mirror of
https://github.com/followmsi/android_kernel_google_msm.git
synced 2024-11-06 23:17:41 +00:00
Merge Linus' tree.
This commit is contained in:
Russell King
Russell King
commit
0a3a98f6dd
590 changed files with 16766 additions and 7749 deletions
2
CREDITS
2
CREDITS
|
|
@ -3203,7 +3203,7 @@ N: Eugene Surovegin
|
|||
E: ebs@ebshome.net
|
||||
W: http://kernel.ebshome.net/
|
||||
P: 1024D/AE5467F1 FF22 39F1 6728 89F6 6E6C 2365 7602 F33D AE54 67F1
|
||||
D: Embedded PowerPC 4xx: I2C, PIC and random hacks/fixes
|
||||
D: Embedded PowerPC 4xx: EMAC, I2C, PIC and random hacks/fixes
|
||||
S: Sunnyvale, California 94085
|
||||
S: USA
|
||||
|
||||
|
|
|
|||
|
|
@ -31,8 +31,6 @@ al espa
|
|||
Eine deutsche Version dieser Datei finden Sie unter
|
||||
<http://www.stefan-winter.de/Changes-2.4.0.txt>.
|
||||
|
||||
Last updated: October 29th, 2002
|
||||
|
||||
Chris Ricker (kaboom@gatech.edu or chris.ricker@genetics.utah.edu).
|
||||
|
||||
Current Minimal Requirements
|
||||
|
|
@ -48,7 +46,7 @@ necessary on all systems; obviously, if you don't have any ISDN
|
|||
hardware, for example, you probably needn't concern yourself with
|
||||
isdn4k-utils.
|
||||
|
||||
o Gnu C 2.95.3 # gcc --version
|
||||
o Gnu C 3.2 # gcc --version
|
||||
o Gnu make 3.79.1 # make --version
|
||||
o binutils 2.12 # ld -v
|
||||
o util-linux 2.10o # fdformat --version
|
||||
|
|
@ -74,26 +72,7 @@ GCC
|
|||
---
|
||||
|
||||
The gcc version requirements may vary depending on the type of CPU in your
|
||||
computer. The next paragraph applies to users of x86 CPUs, but not
|
||||
necessarily to users of other CPUs. Users of other CPUs should obtain
|
||||
information about their gcc version requirements from another source.
|
||||
|
||||
The recommended compiler for the kernel is gcc 2.95.x (x >= 3), and it
|
||||
should be used when you need absolute stability. You may use gcc 3.0.x
|
||||
instead if you wish, although it may cause problems. Later versions of gcc
|
||||
have not received much testing for Linux kernel compilation, and there are
|
||||
almost certainly bugs (mainly, but not exclusively, in the kernel) that
|
||||
will need to be fixed in order to use these compilers. In any case, using
|
||||
pgcc instead of plain gcc is just asking for trouble.
|
||||
|
||||
The Red Hat gcc 2.96 compiler subtree can also be used to build this tree.
|
||||
You should ensure you use gcc-2.96-74 or later. gcc-2.96-54 will not build
|
||||
the kernel correctly.
|
||||
|
||||
In addition, please pay attention to compiler optimization. Anything
|
||||
greater than -O2 may not be wise. Similarly, if you choose to use gcc-2.95.x
|
||||
or derivatives, be sure not to use -fstrict-aliasing (which, depending on
|
||||
your version of gcc 2.95.x, may necessitate using -fno-strict-aliasing).
|
||||
computer.
|
||||
|
||||
Make
|
||||
----
|
||||
|
|
@ -322,9 +301,9 @@ Getting updated software
|
|||
Kernel compilation
|
||||
******************
|
||||
|
||||
gcc 2.95.3
|
||||
----------
|
||||
o <ftp://ftp.gnu.org/gnu/gcc/gcc-2.95.3.tar.gz>
|
||||
gcc
|
||||
---
|
||||
o <ftp://ftp.gnu.org/gnu/gcc/>
|
||||
|
||||
Make
|
||||
----
|
||||
|
|
|
|||
|
|
@ -344,7 +344,7 @@ Remember: if another thread can find your data structure, and you don't
|
|||
have a reference count on it, you almost certainly have a bug.
|
||||
|
||||
|
||||
Chapter 11: Macros, Enums, Inline functions and RTL
|
||||
Chapter 11: Macros, Enums and RTL
|
||||
|
||||
Names of macros defining constants and labels in enums are capitalized.
|
||||
|
||||
|
|
@ -429,7 +429,35 @@ from void pointer to any other pointer type is guaranteed by the C programming
|
|||
language.
|
||||
|
||||
|
||||
Chapter 14: References
|
||||
Chapter 14: The inline disease
|
||||
|
||||
There appears to be a common misperception that gcc has a magic "make me
|
||||
faster" speedup option called "inline". While the use of inlines can be
|
||||
appropriate (for example as a means of replacing macros, see Chapter 11), it
|
||||
very often is not. Abundant use of the inline keyword leads to a much bigger
|
||||
kernel, which in turn slows the system as a whole down, due to a bigger
|
||||
icache footprint for the CPU and simply because there is less memory
|
||||
available for the pagecache. Just think about it; a pagecache miss causes a
|
||||
disk seek, which easily takes 5 miliseconds. There are a LOT of cpu cycles
|
||||
that can go into these 5 miliseconds.
|
||||
|
||||
A reasonable rule of thumb is to not put inline at functions that have more
|
||||
than 3 lines of code in them. An exception to this rule are the cases where
|
||||
a parameter is known to be a compiletime constant, and as a result of this
|
||||
constantness you *know* the compiler will be able to optimize most of your
|
||||
function away at compile time. For a good example of this later case, see
|
||||
the kmalloc() inline function.
|
||||
|
||||
Often people argue that adding inline to functions that are static and used
|
||||
only once is always a win since there is no space tradeoff. While this is
|
||||
technically correct, gcc is capable of inlining these automatically without
|
||||
help, and the maintenance issue of removing the inline when a second user
|
||||
appears outweighs the potential value of the hint that tells gcc to do
|
||||
something it would have done anyway.
|
||||
|
||||
|
||||
|
||||
Chapter 15: References
|
||||
|
||||
The C Programming Language, Second Edition
|
||||
by Brian W. Kernighan and Dennis M. Ritchie.
|
||||
|
|
@ -444,10 +472,13 @@ ISBN 0-201-61586-X.
|
|||
URL: http://cm.bell-labs.com/cm/cs/tpop/
|
||||
|
||||
GNU manuals - where in compliance with K&R and this text - for cpp, gcc,
|
||||
gcc internals and indent, all available from http://www.gnu.org
|
||||
gcc internals and indent, all available from http://www.gnu.org/manual/
|
||||
|
||||
WG14 is the international standardization working group for the programming
|
||||
language C, URL: http://std.dkuug.dk/JTC1/SC22/WG14/
|
||||
language C, URL: http://www.open-std.org/JTC1/SC22/WG14/
|
||||
|
||||
Kernel CodingStyle, by greg@kroah.com at OLS 2002:
|
||||
http://www.kroah.com/linux/talks/ols_2002_kernel_codingstyle_talk/html/
|
||||
|
||||
--
|
||||
Last updated on 16 February 2004 by a community effort on LKML.
|
||||
Last updated on 30 December 2005 by a community effort on LKML.
|
||||
|
|
|
|||
|
|
@ -1,74 +1,67 @@
|
|||
Refcounter framework for elements of lists/arrays protected by
|
||||
RCU.
|
||||
Refcounter design for elements of lists/arrays protected by RCU.
|
||||
|
||||
Refcounting on elements of lists which are protected by traditional
|
||||
reader/writer spinlocks or semaphores are straight forward as in:
|
||||
|
||||
1. 2.
|
||||
add() search_and_reference()
|
||||
{ {
|
||||
alloc_object read_lock(&list_lock);
|
||||
... search_for_element
|
||||
atomic_set(&el->rc, 1); atomic_inc(&el->rc);
|
||||
write_lock(&list_lock); ...
|
||||
add_element read_unlock(&list_lock);
|
||||
... ...
|
||||
write_unlock(&list_lock); }
|
||||
1. 2.
|
||||
add() search_and_reference()
|
||||
{ {
|
||||
alloc_object read_lock(&list_lock);
|
||||
... search_for_element
|
||||
atomic_set(&el->rc, 1); atomic_inc(&el->rc);
|
||||
write_lock(&list_lock); ...
|
||||
add_element read_unlock(&list_lock);
|
||||
... ...
|
||||
write_unlock(&list_lock); }
|
||||
}
|
||||
|
||||
3. 4.
|
||||
release_referenced() delete()
|
||||
{ {
|
||||
... write_lock(&list_lock);
|
||||
atomic_dec(&el->rc, relfunc) ...
|
||||
... delete_element
|
||||
} write_unlock(&list_lock);
|
||||
...
|
||||
if (atomic_dec_and_test(&el->rc))
|
||||
kfree(el);
|
||||
...
|
||||
... write_lock(&list_lock);
|
||||
atomic_dec(&el->rc, relfunc) ...
|
||||
... delete_element
|
||||
} write_unlock(&list_lock);
|
||||
...
|
||||
if (atomic_dec_and_test(&el->rc))
|
||||
kfree(el);
|
||||
...
|
||||
}
|
||||
|
||||
If this list/array is made lock free using rcu as in changing the
|
||||
write_lock in add() and delete() to spin_lock and changing read_lock
|
||||
in search_and_reference to rcu_read_lock(), the rcuref_get in
|
||||
in search_and_reference to rcu_read_lock(), the atomic_get in
|
||||
search_and_reference could potentially hold reference to an element which
|
||||
has already been deleted from the list/array. rcuref_lf_get_rcu takes
|
||||
has already been deleted from the list/array. atomic_inc_not_zero takes
|
||||
care of this scenario. search_and_reference should look as;
|
||||
|
||||
1. 2.
|
||||
add() search_and_reference()
|
||||
{ {
|
||||
alloc_object rcu_read_lock();
|
||||
... search_for_element
|
||||
atomic_set(&el->rc, 1); if (rcuref_inc_lf(&el->rc)) {
|
||||
write_lock(&list_lock); rcu_read_unlock();
|
||||
return FAIL;
|
||||
add_element }
|
||||
... ...
|
||||
write_unlock(&list_lock); rcu_read_unlock();
|
||||
alloc_object rcu_read_lock();
|
||||
... search_for_element
|
||||
atomic_set(&el->rc, 1); if (atomic_inc_not_zero(&el->rc)) {
|
||||
write_lock(&list_lock); rcu_read_unlock();
|
||||
return FAIL;
|
||||
add_element }
|
||||
... ...
|
||||
write_unlock(&list_lock); rcu_read_unlock();
|
||||
} }
|
||||
3. 4.
|
||||
release_referenced() delete()
|
||||
{ {
|
||||
... write_lock(&list_lock);
|
||||
rcuref_dec(&el->rc, relfunc) ...
|
||||
... delete_element
|
||||
} write_unlock(&list_lock);
|
||||
...
|
||||
if (rcuref_dec_and_test(&el->rc))
|
||||
call_rcu(&el->head, el_free);
|
||||
...
|
||||
... write_lock(&list_lock);
|
||||
atomic_dec(&el->rc, relfunc) ...
|
||||
... delete_element
|
||||
} write_unlock(&list_lock);
|
||||
...
|
||||
if (atomic_dec_and_test(&el->rc))
|
||||
call_rcu(&el->head, el_free);
|
||||
...
|
||||
}
|
||||
|
||||
Sometimes, reference to the element need to be obtained in the
|
||||
update (write) stream. In such cases, rcuref_inc_lf might be an overkill
|
||||
since the spinlock serialising list updates are held. rcuref_inc
|
||||
update (write) stream. In such cases, atomic_inc_not_zero might be an
|
||||
overkill since the spinlock serialising list updates are held. atomic_inc
|
||||
is to be used in such cases.
|
||||
For arches which do not have cmpxchg rcuref_inc_lf
|
||||
api uses a hashed spinlock implementation and the same hashed spinlock
|
||||
is acquired in all rcuref_xxx primitives to preserve atomicity.
|
||||
Note: Use rcuref_inc api only if you need to use rcuref_inc_lf on the
|
||||
refcounter atleast at one place. Mixing rcuref_inc and atomic_xxx api
|
||||
might lead to races. rcuref_inc_lf() must be used in lockfree
|
||||
RCU critical sections only.
|
||||
|
||||
|
|
|
|||
|
|
@ -27,18 +27,17 @@ Who To Submit Drivers To
|
|||
------------------------
|
||||
|
||||
Linux 2.0:
|
||||
No new drivers are accepted for this kernel tree
|
||||
No new drivers are accepted for this kernel tree.
|
||||
|
||||
Linux 2.2:
|
||||
No new drivers are accepted for this kernel tree.
|
||||
|
||||
Linux 2.4:
|
||||
If the code area has a general maintainer then please submit it to
|
||||
the maintainer listed in MAINTAINERS in the kernel file. If the
|
||||
maintainer does not respond or you cannot find the appropriate
|
||||
maintainer then please contact the 2.2 kernel maintainer:
|
||||
Marc-Christian Petersen <m.c.p@wolk-project.de>.
|
||||
|
||||
Linux 2.4:
|
||||
The same rules apply as 2.2. The final contact point for Linux 2.4
|
||||
submissions is Marcelo Tosatti <marcelo.tosatti@cyclades.com>.
|
||||
maintainer then please contact Marcelo Tosatti
|
||||
<marcelo.tosatti@cyclades.com>.
|
||||
|
||||
Linux 2.6:
|
||||
The same rules apply as 2.4 except that you should follow linux-kernel
|
||||
|
|
@ -53,6 +52,7 @@ Licensing: The code must be released to us under the
|
|||
of exclusive GPL licensing, and if you wish the driver
|
||||
to be useful to other communities such as BSD you may well
|
||||
wish to release under multiple licenses.
|
||||
See accepted licenses at include/linux/module.h
|
||||
|
||||
Copyright: The copyright owner must agree to use of GPL.
|
||||
It's best if the submitter and copyright owner
|
||||
|
|
@ -143,5 +143,13 @@ KernelNewbies:
|
|||
http://kernelnewbies.org/
|
||||
|
||||
Linux USB project:
|
||||
http://sourceforge.net/projects/linux-usb/
|
||||
http://linux-usb.sourceforge.net/
|
||||
|
||||
How to NOT write kernel driver by arjanv@redhat.com
|
||||
http://people.redhat.com/arjanv/olspaper.pdf
|
||||
|
||||
Kernel Janitor:
|
||||
http://janitor.kernelnewbies.org/
|
||||
|
||||
--
|
||||
Last updated on 17 Nov 2005.
|
||||
|
|
|
|||
|
|
@ -78,7 +78,9 @@ Randy Dunlap's patch scripts:
|
|||
http://www.xenotime.net/linux/scripts/patching-scripts-002.tar.gz
|
||||
|
||||
Andrew Morton's patch scripts:
|
||||
http://www.zip.com.au/~akpm/linux/patches/patch-scripts-0.20
|
||||
http://www.zip.com.au/~akpm/linux/patches/
|
||||
Instead of these scripts, quilt is the recommended patch management
|
||||
tool (see above).
|
||||
|
||||
|
||||
|
||||
|
|
@ -97,7 +99,7 @@ need to split up your patch. See #3, next.
|
|||
|
||||
3) Separate your changes.
|
||||
|
||||
Separate each logical change into its own patch.
|
||||
Separate _logical changes_ into a single patch file.
|
||||
|
||||
For example, if your changes include both bug fixes and performance
|
||||
enhancements for a single driver, separate those changes into two
|
||||
|
|
@ -112,6 +114,10 @@ If one patch depends on another patch in order for a change to be
|
|||
complete, that is OK. Simply note "this patch depends on patch X"
|
||||
in your patch description.
|
||||
|
||||
If you cannot condense your patch set into a smaller set of patches,
|
||||
then only post say 15 or so at a time and wait for review and integration.
|
||||
|
||||
|
||||
|
||||
4) Select e-mail destination.
|
||||
|
||||
|
|
@ -124,6 +130,10 @@ your patch to the primary Linux kernel developer's mailing list,
|
|||
linux-kernel@vger.kernel.org. Most kernel developers monitor this
|
||||
e-mail list, and can comment on your changes.
|
||||
|
||||
|
||||
Do not send more than 15 patches at once to the vger mailing lists!!!
|
||||
|
||||
|
||||
Linus Torvalds is the final arbiter of all changes accepted into the
|
||||
Linux kernel. His e-mail address is <torvalds@osdl.org>. He gets
|
||||
a lot of e-mail, so typically you should do your best to -avoid- sending
|
||||
|
|
@ -149,6 +159,9 @@ USB, framebuffer devices, the VFS, the SCSI subsystem, etc. See the
|
|||
MAINTAINERS file for a mailing list that relates specifically to
|
||||
your change.
|
||||
|
||||
Majordomo lists of VGER.KERNEL.ORG at:
|
||||
<http://vger.kernel.org/vger-lists.html>
|
||||
|
||||
If changes affect userland-kernel interfaces, please send
|
||||
the MAN-PAGES maintainer (as listed in the MAINTAINERS file)
|
||||
a man-pages patch, or at least a notification of the change,
|
||||
|
|
@ -373,27 +386,14 @@ a diffstat, to show what files have changed, and the number of inserted
|
|||
and deleted lines per file. A diffstat is especially useful on bigger
|
||||
patches. Other comments relevant only to the moment or the maintainer,
|
||||
not suitable for the permanent changelog, should also go here.
|
||||
Use diffstat options "-p 1 -w 70" so that filenames are listed from the
|
||||
top of the kernel source tree and don't use too much horizontal space
|
||||
(easily fit in 80 columns, maybe with some indentation).
|
||||
|
||||
See more details on the proper patch format in the following
|
||||
references.
|
||||
|
||||
|
||||
13) More references for submitting patches
|
||||
|
||||
Andrew Morton, "The perfect patch" (tpp).
|
||||
<http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt>
|
||||
|
||||
Jeff Garzik, "Linux kernel patch submission format."
|
||||
<http://linux.yyz.us/patch-format.html>
|
||||
|
||||
Greg KH, "How to piss off a kernel subsystem maintainer"
|
||||
<http://www.kroah.com/log/2005/03/31/>
|
||||
|
||||
Kernel Documentation/CodingStyle
|
||||
<http://sosdg.org/~coywolf/lxr/source/Documentation/CodingStyle>
|
||||
|
||||
Linus Torvald's mail on the canonical patch format:
|
||||
<http://lkml.org/lkml/2005/4/7/183>
|
||||
|
||||
|
||||
-----------------------------------
|
||||
|
|
@ -466,3 +466,30 @@ and 'extern __inline__'.
|
|||
Don't try to anticipate nebulous future cases which may or may not
|
||||
be useful: "Make it as simple as you can, and no simpler."
|
||||
|
||||
|
||||
|
||||
----------------------
|
||||
SECTION 3 - REFERENCES
|
||||
----------------------
|
||||
|
||||
Andrew Morton, "The perfect patch" (tpp).
|
||||
<http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt>
|
||||
|
||||
Jeff Garzik, "Linux kernel patch submission format."
|
||||
<http://linux.yyz.us/patch-format.html>
|
||||
|
||||
Greg Kroah, "How to piss off a kernel subsystem maintainer".
