leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge commit 'origin/master' into next

Browse Source 
Manual merge of:
	arch/powerpc/kernel/asm-offsets.c
This commit is contained in:
Benjamin Herrenschmidt 2009-06-12 16:53:38 +10:00
commit bc47ab0241
1642 changed files with 101409 additions and 33981 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
Documentation/ABI/testing/sysfs-block
View File

@ -60,3 +60,62 @@ Description:
Indicates whether the block layer should automatically
generate checksums for write requests bound for
devices that support receiving integrity metadata.
What: /sys/block/<disk>/alignment_offset
Date: April 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
Storage devices may report a physical block size that is
bigger than the logical block size (for instance a drive
with 4KB physical sectors exposing 512-byte logical
blocks to the operating system). This parameter
indicates how many bytes the beginning of the device is
offset from the disk's natural alignment.
What: /sys/block/<disk>/<partition>/alignment_offset
Date: April 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
Storage devices may report a physical block size that is
bigger than the logical block size (for instance a drive
with 4KB physical sectors exposing 512-byte logical
blocks to the operating system). This parameter
indicates how many bytes the beginning of the partition
is offset from the disk's natural alignment.
What: /sys/block/<disk>/queue/logical_block_size
Date: May 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
This is the smallest unit the storage device can
address. It is typically 512 bytes.
What: /sys/block/<disk>/queue/physical_block_size
Date: May 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
This is the smallest unit the storage device can write
without resorting to read-modify-write operation. It is
usually the same as the logical block size but may be
bigger. One example is SATA drives with 4KB sectors
that expose a 512-byte logical block size to the
operating system.
What: /sys/block/<disk>/queue/minimum_io_size
Date: April 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
Storage devices may report a preferred minimum I/O size,
which is the smallest request the device can perform
without incurring a read-modify-write penalty. For disk
drives this is often the physical block size. For RAID
arrays it is often the stripe chunk size.
What: /sys/block/<disk>/queue/optimal_io_size
Date: April 2009
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
Storage devices may report an optimal I/O size, which is
the device's preferred unit of receiving I/O. This is
rarely reported for disk drives. For RAID devices it is
usually the stripe width or the internal block size.

33
Documentation/ABI/testing/sysfs-bus-pci-devices-cciss Normal file
View File

@ -0,0 +1,33 @@
Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/model
Date: March 2009
Kernel Version: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 0 model for logical drive
Y of controller X.
Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
Date: March 2009
Kernel Version: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 0 revision for logical
drive Y of controller X.
Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
Date: March 2009
Kernel Version: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 83 serial number for logical
drive Y of controller X.
Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
Date: March 2009
Kernel Version: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 0 vendor for logical drive
Y of controller X.
Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
Date: March 2009
Kernel Version: 2.6.30
Contact: iss_storagedev@hp.com
Description: A symbolic link to /sys/block/cciss!cXdY

18
Documentation/ABI/testing/sysfs-devices-cache_disable Normal file
View File

@ -0,0 +1,18 @@
What: /sys/devices/system/cpu/cpu*/cache/index*/cache_disable_X
Date: August 2008
KernelVersion: 2.6.27
Contact: mark.langsdorf@amd.com
Description: These files exist in every cpu's cache index directories.
There are currently 2 cache_disable_# files in each
directory. Reading from these files on a supported
processor will return that cache disable index value
for that processor and node. Writing to one of these
files will cause the specificed cache index to be disabled.
Currently, only AMD Family 10h Processors support cache index
disable, and only for their L3 caches. See the BIOS and
Kernel Developer's Guide at
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/31116-Public-GH-BKDG_3.20_2-4-09.pdf
for formatting information and other details on the
cache index disable.
Users: joachim.deguara@amd.com

12
Documentation/DMA-API.txt
View File

@ -704,12 +704,24 @@ this directory the following files can currently be found:
The current number of free dma_debug_entries
in the allocator.
dma-api/driver-filter
You can write a name of a driver into this file
to limit the debug output to requests from that
particular driver. Write an empty string to
that file to disable the filter and see
all errors again.
If you have this code compiled into your kernel it will be enabled by default.
If you want to boot without the bookkeeping anyway you can provide
'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
Notice that you can not enable it again at runtime. You have to reboot to do
so.
If you want to see debug messages only for a special device driver you can
specify the dma_debug_driver=<drivername> parameter. This will enable the
driver filter at boot time. The debug code will only print errors for that
driver afterwards. This filter can be disabled or changed later using debugfs.
When the code disables itself at runtime this is most likely because it ran
out of dma_debug_entries. These entries are preallocated at boot. The number
of preallocated entries is defined per architecture. If it is too low for you

3
Documentation/DocBook/Makefile
View File

@ -13,7 +13,8 @@ DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
mac80211.xml debugobjects.xml sh.xml regulator.xml \
alsa-driver-api.xml writing-an-alsa-driver.xml
alsa-driver-api.xml writing-an-alsa-driver.xml \
tracepoint.xml
###
# The build process is as follows (targets):

89
Documentation/DocBook/tracepoint.tmpl Normal file
View File

@ -0,0 +1,89 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
"http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
<book id="Tracepoints">
<bookinfo>
<title>The Linux Kernel Tracepoint API</title>
<authorgroup>
<author>
<firstname>Jason</firstname>
<surname>Baron</surname>
<affiliation>
<address>
<email>jbaron@redhat.com</email>
</address>
</affiliation>
</author>
</authorgroup>
<legalnotice>
<para>
This documentation 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.
</para>
<para>
This program is distributed in the hope that it will be
useful, but WITHOUT ANY WARRANTY; without even the implied
warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU General Public License for more details.
</para>
<para>
You should have received a copy of the GNU General Public
License along with this program; if not, write to the Free
Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
MA 02111-1307 USA
</para>
<para>
For more details see the file COPYING in the source
distribution of Linux.
</para>
</legalnotice>
</bookinfo>
<toc></toc>
<chapter id="intro">
<title>Introduction</title>
<para>
Tracepoints are static probe points that are located in strategic points
throughout the kernel. 'Probes' register/unregister with tracepoints
via a callback mechanism. The 'probes' are strictly typed functions that
are passed a unique set of parameters defined by each tracepoint.
</para>
<para>
From this simple callback mechanism, 'probes' can be used to profile, debug,
and understand kernel behavior. There are a number of tools that provide a
framework for using 'probes'. These tools include Systemtap, ftrace, and
LTTng.
</para>
<para>
Tracepoints are defined in a number of header files via various macros. Thus,
the purpose of this document is to provide a clear accounting of the available
tracepoints. The intention is to understand not only what tracepoints are
available but also to understand where future tracepoints might be added.
</para>
<para>
The API presented has functions of the form:
<function>trace_tracepointname(function parameters)</function>. These are the
tracepoints callbacks that are found throughout the code. Registering and
unregistering probes with these callback sites is covered in the
<filename>Documentation/trace/*</filename> directory.
</para>
</chapter>
<chapter id="irq">
<title>IRQ</title>
!Iinclude/trace/events/irq.h
</chapter>
</book>

102
Documentation/RCU/trace.txt
View File

@ -192,23 +192,24 @@ rcu/rcuhier (which displays the struct rcu_node hierarchy).
The output of "cat rcu/rcudata" looks as follows:
rcu:
0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
rcu:
0 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=10951/1 dn=0 df=1101 of=0 ri=36 ql=0 b=10
1 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=16117/1 dn=0 df=1015 of=0 ri=0 ql=0 b=10
2 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1445/1 dn=0 df=1839 of=0 ri=0 ql=0 b=10
3 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=6681/1 dn=0 df=1545 of=0 ri=0 ql=0 b=10
4 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=1003/1 dn=0 df=1992 of=0 ri=0 ql=0 b=10
5 c=17829 g=17830 pq=1 pqc=17829 qp=1 dt=3887/1 dn=0 df=3331 of=0 ri=4 ql=2 b=10
6 c=17829 g=17829 pq=1 pqc=17829 qp=0 dt=859/1 dn=0 df=3224 of=0 ri=0 ql=0 b=10
7 c=17829 g=17830 pq=0 pqc=17829 qp=1 dt=3761/1 dn=0 df=1818 of=0 ri=0 ql=2 b=10
rcu_bh:
0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
0 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=10951/1 dn=0 df=0 of=0 ri=0 ql=0 b=10
1 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=16117/1 dn=0 df=13 of=0 ri=0 ql=0 b=10
2 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1445/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
3 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=6681/1 dn=0 df=9 of=0 ri=0 ql=0 b=10
4 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=1003/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
5 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3887/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
6 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=859/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
7 c=-275 g=-275 pq=1 pqc=-275 qp=0 dt=3761/1 dn=0 df=15 of=0 ri=0 ql=0 b=10
The first section lists the rcu_data structures for rcu, the second for
rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system.
@ -253,12 +254,6 @@ o "pqc" indicates which grace period the last-observed quiescent
o "qp" indicates that RCU still expects a quiescent state from
this CPU.
o "rpfq" is the number of rcu_pending() calls on this CPU required
to induce this CPU to invoke force_quiescent_state().
o "rp" is low-order four hex digits of the count of how many times
rcu_pending() has been invoked on this CPU.
o "dt" is the current value of the dyntick counter that is incremented
when entering or leaving dynticks idle state, either by the
scheduler or by irq. The number after the "/" is the interrupt
@ -305,6 +300,9 @@ o "b" is the batch limit for this CPU. If more than this number
of RCU callbacks is ready to invoke, then the remainder will
be deferred.
There is also an rcu/rcudata.csv file with the same information in
comma-separated-variable spreadsheet format.
The output of "cat rcu/rcugp" looks as follows:
@ -411,3 +409,63 @@ o Each element of the form "1/1 0:127 ^0" represents one struct
For example, the first entry at the lowest level shows
"^0", indicating that it corresponds to bit zero in
the first entry at the middle level.
The output of "cat rcu/rcu_pending" looks as follows:
rcu:
0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
rcu_bh:
0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
As always, this is once again split into "rcu" and "rcu_bh" portions.
The fields are as follows:
o "np" is the number of times that __rcu_pending() has been invoked
for the corresponding flavor of RCU.
o "qsp" is the number of times that the RCU was waiting for a
quiescent state from this CPU.
o "cbr" is the number of times that this CPU had RCU callbacks
that had passed through a grace period, and were thus ready
to be invoked.
o "cng" is the number of times that this CPU needed another
grace period while RCU was idle.
o "gpc" is the number of times that an old grace period had
completed, but this CPU was not yet aware of it.
o "gps" is the number of times that a new grace period had started,
but this CPU was not yet aware of it.
o "nf" is the number of times that this CPU suspected that the
current grace period had run for too long, and thus needed to
be forced.
Please note that "forcing" consists of sending resched IPIs
to holdout CPUs. If that CPU really still is in an old RCU
read-side critical section, then we really do have to wait for it.
The assumption behing "forcing" is that the CPU is not still in
an old RCU read-side critical section, but has not yet responded
for some other reason.
o "nn" is the number of times that this CPU needed nothing. Alert
readers will note that the rcu "nn" number for a given CPU very
closely matches the rcu_bh "np" number for that same CPU. This
is due to short-circuit evaluation in rcu_pending().

20
Documentation/Smack.txt
View File

@ -184,8 +184,9 @@ length. Single character labels using special characters, that being anything
other than a letter or digit, are reserved for use by the Smack development
team. Smack labels are unstructured, case sensitive, and the only operation
ever performed on them is comparison for equality. Smack labels cannot
contain unprintable characters or the "/" (slash) character. Smack labels
cannot begin with a '-', which is reserved for special options.
contain unprintable characters, the "/" (slash), the "\" (backslash), the "'"
(quote) and '"' (double-quote) characters.
Smack labels cannot begin with a '-', which is reserved for special options.
There are some predefined labels:
@ -523,3 +524,18 @@ Smack supports some mount options:
These mount options apply to all file system types.
Smack auditing
If you want Smack auditing of security events, you need to set CONFIG_AUDIT
in your kernel configuration.
By default, all denied events will be audited. You can change this behavior by
writing a single character to the /smack/logging file :
0 : no logging
1 : log denied (default)
2 : log accepted
3 : log denied & accepted
Events are logged as 'key=value' pairs, for each event you at least will get
the subjet, the object, the rights requested, the action, the kernel function
that triggered the event, plus other pairs depending on the type of event
audited.

2
Documentation/block/biodoc.txt
View File

@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
do not have a corresponding kernel virtual address space mapping) and
low-memory pages.
Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
Note: Please refer to Documentation/DMA-mapping.txt for a discussion
on PCI high mem DMA aspects and mapping of scatter gather lists, and support
for 64 bit PCI.

2
Documentation/filesystems/gfs2-glocks.txt
View File

@ -60,7 +60,7 @@ go_lock | Called for the first local holder of a lock
go_unlock | Called on the final local unlock of a lock
go_dump | Called to print content of object for debugfs file, or on
| error to dump glock to the log.
go_type; | The type of the glock, LM_TYPE_.....
go_type | The type of the glock, LM_TYPE_.....
go_min_hold_time | The minimum hold time
The minimum hold time for each lock is the time after a remote lock

19
Documentation/filesystems/gfs2.txt
View File

@ -11,18 +11,15 @@ their I/O so file system consistency is maintained. One of the nifty
features of GFS is perfect consistency -- changes made to the file system
on one machine show up immediately on all other machines in the cluster.
GFS uses interchangable inter-node locking mechanisms. Different lock
modules can plug into GFS and each file system selects the appropriate
lock module at mount time. Lock modules include:
GFS uses interchangable inter-node locking mechanisms, the currently
supported mechanisms are:
lock_nolock -- allows gfs to be used as a local file system
lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
The dlm is found at linux/fs/dlm/
In addition to interfacing with an external locking manager, a gfs lock
module is responsible for interacting with external cluster management
systems. Lock_dlm depends on user space cluster management systems found
Lock_dlm depends on user space cluster management systems found
at the URL above.
To use gfs as a local file system, no external clustering systems are
@ -31,13 +28,19 @@ needed, simply:
$ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
$ mount -t gfs2 /dev/block_device /dir
GFS2 is not on-disk compatible with previous versions of GFS.
If you are using Fedora, you need to install the gfs2-utils package
and, for lock_dlm, you will also need to install the cman package
and write a cluster.conf as per the documentation.
GFS2 is not on-disk compatible with previous versions of GFS, but it
is pretty close.
The following man pages can be found at the URL above:
gfs2_fsck to repair a filesystem
fsck.gfs2 to repair a filesystem
gfs2_grow to expand a filesystem online
gfs2_jadd to add journals to a filesystem online
gfs2_tool to manipulate, examine and tune a filesystem
gfs2_quota to examine and change quota values in a filesystem
gfs2_convert to convert a gfs filesystem to gfs2 in-place
mount.gfs2 to help mount(8) mount a filesystem
mkfs.gfs2 to make a filesystem

