot;

2
arch/ia64/kernel/sys_ia64.c
View file

@ -154,7 +154,7 @@ out:
* and r9) as this is faster than doing a copy_to_user().
*/
asmlinkage long
sys_pipe (void)
sys_ia64_pipe (void)
{
struct pt_regs *regs = task_pt_regs(current);
int fd[2];

6
arch/ia64/kernel/unaligned.c
View file

@ -59,6 +59,7 @@ dump (const char *str, void *vp, size_t len)
* (i.e. don't allow attacker to fill up logs with unaligned accesses).
*/
int no_unaligned_warning;
int unaligned_dump_stack;
static int noprint_warning;
/*
@ -1371,9 +1372,12 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
}
}
} else {
if (within_logging_rate_limit())
if (within_logging_rate_limit()) {
printk(KERN_WARNING "kernel unaligned access to 0x%016lx, ip=0x%016lx\n",
ifa, regs->cr_iip + ipsr->ri);
if (unaligned_dump_stack)
dump_stack();
}
set_fs(KERNEL_DS);
}

27
arch/ia64/pci/pci.c
View file

@ -19,6 +19,7 @@
#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/bootmem.h>
#include <asm/machvec.h>
#include <asm/page.h>
@ -748,6 +749,32 @@ static void __init set_pci_cacheline_size(void)
pci_cache_line_size = (1 << cci.pcci_line_size) / 4;
}
u64 ia64_dma_get_required_mask(struct device *dev)
{
u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
u64 mask;
if (!high_totalram) {
/* convert to mask just covering totalram */
low_totalram = (1 << (fls(low_totalram) - 1));
low_totalram += low_totalram - 1;
mask = low_totalram;
} else {
high_totalram = (1 << (fls(high_totalram) - 1));
high_totalram += high_totalram - 1;
mask = (((u64)high_totalram) << 32) + 0xffffffff;
}
return mask;
}
EXPORT_SYMBOL_GPL(ia64_dma_get_required_mask);
u64 dma_get_required_mask(struct device *dev)
{
return platform_dma_get_required_mask(dev);
}
EXPORT_SYMBOL_GPL(dma_get_required_mask);
static int __init pcibios_init(void)
{
set_pci_cacheline_size();

6
arch/ia64/sn/pci/pci_dma.c
View file

@ -356,6 +356,12 @@ int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
}
EXPORT_SYMBOL(sn_dma_mapping_error);
u64 sn_dma_get_required_mask(struct device *dev)
{
return DMA_64BIT_MASK;
}
EXPORT_SYMBOL_GPL(sn_dma_get_required_mask);
char *sn_pci_get_legacy_mem(struct pci_bus *bus)
{
if (!SN_PCIBUS_BUSSOFT(bus))

4
arch/ia64/xen/time.c
View file

@ -129,8 +129,8 @@ consider_steal_time(unsigned long new_itm)
blocked = stolentick;
if (stolen > 0 || blocked > 0) {
account_steal_time(NULL, jiffies_to_cputime(stolen));
account_steal_time(idle_task(cpu), jiffies_to_cputime(blocked));
account_steal_ticks(stolen);
account_idle_ticks(blocked);
run_local_timers();
if (rcu_pending(cpu))

2
arch/m68k/kernel/entry.S
View file

@ -513,7 +513,7 @@ sys_call_table:
.long sys_uselib
.long sys_swapon
.long sys_reboot
.long old_readdir
.long sys_old_readdir
.long old_mmap /* 90 */
.long sys_munmap
.long sys_truncate

2
arch/m68knommu/include/asm/Kbuild
View file

@ -1,3 +1 @@
include include/asm-generic/Kbuild.asm
unifdef-y += swab.h

1
arch/m68knommu/include/asm/byteorder.h
View file

@ -1,7 +1,6 @@
#ifndef _M68KNOMMU_BYTEORDER_H
#define _M68KNOMMU_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/big_endian.h>
#endif /* _M68KNOMMU_BYTEORDER_H */