|
||||
<http://www.kroah.com/log/2005/03/31/>
|
||||
<http://www.kroah.com/log/2005/07/08/>
|
||||
<http://www.kroah.com/log/2005/10/19/>
|
||||
|
||||
NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!.
|
||||
<http://marc.theaimsgroup.com/?l=linux-kernel&m=112112749912944&w=2>
|
||||
|
||||
Kernel Documentation/CodingStyle
|
||||
<http://sosdg.org/~coywolf/lxr/source/Documentation/CodingStyle>
|
||||
|
||||
Linus Torvald's mail on the canonical patch format:
|
||||
<http://lkml.org/lkml/2005/4/7/183>
|
||||
--
|
||||
Last updated on 17 Nov 2005.
|
||||
|
|
|
|||
|
|
@ -2,7 +2,8 @@
|
|||
Applying Patches To The Linux Kernel
|
||||
------------------------------------
|
||||
|
||||
(Written by Jesper Juhl, August 2005)
|
||||
Original by: Jesper Juhl, August 2005
|
||||
Last update: 2005-12-02
|
||||
|
||||
|
||||
|
||||
|
|
@ -118,7 +119,7 @@ wrong.
|
|||
|
||||
When patch encounters a change that it can't fix up with fuzz it rejects it
|
||||
outright and leaves a file with a .rej extension (a reject file). You can
|
||||
read this file to see exactely what change couldn't be applied, so you can
|
||||
read this file to see exactly what change couldn't be applied, so you can
|
||||
go fix it up by hand if you wish.
|
||||
|
||||
If you don't have any third party patches applied to your kernel source, but
|
||||
|
|
@ -127,7 +128,7 @@ and have made no modifications yourself to the source files, then you should
|
|||
never see a fuzz or reject message from patch. If you do see such messages
|
||||
anyway, then there's a high risk that either your local source tree or the
|
||||
patch file is corrupted in some way. In that case you should probably try
|
||||
redownloading the patch and if things are still not OK then you'd be advised
|
||||
re-downloading the patch and if things are still not OK then you'd be advised
|
||||
to start with a fresh tree downloaded in full from kernel.org.
|
||||
|
||||
Let's look a bit more at some of the messages patch can produce.
|
||||
|
|
@ -180,9 +181,11 @@ wish to apply.
|
|||
|
||||
Are there any alternatives to `patch'?
|
||||
---
|
||||
Yes there are alternatives. You can use the `interdiff' program
|
||||
(http://cyberelk.net/tim/patchutils/) to generate a patch representing the
|
||||
differences between two patches and then apply the result.
|
||||
Yes there are alternatives.
|
||||
|
||||
You can use the `interdiff' program (http://cyberelk.net/tim/patchutils/) to
|
||||
generate a patch representing the differences between two patches and then
|
||||
apply the result.
|
||||
This will let you move from something like 2.6.12.2 to 2.6.12.3 in a single
|
||||
step. The -z flag to interdiff will even let you feed it patches in gzip or
|
||||
bzip2 compressed form directly without the use of zcat or bzcat or manual
|
||||
|
|
@ -197,7 +200,7 @@ do the additional steps since interdiff can get things wrong in some cases.
|
|||
Another alternative is `ketchup', which is a python script for automatic
|
||||
downloading and applying of patches (http://www.selenic.com/ketchup/).
|
||||
|
||||
Other nice tools are diffstat which shows a summary of changes made by a
|
||||
Other nice tools are diffstat which shows a summary of changes made by a
|
||||
patch, lsdiff which displays a short listing of affected files in a patch
|
||||
file, along with (optionally) the line numbers of the start of each patch
|
||||
and grepdiff which displays a list of the files modified by a patch where
|
||||
|
|
@ -258,7 +261,7 @@ $ patch -p1 -R < ../patch-2.6.11.1 # revert the 2.6.11.1 patch
|
|||
# source dir is now 2.6.11
|
||||
$ patch -p1 < ../patch-2.6.12 # apply new 2.6.12 patch
|
||||
$ cd ..
|
||||
$ mv linux-2.6.11.1 inux-2.6.12 # rename source dir
|
||||
$ mv linux-2.6.11.1 linux-2.6.12 # rename source dir
|
||||
|
||||
|
||||
The 2.6.x.y kernels
|
||||
|
|
@ -433,7 +436,11 @@ $ cd ..
|
|||
$ mv linux-2.6.12-mm1 linux-2.6.13-rc3-mm3 # rename the source dir
|
||||
|
||||
|
||||
This concludes this list of explanations of the various kernel trees and I
|
||||
hope you are now crystal clear on how to apply the various patches and help
|
||||
testing the kernel.
|
||||
This concludes this list of explanations of the various kernel trees.
|
||||
I hope you are now clear on how to apply the various patches and help testing
|
||||
the kernel.
|
||||
|
||||
Thank you's to Randy Dunlap, Rolf Eike Beer, Linus Torvalds, Bodo Eggert,
|
||||
Johannes Stezenbach, Grant Coady, Pavel Machek and others that I may have
|
||||
forgotten for their reviews and contributions to this document.
|
||||
|
||||
|
|
|
|||
82
Documentation/block/stat.txt
Normal file
82
Documentation/block/stat.txt
Normal file
|
|
@ -0,0 +1,82 @@
|
|||
Block layer statistics in /sys/block/<dev>/stat
|
||||
===============================================
|
||||
|
||||
This file documents the contents of the /sys/block/<dev>/stat file.
|
||||
|
||||
The stat file provides several statistics about the state of block
|
||||
device <dev>.
|
||||
|
||||
Q. Why are there multiple statistics in a single file? Doesn't sysfs
|
||||
normally contain a single value per file?
|
||||
A. By having a single file, the kernel can guarantee that the statistics
|
||||
represent a consistent snapshot of the state of the device. If the
|
||||
statistics were exported as multiple files containing one statistic
|
||||
each, it would be impossible to guarantee that a set of readings
|
||||
represent a single point in time.
|
||||
|
||||
The stat file consists of a single line of text containing 11 decimal
|
||||
values separated by whitespace. The fields are summarized in the
|
||||
following table, and described in more detail below.
|
||||
|
||||
Name units description
|
||||
---- ----- -----------
|
||||
read I/Os requests number of read I/Os processed
|
||||
read merges requests number of read I/Os merged with in-queue I/O
|
||||
read sectors sectors number of sectors read
|
||||
read ticks milliseconds total wait time for read requests
|
||||
write I/Os requests number of write I/Os processed
|
||||
write merges requests number of write I/Os merged with in-queue I/O
|
||||
write sectors sectors number of sectors written
|
||||
write ticks milliseconds total wait time for write requests
|
||||
in_flight requests number of I/Os currently in flight
|
||||
io_ticks milliseconds total time this block device has been active
|
||||
time_in_queue milliseconds total wait time for all requests
|
||||
|
||||
read I/Os, write I/Os
|
||||
=====================
|
||||
|
||||
These values increment when an I/O request completes.
|
||||
|
||||
read merges, write merges
|
||||
=========================
|
||||
|
||||
These values increment when an I/O request is merged with an
|
||||
already-queued I/O request.
|
||||
|
||||
read sectors, write sectors
|
||||
===========================
|
||||
|
||||
These values count the number of sectors read from or written to this
|
||||
block device. The "sectors" in question are the standard UNIX 512-byte
|
||||
sectors, not any device- or filesystem-specific block size. The
|
||||
counters are incremented when the I/O completes.
|
||||
|
||||
read ticks, write ticks
|
||||
=======================
|
||||
|
||||
These values count the number of milliseconds that I/O requests have
|
||||
waited on this block device. If there are multiple I/O requests waiting,
|
||||
these values will increase at a rate greater than 1000/second; for
|
||||
example, if 60 read requests wait for an average of 30 ms, the read_ticks
|
||||
field will increase by 60*30 = 1800.
|
||||
|
||||
in_flight
|
||||
=========
|
||||
|
||||
This value counts the number of I/O requests that have been issued to
|
||||
the device driver but have not yet completed. It does not include I/O
|
||||
requests that are in the queue but not yet issued to the device driver.
|
||||
|
||||
io_ticks
|
||||
========
|
||||
|
||||
This value counts the number of milliseconds during which the device has
|
||||
had I/O requests queued.
|
||||
|
||||
time_in_queue
|
||||
=============
|
||||
|
||||
This value counts the number of milliseconds that I/O requests have waited
|
||||
on this block device. If there are multiple I/O requests waiting, this
|
||||
value will increase as the product of the number of milliseconds times the
|
||||
number of requests waiting (see "read ticks" above for an example).
|
||||
357
Documentation/cpu-hotplug.txt
Normal file
357
Documentation/cpu-hotplug.txt
Normal file
|
|
@ -0,0 +1,357 @@
|
|||
CPU hotplug Support in Linux(tm) Kernel
|
||||
|
||||
Maintainers:
|
||||
CPU Hotplug Core:
|
||||
Rusty Russell <rusty@rustycorp.com.au>
|
||||
Srivatsa Vaddagiri <vatsa@in.ibm.com>
|
||||
i386:
|
||||
Zwane Mwaikambo <zwane@arm.linux.org.uk>
|
||||
ppc64:
|
||||
Nathan Lynch <nathanl@austin.ibm.com>
|
||||
Joel Schopp <jschopp@austin.ibm.com>
|
||||
ia64/x86_64:
|
||||
Ashok Raj <ashok.raj@intel.com>
|
||||
|
||||
Authors: Ashok Raj <ashok.raj@intel.com>
|
||||
Lots of feedback: Nathan Lynch <nathanl@austin.ibm.com>,
|
||||
Joel Schopp <jschopp@austin.ibm.com>
|
||||
|
||||
Introduction
|
||||
|
||||
Modern advances in system architectures have introduced advanced error
|
||||
reporting and correction capabilities in processors. CPU architectures permit
|
||||
partitioning support, where compute resources of a single CPU could be made
|
||||
available to virtual machine environments. There are couple OEMS that
|
||||
support NUMA hardware which are hot pluggable as well, where physical
|
||||
node insertion and removal require support for CPU hotplug.
|
||||
|
||||
Such advances require CPUs available to a kernel to be removed either for
|
||||
provisioning reasons, or for RAS purposes to keep an offending CPU off
|
||||
system execution path. Hence the need for CPU hotplug support in the
|
||||
Linux kernel.
|
||||
|
||||
A more novel use of CPU-hotplug support is its use today in suspend
|
||||
resume support for SMP. Dual-core and HT support makes even
|
||||
a laptop run SMP kernels which didn't support these methods. SMP support
|
||||
for suspend/resume is a work in progress.
|
||||
|
||||
General Stuff about CPU Hotplug
|
||||
--------------------------------
|
||||
|
||||
Command Line Switches
|
||||
---------------------
|
||||
maxcpus=n Restrict boot time cpus to n. Say if you have 4 cpus, using
|
||||
maxcpus=2 will only boot 2. You can choose to bring the
|
||||
other cpus later online, read FAQ's for more info.
|
||||
|
||||
additional_cpus=n [x86_64 only] use this to limit hotpluggable cpus.
|
||||
This option sets
|
||||
cpu_possible_map = cpu_present_map + additional_cpus
|
||||
|
||||
CPU maps and such
|
||||
-----------------
|
||||
[More on cpumaps and primitive to manipulate, please check
|
||||
include/linux/cpumask.h that has more descriptive text.]
|
||||
|
||||
cpu_possible_map: Bitmap of possible CPUs that can ever be available in the
|
||||
system. This is used to allocate some boot time memory for per_cpu variables
|
||||
that aren't designed to grow/shrink as CPUs are made available or removed.
|
||||
Once set during boot time discovery phase, the map is static, i.e no bits
|
||||
are added or removed anytime. Trimming it accurately for your system needs
|
||||
upfront can save some boot time memory. See below for how we use heuristics
|
||||
in x86_64 case to keep this under check.
|
||||
|
||||
cpu_online_map: Bitmap of all CPUs currently online. Its set in __cpu_up()
|
||||
after a cpu is available for kernel scheduling and ready to receive
|
||||
interrupts from devices. Its cleared when a cpu is brought down using
|
||||
__cpu_disable(), before which all OS services including interrupts are
|
||||
migrated to another target CPU.
|
||||
|
||||
cpu_present_map: Bitmap of CPUs currently present in the system. Not all
|
||||
of them may be online. When physical hotplug is processed by the relevant
|
||||
subsystem (e.g ACPI) can change and new bit either be added or removed
|
||||
from the map depending on the event is hot-add/hot-remove. There are currently
|
||||
no locking rules as of now. Typical usage is to init topology during boot,
|
||||
at which time hotplug is disabled.
|
||||
|
||||
You really dont need to manipulate any of the system cpu maps. They should
|
||||
be read-only for most use. When setting up per-cpu resources almost always use
|
||||
cpu_possible_map/for_each_cpu() to iterate.
|
||||
|
||||
Never use anything other than cpumask_t to represent bitmap of CPUs.
|
||||
|
||||
#include <linux/cpumask.h>
|
||||
|
||||
for_each_cpu - Iterate over cpu_possible_map
|
||||
for_each_online_cpu - Iterate over cpu_online_map
|
||||
for_each_present_cpu - Iterate over cpu_present_map
|
||||
for_each_cpu_mask(x,mask) - Iterate over some random collection of cpu mask.
|
||||
|
||||
#include <linux/cpu.h>
|
||||
lock_cpu_hotplug() and unlock_cpu_hotplug():
|
||||
|
||||
The above calls are used to inhibit cpu hotplug operations. While holding the
|
||||
cpucontrol mutex, cpu_online_map will not change. If you merely need to avoid
|
||||
cpus going away, you could also use preempt_disable() and preempt_enable()
|
||||
for those sections. Just remember the critical section cannot call any
|
||||
function that can sleep or schedule this process away. The preempt_disable()
|
||||
will work as long as stop_machine_run() is used to take a cpu down.
|
||||
|
||||
CPU Hotplug - Frequently Asked Questions.
|
||||
|
||||
Q: How to i enable my kernel to support CPU hotplug?
|
||||
A: When doing make defconfig, Enable CPU hotplug support
|
||||
|
||||
"Processor type and Features" -> Support for Hotpluggable CPUs
|
||||
|
||||
Make sure that you have CONFIG_HOTPLUG, and CONFIG_SMP turned on as well.
|
||||
|
||||
You would need to enable CONFIG_HOTPLUG_CPU for SMP suspend/resume support
|
||||
as well.
|
||||
|
||||
Q: What architectures support CPU hotplug?
|
||||
A: As of 2.6.14, the following architectures support CPU hotplug.
|
||||
|
||||
i386 (Intel), ppc, ppc64, parisc, s390, ia64 and x86_64
|
||||
|
||||
Q: How to test if hotplug is supported on the newly built kernel?
|
||||
A: You should now notice an entry in sysfs.
|
||||
|
||||
Check if sysfs is mounted, using the "mount" command. You should notice
|
||||
an entry as shown below in the output.
|
||||
|
||||
....
|
||||
none on /sys type sysfs (rw)
|
||||
....
|
||||
|
||||
if this is not mounted, do the following.
|
||||
|
||||
#mkdir /sysfs
|
||||
#mount -t sysfs sys /sys
|
||||
|
||||
now you should see entries for all present cpu, the following is an example
|
||||
in a 8-way system.
|
||||
|
||||
#pwd
|
||||
#/sys/devices/system/cpu
|
||||
#ls -l
|
||||
total 0
|
||||
drwxr-xr-x 10 root root 0 Sep 19 07:44 .
|
||||
drwxr-xr-x 13 root root 0 Sep 19 07:45 ..
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu0
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu1
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu2
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu3
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu4
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu5
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:44 cpu6
|
||||
drwxr-xr-x 3 root root 0 Sep 19 07:48 cpu7
|
||||
|
||||
Under each directory you would find an "online" file which is the control
|
||||
file to logically online/offline a processor.
|
||||
|
||||
Q: Does hot-add/hot-remove refer to physical add/remove of cpus?
|
||||
A: The usage of hot-add/remove may not be very consistently used in the code.
|
||||
CONFIG_CPU_HOTPLUG enables logical online/offline capability in the kernel.
|
||||
To support physical addition/removal, one would need some BIOS hooks and
|
||||
the platform should have something like an attention button in PCI hotplug.
|
||||
CONFIG_ACPI_HOTPLUG_CPU enables ACPI support for physical add/remove of CPUs.
|
||||
|
||||
Q: How do i logically offline a CPU?
|
||||
A: Do the following.
|
||||
|
||||
#echo 0 > /sys/devices/system/cpu/cpuX/online
|
||||
|
||||
once the logical offline is successful, check
|
||||
|
||||
#cat /proc/interrupts
|
||||
|
||||
you should now not see the CPU that you removed. Also online file will report
|
||||
the state as 0 when a cpu if offline and 1 when its online.
|
||||
|
||||
#To display the current cpu state.
|
||||
#cat /sys/devices/system/cpu/cpuX/online
|
||||
|
||||
Q: Why cant i remove CPU0 on some systems?
|
||||
A: Some architectures may have some special dependency on a certain CPU.
|
||||
|
||||
For e.g in IA64 platforms we have ability to sent platform interrupts to the
|
||||
OS. a.k.a Corrected Platform Error Interrupts (CPEI). In current ACPI
|
||||
specifications, we didn't have a way to change the target CPU. Hence if the
|
||||
current ACPI version doesn't support such re-direction, we disable that CPU
|
||||
by making it not-removable.
|
||||
|
||||
In such cases you will also notice that the online file is missing under cpu0.
|
||||
|
||||
Q: How do i find out if a particular CPU is not removable?
|
||||
A: Depending on the implementation, some architectures may show this by the
|
||||
absence of the "online" file. This is done if it can be determined ahead of
|
||||
time that this CPU cannot be removed.
|
||||
|
||||
In some situations, this can be a run time check, i.e if you try to remove the
|
||||
last CPU, this will not be permitted. You can find such failures by
|
||||
investigating the return value of the "echo" command.
|
||||
|
||||
Q: What happens when a CPU is being logically offlined?
|
||||
A: The following happen, listed in no particular order :-)
|
||||
|
||||
- A notification is sent to in-kernel registered modules by sending an event
|
||||
CPU_DOWN_PREPARE
|
||||
- All process is migrated away from this outgoing CPU to a new CPU
|
||||
- All interrupts targeted to this CPU is migrated to a new CPU
|
||||
- timers/bottom half/task lets are also migrated to a new CPU
|
||||
- Once all services are migrated, kernel calls an arch specific routine
|
||||
__cpu_disable() to perform arch specific cleanup.
|
||||
- Once this is successful, an event for successful cleanup is sent by an event
|
||||
CPU_DEAD.
|
||||
|
||||
"It is expected that each service cleans up when the CPU_DOWN_PREPARE
|
||||
notifier is called, when CPU_DEAD is called its expected there is nothing
|
||||
running on behalf of this CPU that was offlined"
|
||||
|
||||
Q: If i have some kernel code that needs to be aware of CPU arrival and
|
||||
departure, how to i arrange for proper notification?
|
||||
A: This is what you would need in your kernel code to receive notifications.