131
Documentation/futex-requeue-pi.txt Normal file
View File

@ -0,0 +1,131 @@
Futex Requeue PI
----------------
Requeueing of tasks from a non-PI futex to a PI futex requires
special handling in order to ensure the underlying rt_mutex is never
left without an owner if it has waiters; doing so would break the PI
boosting logic [see rt-mutex-desgin.txt] For the purposes of
brevity, this action will be referred to as "requeue_pi" throughout
this document. Priority inheritance is abbreviated throughout as
"PI".
Motivation
----------
Without requeue_pi, the glibc implementation of
pthread_cond_broadcast() must resort to waking all the tasks waiting
on a pthread_condvar and letting them try to sort out which task
gets to run first in classic thundering-herd formation. An ideal
implementation would wake the highest-priority waiter, and leave the
rest to the natural wakeup inherent in unlocking the mutex
associated with the condvar.
Consider the simplified glibc calls:
/* caller must lock mutex */
pthread_cond_wait(cond, mutex)
{
lock(cond->__data.__lock);
unlock(mutex);
do {
unlock(cond->__data.__lock);
futex_wait(cond->__data.__futex);
lock(cond->__data.__lock);
} while(...)
unlock(cond->__data.__lock);
lock(mutex);
}
pthread_cond_broadcast(cond)
{
lock(cond->__data.__lock);
unlock(cond->__data.__lock);
futex_requeue(cond->data.__futex, cond->mutex);
}
Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
has waiters. Note that pthread_cond_wait() attempts to lock the
mutex only after it has returned to user space. This will leave the
underlying rt_mutex with waiters, and no owner, breaking the
previously mentioned PI-boosting algorithms.
In order to support PI-aware pthread_condvar's, the kernel needs to
be able to requeue tasks to PI futexes. This support implies that
upon a successful futex_wait system call, the caller would return to
user space already holding the PI futex. The glibc implementation
would be modified as follows:
/* caller must lock mutex */
pthread_cond_wait_pi(cond, mutex)
{
lock(cond->__data.__lock);
unlock(mutex);
do {
unlock(cond->__data.__lock);
futex_wait_requeue_pi(cond->__data.__futex);
lock(cond->__data.__lock);
} while(...)
unlock(cond->__data.__lock);
/* the kernel acquired the the mutex for us */
}
pthread_cond_broadcast_pi(cond)
{
lock(cond->__data.__lock);
unlock(cond->__data.__lock);
futex_requeue_pi(cond->data.__futex, cond->mutex);
}
The actual glibc implementation will likely test for PI and make the
necessary changes inside the existing calls rather than creating new
calls for the PI cases. Similar changes are needed for
pthread_cond_timedwait() and pthread_cond_signal().
Implementation
--------------
In order to ensure the rt_mutex has an owner if it has waiters, it
is necessary for both the requeue code, as well as the waiting code,
to be able to acquire the rt_mutex before returning to user space.
The requeue code cannot simply wake the waiter and leave it to
acquire the rt_mutex as it would open a race window between the
requeue call returning to user space and the waiter waking and
starting to run. This is especially true in the uncontended case.
The solution involves two new rt_mutex helper routines,
rt_mutex_start_proxy_lock() and rt_mutex_finish_proxy_lock(), which
allow the requeue code to acquire an uncontended rt_mutex on behalf
of the waiter and to enqueue the waiter on a contended rt_mutex.
Two new system calls provide the kernel<->user interface to
requeue_pi: FUTEX_WAIT_REQUEUE_PI and FUTEX_REQUEUE_CMP_PI.
FUTEX_WAIT_REQUEUE_PI is called by the waiter (pthread_cond_wait()
and pthread_cond_timedwait()) to block on the initial futex and wait
to be requeued to a PI-aware futex. The implementation is the
result of a high-speed collision between futex_wait() and
futex_lock_pi(), with some extra logic to check for the additional
wake-up scenarios.
FUTEX_REQUEUE_CMP_PI is called by the waker
(pthread_cond_broadcast() and pthread_cond_signal()) to requeue and
possibly wake the waiting tasks. Internally, this system call is
still handled by futex_requeue (by passing requeue_pi=1). Before
requeueing, futex_requeue() attempts to acquire the requeue target
PI futex on behalf of the top waiter. If it can, this waiter is
woken. futex_requeue() then proceeds to requeue the remaining
nr_wake+nr_requeue tasks to the PI futex, calling
rt_mutex_start_proxy_lock() prior to each requeue to prepare the
task as a waiter on the underlying rt_mutex. It is possible that
the lock can be acquired at this stage as well, if so, the next
waiter is woken to finish the acquisition of the lock.
FUTEX_REQUEUE_PI accepts nr_wake and nr_requeue as arguments, but
their sum is all that really matters. futex_requeue() will wake or
requeue up to nr_wake + nr_requeue tasks. It will wake only as many
tasks as it can acquire the lock for, which in the majority of cases
should be 0 as good programming practice dictates that the caller of
either pthread_cond_broadcast() or pthread_cond_signal() acquire the
mutex prior to making the call. FUTEX_REQUEUE_PI requires that
nr_wake=1. nr_requeue should be INT_MAX for broadcast and 0 for
signal.

6
Documentation/hwmon/sysfs-interface
View File

@ -150,6 +150,11 @@ fan[1-*]_min Fan minimum value
Unit: revolution/min (RPM)
RW
fan[1-*]_max Fan maximum value
Unit: revolution/min (RPM)
Only rarely supported by the hardware.
RW
fan[1-*]_input Fan input value.
Unit: revolution/min (RPM)
RO
@ -390,6 +395,7 @@ OR
in[0-*]_min_alarm
in[0-*]_max_alarm
fan[1-*]_min_alarm
fan[1-*]_max_alarm
temp[1-*]_min_alarm
temp[1-*]_max_alarm
temp[1-*]_crit_alarm

103
Documentation/input/multi-touch-protocol.txt
View File

@ -18,8 +18,12 @@ Usage
Anonymous finger details are sent sequentially as separate packets of ABS
events. Only the ABS_MT events are recognized as part of a finger
packet. The end of a packet is marked by calling the input_mt_sync()
function, which generates a SYN_MT_REPORT event. The end of multi-touch
transfer is marked by calling the usual input_sync() function.
function, which generates a SYN_MT_REPORT event. This instructs the
receiver to accept the data for the current finger and prepare to receive
another. The end of a multi-touch transfer is marked by calling the usual
input_sync() function. This instructs the receiver to act upon events
accumulated since last EV_SYN/SYN_REPORT and prepare to receive a new
set of events/packets.
A set of ABS_MT events with the desired properties is defined. The events
are divided into categories, to allow for partial implementation. The
@ -27,11 +31,26 @@ minimum set consists of ABS_MT_TOUCH_MAJOR, ABS_MT_POSITION_X and
ABS_MT_POSITION_Y, which allows for multiple fingers to be tracked. If the
device supports it, the ABS_MT_WIDTH_MAJOR may be used to provide the size
of the approaching finger. Anisotropy and direction may be specified with
ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION. Devices with
more granular information may specify general shapes as blobs, i.e., as a
sequence of rectangular shapes grouped together by an
ABS_MT_BLOB_ID. Finally, the ABS_MT_TOOL_TYPE may be used to specify
whether the touching tool is a finger or a pen or something else.
ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MINOR and ABS_MT_ORIENTATION. The
ABS_MT_TOOL_TYPE may be used to specify whether the touching tool is a
finger or a pen or something else. Devices with more granular information
may specify general shapes as blobs, i.e., as a sequence of rectangular
shapes grouped together by an ABS_MT_BLOB_ID. Finally, for the few devices
that currently support it, the ABS_MT_TRACKING_ID event may be used to
report finger tracking from hardware [5].
Here is what a minimal event sequence for a two-finger touch would look
like:
ABS_MT_TOUCH_MAJOR
ABS_MT_POSITION_X
ABS_MT_POSITION_Y
SYN_MT_REPORT
ABS_MT_TOUCH_MAJOR
ABS_MT_POSITION_X
ABS_MT_POSITION_Y
SYN_MT_REPORT
SYN_REPORT
Event Semantics
@ -44,24 +63,24 @@ ABS_MT_TOUCH_MAJOR
The length of the major axis of the contact. The length should be given in
surface units. If the surface has an X times Y resolution, the largest
possible value of ABS_MT_TOUCH_MAJOR is sqrt(X^2 + Y^2), the diagonal.
possible value of ABS_MT_TOUCH_MAJOR is sqrt(X^2 + Y^2), the diagonal [4].
ABS_MT_TOUCH_MINOR
The length, in surface units, of the minor axis of the contact. If the
contact is circular, this event can be omitted.
contact is circular, this event can be omitted [4].
ABS_MT_WIDTH_MAJOR
The length, in surface units, of the major axis of the approaching
tool. This should be understood as the size of the tool itself. The
orientation of the contact and the approaching tool are assumed to be the
same.
same [4].
ABS_MT_WIDTH_MINOR
The length, in surface units, of the minor axis of the approaching
tool. Omit if circular.
tool. Omit if circular [4].
The above four values can be used to derive additional information about
the contact. The ratio ABS_MT_TOUCH_MAJOR / ABS_MT_WIDTH_MAJOR approximates
@ -70,14 +89,17 @@ different characteristic widths [1].
ABS_MT_ORIENTATION
The orientation of the ellipse. The value should describe half a revolution
clockwise around the touch center. The scale of the value is arbitrary, but
zero should be returned for an ellipse aligned along the Y axis of the
surface. As an example, an index finger placed straight onto the axis could
return zero orientation, something negative when twisted to the left, and
something positive when twisted to the right. This value can be omitted if
the touching object is circular, or if the information is not available in
the kernel driver.
The orientation of the ellipse. The value should describe a signed quarter
of a revolution clockwise around the touch center. The signed value range
is arbitrary, but zero should be returned for a finger aligned along the Y
axis of the surface, a negative value when finger is turned to the left, and
a positive value when finger turned to the right. When completely aligned with
the X axis, the range max should be returned. Orientation can be omitted
if the touching object is circular, or if the information is not available
in the kernel driver. Partial orientation support is possible if the device
can distinguish between the two axis, but not (uniquely) any values in
between. In such cases, the range of ABS_MT_ORIENTATION should be [0, 1]
[4].
ABS_MT_POSITION_X
@ -98,8 +120,35 @@ ABS_MT_BLOB_ID
The BLOB_ID groups several packets together into one arbitrarily shaped
contact. This is a low-level anonymous grouping, and should not be confused
with the high-level contactID, explained below. Most kernel drivers will
not have this capability, and can safely omit the event.
with the high-level trackingID [5]. Most kernel drivers will not have blob
capability, and can safely omit the event.
ABS_MT_TRACKING_ID
The TRACKING_ID identifies an initiated contact throughout its life cycle
[5]. There are currently only a few devices that support it, so this event
should normally be omitted.
Event Computation
-----------------
The flora of different hardware unavoidably leads to some devices fitting
better to the MT protocol than others. To simplify and unify the mapping,
this section gives recipes for how to compute certain events.
For devices reporting contacts as rectangular shapes, signed orientation
cannot be obtained. Assuming X and Y are the lengths of the sides of the
touching rectangle, here is a simple formula that retains the most
information possible:
ABS_MT_TOUCH_MAJOR := max(X, Y)
ABS_MT_TOUCH_MINOR := min(X, Y)
ABS_MT_ORIENTATION := bool(X > Y)
The range of ABS_MT_ORIENTATION should be set to [0, 1], to indicate that
the device can distinguish between a finger along the Y axis (0) and a
finger along the X axis (1).
Finger Tracking
@ -109,14 +158,18 @@ The kernel driver should generate an arbitrary enumeration of the set of
anonymous contacts currently on the surface. The order in which the packets
appear in the event stream is not important.
The process of finger tracking, i.e., to assign a unique contactID to each
The process of finger tracking, i.e., to assign a unique trackingID to each
initiated contact on the surface, is left to user space; preferably the
multi-touch X driver [3]. In that driver, the contactID stays the same and
multi-touch X driver [3]. In that driver, the trackingID stays the same and
unique until the contact vanishes (when the finger leaves the surface). The
problem of assigning a set of anonymous fingers to a set of identified
fingers is a euclidian bipartite matching problem at each event update, and
relies on a sufficiently rapid update rate.
There are a few devices that support trackingID in hardware. User space can
make use of these native identifiers to reduce bandwidth and cpu usage.
Notes
-----
@ -136,5 +189,7 @@ could be used to derive tilt.
time of writing (April 2009), the MT protocol is not yet merged, and the
prototype implements finger matching, basic mouse support and two-finger
scrolling. The project aims at improving the quality of current multi-touch
functionality available in the synaptics X driver, and in addition
functionality available in the Synaptics X driver, and in addition
implement more advanced gestures.
[4] See the section on event computation.
[5] See the section on finger tracking.

60
Documentation/kernel-parameters.txt
View File

@ -56,7 +56,6 @@ parameter is applicable:
ISAPNP ISA PnP code is enabled.
ISDN Appropriate ISDN support is enabled.
JOY Appropriate joystick support is enabled.
KMEMTRACE kmemtrace is enabled.
LIBATA Libata driver is enabled
LP Printer support is enabled.
LOOP Loopback device support is enabled.
@ -329,11 +328,6 @@ and is between 256 and 4096 characters. It is defined in the file
flushed before they will be reused, which
is a lot of faster
amd_iommu_size= [HW,X86-64]
Define the size of the aperture for the AMD IOMMU
driver. Possible values are:
'32M', '64M' (default), '128M', '256M', '512M', '1G'
amijoy.map= [HW,JOY] Amiga joystick support
Map of devices attached to JOY0DAT and JOY1DAT
Format: <a>,<b>
@ -653,6 +647,13 @@ and is between 256 and 4096 characters. It is defined in the file
DMA-API debugging code disables itself because the
architectural default is too low.
dma_debug_driver=<driver_name>
With this option the DMA-API debugging driver
filter feature can be enabled at boot time. Just
pass the driver to filter for as the parameter.
The filter can be disabled or changed to another
driver later using sysfs.
dscc4.setup= [NET]
dtc3181e= [HW,SCSI]
@ -759,12 +760,25 @@ and is between 256 and 4096 characters. It is defined in the file
ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
ftrace=[tracer]
[ftrace] will set and start the specified tracer
[FTRACE] will set and start the specified tracer
as early as possible in order to facilitate early
boot debugging.
ftrace_dump_on_oops
[ftrace] will dump the trace buffers on oops.
[FTRACE] will dump the trace buffers on oops.
ftrace_filter=[function-list]
[FTRACE] Limit the functions traced by the function
tracer at boot up. function-list is a comma separated
list of functions. This list can be changed at run
time by the set_ftrace_filter file in the debugfs
tracing directory.
ftrace_notrace=[function-list]
[FTRACE] Do not trace the functions specified in
function-list. This list can be changed at run time
by the set_ftrace_notrace file in the debugfs
tracing directory.
gamecon.map[2|3]=
[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
@ -921,6 +935,12 @@ and is between 256 and 4096 characters. It is defined in the file
Formt: { "sha1" | "md5" }
default: "sha1"
ima_tcb [IMA]
Load a policy which meets the needs of the Trusted
Computing Base. This means IMA will measure all
programs exec'd, files mmap'd for exec, and all files
opened for read by uid=0.
in2000= [HW,SCSI]
See header of drivers/scsi/in2000.c.
@ -1061,15 +1081,6 @@ and is between 256 and 4096 characters. It is defined in the file
use the HighMem zone if it exists, and the Normal
zone if it does not.
kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no }
Controls whether kmemtrace is enabled
at boot-time.
kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of
subbufs kmemtrace's relay channel has. Set this
higher than default (KMEMTRACE_N_SUBBUFS in code) if
you experience buffer overruns.
kgdboc= [HW] kgdb over consoles.
Requires a tty driver that supports console polling.
(only serial suported for now)
@ -1079,6 +1090,10 @@ and is between 256 and 4096 characters. It is defined in the file
Configure the RouterBoard 532 series on-chip
Ethernet adapter MAC address.
kmemleak= [KNL] Boot-time kmemleak enable/disable
Valid arguments: on, off
Default: on
kstack=N [X86] Print N words from the kernel stack
in oops dumps.
@ -1582,6 +1597,9 @@ and is between 256 and 4096 characters. It is defined in the file
noinitrd [RAM] Tells the kernel not to load any configured
initial RAM disk.
nointremap [X86-64, Intel-IOMMU] Do not enable interrupt
remapping.
nointroute [IA-64]
nojitter [IA64] Disables jitter checking for ITC timers.
@ -1667,6 +1685,14 @@ and is between 256 and 4096 characters. It is defined in the file
oprofile.timer= [HW]
Use timer interrupt instead of performance counters
oprofile.cpu_type= Force an oprofile cpu type
This might be useful if you have an older oprofile
userland or if you want common events.
Format: { archperfmon }
archperfmon: [X86] Force use of architectural
perfmon on Intel CPUs instead of the
CPU specific event set.
osst= [HW,SCSI] SCSI Tape Driver
Format: <buffer_size>,<write_threshold>
See also Documentation/scsi/st.txt.