2
arch/m68knommu/kernel/syscalltable.S
View file

@ -107,7 +107,7 @@ ENTRY(sys_call_table)
.long sys_uselib
.long sys_ni_syscall /* sys_swapon */
.long sys_reboot
.long old_readdir
.long sys_old_readdir
.long old_mmap /* 90 */
.long sys_munmap
.long sys_truncate

1
arch/mips/include/asm/Kbuild
View file

@ -1,4 +1,3 @@
include include/asm-generic/Kbuild.asm
header-y += cachectl.h sgidefs.h sysmips.h
header-y += swab.h

2
arch/mips/include/asm/byteorder.h
View file

@ -8,8 +8,6 @@
#ifndef _ASM_BYTEORDER_H
#define _ASM_BYTEORDER_H
#include <asm/swab.h>
#if defined(__MIPSEB__)
#include <linux/byteorder/big_endian.h>
#elif defined(__MIPSEL__)

2
arch/mips/kernel/scall32-o32.S
View file

@ -398,7 +398,7 @@ einval: li v0, -ENOSYS
sys sys_uselib 1
sys sys_swapon 2
sys sys_reboot 3
sys old_readdir 3
sys sys_old_readdir 3
sys old_mmap 6 /* 4090 */
sys sys_munmap 2
sys sys_truncate 2

2
arch/mn10300/kernel/entry.S
View file

@ -478,7 +478,7 @@ ENTRY(sys_call_table)
.long sys_uselib
.long sys_swapon
.long sys_reboot
.long old_readdir
.long sys_old_readdir
.long old_mmap /* 90 */
.long sys_munmap
.long sys_truncate

1
arch/parisc/include/asm/Kbuild
View file

@ -1,4 +1,3 @@
include include/asm-generic/Kbuild.asm
unifdef-y += pdc.h
unifdef-y += swab.h

1
arch/parisc/include/asm/byteorder.h
View file

@ -1,7 +1,6 @@
#ifndef _PARISC_BYTEORDER_H
#define _PARISC_BYTEORDER_H
#include <asm/swab.h>
#include <linux/byteorder/big_endian.h>
#endif /* _PARISC_BYTEORDER_H */

1
arch/powerpc/Kconfig
View file

@ -123,6 +123,7 @@ config PPC
select HAVE_DMA_ATTRS if PPC64
select USE_GENERIC_SMP_HELPERS if SMP
select HAVE_OPROFILE
select HAVE_SYSCALL_WRAPPERS if PPC64
config EARLY_PRINTK
bool

4
arch/powerpc/boot/dts/mpc8315erdb.dts
View file

@ -255,7 +255,7 @@
device_type = "serial";
compatible = "ns16550";
reg = <0x4500 0x100>;
clock-frequency = <0>;
clock-frequency = <133333333>;
interrupts = <9 0x8>;
interrupt-parent = <&ipic>;
};
@ -265,7 +265,7 @@
device_type = "serial";
compatible = "ns16550";
reg = <0x4600 0x100>;
clock-frequency = <0>;
clock-frequency = <133333333>;
interrupts = <10 0x8>;
interrupt-parent = <&ipic>;
};

4
arch/powerpc/boot/dts/mpc8544ds.dts
View file

@ -313,7 +313,7 @@
0x1000000 0x0 0x0 0xe1010000 0x0 0x10000>;
clock-frequency = <33333333>;
interrupt-parent = <&mpic>;
interrupts = <26 2>;
interrupts = <25 2>;
interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
interrupt-map = <
/* IDSEL 0x0 */
@ -350,7 +350,7 @@
0x1000000 0x0 0x0 0xe1020000 0x0 0x10000>;
clock-frequency = <33333333>;
interrupt-parent = <&mpic>;
interrupts = <25 2>;
interrupts = <26 2>;
interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
interrupt-map = <
/* IDSEL 0x0 */