|
||||
|
||||
#include <linux/cpu.h>
|
||||
static int __cpuinit foobar_cpu_callback(struct notifier_block *nfb,
|
||||
unsigned long action, void *hcpu)
|
||||
{
|
||||
unsigned int cpu = (unsigned long)hcpu;
|
||||
|
||||
switch (action) {
|
||||
case CPU_ONLINE:
|
||||
foobar_online_action(cpu);
|
||||
break;
|
||||
case CPU_DEAD:
|
||||
foobar_dead_action(cpu);
|
||||
break;
|
||||
}
|
||||
return NOTIFY_OK;
|
||||
}
|
||||
|
||||
static struct notifier_block foobar_cpu_notifer =
|
||||
{
|
||||
.notifier_call = foobar_cpu_callback,
|
||||
};
|
||||
|
||||
|
||||
In your init function,
|
||||
|
||||
register_cpu_notifier(&foobar_cpu_notifier);
|
||||
|
||||
You can fail PREPARE notifiers if something doesn't work to prepare resources.
|
||||
This will stop the activity and send a following CANCELED event back.
|
||||
|
||||
CPU_DEAD should not be failed, its just a goodness indication, but bad
|
||||
things will happen if a notifier in path sent a BAD notify code.
|
||||
|
||||
Q: I don't see my action being called for all CPUs already up and running?
|
||||
A: Yes, CPU notifiers are called only when new CPUs are on-lined or offlined.
|
||||
If you need to perform some action for each cpu already in the system, then
|
||||
|
||||
for_each_online_cpu(i) {
|
||||
foobar_cpu_callback(&foobar_cpu_notifier, CPU_UP_PREPARE, i);
|
||||
foobar_cpu_callback(&foobar-cpu_notifier, CPU_ONLINE, i);
|
||||
}
|
||||
|
||||
Q: If i would like to develop cpu hotplug support for a new architecture,
|
||||
what do i need at a minimum?
|
||||
A: The following are what is required for CPU hotplug infrastructure to work
|
||||
correctly.
|
||||
|
||||
- Make sure you have an entry in Kconfig to enable CONFIG_HOTPLUG_CPU
|
||||
- __cpu_up() - Arch interface to bring up a CPU
|
||||
- __cpu_disable() - Arch interface to shutdown a CPU, no more interrupts
|
||||
can be handled by the kernel after the routine
|
||||
returns. Including local APIC timers etc are
|
||||
shutdown.
|
||||
- __cpu_die() - This actually supposed to ensure death of the CPU.
|
||||
Actually look at some example code in other arch
|
||||
that implement CPU hotplug. The processor is taken
|
||||
down from the idle() loop for that specific
|
||||
architecture. __cpu_die() typically waits for some
|
||||
per_cpu state to be set, to ensure the processor
|
||||
dead routine is called to be sure positively.
|
||||
|
||||
Q: I need to ensure that a particular cpu is not removed when there is some
|
||||
work specific to this cpu is in progress.
|
||||
A: First switch the current thread context to preferred cpu
|
||||
|
||||
int my_func_on_cpu(int cpu)
|
||||
{
|
||||
cpumask_t saved_mask, new_mask = CPU_MASK_NONE;
|
||||
int curr_cpu, err = 0;
|
||||
|
||||
saved_mask = current->cpus_allowed;
|
||||
cpu_set(cpu, new_mask);
|
||||
err = set_cpus_allowed(current, new_mask);
|
||||
|
||||
if (err)
|
||||
return err;
|
||||
|
||||
/*
|
||||
* If we got scheduled out just after the return from
|
||||
* set_cpus_allowed() before running the work, this ensures
|
||||
* we stay locked.
|
||||
*/
|
||||
curr_cpu = get_cpu();
|
||||
|
||||
if (curr_cpu != cpu) {
|
||||
err = -EAGAIN;
|
||||
goto ret;
|
||||
} else {
|
||||
/*
|
||||
* Do work : But cant sleep, since get_cpu() disables preempt
|
||||
*/
|
||||
}
|
||||
ret:
|
||||
put_cpu();
|
||||
set_cpus_allowed(current, saved_mask);
|
||||
return err;
|
||||
}
|
||||
|
||||
|
||||
Q: How do we determine how many CPUs are available for hotplug.
|
||||
A: There is no clear spec defined way from ACPI that can give us that
|
||||
information today. Based on some input from Natalie of Unisys,
|
||||
that the ACPI MADT (Multiple APIC Description Tables) marks those possible
|
||||
CPUs in a system with disabled status.
|
||||
|
||||
Andi implemented some simple heuristics that count the number of disabled
|
||||
CPUs in MADT as hotpluggable CPUS. In the case there are no disabled CPUS
|
||||
we assume 1/2 the number of CPUs currently present can be hotplugged.
|
||||
|
||||
Caveat: Today's ACPI MADT can only provide 256 entries since the apicid field
|
||||
in MADT is only 8 bits.
|
||||
|
||||
User Space Notification
|
||||
|
||||
Hotplug support for devices is common in Linux today. Its being used today to
|
||||
support automatic configuration of network, usb and pci devices. A hotplug
|
||||
event can be used to invoke an agent script to perform the configuration task.
|
||||
|
||||
You can add /etc/hotplug/cpu.agent to handle hotplug notification user space
|
||||
scripts.
|
||||
|
||||
#!/bin/bash
|
||||
# $Id: cpu.agent
|
||||
# Kernel hotplug params include:
|
||||
#ACTION=%s [online or offline]
|
||||
#DEVPATH=%s
|
||||
#
|
||||
cd /etc/hotplug
|
||||
. ./hotplug.functions
|
||||
|
||||
case $ACTION in
|
||||
online)
|
||||
echo `date` ":cpu.agent" add cpu >> /tmp/hotplug.txt
|
||||
;;
|
||||
offline)
|
||||
echo `date` ":cpu.agent" remove cpu >>/tmp/hotplug.txt
|
||||
;;
|
||||
*)
|
||||
debug_mesg CPU $ACTION event not supported
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
|
@ -14,7 +14,10 @@ CONTENTS:
|
|||
1.1 What are cpusets ?
|
||||
1.2 Why are cpusets needed ?
|
||||
1.3 How are cpusets implemented ?
|
||||
1.4 How do I use cpusets ?
|
||||
1.4 What are exclusive cpusets ?
|
||||
1.5 What does notify_on_release do ?
|
||||
1.6 What is memory_pressure ?
|
||||
1.7 How do I use cpusets ?
|
||||
2. Usage Examples and Syntax
|
||||
2.1 Basic Usage
|
||||
2.2 Adding/removing cpus
|
||||
|
|
@ -49,29 +52,6 @@ its cpus_allowed vector, and the kernel page allocator will not
|
|||
allocate a page on a node that is not allowed in the requesting tasks
|
||||
mems_allowed vector.
|
||||
|
||||
If a cpuset is cpu or mem exclusive, no other cpuset, other than a direct
|
||||
ancestor or descendent, may share any of the same CPUs or Memory Nodes.
|
||||
A cpuset that is cpu exclusive has a sched domain associated with it.
|
||||
The sched domain consists of all cpus in the current cpuset that are not
|
||||
part of any exclusive child cpusets.
|
||||
This ensures that the scheduler load balacing code only balances
|
||||
against the cpus that are in the sched domain as defined above and not
|
||||
all of the cpus in the system. This removes any overhead due to
|
||||
load balancing code trying to pull tasks outside of the cpu exclusive
|
||||
cpuset only to be prevented by the tasks' cpus_allowed mask.
|
||||
|
||||
A cpuset that is mem_exclusive restricts kernel allocations for
|
||||
page, buffer and other data commonly shared by the kernel across
|
||||
multiple users. All cpusets, whether mem_exclusive or not, restrict
|
||||
allocations of memory for user space. This enables configuring a
|
||||
system so that several independent jobs can share common kernel
|
||||
data, such as file system pages, while isolating each jobs user
|
||||
allocation in its own cpuset. To do this, construct a large
|
||||
mem_exclusive cpuset to hold all the jobs, and construct child,
|
||||
non-mem_exclusive cpusets for each individual job. Only a small
|
||||
amount of typical kernel memory, such as requests from interrupt
|
||||
handlers, is allowed to be taken outside even a mem_exclusive cpuset.
|
||||
|
||||
User level code may create and destroy cpusets by name in the cpuset
|
||||
virtual file system, manage the attributes and permissions of these
|
||||
cpusets and which CPUs and Memory Nodes are assigned to each cpuset,
|
||||
|
|
@ -192,9 +172,15 @@ containing the following files describing that cpuset:
|
|||
|
||||
- cpus: list of CPUs in that cpuset
|
||||
- mems: list of Memory Nodes in that cpuset
|
||||
- memory_migrate flag: if set, move pages to cpusets nodes
|
||||
- cpu_exclusive flag: is cpu placement exclusive?
|
||||
- mem_exclusive flag: is memory placement exclusive?
|
||||
- tasks: list of tasks (by pid) attached to that cpuset
|
||||
- notify_on_release flag: run /sbin/cpuset_release_agent on exit?
|
||||
- memory_pressure: measure of how much paging pressure in cpuset
|
||||
|
||||
In addition, the root cpuset only has the following file:
|
||||
- memory_pressure_enabled flag: compute memory_pressure?
|
||||
|
||||
New cpusets are created using the mkdir system call or shell
|
||||
command. The properties of a cpuset, such as its flags, allowed
|
||||
|
|
@ -228,7 +214,108 @@ exclusive cpuset. Also, the use of a Linux virtual file system (vfs)
|
|||
to represent the cpuset hierarchy provides for a familiar permission
|
||||
and name space for cpusets, with a minimum of additional kernel code.
|
||||
|
||||
1.4 How do I use cpusets ?
|
||||
|
||||
1.4 What are exclusive cpusets ?
|
||||
--------------------------------
|
||||
|
||||
If a cpuset is cpu or mem exclusive, no other cpuset, other than
|
||||
a direct ancestor or descendent, may share any of the same CPUs or
|
||||
Memory Nodes.
|
||||
|
||||
A cpuset that is cpu_exclusive has a scheduler (sched) domain
|
||||
associated with it. The sched domain consists of all CPUs in the
|
||||
current cpuset that are not part of any exclusive child cpusets.
|
||||
This ensures that the scheduler load balancing code only balances
|
||||
against the CPUs that are in the sched domain as defined above and
|
||||
not all of the CPUs in the system. This removes any overhead due to
|
||||
load balancing code trying to pull tasks outside of the cpu_exclusive
|
||||
cpuset only to be prevented by the tasks' cpus_allowed mask.
|
||||
|
||||
A cpuset that is mem_exclusive restricts kernel allocations for
|
||||
page, buffer and other data commonly shared by the kernel across
|
||||
multiple users. All cpusets, whether mem_exclusive or not, restrict
|
||||
allocations of memory for user space. This enables configuring a
|
||||
system so that several independent jobs can share common kernel data,
|
||||
such as file system pages, while isolating each jobs user allocation in
|
||||
its own cpuset. To do this, construct a large mem_exclusive cpuset to
|
||||
hold all the jobs, and construct child, non-mem_exclusive cpusets for
|
||||
each individual job. Only a small amount of typical kernel memory,
|
||||
such as requests from interrupt handlers, is allowed to be taken
|
||||
outside even a mem_exclusive cpuset.
|
||||
|
||||
|
||||
1.5 What does notify_on_release do ?
|
||||
------------------------------------
|
||||
|
||||
If the notify_on_release flag is enabled (1) in a cpuset, then whenever
|
||||
the last task in the cpuset leaves (exits or attaches to some other
|
||||
cpuset) and the last child cpuset of that cpuset is removed, then
|
||||
the kernel runs the command /sbin/cpuset_release_agent, supplying the
|
||||
pathname (relative to the mount point of the cpuset file system) of the
|
||||
abandoned cpuset. This enables automatic removal of abandoned cpusets.
|
||||
The default value of notify_on_release in the root cpuset at system
|
||||
boot is disabled (0). The default value of other cpusets at creation
|
||||
is the current value of their parents notify_on_release setting.
|
||||
|
||||
|
||||
1.6 What is memory_pressure ?
|
||||
-----------------------------
|
||||
The memory_pressure of a cpuset provides a simple per-cpuset metric
|
||||
of the rate that the tasks in a cpuset are attempting to free up in
|
||||
use memory on the nodes of the cpuset to satisfy additional memory
|
||||
requests.
|
||||
|
||||
This enables batch managers monitoring jobs running in dedicated
|
||||
cpusets to efficiently detect what level of memory pressure that job
|
||||
is causing.
|
||||
|
||||
This is useful both on tightly managed systems running a wide mix of
|
||||
submitted jobs, which may choose to terminate or re-prioritize jobs that
|
||||
are trying to use more memory than allowed on the nodes assigned them,
|
||||
and with tightly coupled, long running, massively parallel scientific
|
||||
computing jobs that will dramatically fail to meet required performance
|
||||
goals if they start to use more memory than allowed to them.
|
||||
|
||||
This mechanism provides a very economical way for the batch manager
|
||||
to monitor a cpuset for signs of memory pressure. It's up to the
|
||||
batch manager or other user code to decide what to do about it and
|
||||
take action.
|
||||
|
||||
==> Unless this feature is enabled by writing "1" to the special file
|
||||
/dev/cpuset/memory_pressure_enabled, the hook in the rebalance
|
||||
code of __alloc_pages() for this metric reduces to simply noticing
|
||||
that the cpuset_memory_pressure_enabled flag is zero. So only
|
||||
systems that enable this feature will compute the metric.
|
||||
|
||||
Why a per-cpuset, running average:
|
||||
|
||||
Because this meter is per-cpuset, rather than per-task or mm,
|
||||
the system load imposed by a batch scheduler monitoring this
|
||||
metric is sharply reduced on large systems, because a scan of
|
||||
the tasklist can be avoided on each set of queries.
|
||||
|
||||
Because this meter is a running average, instead of an accumulating
|
||||
counter, a batch scheduler can detect memory pressure with a
|
||||
single read, instead of having to read and accumulate results
|
||||
for a period of time.
|
||||
|
||||
Because this meter is per-cpuset rather than per-task or mm,
|
||||
the batch scheduler can obtain the key information, memory
|
||||
pressure in a cpuset, with a single read, rather than having to
|
||||
query and accumulate results over all the (dynamically changing)
|
||||
set of tasks in the cpuset.
|
||||
|
||||
A per-cpuset simple digital filter (requires a spinlock and 3 words
|
||||
of data per-cpuset) is kept, and updated by any task attached to that
|
||||
cpuset, if it enters the synchronous (direct) page reclaim code.
|
||||
|
||||
A per-cpuset file provides an integer number representing the recent
|
||||
(half-life of 10 seconds) rate of direct page reclaims caused by
|
||||
the tasks in the cpuset, in units of reclaims attempted per second,
|
||||
times 1000.
|
||||
|
||||
|
||||
1.7 How do I use cpusets ?
|
||||
--------------------------
|
||||
|
||||
In order to minimize the impact of cpusets on critical kernel
|
||||
|
|
@ -277,6 +364,30 @@ rewritten to the 'tasks' file of its cpuset. This is done to avoid
|
|||
impacting the scheduler code in the kernel with a check for changes
|
||||
in a tasks processor placement.
|
||||
|
||||
Normally, once a page is allocated (given a physical page
|
||||
of main memory) then that page stays on whatever node it
|
||||
was allocated, so long as it remains allocated, even if the
|
||||
cpusets memory placement policy 'mems' subsequently changes.
|
||||
If the cpuset flag file 'memory_migrate' is set true, then when
|
||||
tasks are attached to that cpuset, any pages that task had
|
||||
allocated to it on nodes in its previous cpuset are migrated
|
||||
to the tasks new cpuset. Depending on the implementation,
|
||||
this migration may either be done by swapping the page out,
|
||||
so that the next time the page is referenced, it will be paged
|
||||
into the tasks new cpuset, usually on the node where it was
|
||||
referenced, or this migration may be done by directly copying
|
||||
the pages from the tasks previous cpuset to the new cpuset,
|
||||
where possible to the same node, relative to the new cpuset,
|
||||
as the node that held the page, relative to the old cpuset.
|
||||
Also if 'memory_migrate' is set true, then if that cpusets
|
||||
'mems' file is modified, pages allocated to tasks in that
|
||||
cpuset, that were on nodes in the previous setting of 'mems',
|
||||
will be moved to nodes in the new setting of 'mems.' Again,
|
||||
depending on the implementation, this might be done by swapping,
|
||||
or by direct copying. In either case, pages that were not in
|
||||
the tasks prior cpuset, or in the cpusets prior 'mems' setting,
|
||||
will not be moved.
|
||||
|
||||
There is an exception to the above. If hotplug functionality is used
|
||||
to remove all the CPUs that are currently assigned to a cpuset,
|
||||
then the kernel will automatically update the cpus_allowed of all
|
||||
|
|
|
|||
|
|
@ -22,6 +22,11 @@ journal=inum When a journal already exists, this option is
|
|||
the inode which will represent the ext3 file
|
||||
system's journal file.
|
||||
|
||||
journal_dev=devnum When the external journal device's major/minor numbers
|
||||
have changed, this option allows to specify the new
|
||||
journal location. The journal device is identified
|
||||
through its new major/minor numbers encoded in devnum.
|
||||
|
||||
noload Don't load the journal on mounting.
|
||||
|
||||
data=journal All data are committed into the journal prior
|
||||
|
|
|
|||
|
|
@ -1302,6 +1302,23 @@ 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.
|
||||
|
||||
|
||||
2.5 /proc/sys/dev - Device specific parameters
|
||||
----------------------------------------------
|
||||
|
||||
|
|
|
|||
|
|
@ -143,12 +143,26 @@ as the following example:
|
|||
dir /mnt 755 0 0
|
||||
file /init initramfs/init.sh 755 0 0
|
||||
|
||||
Run "usr/gen_init_cpio" (after the kernel build) to get a usage message
|
||||
documenting the above file format.
|
||||
|
||||
One advantage of the text file is that root access is not required to
|
||||
set permissions or create device nodes in the new archive. (Note that those
|
||||
two example "file" entries expect to find files named "init.sh" and "busybox" in
|
||||
a directory called "initramfs", under the linux-2.6.* directory. See
|
||||
Documentation/early-userspace/README for more details.)
|
||||
|
||||
The kernel does not depend on external cpio tools, gen_init_cpio is created
|
||||
from usr/gen_init_cpio.c which is entirely self-contained, and the kernel's
|
||||
boot-time extractor is also (obviously) self-contained. However, if you _do_
|
||||
happen to have cpio installed, the following command line can extract the
|
||||
generated cpio image back into its component files:
|
||||
|
||||
cpio -i -d -H newc -F initramfs_data.cpio --no-absolute-filenames
|
||||
|
||||
Contents of initramfs:
|
||||
----------------------
|
||||
|
||||
If you don't already understand what shared libraries, devices, and paths
|
||||
you need to get a minimal root filesystem up and running, here are some
|
||||
references:
|
||||
|
|
@ -161,13 +175,69 @@ designed to be a tiny C library to statically link early userspace
|
|||
code against, along with some related utilities. It is BSD licensed.
|
||||
|
||||
I use uClibc (http://www.uclibc.org) and busybox (http://www.busybox.net)
|
||||
myself. These are LGPL and GPL, respectively.
|
||||
myself. These are LGPL and GPL, respectively. (A self-contained initramfs
|
||||
package is planned for the busybox 1.2 release.)
|
||||
|
||||
In theory you could use glibc, but that's not well suited for small embedded
|
||||
uses like this. (A "hello world" program statically linked against glibc is
|
||||
over 400k. With uClibc it's 7k. Also note that glibc dlopens libnss to do
|
||||
name lookups, even when otherwise statically linked.)