142
Documentation/kmemleak.txt Normal file
View File

@ -0,0 +1,142 @@
Kernel Memory Leak Detector
===========================
Introduction
------------
Kmemleak provides a way of detecting possible kernel memory leaks in a
way similar to a tracing garbage collector
(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
with the difference that the orphan objects are not freed but only
reported via /sys/kernel/debug/kmemleak. A similar method is used by the
Valgrind tool (memcheck --leak-check) to detect the memory leaks in
user-space applications.
Usage
-----
CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
thread scans the memory every 10 minutes (by default) and prints any new
unreferenced objects found. To trigger an intermediate scan and display
all the possible memory leaks:
# mount -t debugfs nodev /sys/kernel/debug/
# cat /sys/kernel/debug/kmemleak
Note that the orphan objects are listed in the order they were allocated
and one object at the beginning of the list may cause other subsequent
objects to be reported as orphan.
Memory scanning parameters can be modified at run-time by writing to the
/sys/kernel/debug/kmemleak file. The following parameters are supported:
off - disable kmemleak (irreversible)
stack=on - enable the task stacks scanning
stack=off - disable the tasks stacks scanning
scan=on - start the automatic memory scanning thread
scan=off - stop the automatic memory scanning thread
scan=<secs> - set the automatic memory scanning period in seconds (0
to disable it)
Kmemleak can also be disabled at boot-time by passing "kmemleak=off" on
the kernel command line.
Basic Algorithm
---------------
The memory allocations via kmalloc, vmalloc, kmem_cache_alloc and
friends are traced and the pointers, together with additional
information like size and stack trace, are stored in a prio search tree.
The corresponding freeing function calls are tracked and the pointers
removed from the kmemleak data structures.
An allocated block of memory is considered orphan if no pointer to its
start address or to any location inside the block can be found by
scanning the memory (including saved registers). This means that there
might be no way for the kernel to pass the address of the allocated
block to a freeing function and therefore the block is considered a
memory leak.
The scanning algorithm steps:
1. mark all objects as white (remaining white objects will later be
considered orphan)
2. scan the memory starting with the data section and stacks, checking
the values against the addresses stored in the prio search tree. If
a pointer to a white object is found, the object is added to the
gray list
3. scan the gray objects for matching addresses (some white objects
can become gray and added at the end of the gray list) until the
gray set is finished
4. the remaining white objects are considered orphan and reported via
/sys/kernel/debug/kmemleak
Some allocated memory blocks have pointers stored in the kernel's
internal data structures and they cannot be detected as orphans. To
avoid this, kmemleak can also store the number of values pointing to an
address inside the block address range that need to be found so that the
block is not considered a leak. One example is __vmalloc().
Kmemleak API
------------
See the include/linux/kmemleak.h header for the functions prototype.
kmemleak_init - initialize kmemleak
kmemleak_alloc - notify of a memory block allocation
kmemleak_free - notify of a memory block freeing
kmemleak_not_leak - mark an object as not a leak
kmemleak_ignore - do not scan or report an object as leak
kmemleak_scan_area - add scan areas inside a memory block
kmemleak_no_scan - do not scan a memory block
kmemleak_erase - erase an old value in a pointer variable
kmemleak_alloc_recursive - as kmemleak_alloc but checks the recursiveness
kmemleak_free_recursive - as kmemleak_free but checks the recursiveness
Dealing with false positives/negatives
--------------------------------------
The false negatives are real memory leaks (orphan objects) but not
reported by kmemleak because values found during the memory scanning
point to such objects. To reduce the number of false negatives, kmemleak
provides the kmemleak_ignore, kmemleak_scan_area, kmemleak_no_scan and
kmemleak_erase functions (see above). The task stacks also increase the
amount of false negatives and their scanning is not enabled by default.
The false positives are objects wrongly reported as being memory leaks
(orphan). For objects known not to be leaks, kmemleak provides the
kmemleak_not_leak function. The kmemleak_ignore could also be used if
the memory block is known not to contain other pointers and it will no
longer be scanned.
Some of the reported leaks are only transient, especially on SMP
systems, because of pointers temporarily stored in CPU registers or
stacks. Kmemleak defines MSECS_MIN_AGE (defaulting to 1000) representing
the minimum age of an object to be reported as a memory leak.
Limitations and Drawbacks
-------------------------
The main drawback is the reduced performance of memory allocation and
freeing. To avoid other penalties, the memory scanning is only performed
when the /sys/kernel/debug/kmemleak file is read. Anyway, this tool is
intended for debugging purposes where the performance might not be the
most important requirement.
To keep the algorithm simple, kmemleak scans for values pointing to any
address inside a block's address range. This may lead to an increased
number of false negatives. However, it is likely that a real memory leak
will eventually become visible.
Another source of false negatives is the data stored in non-pointer
values. In a future version, kmemleak could only scan the pointer
members in the allocated structures. This feature would solve many of
the false negative cases described above.
The tool can report false positives. These are cases where an allocated
block doesn't need to be freed (some cases in the init_call functions),
the pointer is calculated by other methods than the usual container_of
macro or the pointer is stored in a location not scanned by kmemleak.
Page allocations and ioremap are not tracked. Only the ARM and x86
architectures are currently supported.

129
Documentation/memory-barriers.txt
View File

@ -31,6 +31,7 @@ Contents:
- Locking functions.
- Interrupt disabling functions.
- Sleep and wake-up functions.
- Miscellaneous functions.
(*) Inter-CPU locking barrier effects.
@ -1217,6 +1218,132 @@ barriers are required in such a situation, they must be provided from some
other means.
SLEEP AND WAKE-UP FUNCTIONS
---------------------------
Sleeping and waking on an event flagged in global data can be viewed as an
interaction between two pieces of data: the task state of the task waiting for
the event and the global data used to indicate the event. To make sure that
these appear to happen in the right order, the primitives to begin the process
of going to sleep, and the primitives to initiate a wake up imply certain
barriers.
Firstly, the sleeper normally follows something like this sequence of events:
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (event_indicated)
break;
schedule();
}
A general memory barrier is interpolated automatically by set_current_state()
after it has altered the task state:
CPU 1
===============================
set_current_state();
set_mb();
STORE current->state
<general barrier>
LOAD event_indicated
set_current_state() may be wrapped by:
prepare_to_wait();
prepare_to_wait_exclusive();
which therefore also imply a general memory barrier after setting the state.
The whole sequence above is available in various canned forms, all of which
interpolate the memory barrier in the right place:
wait_event();
wait_event_interruptible();
wait_event_interruptible_exclusive();
wait_event_interruptible_timeout();
wait_event_killable();
wait_event_timeout();
wait_on_bit();
wait_on_bit_lock();
Secondly, code that performs a wake up normally follows something like this:
event_indicated = 1;
wake_up(&event_wait_queue);
or:
event_indicated = 1;
wake_up_process(event_daemon);
A write memory barrier is implied by wake_up() and co. if and only if they wake
something up. The barrier occurs before the task state is cleared, and so sits
between the STORE to indicate the event and the STORE to set TASK_RUNNING:
CPU 1 CPU 2
=============================== ===============================
set_current_state(); STORE event_indicated
set_mb(); wake_up();
STORE current->state <write barrier>
<general barrier> STORE current->state
LOAD event_indicated
The available waker functions include:
complete();
wake_up();
wake_up_all();
wake_up_bit();
wake_up_interruptible();
wake_up_interruptible_all();
wake_up_interruptible_nr();
wake_up_interruptible_poll();
wake_up_interruptible_sync();
wake_up_interruptible_sync_poll();
wake_up_locked();
wake_up_locked_poll();
wake_up_nr();
wake_up_poll();
wake_up_process();
[!] Note that the memory barriers implied by the sleeper and the waker do _not_
order multiple stores before the wake-up with respect to loads of those stored
values after the sleeper has called set_current_state(). For instance, if the
sleeper does:
set_current_state(TASK_INTERRUPTIBLE);
if (event_indicated)
break;
__set_current_state(TASK_RUNNING);
do_something(my_data);
and the waker does:
my_data = value;
event_indicated = 1;
wake_up(&event_wait_queue);
there's no guarantee that the change to event_indicated will be perceived by
the sleeper as coming after the change to my_data. In such a circumstance, the
code on both sides must interpolate its own memory barriers between the
separate data accesses. Thus the above sleeper ought to do:
set_current_state(TASK_INTERRUPTIBLE);
if (event_indicated) {
smp_rmb();
do_something(my_data);
}
and the waker should do:
my_data = value;
smp_wmb();
event_indicated = 1;
wake_up(&event_wait_queue);
MISCELLANEOUS FUNCTIONS
-----------------------
@ -1366,7 +1493,7 @@ WHERE ARE MEMORY BARRIERS NEEDED?
Under normal operation, memory operation reordering is generally not going to
be a problem as a single-threaded linear piece of code will still appear to
work correctly, even if it's in an SMP kernel. There are, however, three
work correctly, even if it's in an SMP kernel. There are, however, four
circumstances in which reordering definitely _could_ be a problem:
(*) Interprocessor interaction.

20
Documentation/scheduler/sched-rt-group.txt
View File

@ -4,6 +4,7 @@
CONTENTS
========
0. WARNING
1. Overview
1.1 The problem
1.2 The solution
@ -14,6 +15,23 @@ CONTENTS
3. Future plans
0. WARNING
==========
Fiddling with these settings can result in an unstable system, the knobs are
root only and assumes root knows what he is doing.
Most notable:
* very small values in sched_rt_period_us can result in an unstable
system when the period is smaller than either the available hrtimer
resolution, or the time it takes to handle the budget refresh itself.
* very small values in sched_rt_runtime_us can result in an unstable
system when the runtime is so small the system has difficulty making
forward progress (NOTE: the migration thread and kstopmachine both
are real-time processes).
1. Overview
===========
@ -169,7 +187,7 @@ get their allocated time.
Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
the biggest challenge as the current linux PI infrastructure is geared towards
the limited static priority levels 0-139. With deadline scheduling you need to
the limited static priority levels 0-99. With deadline scheduling you need to
do deadline inheritance (since priority is inversely proportional to the
deadline delta (deadline - now).

5
Documentation/sound/alsa/Procfile.txt
View File

@ -104,6 +104,11 @@ card*/pcm*/xrun_debug
When this value is greater than 1, the driver will show the
stack trace additionally. This may help the debugging.
Since 2.6.30, this option also enables the hwptr check using
jiffies. This detects spontaneous invalid pointer callback
values, but can be lead to too much corrections for a (mostly
buggy) hardware that doesn't give smooth pointer updates.
card*/pcm*/sub*/info
The general information of this PCM sub-stream.

11
Documentation/sysctl/kernel.txt
View File

@ -32,6 +32,7 @@ show up in /proc/sys/kernel:
- kstack_depth_to_print [ X86 only ]
- l2cr [ PPC only ]
- modprobe ==> Documentation/debugging-modules.txt
- modules_disabled
- msgmax
- msgmnb
- msgmni
@ -184,6 +185,16 @@ kernel stack.
==============================================================
modules_disabled:
A toggle value indicating if modules are allowed to be loaded
in an otherwise modular kernel. This toggle defaults to off
(0), but can be set true (1). Once true, modules can be
neither loaded nor unloaded, and the toggle cannot be set back
to false.
==============================================================
osrelease, ostype & version:
# cat osrelease

90
Documentation/trace/events.txt Normal file
View File

@ -0,0 +1,90 @@
Event Tracing
Documentation written by Theodore Ts'o
Updated by Li Zefan
1. Introduction
===============
Tracepoints (see Documentation/trace/tracepoints.txt) can be used
without creating custom kernel modules to register probe functions
using the event tracing infrastructure.
Not all tracepoints can be traced using the event tracing system;
the kernel developer must provide code snippets which define how the
tracing information is saved into the tracing buffer, and how the
tracing information should be printed.
2. Using Event Tracing
======================
2.1 Via the 'set_event' interface
---------------------------------
The events which are available for tracing can be found in the file
/debug/tracing/available_events.
To enable a particular event, such as 'sched_wakeup', simply echo it
to /debug/tracing/set_event. For example:
# echo sched_wakeup >> /debug/tracing/set_event
[ Note: '>>' is necessary, otherwise it will firstly disable
all the events. ]
To disable an event, echo the event name to the set_event file prefixed
with an exclamation point:
# echo '!sched_wakeup' >> /debug/tracing/set_event
To disable all events, echo an empty line to the set_event file:
# echo > /debug/tracing/set_event
To enable all events, echo '*:*' or '*:' to the set_event file:
# echo *:* > /debug/tracing/set_event
The events are organized into subsystems, such as ext4, irq, sched,
etc., and a full event name looks like this: <subsystem>:<event>. The
subsystem name is optional, but it is displayed in the available_events
file. All of the events in a subsystem can be specified via the syntax
"<subsystem>:*"; for example, to enable all irq events, you can use the
command:
# echo 'irq:*' > /debug/tracing/set_event
2.2 Via the 'enable' toggle
---------------------------
The events available are also listed in /debug/tracing/events/ hierarchy
of directories.
To enable event 'sched_wakeup':
# echo 1 > /debug/tracing/events/sched/sched_wakeup/enable
To disable it:
# echo 0 > /debug/tracing/events/sched/sched_wakeup/enable
To enable all events in sched subsystem:
# echo 1 > /debug/tracing/events/sched/enable
To eanble all events:
# echo 1 > /debug/tracing/events/enable
When reading one of these enable files, there are four results:
0 - all events this file affects are disabled
1 - all events this file affects are enabled
X - there is a mixture of events enabled and disabled
? - this file does not affect any event
3. Defining an event-enabled tracepoint
=======================================
See The example provided in samples/trace_events