4
arch/powerpc/boot/dts/mpc8572ds.dts
View file

@ -724,7 +724,7 @@
0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x00010000>;
clock-frequency = <33333333>;
interrupt-parent = <&mpic>;
interrupts = <26 2>;
interrupts = <25 2>;
interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
interrupt-map = <
/* IDSEL 0x0 */
@ -761,7 +761,7 @@
0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x00010000>;
clock-frequency = <33333333>;
interrupt-parent = <&mpic>;
interrupts = <27 2>;
interrupts = <26 2>;
interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
interrupt-map = <
/* IDSEL 0x0 */

2
arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
View file

@ -457,7 +457,7 @@
0x1000000 0x0 0x0 0xffc10000 0x0 0x10000>;
clock-frequency = <33333333>;
interrupt-parent = <&mpic>;
interrupts = <26 2>;
interrupts = <25 2>;
interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
interrupt-map = <
/* IDSEL 0x0 */

2
arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
View file

@ -208,7 +208,7 @@
0x1000000 0x0 0x0 0xffc20000 0x0 0x10000>;
clock-frequency = <33333333>;
interrupt-parent = <&mpic>;
interrupts = <27 2>;
interrupts = <26 2>;
interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
interrupt-map = <
/* IDSEL 0x0 */

26
arch/powerpc/configs/ppc64_defconfig
View file

@ -211,11 +211,28 @@ CONFIG_PPC_PASEMI=y
CONFIG_PPC_PASEMI_IOMMU=y
# CONFIG_PPC_PASEMI_IOMMU_DMA_FORCE is not set
CONFIG_PPC_PASEMI_MDIO=y
# CONFIG_PPC_PS3 is not set
CONFIG_PPC_PS3=y
#
# PS3 Platform Options
#
# CONFIG_PS3_ADVANCED is not set
CONFIG_PS3_HTAB_SIZE=20
# CONFIG_PS3_DYNAMIC_DMA is not set
CONFIG_PS3_VUART=y
CONFIG_PS3_PS3AV=y
CONFIG_PS3_SYS_MANAGER=y
CONFIG_PS3_STORAGE=m
CONFIG_PS3_DISK=m
CONFIG_PS3_ROM=m
CONFIG_PS3_FLASH=m
CONFIG_PS3_LPM=m
CONFIG_PPC_CELL=y
CONFIG_PPC_CELL_COMMON=y
CONFIG_PPC_CELL_NATIVE=y
CONFIG_PPC_IBM_CELL_BLADE=y
CONFIG_PPC_CELLEB=y
CONFIG_PPC_CELL_QPACE=y
#
# Cell Broadband Engine options
@ -981,6 +998,9 @@ CONFIG_E1000=y
CONFIG_TIGON3=y
# CONFIG_BNX2 is not set
CONFIG_SPIDER_NET=m
CONFIG_GELIC_NET=m
CONFIG_GELIC_WIRELESS=y
# CONFIG_GELIC_WIRELESS_OLD_PSK_INTERFACE is not set
# CONFIG_QLA3XXX is not set
# CONFIG_ATL1 is not set
# CONFIG_ATL1E is not set
@ -1370,6 +1390,8 @@ CONFIG_FB_RADEON_BACKLIGHT=y
# CONFIG_FB_PM3 is not set
# CONFIG_FB_CARMINE is not set
CONFIG_FB_IBM_GXT4500=y
CONFIG_FB_PS3=m
CONFIG_FB_PS3_DEFAULT_SIZE_M=9
# CONFIG_FB_VIRTUAL is not set
# CONFIG_FB_METRONOME is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
@ -1492,6 +1514,8 @@ CONFIG_SND_PCI=y
CONFIG_SND_PPC=y
CONFIG_SND_POWERMAC=m
CONFIG_SND_POWERMAC_AUTO_DRC=y
CONFIG_SND_PS3=m
CONFIG_SND_PS3_DEFAULT_START_DELAY=2000
CONFIG_SND_AOA=m
CONFIG_SND_AOA_FABRIC_LAYOUT=m
CONFIG_SND_AOA_ONYX=m