|
||||
|
||||
Why cpio rather than tar?
|
||||
-------------------------
|
||||
|
||||
This decision was made back in December, 2001. The discussion started here:
|
||||
|
||||
http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1538.html
|
||||
|
||||
And spawned a second thread (specifically on tar vs cpio), starting here:
|
||||
|
||||
http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1587.html
|
||||
|
||||
The quick and dirty summary version (which is no substitute for reading
|
||||
the above threads) is:
|
||||
|
||||
1) cpio is a standard. It's decades old (from the AT&T days), and already
|
||||
widely used on Linux (inside RPM, Red Hat's device driver disks). Here's
|
||||
a Linux Journal article about it from 1996:
|
||||
|
||||
http://www.linuxjournal.com/article/1213
|
||||
|
||||
It's not as popular as tar because the traditional cpio command line tools
|
||||
require _truly_hideous_ command line arguments. But that says nothing
|
||||
either way about the archive format, and there are alternative tools,
|
||||
such as:
|
||||
|
||||
http://freshmeat.net/projects/afio/
|
||||
|
||||
2) The cpio archive format chosen by the kernel is simpler and cleaner (and
|
||||
thus easier to create and parse) than any of the (literally dozens of)
|
||||
various tar archive formats. The complete initramfs archive format is
|
||||
explained in buffer-format.txt, created in usr/gen_init_cpio.c, and
|
||||
extracted in init/initramfs.c. All three together come to less than 26k
|
||||
total of human-readable text.
|
||||
|
||||
3) The GNU project standardizing on tar is approximately as relevant as
|
||||
Windows standardizing on zip. Linux is not part of either, and is free
|
||||
to make its own technical decisions.
|
||||
|
||||
4) Since this is a kernel internal format, it could easily have been
|
||||
something brand new. The kernel provides its own tools to create and
|
||||
extract this format anyway. Using an existing standard was preferable,
|
||||
but not essential.
|
||||
|
||||
5) Al Viro made the decision (quote: "tar is ugly as hell and not going to be
|
||||
supported on the kernel side"):
|
||||
|
||||
http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1540.html
|
||||
|
||||
explained his reasoning:
|
||||
|
||||
http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1550.html
|
||||
http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1638.html
|
||||
|
||||
and, most importantly, designed and implemented the initramfs code.
|
||||
|
||||
Future directions:
|
||||
------------------
|
||||
|
||||
|
|
|
|||
|
|
@ -44,30 +44,41 @@ relayfs can operate in a mode where it will overwrite data not yet
|
|||
collected by userspace, and not wait for it to consume it.
|
||||
|
||||
relayfs itself does not provide for communication of such data between
|
||||
userspace and kernel, allowing the kernel side to remain simple and not
|
||||
impose a single interface on userspace. It does provide a separate
|
||||
helper though, described below.
|
||||
userspace and kernel, allowing the kernel side to remain simple and
|
||||
not impose a single interface on userspace. It does provide a set of
|
||||
examples and a separate helper though, described below.
|
||||
|
||||
klog, relay-app & librelay
|
||||
==========================
|
||||
klog and relay-apps example code
|
||||
================================
|
||||
|
||||
relayfs itself is ready to use, but to make things easier, two
|
||||
additional systems are provided. klog is a simple wrapper to make
|
||||
writing formatted text or raw data to a channel simpler, regardless of
|
||||
whether a channel to write into exists or not, or whether relayfs is
|
||||
compiled into the kernel or is configured as a module. relay-app is
|
||||
the kernel counterpart of userspace librelay.c, combined these two
|
||||
files provide glue to easily stream data to disk, without having to
|
||||
bother with housekeeping. klog and relay-app can be used together,
|
||||
with klog providing high-level logging functions to the kernel and
|
||||
relay-app taking care of kernel-user control and disk-logging chores.
|
||||
relayfs itself is ready to use, but to make things easier, a couple
|
||||
simple utility functions and a set of examples are provided.
|
||||
|
||||
It is possible to use relayfs without relay-app & librelay, but you'll
|
||||
have to implement communication between userspace and kernel, allowing
|
||||
both to convey the state of buffers (full, empty, amount of padding).
|
||||
The relay-apps example tarball, available on the relayfs sourceforge
|
||||
site, contains a set of self-contained examples, each consisting of a
|
||||
pair of .c files containing boilerplate code for each of the user and
|
||||
kernel sides of a relayfs application; combined these two sets of
|
||||
boilerplate code provide glue to easily stream data to disk, without
|
||||
having to bother with mundane housekeeping chores.
|
||||
|
||||
The 'klog debugging functions' patch (klog.patch in the relay-apps
|
||||
tarball) provides a couple of high-level logging functions to the
|
||||
kernel which allow writing formatted text or raw data to a channel,
|
||||
regardless of whether a channel to write into exists or not, or
|
||||
whether relayfs is compiled into the kernel or is configured as a
|
||||
module. These functions allow you to put unconditional 'trace'
|
||||
statements anywhere in the kernel or kernel modules; only when there
|
||||
is a 'klog handler' registered will data actually be logged (see the
|
||||
klog and kleak examples for details).
|
||||
|
||||
It is of course possible to use relayfs from scratch i.e. without
|
||||
using any of the relay-apps example code or klog, but you'll have to
|
||||
implement communication between userspace and kernel, allowing both to
|
||||
convey the state of buffers (full, empty, amount of padding).
|
||||
|
||||
klog and the relay-apps examples can be found in the relay-apps
|
||||
tarball on http://relayfs.sourceforge.net
|
||||
|
||||
klog, relay-app and librelay can be found in the relay-apps tarball on
|
||||
http://relayfs.sourceforge.net
|
||||
|
||||
The relayfs user space API
|
||||
==========================
|
||||
|
|
@ -125,6 +136,8 @@ Here's a summary of the API relayfs provides to in-kernel clients:
|
|||
relay_reset(chan)
|
||||
relayfs_create_dir(name, parent)
|
||||
relayfs_remove_dir(dentry)
|
||||
relayfs_create_file(name, parent, mode, fops, data)
|
||||
relayfs_remove_file(dentry)
|
||||
|
||||
channel management typically called on instigation of userspace:
|
||||
|
||||
|
|
@ -141,6 +154,8 @@ Here's a summary of the API relayfs provides to in-kernel clients:
|
|||
subbuf_start(buf, subbuf, prev_subbuf, prev_padding)
|
||||
buf_mapped(buf, filp)
|
||||
buf_unmapped(buf, filp)
|
||||
create_buf_file(filename, parent, mode, buf, is_global)
|
||||
remove_buf_file(dentry)
|
||||
|
||||
helper functions:
|
||||
|
||||
|
|
@ -320,6 +335,71 @@ forces a sub-buffer switch on all the channel buffers, and can be used
|
|||
to finalize and process the last sub-buffers before the channel is
|
||||
closed.
|
||||
|
||||
Creating non-relay files
|
||||
------------------------
|
||||
|
||||
relay_open() automatically creates files in the relayfs filesystem to
|
||||
represent the per-cpu kernel buffers; it's often useful for
|
||||
applications to be able to create their own files alongside the relay
|
||||
files in the relayfs filesystem as well e.g. 'control' files much like
|
||||
those created in /proc or debugfs for similar purposes, used to
|
||||
communicate control information between the kernel and user sides of a
|
||||
relayfs application. For this purpose the relayfs_create_file() and
|
||||
relayfs_remove_file() API functions exist. For relayfs_create_file(),
|
||||
the caller passes in a set of user-defined file operations to be used
|
||||
for the file and an optional void * to a user-specified data item,
|
||||
which will be accessible via inode->u.generic_ip (see the relay-apps
|
||||
tarball for examples). The file_operations are a required parameter
|
||||
to relayfs_create_file() and thus the semantics of these files are
|
||||
completely defined by the caller.
|
||||
|
||||
See the relay-apps tarball at http://relayfs.sourceforge.net for
|
||||
examples of how these non-relay files are meant to be used.
|
||||
|
||||
Creating relay files in other filesystems
|
||||
-----------------------------------------
|
||||
|
||||
By default of course, relay_open() creates relay files in the relayfs
|
||||
filesystem. Because relay_file_operations is exported, however, it's
|
||||
also possible to create and use relay files in other pseudo-filesytems
|
||||
such as debugfs.
|
||||
|
||||
For this purpose, two callback functions are provided,
|
||||
create_buf_file() and remove_buf_file(). create_buf_file() is called
|
||||
once for each per-cpu buffer from relay_open() to allow the client to
|
||||
create a file to be used to represent the corresponding buffer; if
|
||||
this callback is not defined, the default implementation will create
|
||||
and return a file in the relayfs filesystem to represent the buffer.
|
||||
The callback should return the dentry of the file created to represent
|
||||
the relay buffer. Note that the parent directory passed to
|
||||
relay_open() (and passed along to the callback), if specified, must
|
||||
exist in the same filesystem the new relay file is created in. If
|
||||
create_buf_file() is defined, remove_buf_file() must also be defined;
|
||||
it's responsible for deleting the file(s) created in create_buf_file()
|
||||
and is called during relay_close().
|
||||
|
||||
The create_buf_file() implementation can also be defined in such a way
|
||||
as to allow the creation of a single 'global' buffer instead of the
|
||||
default per-cpu set. This can be useful for applications interested
|
||||
mainly in seeing the relative ordering of system-wide events without
|
||||
the need to bother with saving explicit timestamps for the purpose of
|
||||
merging/sorting per-cpu files in a postprocessing step.
|
||||
|
||||
To have relay_open() create a global buffer, the create_buf_file()
|
||||
implementation should set the value of the is_global outparam to a
|
||||
non-zero value in addition to creating the file that will be used to
|
||||
represent the single buffer. In the case of a global buffer,
|
||||
create_buf_file() and remove_buf_file() will be called only once. The
|
||||
normal channel-writing functions e.g. relay_write() can still be used
|
||||
- writes from any cpu will transparently end up in the global buffer -
|
||||
but since it is a global buffer, callers should make sure they use the
|
||||
proper locking for such a buffer, either by wrapping writes in a
|
||||
spinlock, or by copying a write function from relayfs_fs.h and
|
||||
creating a local version that internally does the proper locking.
|
||||
|
||||
See the 'exported-relayfile' examples in the relay-apps tarball for
|
||||
examples of creating and using relay files in debugfs.
|
||||
|
||||
Misc
|
||||
----
|
||||
|
||||
|
|
|
|||
|
|
@ -56,10 +56,12 @@ A request proceeds in the following manner:
|
|||
(4) request_key() then forks and executes /sbin/request-key with a new session
|
||||
keyring that contains a link to auth key V.
|
||||
|
||||
(5) /sbin/request-key execs an appropriate program to perform the actual
|
||||
(5) /sbin/request-key assumes the authority associated with key U.
|
||||
|
||||
(6) /sbin/request-key execs an appropriate program to perform the actual
|
||||
instantiation.
|
||||
|
||||
(6) The program may want to access another key from A's context (say a
|
||||
(7) The program may want to access another key from A's context (say a
|
||||
Kerberos TGT key). It just requests the appropriate key, and the keyring
|
||||
search notes that the session keyring has auth key V in its bottom level.
|
||||
|
||||
|
|
@ -67,19 +69,19 @@ A request proceeds in the following manner:
|
|||
UID, GID, groups and security info of process A as if it was process A,
|
||||
and come up with key W.
|
||||
|
||||
(7) The program then does what it must to get the data with which to
|
||||
(8) The program then does what it must to get the data with which to
|
||||
instantiate key U, using key W as a reference (perhaps it contacts a
|
||||
Kerberos server using the TGT) and then instantiates key U.
|
||||
|
||||
(8) Upon instantiating key U, auth key V is automatically revoked so that it
|
||||
(9) Upon instantiating key U, auth key V is automatically revoked so that it
|
||||
may not be used again.
|
||||
|
||||
(9) The program then exits 0 and request_key() deletes key V and returns key
|
||||
(10) The program then exits 0 and request_key() deletes key V and returns key
|
||||
U to the caller.
|
||||
|
||||
This also extends further. If key W (step 5 above) didn't exist, key W would be
|
||||
created uninstantiated, another auth key (X) would be created [as per step 3]
|
||||
and another copy of /sbin/request-key spawned [as per step 4]; but the context
|
||||
This also extends further. If key W (step 7 above) didn't exist, key W would be
|
||||
created uninstantiated, another auth key (X) would be created (as per step 3)
|
||||
and another copy of /sbin/request-key spawned (as per step 4); but the context
|
||||
specified by auth key X will still be process A, as it was in auth key V.
|
||||
|
||||
This is because process A's keyrings can't simply be attached to
|
||||
|
|
@ -138,8 +140,8 @@ until one succeeds:
|
|||
|
||||
(3) The process's session keyring is searched.
|
||||
|
||||
(4) If the process has a request_key() authorisation key in its session
|
||||
keyring then:
|
||||
(4) If the process has assumed the authority associated with a request_key()
|
||||
authorisation key then:
|
||||
|
||||
(a) If extant, the calling process's thread keyring is searched.
|
||||
|
||||
|
|
|
|||
|
|
@ -308,6 +308,8 @@ process making the call:
|
|||
KEY_SPEC_USER_KEYRING -4 UID-specific keyring
|
||||
KEY_SPEC_USER_SESSION_KEYRING -5 UID-session keyring
|
||||
KEY_SPEC_GROUP_KEYRING -6 GID-specific keyring
|
||||
KEY_SPEC_REQKEY_AUTH_KEY -7 assumed request_key()
|
||||
authorisation key
|
||||
|
||||
|
||||
The main syscalls are:
|
||||
|
|
@ -498,7 +500,11 @@ The keyctl syscall functions are:
|
|||
keyring is full, error ENFILE will result.
|
||||
|
||||
The link procedure checks the nesting of the keyrings, returning ELOOP if
|
||||
it appears to deep or EDEADLK if the link would introduce a cycle.
|
||||
it appears too deep or EDEADLK if the link would introduce a cycle.
|
||||
|
||||
Any links within the keyring to keys that match the new key in terms of
|
||||
type and description will be discarded from the keyring as the new one is
|
||||
added.
|
||||
|
||||
|
||||
(*) Unlink a key or keyring from another keyring:
|
||||
|
|
@ -628,6 +634,41 @@ The keyctl syscall functions are:
|
|||
there is one, otherwise the user default session keyring.
|
||||
|
||||
|
||||
(*) Set the timeout on a key.
|
||||
|
||||
long keyctl(KEYCTL_SET_TIMEOUT, key_serial_t key, unsigned timeout);
|
||||
|
||||
This sets or clears the timeout on a key. The timeout can be 0 to clear
|
||||
the timeout or a number of seconds to set the expiry time that far into
|
||||
the future.
|
||||
|
||||
The process must have attribute modification access on a key to set its
|
||||
timeout. Timeouts may not be set with this function on negative, revoked
|
||||
or expired keys.
|
||||
|
||||
|
||||
(*) Assume the authority granted to instantiate a key
|
||||
|
||||
long keyctl(KEYCTL_ASSUME_AUTHORITY, key_serial_t key);
|
||||
|
||||
This assumes or divests the authority required to instantiate the
|
||||
specified key. Authority can only be assumed if the thread has the
|
||||
authorisation key associated with the specified key in its keyrings
|
||||
somewhere.
|
||||
|
||||
Once authority is assumed, searches for keys will also search the
|
||||
requester's keyrings using the requester's security label, UID, GID and
|
||||
groups.
|
||||
|
||||
If the requested authority is unavailable, error EPERM will be returned,
|
||||
likewise if the authority has been revoked because the target key is
|
||||
already instantiated.
|
||||
|
||||
If the specified key is 0, then any assumed authority will be divested.
|
||||
|
||||
The assumed authorititive key is inherited across fork and exec.
|
||||
|
||||
|
||||
===============
|
||||
KERNEL SERVICES
|
||||
===============
|
||||
|
|
|
|||
|
|
@ -26,12 +26,13 @@ Currently, these files are in /proc/sys/vm:
|
|||
- min_free_kbytes
|
||||
- laptop_mode
|
||||
- block_dump
|
||||
- drop-caches
|
||||
|
||||
==============================================================
|
||||
|
||||
dirty_ratio, dirty_background_ratio, dirty_expire_centisecs,
|
||||
dirty_writeback_centisecs, vfs_cache_pressure, laptop_mode,
|
||||
block_dump, swap_token_timeout:
|
||||
block_dump, swap_token_timeout, drop-caches:
|
||||
|
||||
See Documentation/filesystems/proc.txt
|
||||
|
||||
|
|
@ -102,3 +103,20 @@ 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
|
||||
a number of reserved free pages based proportionally on its size.
|
||||
|
||||
==============================================================
|
||||
|
||||
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.
|
||||
|
|
|
|||
|
|
@ -927,7 +927,6 @@ S: Maintained
|
|||
FARSYNC SYNCHRONOUS DRIVER
|
||||
P: Kevin Curtis
|
||||
M: kevin.curtis@farsite.co.uk
|
||||
M: kevin.curtis@farsite.co.uk
|
||||
W: http://www.farsite.co.uk/
|
||||
S: Supported
|
||||
|
||||
|
|
|
|||
7
README
7
README
|
|
@ -183,11 +183,8 @@ CONFIGURING the kernel:
|
|||
|
||||
COMPILING the kernel:
|
||||
|
||||
- Make sure you have gcc 2.95.3 available.
|
||||
gcc 2.91.66 (egcs-1.1.2), and gcc 2.7.2.3 are known to miscompile
|
||||
some parts of the kernel, and are *no longer supported*.
|
||||
Also remember to upgrade your binutils package (for as/ld/nm and company)
|
||||
if necessary. For more information, refer to Documentation/Changes.
|
||||
- Make sure you have at least gcc 3.2 available.
|
||||
For more information, refer to Documentation/Changes.
|
||||
|
||||
Please note that you can still run a.out user programs with this kernel.
|
||||
|
||||
|
|
|
|||
|
|
@ -18,9 +18,6 @@ config MMU
|
|||
bool
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
|
||||
|
|
|
|||
|
|
@ -43,6 +43,11 @@
|
|||
#include "proto.h"
|
||||
#include "pci_impl.h"
|
||||
|
||||
/*
|
||||
* Power off function, if any
|
||||
*/
|
||||
void (*pm_power_off)(void) = machine_power_off;
|
||||
|
||||
void
|
||||
cpu_idle(void)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -265,30 +265,16 @@ do_sys_ptrace(long request, long pid, long addr, long data,
|
|||
lock_kernel();
|
||||
DBG(DBG_MEM, ("request=%ld pid=%ld addr=0x%lx data=0x%lx\n",
|
||||
request, pid, addr, data));
|
||||
ret = -EPERM;
|
||||
if (request == PTRACE_TRACEME) {
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED)
|
||||
goto out_notsk;
|
||||
ret = security_ptrace(current->parent, current);
|
||||
if (ret)
|
||||
goto out_notsk;
|
||||
/* set the ptrace bit in the process ptrace flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = 0;
|
||||
ret = ptrace_traceme();
|
||||
goto out_notsk;
|
||||
}
|
||||
if (pid == 1) /* you may not mess with init */
|
||||
goto out_notsk;
|
||||
|
||||
ret = -ESRCH;
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
if (!child)
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
goto out_notsk;
|
||||
}
|
||||
|
||||
if (request == PTRACE_ATTACH) {
|
||||
ret = ptrace_attach(child);
|
||||
|
|
|
|||
|
|
@ -46,10 +46,6 @@ config MCA
|
|||
<file:Documentation/mca.txt> (and especially the web page given
|
||||
there) before attempting to build an MCA bus kernel.