17
Documentation/trace/ftrace.txt
View File

@ -179,7 +179,7 @@ Here is the list of current tracers that may be configured.
Function call tracer to trace all kernel functions.
"function_graph_tracer"
"function_graph"
Similar to the function tracer except that the
function tracer probes the functions on their entry
@ -518,9 +518,18 @@ priority with zero (0) being the highest priority and the nice
values starting at 100 (nice -20). Below is a quick chart to map
the kernel priority to user land priorities.
Kernel priority: 0 to 99 ==> user RT priority 99 to 0
Kernel priority: 100 to 139 ==> user nice -20 to 19
Kernel priority: 140 ==> idle task priority
Kernel Space User Space
===============================================================
0(high) to 98(low) user RT priority 99(high) to 1(low)
with SCHED_RR or SCHED_FIFO
---------------------------------------------------------------
99 sched_priority is not used in scheduling
decisions(it must be specified as 0)
---------------------------------------------------------------
100(high) to 139(low) user nice -20(high) to 19(low)
---------------------------------------------------------------
140 idle task priority
---------------------------------------------------------------
The task states are:

17
Documentation/trace/power.txt Normal file
View File

@ -0,0 +1,17 @@
The power tracer collects detailed information about C-state and P-state
transitions, instead of just looking at the high-level "average"
information.
There is a helper script found in scrips/tracing/power.pl in the kernel
sources which can be used to parse this information and create a
Scalable Vector Graphics (SVG) picture from the trace data.
To use this tracer:
echo 0 > /sys/kernel/debug/tracing/tracing_enabled
echo power > /sys/kernel/debug/tracing/current_tracer
echo 1 > /sys/kernel/debug/tracing/tracing_enabled
sleep 1
echo 0 > /sys/kernel/debug/tracing/tracing_enabled
cat /sys/kernel/debug/tracing/trace | \
perl scripts/tracing/power.pl > out.sv

122
Documentation/x86/boot.txt
View File

@ -50,6 +50,10 @@ Protocol 2.08: (Kernel 2.6.26) Added crc32 checksum and ELF format
Protocol 2.09: (Kernel 2.6.26) Added a field of 64-bit physical
pointer to single linked list of struct setup_data.
Protocol 2.10: (Kernel 2.6.31) Added a protocol for relaxed alignment
beyond the kernel_alignment added, new init_size and
pref_address fields. Added extended boot loader IDs.
**** MEMORY LAYOUT
The traditional memory map for the kernel loader, used for Image or
@ -168,12 +172,13 @@ Offset Proto Name Meaning
021C/4 2.00+ ramdisk_size initrd size (set by boot loader)
0220/4 2.00+ bootsect_kludge DO NOT USE - for bootsect.S use only
0224/2 2.01+ heap_end_ptr Free memory after setup end
0226/2 N/A pad1 Unused
0226/1 2.02+(3 ext_loader_ver Extended boot loader version
0227/1 2.02+(3 ext_loader_type Extended boot loader ID
0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line
022C/4 2.03+ ramdisk_max Highest legal initrd address
0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel
0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not
0235/1 N/A pad2 Unused
0235/1 2.10+ min_alignment Minimum alignment, as a power of two
0236/2 N/A pad3 Unused
0238/4 2.06+ cmdline_size Maximum size of the kernel command line
023C/4 2.07+ hardware_subarch Hardware subarchitecture
@ -182,6 +187,8 @@ Offset Proto Name Meaning
024C/4 2.08+ payload_length Length of kernel payload
0250/8 2.09+ setup_data 64-bit physical pointer to linked list
of struct setup_data
0258/8 2.10+ pref_address Preferred loading address
0260/4 2.10+ init_size Linear memory required during initialization
(1) For backwards compatibility, if the setup_sects field contains 0, the
real value is 4.
@ -190,6 +197,8 @@ Offset Proto Name Meaning
field are unusable, which means the size of a bzImage kernel
cannot be determined.
(3) Ignored, but safe to set, for boot protocols 2.02-2.09.
If the "HdrS" (0x53726448) magic number is not found at offset 0x202,
the boot protocol version is "old". Loading an old kernel, the
following parameters should be assumed:
@ -343,18 +352,32 @@ Protocol: 2.00+
0xTV here, where T is an identifier for the boot loader and V is
a version number. Otherwise, enter 0xFF here.
For boot loader IDs above T = 0xD, write T = 0xE to this field and
write the extended ID minus 0x10 to the ext_loader_type field.
Similarly, the ext_loader_ver field can be used to provide more than
four bits for the bootloader version.
For example, for T = 0x15, V = 0x234, write:
type_of_loader <- 0xE4
ext_loader_type <- 0x05
ext_loader_ver <- 0x23
Assigned boot loader ids:
0 LILO (0x00 reserved for pre-2.00 bootloader)
1 Loadlin
2 bootsect-loader (0x20, all other values reserved)
3 SYSLINUX
4 EtherBoot
3 Syslinux
4 Etherboot/gPXE
5 ELILO
7 GRUB
8 U-BOOT
8 U-Boot
9 Xen
A Gujin
B Qemu
C Arcturus Networks uCbootloader
E Extended (see ext_loader_type)
F Special (0xFF = undefined)
Please contact <hpa@zytor.com> if you need a bootloader ID
value assigned.
@ -453,6 +476,35 @@ Protocol: 2.01+
Set this field to the offset (from the beginning of the real-mode
code) of the end of the setup stack/heap, minus 0x0200.
Field name: ext_loader_ver
Type: write (optional)
Offset/size: 0x226/1
Protocol: 2.02+
This field is used as an extension of the version number in the
type_of_loader field. The total version number is considered to be
(type_of_loader & 0x0f) + (ext_loader_ver << 4).
The use of this field is boot loader specific. If not written, it
is zero.
Kernels prior to 2.6.31 did not recognize this field, but it is safe
to write for protocol version 2.02 or higher.
Field name: ext_loader_type
Type: write (obligatory if (type_of_loader & 0xf0) == 0xe0)
Offset/size: 0x227/1
Protocol: 2.02+
This field is used as an extension of the type number in
type_of_loader field. If the type in type_of_loader is 0xE, then
the actual type is (ext_loader_type + 0x10).
This field is ignored if the type in type_of_loader is not 0xE.
Kernels prior to 2.6.31 did not recognize this field, but it is safe
to write for protocol version 2.02 or higher.
Field name: cmd_line_ptr
Type: write (obligatory)
Offset/size: 0x228/4
@ -482,11 +534,19 @@ Protocol: 2.03+
0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
Field name: kernel_alignment
Type: read (reloc)
Type: read/modify (reloc)
Offset/size: 0x230/4
Protocol: 2.05+
Protocol: 2.05+ (read), 2.10+ (modify)
Alignment unit required by the kernel (if relocatable_kernel is true.)
Alignment unit required by the kernel (if relocatable_kernel is
true.) A relocatable kernel that is loaded at an alignment
incompatible with the value in this field will be realigned during
kernel initialization.
Starting with protocol version 2.10, this reflects the kernel
alignment preferred for optimal performance; it is possible for the
loader to modify this field to permit a lesser alignment. See the
min_alignment and pref_address field below.
Field name: relocatable_kernel
Type: read (reloc)
@ -498,6 +558,22 @@ Protocol: 2.05+
After loading, the boot loader must set the code32_start field to
point to the loaded code, or to a boot loader hook.
Field name: min_alignment
Type: read (reloc)
Offset/size: 0x235/1
Protocol: 2.10+
This field, if nonzero, indicates as a power of two the minimum
alignment required, as opposed to preferred, by the kernel to boot.
If a boot loader makes use of this field, it should update the
kernel_alignment field with the alignment unit desired; typically:
kernel_alignment = 1 << min_alignment
There may be a considerable performance cost with an excessively
misaligned kernel. Therefore, a loader should typically try each
power-of-two alignment from kernel_alignment down to this alignment.
Field name: cmdline_size
Type: read
Offset/size: 0x238/4
@ -582,6 +658,36 @@ Protocol: 2.09+
sure to consider the case where the linked list already contains
entries.
Field name: pref_address
Type: read (reloc)
Offset/size: 0x258/8
Protocol: 2.10+
This field, if nonzero, represents a preferred load address for the
kernel. A relocating bootloader should attempt to load at this
address if possible.
A non-relocatable kernel will unconditionally move itself and to run
at this address.
Field name: init_size
Type: read
Offset/size: 0x25c/4
This field indicates the amount of linear contiguous memory starting
at the kernel runtime start address that the kernel needs before it
is capable of examining its memory map. This is not the same thing
as the total amount of memory the kernel needs to boot, but it can
be used by a relocating boot loader to help select a safe load
address for the kernel.
The kernel runtime start address is determined by the following algorithm:
if (relocatable_kernel)
runtime_start = align_up(load_address, kernel_alignment)
else
runtime_start = pref_address
**** THE IMAGE CHECKSUM

5
Documentation/x86/x86_64/boot-options.txt
View File

@ -150,11 +150,6 @@ NUMA
Otherwise, the remaining system RAM is allocated to an
additional node.
numa=hotadd=percent
Only allow hotadd memory to preallocate page structures upto
percent of already available memory.
numa=hotadd=0 will disable hotadd memory.
ACPI
acpi=off Don't enable ACPI

9
Documentation/x86/x86_64/mm.txt
View File

@ -6,10 +6,11 @@ Virtual memory map with 4 level page tables:
0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
hole caused by [48:63] sign extension
ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0
ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space

55
MAINTAINERS
View File

@ -71,7 +71,7 @@ P: Person
M: Mail patches to
L: Mailing list that is relevant to this area
W: Web-page with status/info
T: SCM tree type and location. Type is one of: git, hg, quilt.
T: SCM tree type and location. Type is one of: git, hg, quilt, stgit.
S: Status, one of the following:
Supported: Someone is actually paid to look after this.
@ -159,7 +159,8 @@ F: drivers/net/r8169.c
8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
L: linux-serial@vger.kernel.org
W: http://serial.sourceforge.net
S: Orphan
M: alan@lxorguk.ukuu.org.uk
S: Odd Fixes
F: drivers/serial/8250*
F: include/linux/serial_8250.h
@ -434,7 +435,7 @@ F: arch/alpha/
AMD GEODE CS5536 USB DEVICE CONTROLLER DRIVER
P: Thomas Dahlmann
M: thomas.dahlmann@amd.com
M: dahlmann.thomas@arcor.de
L: linux-geode@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: drivers/usb/gadget/amd5536udc.*
@ -624,6 +625,7 @@ M: paulius.zaleckas@teltonika.lt
L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
T: git git://gitorious.org/linux-gemini/mainline.git
S: Maintained
F: arch/arm/mach-gemini/
ARM/EBSA110 MACHINE SUPPORT
P: Russell King
@ -650,6 +652,7 @@ P: Paulius Zaleckas
M: paulius.zaleckas@teltonika.lt
L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
S: Maintained
F: arch/arm/mm/*-fa*
ARM/FOOTBRIDGE ARCHITECTURE
P: Russell King
@ -1540,6 +1543,13 @@ W: http://www.fi.muni.cz/~kas/cosa/
S: Maintained
F: drivers/net/wan/cosa*
CPMAC ETHERNET DRIVER
P: Florian Fainelli
M: florian@openwrt.org
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/cpmac.c
CPU FREQUENCY DRIVERS
P: Dave Jones
M: davej@redhat.com
@ -1792,10 +1802,10 @@ F: drivers/char/epca*
F: drivers/char/digi*
DIRECTORY NOTIFICATION (DNOTIFY)
P: Stephen Rothwell
M: sfr@canb.auug.org.au
P: Eric Paris
M: eparis@parisplace.org
L: linux-kernel@vger.kernel.org
S: Supported
S: Maintained
F: Documentation/filesystems/dnotify.txt
F: fs/notify/dnotify/
F: include/linux/dnotify.h
@ -1969,10 +1979,20 @@ F: Documentation/edac.txt
F: drivers/edac/edac_*
F: include/linux/edac.h
EDAC-AMD64
P: Doug Thompson
M: dougthompson@xmission.com
P: Borislav Petkov
M: borislav.petkov@amd.com
L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers)
W: bluesmoke.sourceforge.net
S: Supported
F: drivers/edac/amd64_edac*
EDAC-E752X
P: Mark Gross
P: Doug Thompson
M: mark.gross@intel.com
P: Doug Thompson
M: dougthompson@xmission.com
L: bluesmoke-devel@lists.sourceforge.net (moderated for non-subscribers)
W: bluesmoke.sourceforge.net
@ -2249,7 +2269,7 @@ P: Li Yang
M: leoli@freescale.com
P: Zhang Wei
M: zw@zh-kernel.org
L: linuxppc-embedded@ozlabs.org
L: linuxppc-dev@ozlabs.org
L: linux-kernel@vger.kernel.org
S: Maintained
F: drivers/dma/fsldma.*
@ -2838,6 +2858,8 @@ P: John McCutchan
M: john@johnmccutchan.com
P: Robert Love
M: rlove@rlove.org
P: Eric Paris
M: eparis@parisplace.org
L: linux-kernel@vger.kernel.org
S: Maintained
F: Documentation/filesystems/inotify.txt
@ -3350,6 +3372,12 @@ F: Documentation/trace/kmemtrace.txt
F: include/trace/kmemtrace.h
F: kernel/trace/kmemtrace.c
KMEMLEAK
P: Catalin Marinas
M: catalin.marinas@arm.com
L: linux-kernel@vger.kernel.org
S: Maintained
KPROBES
P: Ananth N Mavinakayanahalli
M: ananth@in.ibm.com
@ -4383,6 +4411,16 @@ S: Maintained
F: include/linux/delayacct.h
F: kernel/delayacct.c
PERFORMANCE COUNTER SUBSYSTEM
P: Peter Zijlstra
M: a.p.zijlstra@chello.nl
P: Paul Mackerras
M: paulus@samba.org
P: Ingo Molnar
M: mingo@elte.hu
L: linux-kernel@vger.kernel.org
S: Supported
PERSONALITY HANDLING
P: Christoph Hellwig
M: hch@infradead.org
@ -5620,6 +5658,7 @@ P: Alan Cox
M: alan@lxorguk.ukuu.org.uk
L: linux-kernel@vger.kernel.org
S: Maintained
T: stgit http://zeniv.linux.org.uk/~alan/ttydev/
TULIP NETWORK DRIVERS
P: Grant Grundler

4
Makefile
View File

@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 30
EXTRAVERSION = -rc7
EXTRAVERSION =
NAME = Man-Eating Seals of Antiquity
# *DOCUMENTATION*
@ -533,7 +533,7 @@ endif
include $(srctree)/arch/$(SRCARCH)/Makefile
ifneq (CONFIG_FRAME_WARN,0)
ifneq ($(CONFIG_FRAME_WARN),0)
KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
endif