1
arch/powerpc/include/asm/Kbuild
View file

@ -35,4 +35,3 @@ unifdef-y += spu_info.h
unifdef-y += termios.h
unifdef-y += types.h
unifdef-y += unistd.h
unifdef-y += swab.h

2
arch/powerpc/include/asm/byteorder.h
View file

@ -7,8 +7,6 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <asm/swab.h>
#include <linux/byteorder/big_endian.h>
#endif /* _ASM_POWERPC_BYTEORDER_H */

8
arch/powerpc/include/asm/ps3.h
View file

@ -103,10 +103,10 @@ struct ps3_dma_region_ops {
int (*map)(struct ps3_dma_region *,
unsigned long virt_addr,
unsigned long len,
unsigned long *bus_addr,
dma_addr_t *bus_addr,
u64 iopte_pp);
int (*unmap)(struct ps3_dma_region *,
unsigned long bus_addr,
dma_addr_t bus_addr,
unsigned long len);
};
/**
@ -124,9 +124,9 @@ int ps3_dma_region_init(struct ps3_system_bus_device *dev,
int ps3_dma_region_create(struct ps3_dma_region *r);
int ps3_dma_region_free(struct ps3_dma_region *r);
int ps3_dma_map(struct ps3_dma_region *r, unsigned long virt_addr,
unsigned long len, unsigned long *bus_addr,
unsigned long len, dma_addr_t *bus_addr,
u64 iopte_pp);
int ps3_dma_unmap(struct ps3_dma_region *r, unsigned long bus_addr,
int ps3_dma_unmap(struct ps3_dma_region *r, dma_addr_t bus_addr,
unsigned long len);
/* mmio routines */

19
arch/powerpc/include/asm/qe.h
View file

@ -624,7 +624,7 @@ struct ucc_slow_pram {
#define UCC_GETH_UCCE_RXF1 0x00000002
#define UCC_GETH_UCCE_RXF0 0x00000001
/* UPSMR, when used as a UART */
/* UCC Protocol Specific Mode Register (UPSMR), when used for UART */
#define UCC_UART_UPSMR_FLC 0x8000
#define UCC_UART_UPSMR_SL 0x4000
#define UCC_UART_UPSMR_CL_MASK 0x3000
@ -652,6 +652,23 @@ struct ucc_slow_pram {
#define UCC_UART_UPSMR_TPM_EVEN 0x0002
#define UCC_UART_UPSMR_TPM_HIGH 0x0003
/* UCC Protocol Specific Mode Register (UPSMR), when used for Ethernet */
#define UCC_GETH_UPSMR_FTFE 0x80000000
#define UCC_GETH_UPSMR_PTPE 0x40000000
#define UCC_GETH_UPSMR_ECM 0x04000000
#define UCC_GETH_UPSMR_HSE 0x02000000
#define UCC_GETH_UPSMR_PRO 0x00400000
#define UCC_GETH_UPSMR_CAP 0x00200000
#define UCC_GETH_UPSMR_RSH 0x00100000
#define UCC_GETH_UPSMR_RPM 0x00080000
#define UCC_GETH_UPSMR_R10M 0x00040000
#define UCC_GETH_UPSMR_RLPB 0x00020000
#define UCC_GETH_UPSMR_TBIM 0x00010000
#define UCC_GETH_UPSMR_RES1 0x00002000
#define UCC_GETH_UPSMR_RMM 0x00001000
#define UCC_GETH_UPSMR_CAM 0x00000400
#define UCC_GETH_UPSMR_BRO 0x00000200
/* UCC Transmit On Demand Register (UTODR) */
#define UCC_SLOW_TOD 0x8000
#define UCC_FAST_TOD 0x8000

2
arch/powerpc/include/asm/rtas.h
View file

@ -18,7 +18,7 @@
*/
#define RTAS_UNKNOWN_SERVICE (-1)
#define RTAS_INSTANTIATE_MAX (1UL<<30) /* Don't instantiate rtas at/above this value */
#define RTAS_INSTANTIATE_MAX (1ULL<<30) /* Don't instantiate rtas at/above this value */
/* Buffer size for ppc_rtas system call. */
#define RTAS_RMOBUF_MAX (64 * 1024)