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -13,6 +13,7 @@
|
|||
|
||||
#include <linux/device.h>
|
||||
#include <linux/string.h>
|
||||
#include <linux/slab.h>
|
||||
#include <linux/platform_device.h>
|
||||
#include <asm/io.h>
|
||||
#include <asm/hardware/scoop.h>
|
||||
|
|
|
|||
|
|
@ -23,20 +23,15 @@
|
|||
#error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32
|
||||
#endif
|
||||
/*
|
||||
* GCC 2.95.1, 2.95.2: ignores register clobber list in asm().
|
||||
* GCC 3.0, 3.1: general bad code generation.
|
||||
* GCC 3.2.0: incorrect function argument offset calculation.
|
||||
* GCC 3.2.x: miscompiles NEW_AUX_ENT in fs/binfmt_elf.c
|
||||
* (http://gcc.gnu.org/PR8896) and incorrect structure
|
||||
* initialisation in fs/jffs2/erase.c
|
||||
*/
|
||||
#if __GNUC__ < 2 || \
|
||||
(__GNUC__ == 2 && __GNUC_MINOR__ < 95) || \
|
||||
(__GNUC__ == 2 && __GNUC_MINOR__ == 95 && __GNUC_PATCHLEVEL__ != 0 && \
|
||||
__GNUC_PATCHLEVEL__ < 3) || \
|
||||
(__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
#if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
#error Your compiler is too buggy; it is known to miscompile kernels.
|
||||
#error Known good compilers: 2.95.3, 2.95.4, 2.96, 3.3
|
||||
#error Known good compilers: 3.3
|
||||
#endif
|
||||
|
||||
/* Use marker if you need to separate the values later */
|
||||
|
|
|
|||
|
|
@ -684,8 +684,12 @@ int setup_irq(unsigned int irq, struct irqaction *new)
|
|||
spin_lock_irqsave(&irq_controller_lock, flags);
|
||||
p = &desc->action;
|
||||
if ((old = *p) != NULL) {
|
||||
/* Can't share interrupts unless both agree to */
|
||||
if (!(old->flags & new->flags & SA_SHIRQ)) {
|
||||
/*
|
||||
* Can't share interrupts unless both agree to and are
|
||||
* the same type.
|
||||
*/
|
||||
if (!(old->flags & new->flags & SA_SHIRQ) ||
|
||||
(~old->flags & new->flags) & SA_TRIGGER_MASK) {
|
||||
spin_unlock_irqrestore(&irq_controller_lock, flags);
|
||||
return -EBUSY;
|
||||
}
|
||||
|
|
@ -705,6 +709,12 @@ int setup_irq(unsigned int irq, struct irqaction *new)
|
|||
desc->running = 0;
|
||||
desc->pending = 0;
|
||||
desc->disable_depth = 1;
|
||||
|
||||
if (new->flags & SA_TRIGGER_MASK) {
|
||||
unsigned int type = new->flags & SA_TRIGGER_MASK;
|
||||
desc->chip->set_type(irq, type);
|
||||
}
|
||||
|
||||
if (!desc->noautoenable) {
|
||||
desc->disable_depth = 0;
|
||||
desc->chip->unmask(irq);
|
||||
|
|
|
|||
|
|
@ -601,6 +601,7 @@ EXPORT_SYMBOL(gpio_lock);
|
|||
EXPORT_SYMBOL(gpio_modify_op);
|
||||
EXPORT_SYMBOL(gpio_modify_io);
|
||||
EXPORT_SYMBOL(cpld_modify);
|
||||
EXPORT_SYMBOL(gpio_read);
|
||||
|
||||
/*
|
||||
* Initialise any other hardware after we've got the PCI bus
|
||||
|
|
|
|||
|
|
@ -96,7 +96,8 @@ static struct rtc_ops rtc_ops = {
|
|||
.set_alarm = rtc_set_alarm,
|
||||
};
|
||||
|
||||
static irqreturn_t rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
|
||||
static irqreturn_t arm_rtc_interrupt(int irq, void *dev_id,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
writel(0, rtc_base + RTC_EOI);
|
||||
return IRQ_HANDLED;
|
||||
|
|
@ -124,7 +125,7 @@ static int rtc_probe(struct amba_device *dev, void *id)
|
|||
|
||||
xtime.tv_sec = __raw_readl(rtc_base + RTC_DR);
|
||||
|
||||
ret = request_irq(dev->irq[0], rtc_interrupt, SA_INTERRUPT,
|
||||
ret = request_irq(dev->irq[0], arm_rtc_interrupt, SA_INTERRUPT,
|
||||
"rtc-pl030", dev);
|
||||
if (ret)
|
||||
goto map_out;
|
||||
|
|
|
|||
|
|
@ -252,9 +252,8 @@ static void __init omap_serial_set_port_wakeup(int gpio_nr)
|
|||
return;
|
||||
}
|
||||
omap_set_gpio_direction(gpio_nr, 1);
|
||||
set_irq_type(OMAP_GPIO_IRQ(gpio_nr), IRQT_RISING);
|
||||
ret = request_irq(OMAP_GPIO_IRQ(gpio_nr), &omap_serial_wake_interrupt,
|
||||
0, "serial wakeup", NULL);
|
||||
SA_TRIGGER_RISING, "serial wakeup", NULL);
|
||||
if (ret) {
|
||||
omap_free_gpio(gpio_nr);
|
||||
printk(KERN_ERR "No interrupt for UART wake GPIO: %i\n",
|
||||
|
|
|
|||
|
|
@ -213,15 +213,14 @@ static int corgi_mci_init(struct device *dev, irqreturn_t (*corgi_detect_int)(in
|
|||
|
||||
corgi_mci_platform_data.detect_delay = msecs_to_jiffies(250);
|
||||
|
||||
err = request_irq(CORGI_IRQ_GPIO_nSD_DETECT, corgi_detect_int, SA_INTERRUPT,
|
||||
"MMC card detect", data);
|
||||
err = request_irq(CORGI_IRQ_GPIO_nSD_DETECT, corgi_detect_int,
|
||||
SA_INTERRUPT | SA_TRIGGER_RISING | SA_TRIGGER_FALLING,
|
||||
"MMC card detect", data);
|
||||
if (err) {
|
||||
printk(KERN_ERR "corgi_mci_init: MMC/SD: can't request MMC card detect IRQ\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
set_irq_type(CORGI_IRQ_GPIO_nSD_DETECT, IRQT_BOTHEDGE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -146,15 +146,14 @@ static int poodle_mci_init(struct device *dev, irqreturn_t (*poodle_detect_int)(
|
|||
|
||||
poodle_mci_platform_data.detect_delay = msecs_to_jiffies(250);
|
||||
|
||||
err = request_irq(POODLE_IRQ_GPIO_nSD_DETECT, poodle_detect_int, SA_INTERRUPT,
|
||||
"MMC card detect", data);
|
||||
err = request_irq(POODLE_IRQ_GPIO_nSD_DETECT, poodle_detect_int,
|
||||
SA_INTERRUPT | SA_TRIGGER_RISING | SA_TRIGGER_FALLING,
|
||||
"MMC card detect", data);
|
||||
if (err) {
|
||||
printk(KERN_ERR "poodle_mci_init: MMC/SD: can't request MMC card detect IRQ\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
set_irq_type(POODLE_IRQ_GPIO_nSD_DETECT, IRQT_BOTHEDGE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -296,15 +296,14 @@ static int spitz_mci_init(struct device *dev, irqreturn_t (*spitz_detect_int)(in
|
|||
|
||||
spitz_mci_platform_data.detect_delay = msecs_to_jiffies(250);
|
||||
|
||||
err = request_irq(SPITZ_IRQ_GPIO_nSD_DETECT, spitz_detect_int, SA_INTERRUPT,
|
||||
"MMC card detect", data);
|
||||
err = request_irq(SPITZ_IRQ_GPIO_nSD_DETECT, spitz_detect_int,
|
||||
SA_INTERRUPT | SA_TRIGGER_RISING | SA_TRIGGER_FALLING,
|
||||
"MMC card detect", data);
|
||||
if (err) {
|
||||
printk(KERN_ERR "spitz_mci_init: MMC/SD: can't request MMC card detect IRQ\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
set_irq_type(SPITZ_IRQ_GPIO_nSD_DETECT, IRQT_BOTHEDGE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -13,6 +13,7 @@
|
|||
#include <linux/delay.h>
|
||||
#include <linux/device.h>
|
||||
#include <linux/smp.h>
|
||||
#include <linux/jiffies.h>
|
||||
|
||||
#include <asm/mach/time.h>
|
||||
#include <asm/hardware/arm_twd.h>
|
||||
|
|
|
|||
|
|
@ -84,13 +84,13 @@ static void usb_simtec_enableoc(struct s3c2410_hcd_info *info, int on)
|
|||
int ret;
|
||||
|
||||
if (on) {
|
||||
ret = request_irq(IRQ_USBOC, usb_simtec_ocirq, SA_INTERRUPT,
|
||||
ret = request_irq(IRQ_USBOC, usb_simtec_ocirq,
|
||||
SA_INTERRUPT | SA_TRIGGER_RISING |
|
||||
SA_TRIGGER_FALLING,
|
||||
"USB Over-current", info);
|
||||
if (ret != 0) {
|
||||
printk(KERN_ERR "failed to request usb oc irq\n");
|
||||
}
|
||||
|
||||
set_irq_type(IRQ_USBOC, IRQT_BOTHEDGE);
|
||||
} else {
|
||||
free_irq(IRQ_USBOC, info);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -34,10 +34,6 @@ config FORCE_MAX_ZONEORDER
|
|||
int
|
||||
default 9
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -25,13 +25,6 @@
|
|||
#if defined(__APCS_32__) && defined(CONFIG_CPU_26)
|
||||
#error Sorry, your compiler targets APCS-32 but this kernel requires APCS-26
|
||||
#endif
|
||||
#if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 95)
|
||||
#error Sorry, your compiler is known to miscompile kernels. Only use gcc 2.95.3 and later.
|
||||
#endif
|
||||
#if __GNUC__ == 2 && __GNUC_MINOR__ == 95
|
||||
/* shame we can't detect the .1 or .2 releases */
|
||||
#warning GCC 2.95.2 and earlier miscompiles kernels.
|
||||
#endif
|
||||
|
||||
/* Use marker if you need to separate the values later */
|
||||
|
||||
|
|
|
|||
|
|
@ -9,10 +9,6 @@ config MMU
|
|||
bool
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -274,6 +274,11 @@ config GPREL_DATA_NONE
|
|||
|
||||
endchoice
|
||||
|
||||
config FRV_ONCPU_SERIAL
|
||||
bool "Use on-CPU serial ports"
|
||||
select SERIAL_8250
|
||||
default y
|
||||
|
||||
config PCI
|
||||
bool "Use PCI"
|
||||
depends on MB93090_MB00
|
||||
|
|
@ -305,23 +310,7 @@ config RESERVE_DMA_COHERENT
|
|||
|
||||
source "drivers/pci/Kconfig"
|
||||
|
||||
config PCMCIA
|
||||
tristate "Use PCMCIA"
|
||||
help
|
||||
Say Y here if you want to attach PCMCIA- or PC-cards to your FR-V
|
||||
board. These are credit-card size devices such as network cards,
|
||||
modems or hard drives often used with laptops computers. There are
|
||||
actually two varieties of these cards: the older 16 bit PCMCIA cards
|
||||
and the newer 32 bit CardBus cards. If you want to use CardBus
|
||||
cards, you need to say Y here and also to "CardBus support" below.
|
||||
|
||||
To use your PC-cards, you will need supporting software from David
|
||||
Hinds pcmcia-cs package (see the file <file:Documentation/Changes>
|
||||
for location). Please also read the PCMCIA-HOWTO, available from
|
||||
<http://www.tldp.org/docs.html#howto>.
|
||||
|
||||
To compile this driver as modules, choose M here: the
|
||||
modules will be called pcmcia_core and ds.
|
||||
source "drivers/pcmcia/Kconfig"
|
||||
|
||||
#config MATH_EMULATION
|
||||
# bool "Math emulation support (EXPERIMENTAL)"
|
||||
|
|
|
|||
|
|
@ -2,32 +2,10 @@ menu "Kernel hacking"
|
|||
|
||||
source "lib/Kconfig.debug"
|
||||
|
||||
config EARLY_PRINTK
|
||||
bool "Early printk"
|
||||
depends on EMBEDDED && DEBUG_KERNEL
|
||||
default n
|
||||
help
|
||||
Write kernel log output directly into the VGA buffer or to a serial
|
||||
port.
|
||||
|
||||
This is useful for kernel debugging when your machine crashes very
|
||||
early before the console code is initialized. For normal operation
|
||||
it is not recommended because it looks ugly and doesn't cooperate
|
||||
with klogd/syslogd or the X server. You should normally N here,
|
||||
unless you want to debug such a crash.
|
||||
|
||||
config DEBUG_STACKOVERFLOW
|
||||
bool "Check for stack overflows"
|
||||
depends on DEBUG_KERNEL
|
||||
|
||||
config DEBUG_PAGEALLOC
|
||||
bool "Page alloc debugging"
|
||||
depends on DEBUG_KERNEL
|
||||
help
|
||||
Unmap pages from the kernel linear mapping after free_pages().
|
||||
This results in a large slowdown, but helps to find certain types
|
||||
of memory corruptions.
|
||||
|
||||
config GDBSTUB
|
||||
bool "Remote GDB kernel debugging"
|
||||
depends on DEBUG_KERNEL
|
||||
|
|
|
|||
|
|
@ -109,10 +109,10 @@ bootstrap:
|
|||
$(Q)$(MAKEBOOT) bootstrap
|
||||
|
||||
archmrproper:
|
||||
$(Q)$(MAKE) -C arch/frv/boot mrproper
|
||||
$(Q)$(MAKE) $(build)=arch/frv/boot mrproper
|
||||
|
||||
archclean:
|
||||
$(Q)$(MAKE) -C arch/frv/boot clean
|
||||
$(Q)$(MAKE) $(build)=arch/frv/boot clean
|
||||
|
||||
archdep: scripts/mkdep symlinks
|
||||
$(Q)$(MAKE) -C arch/frv/boot dep
|
||||
$(Q)$(MAKE) $(build)=arch/frv/boot dep
|
||||
|
|
|
|||
|
|
@ -21,3 +21,4 @@ obj-$(CONFIG_PM) += pm.o cmode.o
|
|||
obj-$(CONFIG_MB93093_PDK) += pm-mb93093.o
|
||||
obj-$(CONFIG_SYSCTL) += sysctl.o
|
||||
obj-$(CONFIG_FUTEX) += futex.o
|
||||
obj-$(CONFIG_MODULES) += module.o
|
||||
|
|
|
|||
|
|
@ -16,10 +16,11 @@
|
|||
#include <asm/semaphore.h>
|
||||
#include <asm/checksum.h>
|
||||
#include <asm/hardirq.h>
|
||||
#include <asm/current.h>
|
||||
#include <asm/cacheflush.h>
|
||||
|
||||
extern void dump_thread(struct pt_regs *, struct user *);
|
||||
extern long __memcpy_user(void *dst, const void *src, size_t count);
|
||||
extern long __memset_user(void *dst, const void *src, size_t count);
|
||||
|
||||
/* platform dependent support */
|
||||
|
||||
|
|
@ -50,7 +51,11 @@ EXPORT_SYMBOL(disable_irq);
|
|||
EXPORT_SYMBOL(__res_bus_clock_speed_HZ);
|
||||
EXPORT_SYMBOL(__page_offset);
|
||||
EXPORT_SYMBOL(__memcpy_user);
|
||||
EXPORT_SYMBOL(flush_dcache_page);
|
||||
EXPORT_SYMBOL(__memset_user);
|
||||
EXPORT_SYMBOL(frv_dcache_writeback);
|
||||
EXPORT_SYMBOL(frv_cache_invalidate);
|
||||
EXPORT_SYMBOL(frv_icache_invalidate);
|
||||
EXPORT_SYMBOL(frv_cache_wback_inv);
|
||||
|
||||
#ifndef CONFIG_MMU
|
||||
EXPORT_SYMBOL(memory_start);
|
||||
|
|
@ -72,6 +77,9 @@ EXPORT_SYMBOL(memcmp);
|
|||
EXPORT_SYMBOL(memscan);
|
||||
EXPORT_SYMBOL(memmove);
|
||||
|
||||
EXPORT_SYMBOL(__outsl_ns);
|
||||
EXPORT_SYMBOL(__insl_ns);
|
||||
|
||||
EXPORT_SYMBOL(get_wchan);
|
||||
|
||||
#ifdef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
|
||||
|
|
@ -80,14 +88,13 @@ EXPORT_SYMBOL(atomic_test_and_OR_mask);
|
|||
EXPORT_SYMBOL(atomic_test_and_XOR_mask);
|
||||
EXPORT_SYMBOL(atomic_add_return);
|
||||
EXPORT_SYMBOL(atomic_sub_return);
|
||||
EXPORT_SYMBOL(__xchg_8);
|
||||
EXPORT_SYMBOL(__xchg_16);
|
||||
EXPORT_SYMBOL(__xchg_32);
|
||||
EXPORT_SYMBOL(__cmpxchg_8);
|
||||
EXPORT_SYMBOL(__cmpxchg_16);
|
||||
EXPORT_SYMBOL(__cmpxchg_32);
|
||||
#endif
|
||||
|
||||
EXPORT_SYMBOL(__debug_bug_printk);
|
||||
EXPORT_SYMBOL(__delay_loops_MHz);
|
||||
|
||||
/*
|
||||
* libgcc functions - functions that are used internally by the
|
||||
* compiler... (prototypes are not correct though, but that
|
||||
|
|
@ -101,6 +108,8 @@ extern void __divdi3(void);
|
|||
extern void __lshrdi3(void);
|
||||
extern void __moddi3(void);
|
||||
extern void __muldi3(void);
|
||||
extern void __mulll(void);
|
||||
extern void __umulll(void);
|
||||
extern void __negdi2(void);
|
||||
extern void __ucmpdi2(void);
|
||||
extern void __udivdi3(void);
|
||||
|
|
@ -116,8 +125,10 @@ EXPORT_SYMBOL(__ashrdi3);
|
|||
EXPORT_SYMBOL(__lshrdi3);
|
||||
//EXPORT_SYMBOL(__moddi3);
|
||||
EXPORT_SYMBOL(__muldi3);
|
||||
EXPORT_SYMBOL(__mulll);
|
||||
EXPORT_SYMBOL(__umulll);
|
||||
EXPORT_SYMBOL(__negdi2);
|
||||
//EXPORT_SYMBOL(__ucmpdi2);
|
||||
EXPORT_SYMBOL(__ucmpdi2);
|
||||
//EXPORT_SYMBOL(__udivdi3);
|
||||
//EXPORT_SYMBOL(__udivmoddi4);
|
||||
//EXPORT_SYMBOL(__umoddi3);
|
||||
|
|
|
|||
|
|
@ -32,6 +32,7 @@
|
|||
#include <linux/irq.h>
|
||||
#include <linux/proc_fs.h>
|
||||
#include <linux/seq_file.h>
|
||||
#include <linux/module.h>
|
||||
|
||||
#include <asm/atomic.h>
|
||||
#include <asm/io.h>
|
||||
|
|
@ -178,6 +179,8 @@ void disable_irq_nosync(unsigned int irq)
|
|||
spin_unlock_irqrestore(&level->lock, flags);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(disable_irq_nosync);
|
||||
|
||||
/**
|
||||
* disable_irq - disable an irq and wait for completion
|
||||
* @irq: Interrupt to disable
|
||||
|
|
@ -204,6 +207,8 @@ void disable_irq(unsigned int irq)
|
|||
#endif
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(disable_irq);
|
||||
|
||||
/**
|
||||
* enable_irq - enable handling of an irq
|
||||
* @irq: Interrupt to enable
|
||||
|
|
@ -268,6 +273,8 @@ void enable_irq(unsigned int irq)
|
|||
spin_unlock_irqrestore(&level->lock, flags);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(enable_irq);
|
||||
|
||||
/*****************************************************************************/
|
||||
/*
|
||||
* handles all normal device IRQ's
|
||||
|
|
@ -425,6 +432,8 @@ int request_irq(unsigned int irq,
|
|||
return retval;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(request_irq);
|
||||
|
||||
/**
|
||||
* free_irq - free an interrupt
|
||||
* @irq: Interrupt line to free
|
||||
|
|
@ -496,6 +505,8 @@ void free_irq(unsigned int irq, void *dev_id)
|
|||
}
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(free_irq);
|
||||
|
||||
/*
|
||||
* IRQ autodetection code..
|
||||
*
|
||||
|
|
@ -519,6 +530,8 @@ unsigned long probe_irq_on(void)
|
|||
return 0;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(probe_irq_on);
|
||||
|
||||
/*
|
||||
* Return a mask of triggered interrupts (this
|
||||
* can handle only legacy ISA interrupts).
|
||||
|
|
@ -542,6 +555,8 @@ unsigned int probe_irq_mask(unsigned long xmask)
|
|||
return 0;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(probe_irq_mask);
|
||||
|
||||
/*
|
||||
* Return the one interrupt that triggered (this can
|
||||
* handle any interrupt source).
|
||||
|
|
@ -571,6 +586,8 @@ int probe_irq_off(unsigned long xmask)
|
|||
return -1;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(probe_irq_off);
|
||||
|
||||
/* this was setup_x86_irq but it seems pretty generic */
|
||||
int setup_irq(unsigned int irq, struct irqaction *new)
|
||||
{
|
||||
|
|
|
|||
80
arch/frv/kernel/module.c
Normal file
80
arch/frv/kernel/module.c
Normal file
|
|
@ -0,0 +1,80 @@
|
|||
/* module.c: FRV specific module loading bits
|
||||
*
|
||||
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
|
||||
* Written by David Howells (dhowells@redhat.com)
|
||||
* - Derived from arch/i386/kernel/module.c, Copyright (C) 2001 Rusty Russell.