3
arch/alpha/kernel/osf_sys.c
View File

@ -371,8 +371,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path,
int retval = -EINVAL;
char *name;
lock_kernel();
name = getname(path);
retval = PTR_ERR(name);
if (IS_ERR(name))
@ -392,7 +390,6 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path,
}
putname(name);
out:
unlock_kernel();
return retval;
}

8
arch/alpha/kernel/sys_dp264.c
View File

@ -176,22 +176,26 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
}
}
static void
static int
dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
{
spin_lock(&dp264_irq_lock);
cpu_set_irq_affinity(irq, *affinity);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
return 0;
}
static void
static int
clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
{
spin_lock(&dp264_irq_lock);
cpu_set_irq_affinity(irq - 16, *affinity);
tsunami_update_irq_hw(cached_irq_mask);
spin_unlock(&dp264_irq_lock);
return 0;
}
static struct hw_interrupt_type dp264_irq_type = {

4
arch/alpha/kernel/sys_titan.c
View File

@ -157,13 +157,15 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
}
static void
static int
titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
{
spin_lock(&titan_irq_lock);
titan_cpu_set_irq_affinity(irq - 16, *affinity);
titan_update_irq_hw(titan_cached_irq_mask);
spin_unlock(&titan_irq_lock);
return 0;
}
static void

4
arch/arm/common/gic.c
View File

@ -109,7 +109,7 @@ static void gic_unmask_irq(unsigned int irq)
}
#ifdef CONFIG_SMP
static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
static int gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
{
void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3);
unsigned int shift = (irq % 4) * 8;
@ -122,6 +122,8 @@ static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
val |= 1 << (cpu + shift);
writel(val, reg);
spin_unlock(&irq_controller_lock);
return 0;
}
#endif

13
arch/arm/include/asm/assembler.h
View File

@ -114,3 +114,16 @@
.align 3; \
.long 9999b,9001f; \
.previous
/*
* SMP data memory barrier
*/
.macro smp_dmb
#ifdef CONFIG_SMP
#if __LINUX_ARM_ARCH__ >= 7
dmb
#elif __LINUX_ARM_ARCH__ == 6
mcr p15, 0, r0, c7, c10, 5 @ dmb
#endif
#endif
.endm

61
arch/arm/include/asm/atomic.h
View File

@ -44,11 +44,29 @@ static inline void atomic_set(atomic_t *v, int i)
: "cc");
}
static inline void atomic_add(int i, atomic_t *v)
{
unsigned long tmp;
int result;
__asm__ __volatile__("@ atomic_add\n"
"1: ldrex %0, [%2]\n"
" add %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "Ir" (i)
: "cc");
}
static inline int atomic_add_return(int i, atomic_t *v)
{
unsigned long tmp;
int result;
smp_mb();
__asm__ __volatile__("@ atomic_add_return\n"
"1: ldrex %0, [%2]\n"
" add %0, %0, %3\n"
@ -59,14 +77,34 @@ static inline int atomic_add_return(int i, atomic_t *v)
: "r" (&v->counter), "Ir" (i)
: "cc");
smp_mb();
return result;
}
static inline void atomic_sub(int i, atomic_t *v)
{
unsigned long tmp;
int result;
__asm__ __volatile__("@ atomic_sub\n"
"1: ldrex %0, [%2]\n"
" sub %0, %0, %3\n"
" strex %1, %0, [%2]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (result), "=&r" (tmp)
: "r" (&v->counter), "Ir" (i)
: "cc");
}
static inline int atomic_sub_return(int i, atomic_t *v)
{
unsigned long tmp;
int result;
smp_mb();
__asm__ __volatile__("@ atomic_sub_return\n"
"1: ldrex %0, [%2]\n"
" sub %0, %0, %3\n"
@ -77,6 +115,8 @@ static inline int atomic_sub_return(int i, atomic_t *v)
: "r" (&v->counter), "Ir" (i)
: "cc");
smp_mb();
return result;
}
@ -84,6 +124,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
{
unsigned long oldval, res;
smp_mb();
do {
__asm__ __volatile__("@ atomic_cmpxchg\n"
"ldrex %1, [%2]\n"
@ -95,6 +137,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
: "cc");
} while (res);
smp_mb();
return oldval;
}
@ -135,6 +179,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
return val;
}
#define atomic_add(i, v) (void) atomic_add_return(i, v)
static inline int atomic_sub_return(int i, atomic_t *v)
{
@ -148,6 +193,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
return val;
}
#define atomic_sub(i, v) (void) atomic_sub_return(i, v)
static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
@ -187,10 +233,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
}
#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
#define atomic_add(i, v) (void) atomic_add_return(i, v)
#define atomic_inc(v) (void) atomic_add_return(1, v)
#define atomic_sub(i, v) (void) atomic_sub_return(i, v)
#define atomic_dec(v) (void) atomic_sub_return(1, v)
#define atomic_inc(v) atomic_add(1, v)
#define atomic_dec(v) atomic_sub(1, v)
#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
@ -200,11 +244,10 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
/* Atomic operations are already serializing on ARM */
#define smp_mb__before_atomic_dec() barrier()
#define smp_mb__after_atomic_dec() barrier()
#define smp_mb__before_atomic_inc() barrier()
#define smp_mb__after_atomic_inc() barrier()
#define smp_mb__before_atomic_dec() smp_mb()
#define smp_mb__after_atomic_dec() smp_mb()
#define smp_mb__before_atomic_inc() smp_mb()
#define smp_mb__after_atomic_inc() smp_mb()
#include <asm-generic/atomic.h>
#endif

16
arch/arm/include/asm/cache.h
View File

@ -7,4 +7,20 @@
#define L1_CACHE_SHIFT 5
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
/*
* Memory returned by kmalloc() may be used for DMA, so we must make
* sure that all such allocations are cache aligned. Otherwise,
* unrelated code may cause parts of the buffer to be read into the
* cache before the transfer is done, causing old data to be seen by
* the CPU.
*/
#define ARCH_KMALLOC_MINALIGN L1_CACHE_BYTES
/*
* With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
*/
#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
#define ARCH_SLAB_MINALIGN 8
#endif
#endif

3
arch/arm/include/asm/flat.h
View File

@ -5,9 +5,6 @@
#ifndef __ARM_FLAT_H__
#define __ARM_FLAT_H__
/* An odd number of words will be pushed after this alignment, so
deliberately misalign the value. */
#define flat_stack_align(sp) sp = (void *)(((unsigned long)(sp) - 4) | 4)
#define flat_argvp_envp_on_stack() 1
#define flat_old_ram_flag(flags) (flags)
#define flat_reloc_valid(reloc, size) ((reloc) <= (size))

7
arch/arm/include/asm/page.h
View File

@ -202,13 +202,6 @@ typedef struct page *pgtable_t;
(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
/*
* With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
*/
#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
#define ARCH_SLAB_MINALIGN 8
#endif
#include <asm-generic/page.h>
#endif

176
arch/arm/include/asm/system.h
View File

@ -248,6 +248,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
unsigned int tmp;
#endif
smp_mb();
switch (size) {
#if __LINUX_ARM_ARCH__ >= 6
case 1:
@ -307,6 +309,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
__bad_xchg(ptr, size), ret = 0;
break;
}
smp_mb();
return ret;
}
@ -316,6 +319,12 @@ extern void enable_hlt(void);
#include <asm-generic/cmpxchg-local.h>
#if __LINUX_ARM_ARCH__ < 6
#ifdef CONFIG_SMP
#error "SMP is not supported on this platform"
#endif
/*
* cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
* them available.
@ -329,6 +338,173 @@ extern void enable_hlt(void);
#include <asm-generic/cmpxchg.h>
#endif
#else /* __LINUX_ARM_ARCH__ >= 6 */
extern void __bad_cmpxchg(volatile void *ptr, int size);
/*
* cmpxchg only support 32-bits operands on ARMv6.
*/
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
unsigned long oldval, res;
switch (size) {
#ifdef CONFIG_CPU_32v6K
case 1:
do {
asm volatile("@ __cmpxchg1\n"
" ldrexb %1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" strexbeq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (old), "r" (new)
: "memory", "cc");
} while (res);
break;
case 2:
do {
asm volatile("@ __cmpxchg1\n"
" ldrexh %1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" strexheq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (old), "r" (new)
: "memory", "cc");
} while (res);
break;
#endif /* CONFIG_CPU_32v6K */
case 4:
do {
asm volatile("@ __cmpxchg4\n"
" ldrex %1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" strexeq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (old), "r" (new)
: "memory", "cc");
} while (res);
break;
default:
__bad_cmpxchg(ptr, size);
oldval = 0;
}
return oldval;
}
static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
unsigned long ret;
smp_mb();
ret = __cmpxchg(ptr, old, new, size);
smp_mb();
return ret;
}
#define cmpxchg(ptr,o,n) \
((__typeof__(*(ptr)))__cmpxchg_mb((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
sizeof(*(ptr))))
static inline unsigned long __cmpxchg_local(volatile void *ptr,
unsigned long old,
unsigned long new, int size)
{
unsigned long ret;
switch (size) {
#ifndef CONFIG_CPU_32v6K
case 1:
case 2:
ret = __cmpxchg_local_generic(ptr, old, new, size);
break;
#endif /* !CONFIG_CPU_32v6K */
default:
ret = __cmpxchg(ptr, old, new, size);
}
return ret;
}
#define cmpxchg_local(ptr,o,n) \
((__typeof__(*(ptr)))__cmpxchg_local((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
sizeof(*(ptr))))
#ifdef CONFIG_CPU_32v6K
/*
* Note : ARMv7-M (currently unsupported by Linux) does not support
* ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
* not be allowed to use __cmpxchg64.
*/
static inline unsigned long long __cmpxchg64(volatile void *ptr,
unsigned long long old,
unsigned long long new)
{
register unsigned long long oldval asm("r0");
register unsigned long long __old asm("r2") = old;
register unsigned long long __new asm("r4") = new;
unsigned long res;
do {
asm volatile(
" @ __cmpxchg8\n"
" ldrexd %1, %H1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" teqeq %H1, %H3\n"
" strexdeq %0, %4, %H4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (__old), "r" (__new)
: "memory", "cc");
} while (res);
return oldval;
}
static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
unsigned long long old,
unsigned long long new)
{
unsigned long long ret;
smp_mb();
ret = __cmpxchg64(ptr, old, new);
smp_mb();
return ret;
}
#define cmpxchg64(ptr,o,n) \
((__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)))
#define cmpxchg64_local(ptr,o,n) \
((__typeof__(*(ptr)))__cmpxchg64((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)))
#else /* !CONFIG_CPU_32v6K */
#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
#endif /* CONFIG_CPU_32v6K */
#endif /* __LINUX_ARM_ARCH__ >= 6 */
#endif /* __ASSEMBLY__ */
#define arch_align_stack(x) (x)

9
arch/arm/kernel/elf.c
View File

@ -78,6 +78,15 @@ int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack)
return 1;
if (cpu_architecture() < CPU_ARCH_ARMv6)
return 1;
#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT)
/*
* If we have support for OABI programs, we can never allow NX
* support - our signal syscall restart mechanism relies upon
* being able to execute code placed on the user stack.
*/
return 1;
#else
return 0;
#endif
}
EXPORT_SYMBOL(arm_elf_read_implies_exec);

5
arch/arm/kernel/entry-armv.S
View File

@ -815,10 +815,7 @@ __kuser_helper_start:
*/
__kuser_memory_barrier: @ 0xffff0fa0
#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP)
mcr p15, 0, r0, c7, c10, 5 @ dmb
#endif
smp_dmb
usr_ret lr
.align 5

2
arch/arm/lib/bitops.h
View File

@ -18,12 +18,14 @@
mov r2, #1
add r1, r1, r0, lsr #3 @ Get byte offset
mov r3, r2, lsl r3 @ create mask
smp_dmb
1: ldrexb r2, [r1]
ands r0, r2, r3 @ save old value of bit
\instr r2, r2, r3 @ toggle bit
strexb ip, r2, [r1]
cmp ip, #0
bne 1b
smp_dmb
cmp r0, #0
movne r0, #1
2: mov pc, lr

3
arch/arm/mach-gemini/include/mach/hardware.h
View File

@ -15,10 +15,9 @@
/*
* Memory Map definitions
*/
/* FIXME: Does it really swap SRAM like this? */
#ifdef CONFIG_GEMINI_MEM_SWAP
# define GEMINI_DRAM_BASE 0x00000000
# define GEMINI_SRAM_BASE 0x20000000
# define GEMINI_SRAM_BASE 0x70000000
#else
# define GEMINI_SRAM_BASE 0x00000000
# define GEMINI_DRAM_BASE 0x10000000

8
arch/arm/mach-kirkwood/common.c
View File

@ -144,6 +144,9 @@ static struct platform_device kirkwood_ge00 = {
.id = 0,
.num_resources = 1,
.resource = kirkwood_ge00_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init kirkwood_ge00_init(struct mv643xx_eth_platform_data *eth_data)
@ -202,6 +205,9 @@ static struct platform_device kirkwood_ge01 = {
.id = 1,
.num_resources = 1,
.resource = kirkwood_ge01_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init kirkwood_ge01_init(struct mv643xx_eth_platform_data *eth_data)
@ -386,12 +392,10 @@ static struct mv64xxx_i2c_pdata kirkwood_i2c_pdata = {
static struct resource kirkwood_i2c_resources[] = {
{
.name = "i2c",
.start = I2C_PHYS_BASE,
.end = I2C_PHYS_BASE + 0x1f,
.flags = IORESOURCE_MEM,
}, {
.name = "i2c",
.start = IRQ_KIRKWOOD_TWSI,
.end = IRQ_KIRKWOOD_TWSI,
.flags = IORESOURCE_IRQ,

6
arch/arm/mach-kirkwood/ts219-setup.c
View File

@ -142,6 +142,8 @@ static unsigned int qnap_ts219_mpp_config[] __initdata = {
MPP1_SPI_MOSI,
MPP2_SPI_SCK,
MPP3_SPI_MISO,
MPP4_SATA1_ACTn,
MPP5_SATA0_ACTn,
MPP8_TW_SDA,
MPP9_TW_SCK,
MPP10_UART0_TXD,
@ -150,10 +152,6 @@ static unsigned int qnap_ts219_mpp_config[] __initdata = {
MPP14_UART1_RXD, /* PIC controller */
MPP15_GPIO, /* USB Copy button */
MPP16_GPIO, /* Reset button */
MPP20_SATA1_ACTn,
MPP21_SATA0_ACTn,
MPP22_SATA1_PRESENTn,
MPP23_SATA0_PRESENTn,
0
};

6
arch/arm/mach-loki/common.c
View File

@ -82,6 +82,9 @@ static struct platform_device loki_ge0 = {
.id = 0,
.num_resources = 1,
.resource = loki_ge0_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init loki_ge0_init(struct mv643xx_eth_platform_data *eth_data)
@ -136,6 +139,9 @@ static struct platform_device loki_ge1 = {
.id = 1,
.num_resources = 1,
.resource = loki_ge1_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init loki_ge1_init(struct mv643xx_eth_platform_data *eth_data)