2
arch/powerpc/include/asm/systbl.h
View file

@ -92,7 +92,7 @@ COMPAT_SYS_SPU(readlink)
SYSCALL(uselib)
SYSCALL(swapon)
SYSCALL(reboot)
SYSX(sys_ni_syscall,compat_sys_old_readdir,old_readdir)
SYSX(sys_ni_syscall,compat_sys_old_readdir,sys_old_readdir)
SYSCALL_SPU(mmap)
SYSCALL_SPU(munmap)
SYSCALL_SPU(truncate)

7
arch/powerpc/include/asm/types.h
View file

@ -1,7 +1,12 @@
#ifndef _ASM_POWERPC_TYPES_H
#define _ASM_POWERPC_TYPES_H
#ifdef __powerpc64__
/*
* This is here because we used to use l64 for 64bit powerpc
* and we don't want to impact user mode with our change to ll64
* in the kernel.
*/
#if defined(__powerpc64__) && !defined(__KERNEL__)
# include <asm-generic/int-l64.h>
#else
# include <asm-generic/int-ll64.h>

7
arch/powerpc/kernel/asm-offsets.c
View file

@ -56,6 +56,10 @@
#include "head_booke.h"
#endif
#if defined(CONFIG_FSL_BOOKE)
#include "../mm/mmu_decl.h"
#endif
int main(void)
{
DEFINE(THREAD, offsetof(struct task_struct, thread));
@ -382,6 +386,9 @@ int main(void)
DEFINE(PGD_T_LOG2, PGD_T_LOG2);
DEFINE(PTE_T_LOG2, PTE_T_LOG2);
#endif
#ifdef CONFIG_FSL_BOOKE
DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
#endif
#ifdef CONFIG_KVM_EXIT_TIMING
DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,

10
arch/powerpc/kernel/cacheinfo.c
View file

@ -113,7 +113,7 @@ struct cache {
struct cache *next_local; /* next cache of >= level */
};
static DEFINE_PER_CPU(struct cache_dir *, cache_dir);
static DEFINE_PER_CPU(struct cache_dir *, cache_dir_pcpu);
/* traversal/modification of this list occurs only at cpu hotplug time;
* access is serialized by cpu hotplug locking
@ -468,9 +468,9 @@ static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_i
cache_dir->kobj = kobj;
WARN_ON_ONCE(per_cpu(cache_dir, cpu_id) != NULL);
WARN_ON_ONCE(per_cpu(cache_dir_pcpu, cpu_id) != NULL);
per_cpu(cache_dir, cpu_id) = cache_dir;
per_cpu(cache_dir_pcpu, cpu_id) = cache_dir;
return cache_dir;
err:
@ -820,13 +820,13 @@ void cacheinfo_cpu_offline(unsigned int cpu_id)
/* Prevent userspace from seeing inconsistent state - remove
* the sysfs hierarchy first */
cache_dir = per_cpu(cache_dir, cpu_id);
cache_dir = per_cpu(cache_dir_pcpu, cpu_id);
/* careful, sysfs population may have failed */
if (cache_dir)
remove_cache_dir(cache_dir);
per_cpu(cache_dir, cpu_id) = NULL;
per_cpu(cache_dir_pcpu, cpu_id) = NULL;
/* clear the CPU's bit in its cache chain, possibly freeing
* cache objects */

4
arch/powerpc/kernel/dma-iommu.c
View file

@ -79,10 +79,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
"Warning: IOMMU offset too big for device mask\n");
if (tbl)
printk(KERN_INFO
"mask: 0x%08lx, table offset: 0x%08lx\n",
"mask: 0x%08llx, table offset: 0x%08lx\n",
mask, tbl->it_offset);
else
printk(KERN_INFO "mask: 0x%08lx, table unavailable\n",
printk(KERN_INFO "mask: 0x%08llx, table unavailable\n",
mask);
return 0;
} else

Some files were not shown because too many files have changed in this diff Show more