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or
|
||||
* modify it under the terms of the GNU General Public License
|
||||
* as published by the Free Software Foundation; either version
|
||||
* 2 of the License, or (at your option) any later version.
|
||||
*/
|
||||
#include <linux/moduleloader.h>
|
||||
#include <linux/elf.h>
|
||||
#include <linux/vmalloc.h>
|
||||
#include <linux/fs.h>
|
||||
#include <linux/string.h>
|
||||
#include <linux/kernel.h>
|
||||
|
||||
#if 0
|
||||
#define DEBUGP printk
|
||||
#else
|
||||
#define DEBUGP(fmt...)
|
||||
#endif
|
||||
|
||||
void *module_alloc(unsigned long size)
|
||||
{
|
||||
if (size == 0)
|
||||
return NULL;
|
||||
|
||||
return vmalloc_exec(size);
|
||||
}
|
||||
|
||||
|
||||
/* Free memory returned from module_alloc */
|
||||
void module_free(struct module *mod, void *module_region)
|
||||
{
|
||||
vfree(module_region);
|
||||
/* FIXME: If module_region == mod->init_region, trim exception
|
||||
table entries. */
|
||||
}
|
||||
|
||||
/* We don't need anything special. */
|
||||
int module_frob_arch_sections(Elf_Ehdr *hdr,
|
||||
Elf_Shdr *sechdrs,
|
||||
char *secstrings,
|
||||
struct module *mod)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
int apply_relocate(Elf32_Shdr *sechdrs,
|
||||
const char *strtab,
|
||||
unsigned int symindex,
|
||||
unsigned int relsec,
|
||||
struct module *me)
|
||||
{
|
||||
printk(KERN_ERR "module %s: ADD RELOCATION unsupported\n", me->name);
|
||||
return -ENOEXEC;
|
||||
}
|
||||
|
||||
int apply_relocate_add(Elf32_Shdr *sechdrs,
|
||||
const char *strtab,
|
||||
unsigned int symindex,
|
||||
unsigned int relsec,
|
||||
struct module *me)
|
||||
{
|
||||
printk(KERN_ERR "module %s: ADD RELOCATION unsupported\n", me->name);
|
||||
return -ENOEXEC;
|
||||
}
|
||||
|
||||
int module_finalize(const Elf_Ehdr *hdr,
|
||||
const Elf_Shdr *sechdrs,
|
||||
struct module *me)
|
||||
{
|
||||
return 0;
|
||||
}
|
||||
|
||||
void module_arch_cleanup(struct module *mod)
|
||||
{
|
||||
}
|
||||
|
|
@ -13,6 +13,7 @@
|
|||
|
||||
#include <linux/config.h>
|
||||
#include <linux/init.h>
|
||||
#include <linux/module.h>
|
||||
#include <linux/pm.h>
|
||||
#include <linux/pm_legacy.h>
|
||||
#include <linux/sched.h>
|
||||
|
|
@ -27,6 +28,7 @@
|
|||
#include "local.h"
|
||||
|
||||
void (*pm_power_off)(void);
|
||||
EXPORT_SYMBOL(pm_power_off);
|
||||
|
||||
extern void frv_change_cmode(int);
|
||||
|
||||
|
|
|
|||
|
|
@ -787,6 +787,7 @@ void __init setup_arch(char **cmdline_p)
|
|||
#endif
|
||||
|
||||
/* register those serial ports that are available */
|
||||
#ifdef CONFIG_FRV_ONCPU_SERIAL
|
||||
#ifndef CONFIG_GDBSTUB_UART0
|
||||
__reg(UART0_BASE + UART_IER * 8) = 0;
|
||||
early_serial_setup(&__frv_uart0);
|
||||
|
|
@ -795,6 +796,7 @@ void __init setup_arch(char **cmdline_p)
|
|||
__reg(UART1_BASE + UART_IER * 8) = 0;
|
||||
early_serial_setup(&__frv_uart1);
|
||||
#endif
|
||||
#endif
|
||||
|
||||
#if defined(CONFIG_CHR_DEV_FLASH) || defined(CONFIG_BLK_DEV_FLASH)
|
||||
/* we need to initialize the Flashrom device here since we might
|
||||
|
|
|
|||
|
|
@ -189,6 +189,8 @@ void do_gettimeofday(struct timeval *tv)
|
|||
tv->tv_usec = usec;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(do_gettimeofday);
|
||||
|
||||
int do_settimeofday(struct timespec *tv)
|
||||
{
|
||||
time_t wtm_sec, sec = tv->tv_sec;
|
||||
|
|
@ -218,6 +220,7 @@ int do_settimeofday(struct timespec *tv)
|
|||
clock_was_set();
|
||||
return 0;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(do_settimeofday);
|
||||
|
||||
/*
|
||||
|
|
|
|||
|
|
@ -19,6 +19,7 @@
|
|||
#include <linux/string.h>
|
||||
#include <linux/linkage.h>
|
||||
#include <linux/init.h>
|
||||
#include <linux/module.h>
|
||||
|
||||
#include <asm/setup.h>
|
||||
#include <asm/fpu.h>
|
||||
|
|
@ -250,6 +251,8 @@ void dump_stack(void)
|
|||
show_stack(NULL, NULL);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dump_stack);
|
||||
|
||||
void show_stack(struct task_struct *task, unsigned long *sp)
|
||||
{
|
||||
}
|
||||
|
|
|
|||
|
|
@ -10,6 +10,7 @@
|
|||
*/
|
||||
|
||||
#include <linux/mm.h>
|
||||
#include <linux/module.h>
|
||||
#include <asm/uaccess.h>
|
||||
|
||||
/*****************************************************************************/
|
||||
|
|
@ -58,8 +59,11 @@ long strncpy_from_user(char *dst, const char *src, long count)
|
|||
memset(p, 0, count); /* clear remainder of buffer [security] */
|
||||
|
||||
return err;
|
||||
|
||||
} /* end strncpy_from_user() */
|
||||
|
||||
EXPORT_SYMBOL(strncpy_from_user);
|
||||
|
||||
/*****************************************************************************/
|
||||
/*
|
||||
* Return the size of a string (including the ending 0)
|
||||
|
|
@ -92,4 +96,7 @@ long strnlen_user(const char *src, long count)
|
|||
}
|
||||
|
||||
return p - src + 1; /* return length including NUL */
|
||||
|
||||
} /* end strnlen_user() */
|
||||
|
||||
EXPORT_SYMBOL(strnlen_user);
|
||||
|
|
|
|||
|
|
@ -112,6 +112,7 @@ SECTIONS
|
|||
#endif
|
||||
)
|
||||
SCHED_TEXT
|
||||
LOCK_TEXT
|
||||
*(.fixup)
|
||||
*(.gnu.warning)
|
||||
*(.exitcall.exit)
|
||||
|
|
|
|||
|
|
@ -3,6 +3,6 @@
|
|||
#
|
||||
|
||||
lib-y := \
|
||||
__ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o \
|
||||
__ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o __ucmpdi2.o \
|
||||
checksum.o memcpy.o memset.o atomic-ops.o \
|
||||
outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o
|
||||
|
|
|
|||
45
arch/frv/lib/__ucmpdi2.S
Normal file
45
arch/frv/lib/__ucmpdi2.S
Normal file
|
|
@ -0,0 +1,45 @@
|
|||
/* __ucmpdi2.S: 64-bit unsigned compare
|
||||
*
|
||||
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
|
||||
* Written by David Howells (dhowells@redhat.com)
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or
|
||||
* modify it under the terms of the GNU General Public License
|
||||
* as published by the Free Software Foundation; either version
|
||||
* 2 of the License, or (at your option) any later version.
|
||||
*/
|
||||
|
||||
|
||||
.text
|
||||
.p2align 4
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# int __ucmpdi2(unsigned long long a [GR8:GR9],
|
||||
# unsigned long long b [GR10:GR11])
|
||||
#
|
||||
# - returns 0, 1, or 2 as a <, =, > b respectively.
|
||||
#
|
||||
###############################################################################
|
||||
.globl __ucmpdi2
|
||||
.type __ucmpdi2,@function
|
||||
__ucmpdi2:
|
||||
or.p gr8,gr0,gr4
|
||||
subcc gr8,gr10,gr0,icc0
|
||||
setlos.p #0,gr8
|
||||
bclr icc0,#2 ; a.msw < b.msw
|
||||
|
||||
setlos.p #2,gr8
|
||||
bhilr icc0,#0 ; a.msw > b.msw
|
||||
|
||||
subcc.p gr9,gr11,gr0,icc1
|
||||
setlos #0,gr8
|
||||
setlos.p #2,gr9
|
||||
setlos #1,gr7
|
||||
cknc icc1,cc6
|
||||
cor.p gr9,gr0,gr8, cc6,#1
|
||||
cckls icc1,cc4, cc6,#1
|
||||
andcr cc6,cc4,cc4
|
||||
cor gr7,gr0,gr8, cc4,#1
|
||||
bralr
|
||||
.size __ucmpdi2, .-__ucmpdi2
|
||||
|
|
@ -127,48 +127,6 @@ atomic_sub_return:
|
|||
|
||||
.size atomic_sub_return, .-atomic_sub_return
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# uint8_t __xchg_8(uint8_t i, uint8_t *v)
|
||||
#
|
||||
###############################################################################
|
||||
.globl __xchg_8
|
||||
.type __xchg_8,@function
|
||||
__xchg_8:
|
||||
or.p gr8,gr8,gr10
|
||||
0:
|
||||
orcc gr0,gr0,gr0,icc3 /* set ICC3.Z */
|
||||
ckeq icc3,cc7
|
||||
ldub.p @(gr9,gr0),gr8 /* LD.P/ORCR must be atomic */
|
||||
orcr cc7,cc7,cc3 /* set CC3 to true */
|
||||
cstb.p gr10,@(gr9,gr0) ,cc3,#1
|
||||
corcc gr29,gr29,gr0 ,cc3,#1 /* clear ICC3.Z if store happens */
|
||||
beq icc3,#0,0b
|
||||
bralr
|
||||
|
||||
.size __xchg_8, .-__xchg_8
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# uint16_t __xchg_16(uint16_t i, uint16_t *v)
|
||||
#
|
||||
###############################################################################
|
||||
.globl __xchg_16
|
||||
.type __xchg_16,@function
|
||||
__xchg_16:
|
||||
or.p gr8,gr8,gr10
|
||||
0:
|
||||
orcc gr0,gr0,gr0,icc3 /* set ICC3.Z */
|
||||
ckeq icc3,cc7
|
||||
lduh.p @(gr9,gr0),gr8 /* LD.P/ORCR must be atomic */
|
||||
orcr cc7,cc7,cc3 /* set CC3 to true */
|
||||
csth.p gr10,@(gr9,gr0) ,cc3,#1
|
||||
corcc gr29,gr29,gr0 ,cc3,#1 /* clear ICC3.Z if store happens */
|
||||
beq icc3,#0,0b
|
||||
bralr
|
||||
|
||||
.size __xchg_16, .-__xchg_16
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# uint32_t __xchg_32(uint32_t i, uint32_t *v)
|
||||
|
|
@ -190,56 +148,6 @@ __xchg_32:
|
|||
|
||||
.size __xchg_32, .-__xchg_32
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# uint8_t __cmpxchg_8(uint8_t *v, uint8_t test, uint8_t new)
|
||||
#
|
||||
###############################################################################
|
||||
.globl __cmpxchg_8
|
||||
.type __cmpxchg_8,@function
|
||||
__cmpxchg_8:
|
||||
or.p gr8,gr8,gr11
|
||||
0:
|
||||
orcc gr0,gr0,gr0,icc3
|
||||
ckeq icc3,cc7
|
||||
ldub.p @(gr11,gr0),gr8
|
||||
orcr cc7,cc7,cc3
|
||||
sub gr8,gr9,gr7
|
||||
sllicc gr7,#24,gr0,icc0
|
||||
bne icc0,#0,1f
|
||||
cstb.p gr10,@(gr11,gr0) ,cc3,#1
|
||||
corcc gr29,gr29,gr0 ,cc3,#1
|
||||
beq icc3,#0,0b
|
||||
1:
|
||||
bralr
|
||||
|
||||
.size __cmpxchg_8, .-__cmpxchg_8
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# uint16_t __cmpxchg_16(uint16_t *v, uint16_t test, uint16_t new)
|
||||
#
|
||||
###############################################################################
|
||||
.globl __cmpxchg_16
|
||||
.type __cmpxchg_16,@function
|
||||
__cmpxchg_16:
|
||||
or.p gr8,gr8,gr11
|
||||
0:
|
||||
orcc gr0,gr0,gr0,icc3
|
||||
ckeq icc3,cc7
|
||||
lduh.p @(gr11,gr0),gr8
|
||||
orcr cc7,cc7,cc3
|
||||
sub gr8,gr9,gr7
|
||||
sllicc gr7,#16,gr0,icc0
|
||||
bne icc0,#0,1f
|
||||
csth.p gr10,@(gr11,gr0) ,cc3,#1
|
||||
corcc gr29,gr29,gr0 ,cc3,#1
|
||||
beq icc3,#0,0b
|
||||
1:
|
||||
bralr
|
||||
|
||||
.size __cmpxchg_16, .-__cmpxchg_16
|
||||
|
||||
###############################################################################
|
||||
#
|
||||
# uint32_t __cmpxchg_32(uint32_t *v, uint32_t test, uint32_t new)
|
||||
|
|
|
|||
|
|
@ -33,6 +33,7 @@
|
|||
|
||||
#include <net/checksum.h>
|
||||
#include <asm/checksum.h>
|
||||
#include <linux/module.h>
|
||||
|
||||
static inline unsigned short from32to16(unsigned long x)
|
||||
{
|
||||
|
|
@ -115,34 +116,52 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
|
|||
return result;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(csum_partial);
|
||||
|
||||
/*
|
||||
* this routine is used for miscellaneous IP-like checksums, mainly
|
||||
* in icmp.c
|
||||
*/
|
||||
unsigned short ip_compute_csum(const unsigned char * buff, int len)
|
||||
{
|
||||
return ~do_csum(buff,len);
|
||||
return ~do_csum(buff, len);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(ip_compute_csum);
|
||||
|
||||
/*
|
||||
* copy from fs while checksumming, otherwise like csum_partial
|
||||
*/
|
||||
|
||||
unsigned int
|
||||
csum_partial_copy_from_user(const char *src, char *dst, int len, int sum, int *csum_err)
|
||||
csum_partial_copy_from_user(const char __user *src, char *dst,
|
||||
int len, int sum, int *csum_err)
|
||||
{
|
||||
if (csum_err) *csum_err = 0;
|
||||
memcpy(dst, src, len);
|
||||
int rem;
|
||||
|
||||
if (csum_err)
|
||||
*csum_err = 0;
|
||||
|
||||
rem = copy_from_user(dst, src, len);
|
||||
if (rem != 0) {
|
||||
if (csum_err)
|
||||
*csum_err = -EFAULT;
|
||||
memset(dst + len - rem, 0, rem);
|
||||
len = rem;
|
||||
}
|
||||
|
||||
return csum_partial(dst, len, sum);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(csum_partial_copy_from_user);
|
||||
|
||||
/*
|
||||
* copy from ds while checksumming, otherwise like csum_partial
|
||||
*/
|
||||
|
||||
unsigned int
|
||||
csum_partial_copy(const char *src, char *dst, int len, int sum)
|
||||
{
|
||||
memcpy(dst, src, len);
|
||||
return csum_partial(dst, len, sum);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(csum_partial_copy);
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@
|
|||
#
|
||||
|
||||
ifeq "$(CONFIG_PCI)" "y"
|
||||
obj-y := pci-frv.o pci-irq.o pci-vdk.o
|
||||
obj-y := pci-frv.o pci-irq.o pci-vdk.o pci-iomap.o
|
||||
|
||||
ifeq "$(CONFIG_MMU)" "y"
|
||||
obj-y += pci-dma.o
|
||||
|
|
|
|||
|
|
@ -83,6 +83,8 @@ void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_hand
|
|||
return NULL;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_alloc_coherent);
|
||||
|
||||
void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle)
|
||||
{
|
||||
struct dma_alloc_record *rec;
|
||||
|
|
@ -102,6 +104,8 @@ void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_
|
|||
BUG();
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_free_coherent);
|
||||
|
||||
/*
|
||||
* Map a single buffer of the indicated size for DMA in streaming mode.
|
||||
* The 32-bit bus address to use is returned.