5
arch/arm/mach-mmp/include/mach/mfp-pxa168.h
View File

@ -3,6 +3,11 @@
#include <mach/mfp.h>
#define MFP_DRIVE_VERY_SLOW (0x0 << 13)
#define MFP_DRIVE_SLOW (0x1 << 13)
#define MFP_DRIVE_MEDIUM (0x2 << 13)
#define MFP_DRIVE_FAST (0x3 << 13)
/* GPIO */
#define GPIO0_GPIO MFP_CFG(GPIO0, AF5)
#define GPIO1_GPIO MFP_CFG(GPIO1, AF5)

5
arch/arm/mach-mmp/include/mach/mfp-pxa910.h
View File

@ -3,6 +3,11 @@
#include <mach/mfp.h>
#define MFP_DRIVE_VERY_SLOW (0x0 << 13)
#define MFP_DRIVE_SLOW (0x2 << 13)
#define MFP_DRIVE_MEDIUM (0x4 << 13)
#define MFP_DRIVE_FAST (0x8 << 13)
/* UART2 */
#define GPIO47_UART2_RXD MFP_CFG(GPIO47, AF6)
#define GPIO48_UART2_TXD MFP_CFG(GPIO48, AF6)

9
arch/arm/mach-mmp/include/mach/mfp.h
View File

@ -12,16 +12,13 @@
* possible, we make the following compromise:
*
* 1. SLEEP_OE_N will always be programmed to '1' (by MFP_LPM_FLOAT)
* 2. DRIVE strength definitions redefined to include the reserved bit10
* 2. DRIVE strength definitions redefined to include the reserved bit
* - the reserved bit differs between pxa168 and pxa910, and the
* MFP_DRIVE_* macros are individually defined in mfp-pxa{168,910}.h
* 3. Override MFP_CFG() and MFP_CFG_DRV()
* 4. Drop the use of MFP_CFG_LPM() and MFP_CFG_X()
*/
#define MFP_DRIVE_VERY_SLOW (0x0 << 13)
#define MFP_DRIVE_SLOW (0x2 << 13)
#define MFP_DRIVE_MEDIUM (0x4 << 13)
#define MFP_DRIVE_FAST (0x8 << 13)
#undef MFP_CFG
#undef MFP_CFG_DRV
#undef MFP_CFG_LPM

2
arch/arm/mach-mmp/time.c
View File

@ -136,7 +136,7 @@ static struct clock_event_device ckevt = {
.set_mode = timer_set_mode,
};
static cycle_t clksrc_read(void)
static cycle_t clksrc_read(struct clocksource *cs)
{
return timer_read();
}

16
arch/arm/mach-mv78xx0/common.c
View File

@ -321,6 +321,9 @@ static struct platform_device mv78xx0_ge00 = {
.id = 0,
.num_resources = 1,
.resource = mv78xx0_ge00_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init mv78xx0_ge00_init(struct mv643xx_eth_platform_data *eth_data)
@ -375,6 +378,9 @@ static struct platform_device mv78xx0_ge01 = {
.id = 1,
.num_resources = 1,
.resource = mv78xx0_ge01_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init mv78xx0_ge01_init(struct mv643xx_eth_platform_data *eth_data)
@ -429,6 +435,9 @@ static struct platform_device mv78xx0_ge10 = {
.id = 2,
.num_resources = 1,
.resource = mv78xx0_ge10_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init mv78xx0_ge10_init(struct mv643xx_eth_platform_data *eth_data)
@ -496,6 +505,9 @@ static struct platform_device mv78xx0_ge11 = {
.id = 3,
.num_resources = 1,
.resource = mv78xx0_ge11_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init mv78xx0_ge11_init(struct mv643xx_eth_platform_data *eth_data)
@ -532,12 +544,10 @@ static struct mv64xxx_i2c_pdata mv78xx0_i2c_0_pdata = {
static struct resource mv78xx0_i2c_0_resources[] = {
{
.name = "i2c 0 base",
.start = I2C_0_PHYS_BASE,
.end = I2C_0_PHYS_BASE + 0x1f,
.flags = IORESOURCE_MEM,
}, {
.name = "i2c 0 irq",
.start = IRQ_MV78XX0_I2C_0,
.end = IRQ_MV78XX0_I2C_0,
.flags = IORESOURCE_IRQ,
@ -567,12 +577,10 @@ static struct mv64xxx_i2c_pdata mv78xx0_i2c_1_pdata = {
static struct resource mv78xx0_i2c_1_resources[] = {
{
.name = "i2c 1 base",
.start = I2C_1_PHYS_BASE,
.end = I2C_1_PHYS_BASE + 0x1f,
.flags = IORESOURCE_MEM,
}, {
.name = "i2c 1 irq",
.start = IRQ_MV78XX0_I2C_1,
.end = IRQ_MV78XX0_I2C_1,
.flags = IORESOURCE_IRQ,

2
arch/arm/mach-mx2/clock_imx21.c
View File

@ -890,7 +890,7 @@ static struct clk clko_clk = {
.con_id = n, \
.clk = &c, \
},
static struct clk_lookup lookups[] __initdata = {
static struct clk_lookup lookups[] = {
/* It's unlikely that any driver wants one of them directly:
_REGISTER_CLOCK(NULL, "ckih", ckih_clk)
_REGISTER_CLOCK(NULL, "ckil", ckil_clk)

2
arch/arm/mach-mx2/clock_imx27.c
View File

@ -621,7 +621,7 @@ DEFINE_CLOCK1(csi_clk, 0, 0, 0, parent, &csi_clk1, &per4_clk);
.clk = &c, \
},
static struct clk_lookup lookups[] __initdata = {
static struct clk_lookup lookups[] = {
_REGISTER_CLOCK("imx-uart.0", NULL, uart1_clk)
_REGISTER_CLOCK("imx-uart.1", NULL, uart2_clk)
_REGISTER_CLOCK("imx-uart.2", NULL, uart3_clk)

2
arch/arm/mach-mx3/clock-imx35.c
View File

@ -404,7 +404,7 @@ DEFINE_CLOCK(gpu2d_clk, 0, CCM_CGR3, 4, NULL, NULL);
.clk = &c, \
},
static struct clk_lookup lookups[] __initdata = {
static struct clk_lookup lookups[] = {
_REGISTER_CLOCK(NULL, "asrc", asrc_clk)
_REGISTER_CLOCK(NULL, "ata", ata_clk)
_REGISTER_CLOCK(NULL, "audmux", audmux_clk)

2
arch/arm/mach-mx3/clock.c
View File

@ -516,7 +516,7 @@ DEFINE_CLOCK(ipg_clk, 0, NULL, 0, ipg_get_rate, NULL, &ahb_clk);
.clk = &c, \
},
static struct clk_lookup lookups[] __initdata = {
static struct clk_lookup lookups[] = {
_REGISTER_CLOCK(NULL, "emi", emi_clk)
_REGISTER_CLOCK(NULL, "cspi", cspi1_clk)
_REGISTER_CLOCK(NULL, "cspi", cspi2_clk)

5
arch/arm/mach-orion5x/common.c
View File

@ -188,6 +188,9 @@ static struct platform_device orion5x_eth = {
.id = 0,
.num_resources = 1,
.resource = orion5x_eth_resources,
.dev = {
.coherent_dma_mask = 0xffffffff,
},
};
void __init orion5x_eth_init(struct mv643xx_eth_platform_data *eth_data)
@ -248,12 +251,10 @@ static struct mv64xxx_i2c_pdata orion5x_i2c_pdata = {
static struct resource orion5x_i2c_resources[] = {
{
.name = "i2c base",
.start = I2C_PHYS_BASE,
.end = I2C_PHYS_BASE + 0x1f,
.flags = IORESOURCE_MEM,
}, {
.name = "i2c irq",
.start = IRQ_ORION5X_I2C,
.end = IRQ_ORION5X_I2C,
.flags = IORESOURCE_IRQ,

5
arch/arm/mach-pxa/devices.c
View File

@ -72,7 +72,10 @@ void __init pxa_set_mci_info(struct pxamci_platform_data *info)
}
static struct pxa2xx_udc_mach_info pxa_udc_info;
static struct pxa2xx_udc_mach_info pxa_udc_info = {
.gpio_pullup = -1,
.gpio_vbus = -1,
};
void __init pxa_set_udc_info(struct pxa2xx_udc_mach_info *info)
{

36
arch/arm/mach-pxa/ezx.c
View File

@ -111,9 +111,9 @@ static unsigned long ezx_pin_config[] __initdata = {
GPIO25_SSP1_TXD,
GPIO26_SSP1_RXD,
GPIO24_GPIO, /* pcap chip select */
GPIO1_GPIO, /* pcap interrupt */
GPIO4_GPIO, /* WDI_AP */
GPIO55_GPIO, /* SYS_RESTART */
GPIO1_GPIO | WAKEUP_ON_EDGE_RISE, /* pcap interrupt */
GPIO4_GPIO | MFP_LPM_DRIVE_HIGH, /* WDI_AP */
GPIO55_GPIO | MFP_LPM_DRIVE_HIGH, /* SYS_RESTART */
/* MMC */
GPIO32_MMC_CLK,
@ -144,20 +144,20 @@ static unsigned long ezx_pin_config[] __initdata = {
#if defined(CONFIG_MACH_EZX_A780) || defined(CONFIG_MACH_EZX_E680)
static unsigned long gen1_pin_config[] __initdata = {
/* flip / lockswitch */
GPIO12_GPIO,
GPIO12_GPIO | WAKEUP_ON_EDGE_BOTH,
/* bluetooth (bcm2035) */
GPIO14_GPIO | WAKEUP_ON_LEVEL_HIGH, /* HOSTWAKE */
GPIO14_GPIO | WAKEUP_ON_EDGE_RISE, /* HOSTWAKE */
GPIO48_GPIO, /* RESET */
GPIO28_GPIO, /* WAKEUP */
/* Neptune handshake */
GPIO0_GPIO | WAKEUP_ON_LEVEL_HIGH, /* BP_RDY */
GPIO57_GPIO, /* AP_RDY */
GPIO13_GPIO | WAKEUP_ON_LEVEL_HIGH, /* WDI */
GPIO3_GPIO | WAKEUP_ON_LEVEL_HIGH, /* WDI2 */
GPIO82_GPIO, /* RESET */
GPIO99_GPIO, /* TC_MM_EN */
GPIO0_GPIO | WAKEUP_ON_EDGE_FALL, /* BP_RDY */
GPIO57_GPIO | MFP_LPM_DRIVE_HIGH, /* AP_RDY */
GPIO13_GPIO | WAKEUP_ON_EDGE_BOTH, /* WDI */
GPIO3_GPIO | WAKEUP_ON_EDGE_BOTH, /* WDI2 */
GPIO82_GPIO | MFP_LPM_DRIVE_HIGH, /* RESET */
GPIO99_GPIO | MFP_LPM_DRIVE_HIGH, /* TC_MM_EN */
/* sound */
GPIO52_SSP3_SCLK,
@ -199,21 +199,21 @@ static unsigned long gen1_pin_config[] __initdata = {
defined(CONFIG_MACH_EZX_E2) || defined(CONFIG_MACH_EZX_E6)
static unsigned long gen2_pin_config[] __initdata = {
/* flip / lockswitch */
GPIO15_GPIO,
GPIO15_GPIO | WAKEUP_ON_EDGE_BOTH,
/* EOC */
GPIO10_GPIO,
GPIO10_GPIO | WAKEUP_ON_EDGE_RISE,
/* bluetooth (bcm2045) */
GPIO13_GPIO | WAKEUP_ON_LEVEL_HIGH, /* HOSTWAKE */
GPIO13_GPIO | WAKEUP_ON_EDGE_RISE, /* HOSTWAKE */
GPIO37_GPIO, /* RESET */
GPIO57_GPIO, /* WAKEUP */
/* Neptune handshake */
GPIO0_GPIO | WAKEUP_ON_LEVEL_HIGH, /* BP_RDY */
GPIO96_GPIO, /* AP_RDY */
GPIO3_GPIO | WAKEUP_ON_LEVEL_HIGH, /* WDI */
GPIO116_GPIO, /* RESET */
GPIO0_GPIO | WAKEUP_ON_EDGE_FALL, /* BP_RDY */
GPIO96_GPIO | MFP_LPM_DRIVE_HIGH, /* AP_RDY */
GPIO3_GPIO | WAKEUP_ON_EDGE_FALL, /* WDI */
GPIO116_GPIO | MFP_LPM_DRIVE_HIGH, /* RESET */
GPIO41_GPIO, /* BP_FLASH */
/* sound */

2
arch/arm/mach-pxa/imote2.c
View File

@ -412,7 +412,7 @@ static struct platform_device imote2_flash_device = {
*/
static struct i2c_board_info __initdata imote2_i2c_board_info[] = {
{ /* UCAM sensor board */
.type = "max1238",
.type = "max1239",
.addr = 0x35,
}, { /* ITS400 Sensor board only */
.type = "max1363",

5
arch/arm/mach-pxa/include/mach/reset.h
View File

@ -13,8 +13,9 @@ extern void clear_reset_status(unsigned int mask);
/**
* init_gpio_reset() - register GPIO as reset generator
* @gpio: gpio nr
* @output: set gpio as out/low instead of input during normal work
* @output: set gpio as output instead of input during normal work
* @level: output level
*/
extern int init_gpio_reset(int gpio, int output);
extern int init_gpio_reset(int gpio, int output, int level);
#endif /* __ASM_ARCH_RESET_H */

6
arch/arm/mach-pxa/mfp-pxa2xx.c
View File

@ -322,6 +322,7 @@ static inline void pxa27x_mfp_init(void) {}
#ifdef CONFIG_PM
static unsigned long saved_gafr[2][4];
static unsigned long saved_gpdr[4];
static unsigned long saved_pgsr[4];
static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state)
{
@ -332,6 +333,7 @@ static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state)
saved_gafr[0][i] = GAFR_L(i);
saved_gafr[1][i] = GAFR_U(i);
saved_gpdr[i] = GPDR(i * 32);
saved_pgsr[i] = PGSR(i);
GPDR(i * 32) = gpdr_lpm[i];
}
@ -346,6 +348,7 @@ static int pxa2xx_mfp_resume(struct sys_device *d)
GAFR_L(i) = saved_gafr[0][i];
GAFR_U(i) = saved_gafr[1][i];
GPDR(i * 32) = saved_gpdr[i];
PGSR(i) = saved_pgsr[i];
}
PSSR = PSSR_RDH | PSSR_PH;
return 0;
@ -374,6 +377,9 @@ static int __init pxa2xx_mfp_init(void)
if (cpu_is_pxa27x())
pxa27x_mfp_init();
/* clear RDH bit to enable GPIO receivers after reset/sleep exit */
PSSR = PSSR_RDH;
/* initialize gafr_run[], pgsr_lpm[] from existing values */
for (i = 0; i <= gpio_to_bank(pxa_last_gpio); i++)
gpdr_lpm[i] = GPDR(i * 32);

2
arch/arm/mach-pxa/palmld.c
View File

@ -62,6 +62,8 @@ static unsigned long palmld_pin_config[] __initdata = {
GPIO29_AC97_SDATA_IN_0,
GPIO30_AC97_SDATA_OUT,
GPIO31_AC97_SYNC,
GPIO89_AC97_SYSCLK,
GPIO95_AC97_nRESET,
/* IrDA */
GPIO108_GPIO, /* ir disable */