|
||||
|
|
@ -120,6 +124,8 @@ dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
|
|||
return virt_to_bus(ptr);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_map_single);
|
||||
|
||||
/*
|
||||
* Map a set of buffers described by scatterlist in streaming
|
||||
* mode for DMA. This is the scather-gather version of the
|
||||
|
|
@ -150,3 +156,5 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
|
|||
|
||||
return nents;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_map_sg);
|
||||
|
|
|
|||
|
|
@ -28,11 +28,15 @@ void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_hand
|
|||
return ret;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_alloc_coherent);
|
||||
|
||||
void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle)
|
||||
{
|
||||
consistent_free(vaddr);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_free_coherent);
|
||||
|
||||
/*
|
||||
* Map a single buffer of the indicated size for DMA in streaming mode.
|
||||
* The 32-bit bus address to use is returned.
|
||||
|
|
@ -51,6 +55,8 @@ dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
|
|||
return virt_to_bus(ptr);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_map_single);
|
||||
|
||||
/*
|
||||
* Map a set of buffers described by scatterlist in streaming
|
||||
* mode for DMA. This is the scather-gather version of the
|
||||
|
|
@ -96,6 +102,8 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
|
|||
return nents;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_map_sg);
|
||||
|
||||
dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long offset,
|
||||
size_t size, enum dma_data_direction direction)
|
||||
{
|
||||
|
|
@ -103,3 +111,5 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long off
|
|||
flush_dcache_page(page);
|
||||
return (dma_addr_t) page_to_phys(page) + offset;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(dma_map_page);
|
||||
|
|
|
|||
29
arch/frv/mb93090-mb00/pci-iomap.c
Normal file
29
arch/frv/mb93090-mb00/pci-iomap.c
Normal file
|
|
@ -0,0 +1,29 @@
|
|||
/* pci-iomap.c: description
|
||||
*
|
||||
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
|
||||
* Written by David Howells (dhowells@redhat.com)
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or
|
||||
* modify it under the terms of the GNU General Public License
|
||||
* as published by the Free Software Foundation; either version
|
||||
* 2 of the License, or (at your option) any later version.
|
||||
*/
|
||||
#include <linux/pci.h>
|
||||
#include <linux/module.h>
|
||||
|
||||
void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
|
||||
{
|
||||
unsigned long start = pci_resource_start(dev, bar);
|
||||
unsigned long len = pci_resource_len(dev, bar);
|
||||
unsigned long flags = pci_resource_flags(dev, bar);
|
||||
|
||||
if (!len || !start)
|
||||
return NULL;
|
||||
|
||||
if ((flags & IORESOURCE_IO) || (flags & IORESOURCE_MEM))
|
||||
return (void __iomem *) start;
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(pci_iomap);
|
||||
|
|
@ -11,6 +11,7 @@
|
|||
#include <linux/sched.h>
|
||||
#include <linux/mm.h>
|
||||
#include <linux/highmem.h>
|
||||
#include <linux/module.h>
|
||||
#include <asm/pgalloc.h>
|
||||
|
||||
/*****************************************************************************/
|
||||
|
|
@ -38,6 +39,8 @@ void flush_dcache_page(struct page *page)
|
|||
|
||||
} /* end flush_dcache_page() */
|
||||
|
||||
EXPORT_SYMBOL(flush_dcache_page);
|
||||
|
||||
/*****************************************************************************/
|
||||
/*
|
||||
* ICI takes a virtual address and the page may not currently have one
|
||||
|
|
@ -64,3 +67,5 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
|
|||
}
|
||||
|
||||
} /* end flush_icache_user_range() */
|
||||
|
||||
EXPORT_SYMBOL(flush_icache_user_range);
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ static inline unsigned long search_one_table(const struct exception_table_entry
|
|||
*/
|
||||
unsigned long search_exception_table(unsigned long pc)
|
||||
{
|
||||
unsigned long ret = 0;
|
||||
const struct exception_table_entry *extab;
|
||||
|
||||
/* determine if the fault lay during a memcpy_user or a memset_user */
|
||||
if (__frame->lr == (unsigned long) &__memset_user_error_lr &&
|
||||
|
|
@ -55,9 +55,10 @@ unsigned long search_exception_table(unsigned long pc)
|
|||
*/
|
||||
return (unsigned long) &__memset_user_error_handler;
|
||||
}
|
||||
else if (__frame->lr == (unsigned long) &__memcpy_user_error_lr &&
|
||||
(unsigned long) &memcpy <= pc && pc < (unsigned long) &__memcpy_end
|
||||
) {
|
||||
|
||||
if (__frame->lr == (unsigned long) &__memcpy_user_error_lr &&
|
||||
(unsigned long) &memcpy <= pc && pc < (unsigned long) &__memcpy_end
|
||||
) {
|
||||
/* the fault occurred in a protected memset
|
||||
* - we search for the return address (in LR) instead of the program counter
|
||||
* - it was probably during a copy_to/from_user()
|
||||
|
|
@ -65,27 +66,10 @@ unsigned long search_exception_table(unsigned long pc)
|
|||
return (unsigned long) &__memcpy_user_error_handler;
|
||||
}
|
||||
|
||||
#ifndef CONFIG_MODULES
|
||||
/* there is only the kernel to search. */
|
||||
ret = search_one_table(__start___ex_table, __stop___ex_table - 1, pc);
|
||||
return ret;
|
||||
extab = search_exception_tables(pc);
|
||||
if (extab)
|
||||
return extab->fixup;
|
||||
|
||||
#else
|
||||
/* the kernel is the last "module" -- no need to treat it special */
|
||||
unsigned long flags;
|
||||
struct module *mp;
|
||||
return 0;
|
||||
|
||||
spin_lock_irqsave(&modlist_lock, flags);
|
||||
|
||||
for (mp = module_list; mp != NULL; mp = mp->next) {
|
||||
if (mp->ex_table_start == NULL || !(mp->flags & (MOD_RUNNING | MOD_INITIALIZING)))
|
||||
continue;
|
||||
ret = search_one_table(mp->ex_table_start, mp->ex_table_end - 1, pc);
|
||||
if (ret)
|
||||
break;
|
||||
}
|
||||
|
||||
spin_unlock_irqrestore(&modlist_lock, flags);
|
||||
return ret;
|
||||
#endif
|
||||
} /* end search_exception_table() */
|
||||
|
|
|
|||
|
|
@ -9,6 +9,7 @@
|
|||
* 2 of the License, or (at your option) any later version.
|
||||
*/
|
||||
#include <linux/highmem.h>
|
||||
#include <linux/module.h>
|
||||
|
||||
void *kmap(struct page *page)
|
||||
{
|
||||
|
|
@ -18,6 +19,8 @@ void *kmap(struct page *page)
|
|||
return kmap_high(page);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(kmap);
|
||||
|
||||
void kunmap(struct page *page)
|
||||
{
|
||||
if (in_interrupt())
|
||||
|
|
@ -27,7 +30,12 @@ void kunmap(struct page *page)
|
|||
kunmap_high(page);
|
||||
}
|
||||
|
||||
EXPORT_SYMBOL(kunmap);
|
||||
|
||||
struct page *kmap_atomic_to_page(void *ptr)
|
||||
{
|
||||
return virt_to_page(ptr);
|
||||
}
|
||||
|
||||
|
||||
EXPORT_SYMBOL(kmap_atomic_to_page);
|
||||
|
|
|
|||
|
|
@ -21,10 +21,6 @@ config FPU
|
|||
bool
|
||||
default n
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -29,10 +29,6 @@ config MMU
|
|||
config SBUS
|
||||
bool
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config GENERIC_ISA_DMA
|
||||
bool
|
||||
default y
|
||||
|
|
@ -630,10 +626,6 @@ config REGPARM
|
|||
and passes the first three arguments of a function call in registers.
|
||||
This will probably break binary only modules.
|
||||
|
||||
This feature is only enabled for gcc-3.0 and later - earlier compilers
|
||||
generate incorrect output with certain kernel constructs when
|
||||
-mregparm=3 is used.
|
||||
|
||||
config SECCOMP
|
||||
bool "Enable seccomp to safely compute untrusted bytecode"
|
||||
depends on PROC_FS
|
||||
|
|
@ -703,7 +695,7 @@ depends on PM && !X86_VISWS
|
|||
|
||||
config APM
|
||||
tristate "APM (Advanced Power Management) BIOS support"
|
||||
depends on PM && PM_LEGACY
|
||||
depends on PM
|
||||
---help---
|
||||
APM is a BIOS specification for saving power using several different
|
||||
techniques. This is mostly useful for battery powered laptops with
|
||||
|
|
|
|||
|
|
@ -37,10 +37,7 @@ CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
|
|||
# CPU-specific tuning. Anything which can be shared with UML should go here.
|
||||
include $(srctree)/arch/i386/Makefile.cpu
|
||||
|
||||
# -mregparm=3 works ok on gcc-3.0 and later
|
||||
#
|
||||
GCC_VERSION := $(call cc-version)
|
||||
cflags-$(CONFIG_REGPARM) += $(shell if [ $(GCC_VERSION) -ge 0300 ] ; then echo "-mregparm=3"; fi ;)
|
||||
cflags-$(CONFIG_REGPARM) += -mregparm=3
|
||||
|
||||
# Disable unit-at-a-time mode, it makes gcc use a lot more stack
|
||||
# due to the lack of sharing of stacklots.
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
# CPU tuning section - shared with UML.
|
||||
# Must change only cflags-y (or [yn]), not CFLAGS! That makes a difference for UML.
|
||||
|
||||
#-mtune exists since gcc 3.4, and some -mcpu flavors didn't exist in gcc 2.95.
|
||||
#-mtune exists since gcc 3.4
|
||||
HAS_MTUNE := $(call cc-option-yn, -mtune=i386)
|
||||
ifeq ($(HAS_MTUNE),y)
|
||||
tune = $(call cc-option,-mtune=$(1),)
|
||||
|
|
@ -14,7 +14,7 @@ cflags-$(CONFIG_M386) += -march=i386
|
|||
cflags-$(CONFIG_M486) += -march=i486
|
||||
cflags-$(CONFIG_M586) += -march=i586
|
||||
cflags-$(CONFIG_M586TSC) += -march=i586
|
||||
cflags-$(CONFIG_M586MMX) += $(call cc-option,-march=pentium-mmx,-march=i586)
|
||||
cflags-$(CONFIG_M586MMX) += -march=pentium-mmx
|
||||
cflags-$(CONFIG_M686) += -march=i686
|
||||
cflags-$(CONFIG_MPENTIUMII) += -march=i686 $(call tune,pentium2)
|
||||
cflags-$(CONFIG_MPENTIUMIII) += -march=i686 $(call tune,pentium3)
|
||||
|
|
@ -23,8 +23,8 @@ cflags-$(CONFIG_MPENTIUM4) += -march=i686 $(call tune,pentium4)
|
|||
cflags-$(CONFIG_MK6) += -march=k6
|
||||
# Please note, that patches that add -march=athlon-xp and friends are pointless.
|
||||
# They make zero difference whatsosever to performance at this time.
|
||||
cflags-$(CONFIG_MK7) += $(call cc-option,-march=athlon,-march=i686 $(align)-functions=4)
|
||||
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,$(call cc-option,-march=athlon,-march=i686 $(align)-functions=4))
|
||||
cflags-$(CONFIG_MK7) += -march=athlon
|
||||
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon)
|
||||
cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
|
||||
cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
|
||||
cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586)
|
||||
|
|
@ -37,5 +37,5 @@ cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686)
|
|||
cflags-$(CONFIG_X86_ELAN) += -march=i486
|
||||
|
||||
# Geode GX1 support
|
||||
cflags-$(CONFIG_MGEODEGX1) += $(call cc-option,-march=pentium-mmx,-march=i486)
|
||||
cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx
|
||||
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@
|
|||
|
||||
#include <linux/linkage.h>
|
||||
#include <linux/vmalloc.h>
|
||||
#include <linux/tty.h>
|
||||
#include <linux/screen_info.h>
|
||||
#include <asm/io.h>
|
||||
#include <asm/page.h>
|
||||
|
||||
|
|
|
|||
|
|
@ -4,10 +4,10 @@
|
|||
|
||||
extra-y := head.o init_task.o vmlinux.lds
|
||||
|
||||
obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o vm86.o \
|
||||
obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \
|
||||
ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \
|
||||
pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \
|
||||
doublefault.o quirks.o i8237.o
|
||||
quirks.o i8237.o
|
||||
|
||||
obj-y += cpu/
|
||||
obj-y += timers/
|
||||
|
|
@ -33,6 +33,8 @@ obj-y += sysenter.o vsyscall.o
|
|||
obj-$(CONFIG_ACPI_SRAT) += srat.o
|
||||
obj-$(CONFIG_HPET_TIMER) += time_hpet.o
|
||||
obj-$(CONFIG_EFI) += efi.o efi_stub.o
|
||||
obj-$(CONFIG_DOUBLEFAULT) += doublefault.o
|
||||
obj-$(CONFIG_VM86) += vm86.o
|
||||
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
|
||||
|
||||
EXTRA_AFLAGS := -traditional
|
||||
|
|
|
|||
|
|
@ -2291,7 +2291,9 @@ static int __init apm_init(void)
|
|||
apm_info.disabled = 1;
|
||||
return -ENODEV;
|
||||
}
|
||||
#ifdef CONFIG_PM_LEGACY
|
||||
pm_active = 1;
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Set up a segment that references the real mode segment 0x40
|
||||
|
|
@ -2382,7 +2384,9 @@ static void __exit apm_exit(void)
|
|||
exit_kapmd = 1;
|
||||
while (kapmd_running)
|
||||
schedule();
|
||||
#ifdef CONFIG_PM_LEGACY
|
||||
pm_active = 0;
|
||||
#endif
|
||||
}
|
||||
|
||||
module_init(apm_init);
|
||||
|
|
|
|||
|
|
@ -609,8 +609,10 @@ void __devinit cpu_init(void)
|
|||
load_TR_desc();
|
||||
load_LDT(&init_mm.context);
|
||||
|
||||
#ifdef CONFIG_DOUBLEFAULT
|
||||
/* Set up doublefault TSS pointer in the GDT */
|
||||
__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
|
||||
#endif
|
||||
|
||||
/* Clear %fs and %gs. */
|
||||
asm volatile ("xorl %eax, %eax; movl %eax, %fs; movl %eax, %gs");
|
||||
|
|
|
|||
|
|
@ -323,6 +323,7 @@ work_notifysig: # deal with pending signals and
|
|||
|
||||
ALIGN
|
||||
work_notifysig_v86:
|
||||
#ifdef CONFIG_VM86
|
||||
pushl %ecx # save ti_flags for do_notify_resume
|
||||
call save_v86_state # %eax contains pt_regs pointer
|
||||
popl %ecx
|
||||
|
|
@ -330,6 +331,7 @@ work_notifysig_v86:
|
|||
xorl %edx, %edx
|
||||
call do_notify_resume
|
||||
jmp resume_userspace
|
||||
#endif
|
||||
|
||||
# perform syscall exit tracing
|
||||
ALIGN
|
||||
|
|
|
|||
|
|
@ -42,5 +42,5 @@ EXPORT_SYMBOL(init_task);
|
|||
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
|
||||
* no more per-task TSS's.
|
||||
*/
|
||||
DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_maxaligned_in_smp = INIT_TSS;
|
||||
DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS;
|
||||
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@
|
|||
#include <linux/cpu.h>
|
||||
#include <linux/delay.h>
|
||||
|
||||
DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp;
|
||||
DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
|
||||
EXPORT_PER_CPU_SYMBOL(irq_stat);
|
||||
|
||||
#ifndef CONFIG_X86_LOCAL_APIC
|
||||
|
|
|
|||
|
|
@ -48,6 +48,7 @@
|
|||
#include <asm/processor.h>
|
||||
#include <asm/i387.h>
|
||||
#include <asm/desc.h>
|
||||
#include <asm/vm86.h>
|
||||
#ifdef CONFIG_MATH_EMULATION
|
||||
#include <asm/math_emu.h>
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -293,3 +293,4 @@ ENTRY(sys_call_table)
|
|||
.long sys_inotify_init
|
||||
.long sys_inotify_add_watch
|
||||
.long sys_inotify_rm_watch
|
||||
.long sys_migrate_pages
|
||||
|
|
|
|||
|
|
@ -259,8 +259,6 @@ __setup("hpet=", hpet_setup);
|
|||
#include <linux/mc146818rtc.h>
|
||||
#include <linux/rtc.h>
|
||||
|
||||
extern irqreturn_t rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs);
|
||||
|
||||
#define DEFAULT_RTC_INT_FREQ 64
|
||||
#define RTC_NUM_INTS 1
|
||||
|
||||
|
|
|
|||
|
|
@ -37,10 +37,6 @@ $(error Sorry, you need a newer version of the assember, one that is built from
|
|||
ftp://ftp.hpl.hp.com/pub/linux-ia64/gas-030124.tar.gz)
|
||||
endif
|
||||
|
||||
ifneq ($(shell if [ $(GCC_VERSION) -lt 0300 ] ; then echo "bad"; fi ;),)
|
||||
$(error Sorry, your compiler is too old. GCC v2.96 is known to generate bad code.)