1
arch/arm/mach-pxa/palmt5.c
View File

@ -64,6 +64,7 @@ static unsigned long palmt5_pin_config[] __initdata = {
GPIO29_AC97_SDATA_IN_0,
GPIO30_AC97_SDATA_OUT,
GPIO31_AC97_SYNC,
GPIO89_AC97_SYSCLK,
GPIO95_AC97_nRESET,
/* IrDA */

1
arch/arm/mach-pxa/palmtx.c
View File

@ -65,6 +65,7 @@ static unsigned long palmtx_pin_config[] __initdata = {
GPIO29_AC97_SDATA_IN_0,
GPIO30_AC97_SDATA_OUT,
GPIO31_AC97_SYNC,
GPIO89_AC97_SYSCLK,
GPIO95_AC97_nRESET,
/* IrDA */

4
arch/arm/mach-pxa/reset.c
View File

@ -20,7 +20,7 @@ static void do_hw_reset(void);
static int reset_gpio = -1;
int init_gpio_reset(int gpio, int output)
int init_gpio_reset(int gpio, int output, int level)
{
int rc;
@ -31,7 +31,7 @@ int init_gpio_reset(int gpio, int output)
}
if (output)
rc = gpio_direction_output(gpio, 0);
rc = gpio_direction_output(gpio, level);
else
rc = gpio_direction_input(gpio);
if (rc) {

8
arch/arm/mach-pxa/spitz.c
View File

@ -531,9 +531,15 @@ static int spitz_ohci_init(struct device *dev)
return gpio_direction_output(SPITZ_GPIO_USB_HOST, 1);
}
static void spitz_ohci_exit(struct device *dev)
{
gpio_free(SPITZ_GPIO_USB_HOST);
}
static struct pxaohci_platform_data spitz_ohci_platform_data = {
.port_mode = PMM_NPS_MODE,
.init = spitz_ohci_init,
.exit = spitz_ohci_exit,
.flags = ENABLE_PORT_ALL | NO_OC_PROTECTION,
.power_budget = 150,
};
@ -731,7 +737,7 @@ static void spitz_restart(char mode, const char *cmd)
static void __init common_init(void)
{
init_gpio_reset(SPITZ_GPIO_ON_RESET, 1);
init_gpio_reset(SPITZ_GPIO_ON_RESET, 1, 0);
pm_power_off = spitz_poweroff;
arm_pm_restart = spitz_restart;

2
arch/arm/mach-pxa/tosa.c
View File

@ -897,7 +897,7 @@ static void __init tosa_init(void)
gpio_set_wake(MFP_PIN_GPIO1, 1);
/* We can't pass to gpio-keys since it will drop the Reset altfunc */
init_gpio_reset(TOSA_GPIO_ON_RESET, 0);
init_gpio_reset(TOSA_GPIO_ON_RESET, 0, 0);
pm_power_off = tosa_poweroff;
arm_pm_restart = tosa_restart;

36
arch/arm/mm/proc-v7.S
View File

@ -184,23 +184,37 @@ __v7_setup:
stmia r12, {r0-r5, r7, r9, r11, lr}
bl v7_flush_dcache_all
ldmia r12, {r0-r5, r7, r9, r11, lr}
mrc p15, 0, r0, c0, c0, 0 @ read main ID register
and r10, r0, #0xff000000 @ ARM?
teq r10, #0x41000000
bne 2f
and r5, r0, #0x00f00000 @ variant
and r6, r0, #0x0000000f @ revision
orr r0, r6, r5, lsr #20-4 @ combine variant and revision
#ifdef CONFIG_ARM_ERRATA_430973
mrc p15, 0, r10, c1, c0, 1 @ read aux control register
orr r10, r10, #(1 << 6) @ set IBE to 1
mcr p15, 0, r10, c1, c0, 1 @ write aux control register
teq r5, #0x00100000 @ only present in r1p*
mrceq p15, 0, r10, c1, c0, 1 @ read aux control register
orreq r10, r10, #(1 << 6) @ set IBE to 1
mcreq p15, 0, r10, c1, c0, 1 @ write aux control register
#endif
#ifdef CONFIG_ARM_ERRATA_458693
mrc p15, 0, r10, c1, c0, 1 @ read aux control register
orr r10, r10, #(1 << 5) @ set L1NEON to 1
orr r10, r10, #(1 << 9) @ set PLDNOP to 1
mcr p15, 0, r10, c1, c0, 1 @ write aux control register
teq r0, #0x20 @ only present in r2p0
mrceq p15, 0, r10, c1, c0, 1 @ read aux control register
orreq r10, r10, #(1 << 5) @ set L1NEON to 1
orreq r10, r10, #(1 << 9) @ set PLDNOP to 1
mcreq p15, 0, r10, c1, c0, 1 @ write aux control register
#endif
#ifdef CONFIG_ARM_ERRATA_460075
mrc p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register
orr r10, r10, #(1 << 22) @ set the Write Allocate disable bit
mcr p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register
teq r0, #0x20 @ only present in r2p0
mrceq p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register
tsteq r10, #1 << 22
orreq r10, r10, #(1 << 22) @ set the Write Allocate disable bit
mcreq p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register
#endif
mov r10, #0
2: mov r10, #0
#ifdef HARVARD_CACHE
mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate
#endif

5
arch/arm/plat-mxc/include/mach/imx-uart.h
View File

@ -20,11 +20,16 @@
#define ASMARM_ARCH_UART_H
#define IMXUART_HAVE_RTSCTS (1<<0)
#define IMXUART_IRDA (1<<1)
struct imxuart_platform_data {
int (*init)(struct platform_device *pdev);
int (*exit)(struct platform_device *pdev);
unsigned int flags;
void (*irda_enable)(int enable);
unsigned int irda_inv_rx:1;
unsigned int irda_inv_tx:1;
unsigned short transceiver_delay;
};
#endif

63
arch/arm/plat-omap/mailbox.c
View File

@ -147,24 +147,40 @@ static int __mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void *arg)
return ret;
}
struct omap_msg_tx_data {
mbox_msg_t msg;
void *arg;
};
static void omap_msg_tx_end_io(struct request *rq, int error)
{
kfree(rq->special);
__blk_put_request(rq->q, rq);
}
int omap_mbox_msg_send(struct omap_mbox *mbox, mbox_msg_t msg, void* arg)
{
struct omap_msg_tx_data *tx_data;
struct request *rq;
struct request_queue *q = mbox->txq->queue;
int ret = 0;
tx_data = kmalloc(sizeof(*tx_data), GFP_ATOMIC);
if (unlikely(!tx_data))
return -ENOMEM;
rq = blk_get_request(q, WRITE, GFP_ATOMIC);
if (unlikely(!rq)) {
ret = -ENOMEM;
goto fail;
kfree(tx_data);
return -ENOMEM;
}
rq->data = (void *)msg;
blk_insert_request(q, rq, 0, arg);
tx_data->msg = msg;
tx_data->arg = arg;
rq->end_io = omap_msg_tx_end_io;
blk_insert_request(q, rq, 0, tx_data);
schedule_work(&mbox->txq->work);
fail:
return ret;
return 0;
}
EXPORT_SYMBOL(omap_mbox_msg_send);
@ -178,22 +194,28 @@ static void mbox_tx_work(struct work_struct *work)
struct request_queue *q = mbox->txq->queue;
while (1) {
struct omap_msg_tx_data *tx_data;
spin_lock(q->queue_lock);
rq = elv_next_request(q);
rq = blk_fetch_request(q);
spin_unlock(q->queue_lock);
if (!rq)
break;
ret = __mbox_msg_send(mbox, (mbox_msg_t) rq->data, rq->special);
tx_data = rq->special;
ret = __mbox_msg_send(mbox, tx_data->msg, tx_data->arg);
if (ret) {
enable_mbox_irq(mbox, IRQ_TX);
spin_lock(q->queue_lock);
blk_requeue_request(q, rq);
spin_unlock(q->queue_lock);
return;
}
spin_lock(q->queue_lock);
if (__blk_end_request(rq, 0, 0))
BUG();
__blk_end_request_all(rq, 0);
spin_unlock(q->queue_lock);
}
}
@ -218,16 +240,13 @@ static void mbox_rx_work(struct work_struct *work)
while (1) {
spin_lock_irqsave(q->queue_lock, flags);
rq = elv_next_request(q);
rq = blk_fetch_request(q);
spin_unlock_irqrestore(q->queue_lock, flags);
if (!rq)
break;
msg = (mbox_msg_t) rq->data;
if (blk_end_request(rq, 0, 0))
BUG();
msg = (mbox_msg_t)rq->special;
blk_end_request_all(rq, 0);
mbox->rxq->callback((void *)msg);
}
}
@ -264,7 +283,6 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
goto nomem;
msg = mbox_fifo_read(mbox);
rq->data = (void *)msg;
if (unlikely(mbox_seq_test(mbox, msg))) {
pr_info("mbox: Illegal seq bit!(%08x)\n", msg);
@ -272,7 +290,7 @@ static void __mbox_rx_interrupt(struct omap_mbox *mbox)
mbox->err_notify();
}
blk_insert_request(q, rq, 0, NULL);
blk_insert_request(q, rq, 0, (void *)msg);
if (mbox->ops->type == OMAP_MBOX_TYPE1)
break;
}
@ -329,16 +347,15 @@ omap_mbox_read(struct device *dev, struct device_attribute *attr, char *buf)
while (1) {
spin_lock_irqsave(q->queue_lock, flags);
rq = elv_next_request(q);
rq = blk_fetch_request(q);
spin_unlock_irqrestore(q->queue_lock, flags);
if (!rq)
break;
*p = (mbox_msg_t) rq->data;
*p = (mbox_msg_t)rq->special;
if (blk_end_request(rq, 0, 0))
BUG();
blk_end_request_all(rq, 0);
if (unlikely(mbox_seq_test(mbox, *p))) {
pr_info("mbox: Illegal seq bit!(%08x) ignored\n", *p);