|
||||
endif
|
||||
|
||||
ifeq ($(GCC_VERSION),0304)
|
||||
cflags-$(CONFIG_ITANIUM) += -mtune=merced
|
||||
cflags-$(CONFIG_MCKINLEY) += -mtune=mckinley
|
||||
|
|
|
|||
|
|
@ -1761,21 +1761,15 @@ sys32_ptrace (int request, pid_t pid, unsigned int addr, unsigned int data)
|
|||
|
||||
lock_kernel();
|
||||
if (request == PTRACE_TRACEME) {
|
||||
ret = sys_ptrace(request, pid, addr, data);
|
||||
ret = ptrace_traceme();
|
||||
goto out;
|
||||
}
|
||||
|
||||
ret = -ESRCH;
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
if (!child)
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
goto out;
|
||||
ret = -EPERM;
|
||||
if (pid == 1) /* no messing around with init! */
|
||||
goto out_tsk;
|
||||
}
|
||||
|
||||
if (request == PTRACE_ATTACH) {
|
||||
ret = sys_ptrace(request, pid, addr, data);
|
||||
|
|
|
|||
|
|
@ -247,6 +247,32 @@ typedef struct kern_memdesc {
|
|||
|
||||
static kern_memdesc_t *kern_memmap;
|
||||
|
||||
#define efi_md_size(md) (md->num_pages << EFI_PAGE_SHIFT)
|
||||
|
||||
static inline u64
|
||||
kmd_end(kern_memdesc_t *kmd)
|
||||
{
|
||||
return (kmd->start + (kmd->num_pages << EFI_PAGE_SHIFT));
|
||||
}
|
||||
|
||||
static inline u64
|
||||
efi_md_end(efi_memory_desc_t *md)
|
||||
{
|
||||
return (md->phys_addr + efi_md_size(md));
|
||||
}
|
||||
|
||||
static inline int
|
||||
efi_wb(efi_memory_desc_t *md)
|
||||
{
|
||||
return (md->attribute & EFI_MEMORY_WB);
|
||||
}
|
||||
|
||||
static inline int
|
||||
efi_uc(efi_memory_desc_t *md)
|
||||
{
|
||||
return (md->attribute & EFI_MEMORY_UC);
|
||||
}
|
||||
|
||||
static void
|
||||
walk (efi_freemem_callback_t callback, void *arg, u64 attr)
|
||||
{
|
||||
|
|
@ -595,8 +621,8 @@ efi_get_iobase (void)
|
|||
return 0;
|
||||
}
|
||||
|
||||
u32
|
||||
efi_mem_type (unsigned long phys_addr)
|
||||
static efi_memory_desc_t *
|
||||
efi_memory_descriptor (unsigned long phys_addr)
|
||||
{
|
||||
void *efi_map_start, *efi_map_end, *p;
|
||||
efi_memory_desc_t *md;
|
||||
|
|
@ -610,55 +636,117 @@ efi_mem_type (unsigned long phys_addr)
|
|||
md = p;
|
||||
|
||||
if (phys_addr - md->phys_addr < (md->num_pages << EFI_PAGE_SHIFT))
|
||||
return md->type;
|
||||
return md;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
efi_memmap_has_mmio (void)
|
||||
{
|
||||
void *efi_map_start, *efi_map_end, *p;
|
||||
efi_memory_desc_t *md;
|
||||
u64 efi_desc_size;
|
||||
|
||||
efi_map_start = __va(ia64_boot_param->efi_memmap);
|
||||
efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size;
|
||||
efi_desc_size = ia64_boot_param->efi_memdesc_size;
|
||||
|
||||
for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
|
||||
md = p;
|
||||
|
||||
if (md->type == EFI_MEMORY_MAPPED_IO)
|
||||
return 1;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
u32
|
||||
efi_mem_type (unsigned long phys_addr)
|
||||
{
|
||||
efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);
|
||||
|
||||
if (md)
|
||||
return md->type;
|
||||
return 0;
|
||||
}
|
||||
|
||||
u64
|
||||
efi_mem_attributes (unsigned long phys_addr)
|
||||
{
|
||||
void *efi_map_start, *efi_map_end, *p;
|
||||
efi_memory_desc_t *md;
|
||||
u64 efi_desc_size;
|
||||
efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);
|
||||
|
||||
efi_map_start = __va(ia64_boot_param->efi_memmap);
|
||||
efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size;
|
||||
efi_desc_size = ia64_boot_param->efi_memdesc_size;
|
||||
|
||||
for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
|
||||
md = p;
|
||||
|
||||
if (phys_addr - md->phys_addr < (md->num_pages << EFI_PAGE_SHIFT))
|
||||
return md->attribute;
|
||||
}
|
||||
if (md)
|
||||
return md->attribute;
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL(efi_mem_attributes);
|
||||
|
||||
/*
|
||||
* Determines whether the memory at phys_addr supports the desired
|
||||
* attribute (WB, UC, etc). If this returns 1, the caller can safely
|
||||
* access *size bytes at phys_addr with the specified attribute.
|
||||
*/
|
||||
static int
|
||||
efi_mem_attribute_range (unsigned long phys_addr, unsigned long *size, u64 attr)
|
||||
{
|
||||
efi_memory_desc_t *md = efi_memory_descriptor(phys_addr);
|
||||
unsigned long md_end;
|
||||
|
||||
if (!md || (md->attribute & attr) != attr)
|
||||
return 0;
|
||||
|
||||
do {
|
||||
md_end = efi_md_end(md);
|
||||
if (phys_addr + *size <= md_end)
|
||||
return 1;
|
||||
|
||||
md = efi_memory_descriptor(md_end);
|
||||
if (!md || (md->attribute & attr) != attr) {
|
||||
*size = md_end - phys_addr;
|
||||
return 1;
|
||||
}
|
||||
} while (md);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* For /dev/mem, we only allow read & write system calls to access
|
||||
* write-back memory, because read & write don't allow the user to
|
||||
* control access size.
|
||||
*/
|
||||
int
|
||||
valid_phys_addr_range (unsigned long phys_addr, unsigned long *size)
|
||||
{
|
||||
void *efi_map_start, *efi_map_end, *p;
|
||||
efi_memory_desc_t *md;
|
||||
u64 efi_desc_size;
|
||||
return efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB);
|
||||
}
|
||||
|
||||
efi_map_start = __va(ia64_boot_param->efi_memmap);
|
||||
efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size;
|
||||
efi_desc_size = ia64_boot_param->efi_memdesc_size;
|
||||
/*
|
||||
* We allow mmap of anything in the EFI memory map that supports
|
||||
* either write-back or uncacheable access. For uncacheable regions,
|
||||
* the supported access sizes are system-dependent, and the user is
|
||||
* responsible for using the correct size.
|
||||
*
|
||||
* Note that this doesn't currently allow access to hot-added memory,
|
||||
* because that doesn't appear in the boot-time EFI memory map.
|
||||
*/
|
||||
int
|
||||
valid_mmap_phys_addr_range (unsigned long phys_addr, unsigned long *size)
|
||||
{
|
||||
if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_WB))
|
||||
return 1;
|
||||
|
||||
for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
|
||||
md = p;
|
||||
if (efi_mem_attribute_range(phys_addr, size, EFI_MEMORY_UC))
|
||||
return 1;
|
||||
|
||||
if (phys_addr - md->phys_addr < (md->num_pages << EFI_PAGE_SHIFT)) {
|
||||
if (!(md->attribute & EFI_MEMORY_WB))
|
||||
return 0;
|
||||
/*
|
||||
* Some firmware doesn't report MMIO regions in the EFI memory map.
|
||||
* The Intel BigSur (a.k.a. HP i2000) has this problem. In this
|
||||
* case, we can't use the EFI memory map to validate mmap requests.
|
||||
*/
|
||||
if (!efi_memmap_has_mmio())
|
||||
return 1;
|
||||
|
||||
if (*size > md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - phys_addr)
|
||||
*size = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - phys_addr;
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -707,32 +795,6 @@ efi_uart_console_only(void)
|
|||
return 0;
|
||||
}
|
||||
|
||||
#define efi_md_size(md) (md->num_pages << EFI_PAGE_SHIFT)
|
||||
|
||||
static inline u64
|
||||
kmd_end(kern_memdesc_t *kmd)
|
||||
{
|
||||
return (kmd->start + (kmd->num_pages << EFI_PAGE_SHIFT));
|
||||
}
|
||||
|
||||
static inline u64
|
||||
efi_md_end(efi_memory_desc_t *md)
|
||||
{
|
||||
return (md->phys_addr + efi_md_size(md));
|
||||
}
|
||||
|
||||
static inline int
|
||||
efi_wb(efi_memory_desc_t *md)
|
||||
{
|
||||
return (md->attribute & EFI_MEMORY_WB);
|
||||
}
|
||||
|
||||
static inline int
|
||||
efi_uc(efi_memory_desc_t *md)
|
||||
{
|
||||
return (md->attribute & EFI_MEMORY_UC);
|
||||
}
|
||||
|
||||
/*
|
||||
* Look for the first granule aligned memory descriptor memory
|
||||
* that is big enough to hold EFI memory map. Make sure this
|
||||
|
|
|
|||
|
|
@ -1600,5 +1600,6 @@ sys_call_table:
|
|||
data8 sys_inotify_init
|
||||
data8 sys_inotify_add_watch
|
||||
data8 sys_inotify_rm_watch
|
||||
data8 sys_migrate_pages // 1280
|
||||
|
||||
.org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls
|
||||
|
|
|
|||
|
|
@ -1060,7 +1060,7 @@ SET_REG(b5);
|
|||
* the clobber lists for spin_lock() in include/asm-ia64/spinlock.h.
|
||||
*/
|
||||
|
||||
#if __GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
#if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
|
||||
GLOBAL_ENTRY(ia64_spinlock_contention_pre3_4)
|
||||
.prologue
|
||||
|
|
|
|||
|
|
@ -103,7 +103,7 @@ EXPORT_SYMBOL(unw_init_running);
|
|||
|
||||
#ifdef ASM_SUPPORTED
|
||||
# ifdef CONFIG_SMP
|
||||
# if __GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
# if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
/*
|
||||
* This is not a normal routine and we don't want a function descriptor for it, so we use
|
||||
* a fake declaration here.
|
||||
|
|
|
|||
|
|
@ -1422,14 +1422,7 @@ sys_ptrace (long request, pid_t pid, unsigned long addr, unsigned long data)
|
|||
lock_kernel();
|
||||
ret = -EPERM;
|
||||
if (request == PTRACE_TRACEME) {
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED)
|
||||
goto out;
|
||||
ret = security_ptrace(current->parent, current);
|
||||
if (ret)
|
||||
goto out;
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = 0;
|
||||
ret = ptrace_traceme();
|
||||
goto out;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ typedef struct
|
|||
u64 *prev_pfs_loc; /* state for WAR for old spinlock ool code */
|
||||
} ia64_backtrace_t;
|
||||
|
||||
#if __GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
#if (__GNUC__ == 3 && __GNUC_MINOR__ < 3)
|
||||
/*
|
||||
* Returns non-zero if the PC is in the spinlock contention out-of-line code
|
||||
* with non-standard calling sequence (on older compilers).
|
||||
|
|
|
|||
|
|
@ -50,6 +50,10 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
|
|||
* Powermanagement idle function, if any..
|
||||
*/
|
||||
void (*pm_idle)(void) = NULL;
|
||||
EXPORT_SYMBOL(pm_idle);
|
||||
|
||||
void (*pm_power_off)(void) = NULL;
|
||||
EXPORT_SYMBOL(pm_power_off);
|
||||
|
||||
void disable_hlt(void)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -762,28 +762,16 @@ asmlinkage long sys_ptrace(long request, long pid, long addr, long data)
|
|||
int ret;
|
||||
|
||||
lock_kernel();
|
||||
ret = -EPERM;
|
||||
if (request == PTRACE_TRACEME) {
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED)
|
||||
goto out;
|
||||
/* set the ptrace bit in the process flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = 0;
|
||||
ret = ptrace_traceme();
|
||||
goto out;
|
||||
}
|
||||
ret = -ESRCH;
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
if (!child)
|
||||
goto out;
|
||||
|
||||
ret = -EPERM;
|
||||
if (pid == 1) /* you may not mess with init */
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (request == PTRACE_ATTACH) {
|
||||
ret = ptrace_attach(child);
|
||||
|
|
|
|||
|
|
@ -10,10 +10,6 @@ config MMU
|
|||
bool
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -17,10 +17,6 @@ config FPU
|
|||
bool
|
||||
default n
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -57,30 +57,16 @@ asmlinkage int sys32_ptrace(int request, int pid, int addr, int data)
|
|||
(unsigned long) data);
|
||||
#endif
|
||||
lock_kernel();
|
||||
ret = -EPERM;
|
||||
if (request == PTRACE_TRACEME) {
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED)
|
||||
goto out;
|
||||
if ((ret = security_ptrace(current->parent, current)))
|
||||
goto out;
|
||||
/* set the ptrace bit in the process flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = 0;
|
||||
ret = ptrace_traceme();
|
||||
goto out;
|
||||
}
|
||||
ret = -ESRCH;
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
if (!child)
|
||||
goto out;
|
||||
|
||||
ret = -EPERM;
|
||||
if (pid == 1) /* you may not mess with init */
|
||||
goto out_tsk;
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (request == PTRACE_ATTACH) {
|
||||
ret = ptrace_attach(child);
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@
|
|||
#include <linux/kernel.h>
|
||||
#include <linux/module.h>
|
||||
#include <linux/signal.h> /* for SIGBUS */
|
||||
#include <linux/sched.h> /* schow_regs(), force_sig() */
|
||||
|
||||
#include <asm/module.h>
|
||||
#include <asm/sn/addrs.h>
|
||||
|
|
|
|||
|
|
@ -19,9 +19,6 @@ config MMU
|
|||
config STACK_GROWSUP
|
||||
def_bool y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
def_bool y
|
||||
|
||||
|
|
|
|||
|
|
@ -26,9 +26,6 @@ config MMU
|
|||
bool
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
|
||||
config GENERIC_HARDIRQS
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -45,33 +45,19 @@ long compat_sys_ptrace(int request, int pid, unsigned long addr,
|
|||
unsigned long data)
|
||||
{
|
||||
struct task_struct *child;
|
||||
int ret = -EPERM;
|
||||
int ret;
|
||||
|
||||
lock_kernel();
|
||||
if (request == PTRACE_TRACEME) {
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED)
|
||||
goto out;
|
||||
ret = security_ptrace(current->parent, current);
|
||||
if (ret)
|
||||
goto out;
|
||||
/* set the ptrace bit in the process flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = 0;
|
||||
ret = ptrace_traceme();
|
||||
goto out;
|
||||
}
|
||||
ret = -ESRCH;
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
if (!child)
|
||||
goto out;
|
||||
|
||||
ret = -EPERM;
|
||||
if (pid == 1) /* you may not mess with init */
|
||||
goto out_tsk;
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (request == PTRACE_ATTACH) {
|
||||
ret = ptrace_attach(child);
|
||||
|
|
|
|||
|
|
@ -8,9 +8,6 @@ config MMU
|
|||
bool
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
|
||||
config GENERIC_HARDIRQS
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -712,35 +712,18 @@ sys_ptrace(long request, long pid, long addr, long data)
|
|||
int ret;
|
||||
|
||||
lock_kernel();
|
||||
|
||||
if (request == PTRACE_TRACEME) {
|
||||
/* are we already being traced? */
|
||||
ret = -EPERM;
|
||||
if (current->ptrace & PT_PTRACED)
|
||||
goto out;
|
||||
ret = security_ptrace(current->parent, current);
|
||||
if (ret)
|
||||
goto out;
|
||||
/* set the ptrace bit in the process flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = ptrace_traceme();
|
||||
goto out;
|
||||
}
|
||||
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
goto out;
|
||||
}
|
||||
|
||||
ret = -EPERM;
|
||||
if (pid == 1) /* you may not mess with init */
|
||||
goto out;
|
||||
|
||||
ret = -ESRCH;
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
if (!child)
|
||||
goto out;
|
||||
|
||||
ret = do_ptrace(child, request, addr, data);
|
||||
|
||||
put_task_struct(child);
|
||||
out:
|
||||
unlock_kernel();
|
||||
|
|
|
|||
|
|
@ -14,10 +14,6 @@ config SUPERH
|
|||
gaming console. The SuperH port has a home page at
|
||||
<http://www.linux-sh.org/>.
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config RWSEM_GENERIC_SPINLOCK
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -417,7 +417,7 @@ static __init unsigned int get_cpu_hz(void)
|
|||
/*
|
||||
** Regardless the toolchain, force the compiler to use the
|
||||
** arbitrary register r3 as a clock tick counter.
|
||||
** NOTE: r3 must be in accordance with rtc_interrupt()
|
||||
** NOTE: r3 must be in accordance with sh64_rtc_interrupt()
|
||||
*/
|
||||
register unsigned long long __rtc_irq_flag __asm__ ("r3");
|
||||
|
||||
|
|
@ -482,7 +482,8 @@ static __init unsigned int get_cpu_hz(void)
|
|||
#endif
|
||||
}
|
||||
|
||||
static irqreturn_t rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
|
||||
static irqreturn_t sh64_rtc_interrupt(int irq, void *dev_id,
|
||||
struct pt_regs *regs)
|
||||
{
|
||||
ctrl_outb(0, RCR1); /* Disable Carry Interrupts */
|
||||
regs->regs[3] = 1; /* Using r3 */
|
||||
|
|
@ -491,7 +492,7 @@ static irqreturn_t rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
|
|||
}
|
||||
|
||||
static struct irqaction irq0 = { timer_interrupt, SA_INTERRUPT, CPU_MASK_NONE, "timer", NULL, NULL};
|
||||
static struct irqaction irq1 = { rtc_interrupt, SA_INTERRUPT, CPU_MASK_NONE, "rtc", NULL, NULL};
|
||||
static struct irqaction irq1 = { sh64_rtc_interrupt, SA_INTERRUPT, CPU_MASK_NONE, "rtc", NULL, NULL};
|
||||
|
||||
void __init time_init(void)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -9,10 +9,6 @@ config MMU
|
|||
bool
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
default y
|
||||
|
||||
config HIGHMEM
|
||||
bool
|
||||
default y
|
||||
|
|
|
|||
|
|
@ -286,40 +286,17 @@ asmlinkage void do_ptrace(struct pt_regs *regs)
|
|||
s, (int) request, (int) pid, addr, data, addr2);
|
||||
}
|
||||
#endif
|
||||
|
||||
if (request == PTRACE_TRACEME) {
|
||||
int my_ret;
|
||||
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED) {
|
||||
pt_error_return(regs, EPERM);
|
||||
goto out;
|
||||
}
|
||||
my_ret = security_ptrace(current->parent, current);
|
||||
if (my_ret) {
|
||||
pt_error_return(regs, -my_ret);
|
||||
goto out;
|
||||
}
|
||||
|
||||
/* set the ptrace bit in the process flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = ptrace_traceme();
|
||||
pt_succ_return(regs, 0);
|
||||
goto out;
|
||||
}
|
||||
#ifndef ALLOW_INIT_TRACING
|
||||
if (pid == 1) {
|
||||
/* Can't dork with init. */
|
||||
pt_error_return(regs, EPERM);
|
||||
goto out;
|
||||
}
|
||||
#endif
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
|
||||
if (!child) {
|
||||
pt_error_return(regs, ESRCH);
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
pt_error_return(regs, -ret);
|
||||
goto out;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -309,11 +309,6 @@ config COMPAT
|
|||
depends on SPARC32_COMPAT
|
||||
default y
|
||||
|
||||
config UID16
|
||||
bool
|
||||
depends on SPARC32_COMPAT
|
||||
default y
|
||||
|
||||
config BINFMT_ELF32
|
||||
tristate "Kernel support for 32-bit ELF binaries"
|
||||
depends on SPARC32_COMPAT
|
||||
|
|
|
|||
|
|
@ -198,39 +198,15 @@ asmlinkage void do_ptrace(struct pt_regs *regs)
|
|||
}
|
||||
#endif
|
||||
if (request == PTRACE_TRACEME) {
|
||||
int ret;
|
||||
|
||||
/* are we already being traced? */
|
||||
if (current->ptrace & PT_PTRACED) {
|
||||
pt_error_return(regs, EPERM);
|
||||
goto out;
|
||||
}
|
||||
ret = security_ptrace(current->parent, current);
|
||||
if (ret) {
|
||||
pt_error_return(regs, -ret);
|
||||
goto out;
|
||||
}
|
||||
|
||||
/* set the ptrace bit in the process flags. */
|
||||
current->ptrace |= PT_PTRACED;
|
||||
ret = ptrace_traceme();
|
||||
pt_succ_return(regs, 0);
|
||||
goto out;
|
||||
}
|
||||
#ifndef ALLOW_INIT_TRACING
|
||||
if (pid == 1) {
|
||||
/* Can't dork with init. */
|
||||
pt_error_return(regs, EPERM);
|
||||
goto out;
|
||||
}
|
||||
#endif
|
||||
read_lock(&tasklist_lock);
|
||||
child = find_task_by_pid(pid);
|
||||
if (child)
|
||||
get_task_struct(child);
|
||||
read_unlock(&tasklist_lock);
|
||||
|
||||
if (!child) {
|
||||
pt_error_return(regs, ESRCH);
|
||||
child = ptrace_get_task_struct(pid);
|
||||
if (IS_ERR(child)) {
|
||||
ret = PTR_ERR(child);
|
||||
pt_error_return(regs, -ret);
|
||||
goto out;
|
||||
}
|
||||
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Reference in a new issue