131
arch/arm/tools/mach-types
View File

@ -12,7 +12,7 @@
#
# http://www.arm.linux.org.uk/developer/machines/?action=new
#
# Last update: Mon Mar 23 20:09:01 2009
# Last update: Fri May 29 10:14:20 2009
#
# machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number
#
@ -916,7 +916,7 @@ nxdb500 MACH_NXDB500 NXDB500 905
apf9328 MACH_APF9328 APF9328 906
omap_wipoq MACH_OMAP_WIPOQ OMAP_WIPOQ 907
omap_twip MACH_OMAP_TWIP OMAP_TWIP 908
palmt650 MACH_PALMT650 PALMT650 909
treo650 MACH_TREO650 TREO650 909
acumen MACH_ACUMEN ACUMEN 910
xp100 MACH_XP100 XP100 911
fs2410 MACH_FS2410 FS2410 912
@ -1232,7 +1232,7 @@ ql202b MACH_QL202B QL202B 1226
vpac270 MACH_VPAC270 VPAC270 1227
rd129 MACH_RD129 RD129 1228
htcwizard MACH_HTCWIZARD HTCWIZARD 1229
xscale_treo680 MACH_XSCALE_TREO680 XSCALE_TREO680 1230
treo680 MACH_TREO680 TREO680 1230
tecon_tmezon MACH_TECON_TMEZON TECON_TMEZON 1231
zylonite MACH_ZYLONITE ZYLONITE 1233
gene1270 MACH_GENE1270 GENE1270 1234
@ -1418,10 +1418,10 @@ looxc550 MACH_LOOXC550 LOOXC550 1417
cnty_titan MACH_CNTY_TITAN CNTY_TITAN 1418
app3xx MACH_APP3XX APP3XX 1419
sideoatsgrama MACH_SIDEOATSGRAMA SIDEOATSGRAMA 1420
palmtreo700p MACH_PALMTREO700P PALMTREO700P 1421
palmtreo700w MACH_PALMTREO700W PALMTREO700W 1422
palmtreo750 MACH_PALMTREO750 PALMTREO750 1423
palmtreo755p MACH_PALMTREO755P PALMTREO755P 1424
treo700p MACH_TREO700P TREO700P 1421
treo700w MACH_TREO700W TREO700W 1422
treo750 MACH_TREO750 TREO750 1423
treo755p MACH_TREO755P TREO755P 1424
ezreganut9200 MACH_EZREGANUT9200 EZREGANUT9200 1425
sarge MACH_SARGE SARGE 1426
a696 MACH_A696 A696 1427
@ -1721,7 +1721,7 @@ sapphire MACH_SAPPHIRE SAPPHIRE 1729
csb637xo MACH_CSB637XO CSB637XO 1730
evisiong MACH_EVISIONG EVISIONG 1731
stmp37xx MACH_STMP37XX STMP37XX 1732
stmp378x MACH_STMP38XX STMP38XX 1733
stmp378x MACH_STMP378X STMP378X 1733
tnt MACH_TNT TNT 1734
tbxt MACH_TBXT TBXT 1735
playmate MACH_PLAYMATE PLAYMATE 1736
@ -1817,7 +1817,7 @@ smdkc100 MACH_SMDKC100 SMDKC100 1826
tavorevb MACH_TAVOREVB TAVOREVB 1827
saar MACH_SAAR SAAR 1828
deister_eyecam MACH_DEISTER_EYECAM DEISTER_EYECAM 1829
at91sam9m10ek MACH_AT91SAM9M10EK AT91SAM9M10EK 1830
at91sam9m10g45ek MACH_AT91SAM9M10G45EK AT91SAM9M10G45EK 1830
linkstation_produo MACH_LINKSTATION_PRODUO LINKSTATION_PRODUO 1831
hit_b0 MACH_HIT_B0 HIT_B0 1832
adx_rmu MACH_ADX_RMU ADX_RMU 1833
@ -2132,3 +2132,116 @@ apollo MACH_APOLLO APOLLO 2141
at91cap9stk MACH_AT91CAP9STK AT91CAP9STK 2142
spc300 MACH_SPC300 SPC300 2143
eko MACH_EKO EKO 2144
ccw9m2443 MACH_CCW9M2443 CCW9M2443 2145
ccw9m2443js MACH_CCW9M2443JS CCW9M2443JS 2146
m2m_router_device MACH_M2M_ROUTER_DEVICE M2M_ROUTER_DEVICE 2147
str9104nas MACH_STAR9104NAS STAR9104NAS 2148
pca100 MACH_PCA100 PCA100 2149
z3_dm365_mod_01 MACH_Z3_DM365_MOD_01 Z3_DM365_MOD_01 2150
hipox MACH_HIPOX HIPOX 2151
omap3_piteds MACH_OMAP3_PITEDS OMAP3_PITEDS 2152
bm150r MACH_BM150R BM150R 2153
tbone MACH_TBONE TBONE 2154
merlin MACH_MERLIN MERLIN 2155
falcon MACH_FALCON FALCON 2156
davinci_da850_evm MACH_DAVINCI_DA850_EVM DAVINCI_DA850_EVM 2157
s5p6440 MACH_S5P6440 S5P6440 2158
at91sam9g10ek MACH_AT91SAM9G10EK AT91SAM9G10EK 2159
omap_4430sdp MACH_OMAP_4430SDP OMAP_4430SDP 2160
lpc313x MACH_LPC313X LPC313X 2161
magx_zn5 MACH_MAGX_ZN5 MAGX_ZN5 2162
magx_em30 MACH_MAGX_EM30 MAGX_EM30 2163
magx_ve66 MACH_MAGX_VE66 MAGX_VE66 2164
meesc MACH_MEESC MEESC 2165
otc570 MACH_OTC570 OTC570 2166
bcu2412 MACH_BCU2412 BCU2412 2167
beacon MACH_BEACON BEACON 2168
actia_tgw MACH_ACTIA_TGW ACTIA_TGW 2169
e4430 MACH_E4430 E4430 2170
ql300 MACH_QL300 QL300 2171
btmavb101 MACH_BTMAVB101 BTMAVB101 2172
btmawb101 MACH_BTMAWB101 BTMAWB101 2173
sq201 MACH_SQ201 SQ201 2174
quatro45xx MACH_QUATRO45XX QUATRO45XX 2175
openpad MACH_OPENPAD OPENPAD 2176
tx25 MACH_TX25 TX25 2177
omap3_torpedo MACH_OMAP3_TORPEDO OMAP3_TORPEDO 2178
htcraphael_k MACH_HTCRAPHAEL_K HTCRAPHAEL_K 2179
lal43 MACH_LAL43 LAL43 2181
htcraphael_cdma500 MACH_HTCRAPHAEL_CDMA500 HTCRAPHAEL_CDMA500 2182
anw6410 MACH_ANW6410 ANW6410 2183
htcprophet MACH_HTCPROPHET HTCPROPHET 2185
cfa_10022 MACH_CFA_10022 CFA_10022 2186
imx27_visstrim_m10 MACH_IMX27_VISSTRIM_M10 IMX27_VISSTRIM_M10 2187
px2imx27 MACH_PX2IMX27 PX2IMX27 2188
stm3210e_eval MACH_STM3210E_EVAL STM3210E_EVAL 2189
dvs10 MACH_DVS10 DVS10 2190
portuxg20 MACH_PORTUXG20 PORTUXG20 2191
arm_spv MACH_ARM_SPV ARM_SPV 2192
smdkc110 MACH_SMDKC110 SMDKC110 2193
cabespresso MACH_CABESPRESSO CABESPRESSO 2194
hmc800 MACH_HMC800 HMC800 2195
sholes MACH_SHOLES SHOLES 2196
btmxc31 MACH_BTMXC31 BTMXC31 2197
dt501 MACH_DT501 DT501 2198
ktx MACH_KTX KTX 2199
omap3517evm MACH_OMAP3517EVM OMAP3517EVM 2200
netspace_v2 MACH_NETSPACE_V2 NETSPACE_V2 2201
netspace_max_v2 MACH_NETSPACE_MAX_V2 NETSPACE_MAX_V2 2202
d2net_v2 MACH_D2NET_V2 D2NET_V2 2203
net2big_v2 MACH_NET2BIG_V2 NET2BIG_V2 2204
net4big_v2 MACH_NET4BIG_V2 NET4BIG_V2 2205
net5big_v2 MACH_NET5BIG_V2 NET5BIG_V2 2206
endb2443 MACH_ENDB2443 ENDB2443 2207
inetspace_v2 MACH_INETSPACE_V2 INETSPACE_V2 2208
tros MACH_TROS TROS 2209
pelco_homer MACH_PELCO_HOMER PELCO_HOMER 2210
ofsp8 MACH_OFSP8 OFSP8 2211
at91sam9g45ekes MACH_AT91SAM9G45EKES AT91SAM9G45EKES 2212
guf_cupid MACH_GUF_CUPID GUF_CUPID 2213
eab1r MACH_EAB1R EAB1R 2214
desirec MACH_DESIREC DESIREC 2215
cordoba MACH_CORDOBA CORDOBA 2216
irvine MACH_IRVINE IRVINE 2217
sff772 MACH_SFF772 SFF772 2218
pelco_milano MACH_PELCO_MILANO PELCO_MILANO 2219
pc7302 MACH_PC7302 PC7302 2220
bip6000 MACH_BIP6000 BIP6000 2221
silvermoon MACH_SILVERMOON SILVERMOON 2222
vc0830 MACH_VC0830 VC0830 2223
dt430 MACH_DT430 DT430 2224
ji42pf MACH_JI42PF JI42PF 2225
gnet_ksm MACH_GNET_KSM GNET_KSM 2226
gnet_sgm MACH_GNET_SGM GNET_SGM 2227
gnet_sgr MACH_GNET_SGR GNET_SGR 2228
omap3_icetekevm MACH_OMAP3_ICETEKEVM OMAP3_ICETEKEVM 2229
pnp MACH_PNP PNP 2230
ctera_2bay_k MACH_CTERA_2BAY_K CTERA_2BAY_K 2231
ctera_2bay_u MACH_CTERA_2BAY_U CTERA_2BAY_U 2232
sas_c MACH_SAS_C SAS_C 2233
vma2315 MACH_VMA2315 VMA2315 2234
vcs MACH_VCS VCS 2235
spear600 MACH_SPEAR600 SPEAR600 2236
spear300 MACH_SPEAR300 SPEAR300 2237
spear1300 MACH_SPEAR1300 SPEAR1300 2238
lilly1131 MACH_LILLY1131 LILLY1131 2239
arvoo_ax301 MACH_ARVOO_AX301 ARVOO_AX301 2240
mapphone MACH_MAPPHONE MAPPHONE 2241
legend MACH_LEGEND LEGEND 2242
salsa MACH_SALSA SALSA 2243
lounge MACH_LOUNGE LOUNGE 2244
vision MACH_VISION VISION 2245
vmb20 MACH_VMB20 VMB20 2246
hy2410 MACH_HY2410 HY2410 2247
hy9315 MACH_HY9315 HY9315 2248
bullwinkle MACH_BULLWINKLE BULLWINKLE 2249
arm_ultimator2 MACH_ARM_ULTIMATOR2 ARM_ULTIMATOR2 2250
vs_v210 MACH_VS_V210 VS_V210 2252
vs_v212 MACH_VS_V212 VS_V212 2253
hmt MACH_HMT HMT 2254
suen3 MACH_SUEN3 SUEN3 2255
vesper MACH_VESPER VESPER 2256
str9 MACH_STR9 STR9 2257
omap3_wl_ff MACH_OMAP3_WL_FF OMAP3_WL_FF 2258
simcom MACH_SIMCOM SIMCOM 2259
mcwebio MACH_MCWEBIO MCWEBIO 2260

1
arch/blackfin/include/asm/flat.h
View File

@ -10,7 +10,6 @@
#include <asm/unaligned.h>
#define flat_stack_align(sp) /* nothing needed */
#define flat_argvp_envp_on_stack() 0
#define flat_old_ram_flag(flags) (flags)

4
arch/cris/arch-v32/kernel/irq.c
View File

@ -325,12 +325,14 @@ static void end_crisv32_irq(unsigned int irq)
{
}
void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
int set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
{
unsigned long flags;
spin_lock_irqsave(&irq_lock, flags);
irq_allocations[irq - FIRST_IRQ].mask = *dest;
spin_unlock_irqrestore(&irq_lock, flags);
return 0;
}
static struct irq_chip crisv32_irq_type = {

1
arch/frv/Kconfig
View File

@ -6,6 +6,7 @@ config FRV
bool
default y
select HAVE_IDE
select HAVE_ARCH_TRACEHOOK
config ZONE_DMA
bool

29
arch/frv/include/asm/bitops.h
View File

@ -112,7 +112,7 @@ extern unsigned long atomic_test_and_XOR_mask(unsigned long mask, volatile unsig
#define atomic_clear_mask(mask, v) atomic_test_and_ANDNOT_mask((mask), (v))
#define atomic_set_mask(mask, v) atomic_test_and_OR_mask((mask), (v))
static inline int test_and_clear_bit(int nr, volatile void *addr)
static inline int test_and_clear_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *ptr = addr;
unsigned long mask = 1UL << (nr & 31);
@ -120,7 +120,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
return (atomic_test_and_ANDNOT_mask(mask, ptr) & mask) != 0;
}
static inline int test_and_set_bit(int nr, volatile void *addr)
static inline int test_and_set_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *ptr = addr;
unsigned long mask = 1UL << (nr & 31);
@ -128,7 +128,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
return (atomic_test_and_OR_mask(mask, ptr) & mask) != 0;
}
static inline int test_and_change_bit(int nr, volatile void *addr)
static inline int test_and_change_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *ptr = addr;
unsigned long mask = 1UL << (nr & 31);
@ -136,22 +136,22 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
return (atomic_test_and_XOR_mask(mask, ptr) & mask) != 0;
}
static inline void clear_bit(int nr, volatile void *addr)
static inline void clear_bit(unsigned long nr, volatile void *addr)
{
test_and_clear_bit(nr, addr);
}
static inline void set_bit(int nr, volatile void *addr)
static inline void set_bit(unsigned long nr, volatile void *addr)
{
test_and_set_bit(nr, addr);
}
static inline void change_bit(int nr, volatile void * addr)
static inline void change_bit(unsigned long nr, volatile void *addr)
{
test_and_change_bit(nr, addr);
}
static inline void __clear_bit(int nr, volatile void * addr)
static inline void __clear_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask;
@ -161,7 +161,7 @@ static inline void __clear_bit(int nr, volatile void * addr)
*a &= ~mask;
}
static inline void __set_bit(int nr, volatile void * addr)
static inline void __set_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask;
@ -171,7 +171,7 @@ static inline void __set_bit(int nr, volatile void * addr)
*a |= mask;
}
static inline void __change_bit(int nr, volatile void *addr)
static inline void __change_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask;
@ -181,7 +181,7 @@ static inline void __change_bit(int nr, volatile void *addr)
*a ^= mask;
}
static inline int __test_and_clear_bit(int nr, volatile void * addr)
static inline int __test_and_clear_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask, retval;
@ -193,7 +193,7 @@ static inline int __test_and_clear_bit(int nr, volatile void * addr)
return retval;
}
static inline int __test_and_set_bit(int nr, volatile void * addr)
static inline int __test_and_set_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask, retval;
@ -205,7 +205,7 @@ static inline int __test_and_set_bit(int nr, volatile void * addr)
return retval;
}
static inline int __test_and_change_bit(int nr, volatile void * addr)
static inline int __test_and_change_bit(unsigned long nr, volatile void *addr)
{
volatile unsigned long *a = addr;
int mask, retval;
@ -220,12 +220,13 @@ static inline int __test_and_change_bit(int nr, volatile void * addr)
/*
* This routine doesn't need to be atomic.
*/
static inline int __constant_test_bit(int nr, const volatile void * addr)
static inline int
__constant_test_bit(unsigned long nr, const volatile void *addr)
{
return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
}
static inline int __test_bit(int nr, const volatile void * addr)
static inline int __test_bit(unsigned long nr, const volatile void *addr)
{
int * a = (int *) addr;
int mask;

1
arch/frv/include/asm/elf.h
View File

@ -116,6 +116,7 @@ do { \
} while(0)
#define USE_ELF_CORE_DUMP
#define CORE_DUMP_USE_REGSET
#define ELF_FDPIC_CORE_EFLAGS EF_FRV_FDPIC
#define ELF_EXEC_PAGESIZE 16384

7
arch/frv/include/asm/pci.h
View File

@ -87,8 +87,7 @@ static inline void pci_dma_sync_single(struct pci_dev *hwdev,
dma_addr_t dma_handle,
size_t size, int direction)
{
if (direction == PCI_DMA_NONE)
BUG();
BUG_ON(direction == PCI_DMA_NONE);
frv_cache_wback_inv((unsigned long)bus_to_virt(dma_handle),
(unsigned long)bus_to_virt(dma_handle) + size);
@ -105,9 +104,7 @@ static inline void pci_dma_sync_sg(struct pci_dev *hwdev,
int nelems, int direction)
{
int i;
if (direction == PCI_DMA_NONE)
BUG();
BUG_ON(direction == PCI_DMA_NONE);
for (i = 0; i < nelems; i++)
frv_cache_wback_inv(sg_dma_address(&sg[i]),

11
arch/frv/include/asm/ptrace.h
View File

@ -65,6 +65,8 @@
#ifdef __KERNEL__
#ifndef __ASSEMBLY__
struct task_struct;
/*
* we dedicate GR28 to keeping a pointer to the current exception frame
* - gr28 is destroyed on entry to the kernel from userspace
@ -73,11 +75,18 @@ register struct pt_regs *__frame asm("gr28");
#define user_mode(regs) (!((regs)->psr & PSR_S))
#define instruction_pointer(regs) ((regs)->pc)
#define user_stack_pointer(regs) ((regs)->sp)
extern unsigned long user_stack(const struct pt_regs *);
extern void show_regs(struct pt_regs *);
#define profile_pc(regs) ((regs)->pc)
#endif
#define task_pt_regs(task) ((task)->thread.frame0)
#define arch_has_single_step() (1)
extern void user_enable_single_step(struct task_struct *);
extern void user_disable_single_step(struct task_struct *);
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _ASM_PTRACE_H */

123
arch/frv/include/asm/syscall.h Normal file
View File

@ -0,0 +1,123 @@
/* syscall parameter access functions
*
* Copyright (C) 2009 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 Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#ifndef _ASM_SYSCALL_H
#define _ASM_SYSCALL_H
#include <linux/err.h>
#include <asm/ptrace.h>
/*
* Get the system call number or -1
*/
static inline long syscall_get_nr(struct task_struct *task,
struct pt_regs *regs)
{
return regs->syscallno;
}
/*
* Restore the clobbered GR8 register
* (1st syscall arg was overwritten with syscall return or error)
*/
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
regs->gr8 = regs->orig_gr8;
}
/*
* See if the syscall return value is an error, returning it if it is and 0 if
* not
*/
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
return IS_ERR_VALUE(regs->gr8) ? regs->gr8 : 0;
}
/*
* Get the syscall return value
*/
static inline long syscall_get_return_value(struct task_struct *task,
struct pt_regs *regs)
{
return regs->gr8;
}
/*
* Set the syscall return value
*/
static inline void syscall_set_return_value(struct task_struct *task,
struct pt_regs *regs,
int error, long val)
{
if (error)
regs->gr8 = -error;
else
regs->gr8 = val;
}
/*
* Retrieve the system call arguments
*/
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned int i, unsigned int n,
unsigned long *args)
{
/*
* Do this simply for now. If we need to start supporting
* fetching arguments from arbitrary indices, this will need some
* extra logic. Presently there are no in-tree users that depend
* on this behaviour.
*/
BUG_ON(i);
/* Argument pattern is: GR8, GR9, GR10, GR11, GR12, GR13 */
switch (n) {
case 6: args[5] = regs->gr13;
case 5: args[4] = regs->gr12;
case 4: args[3] = regs->gr11;
case 3: args[2] = regs->gr10;
case 2: args[1] = regs->gr9;
case 1: args[0] = regs->gr8;
break;
default:
BUG();
}
}
/*
* Alter the system call arguments
*/
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned int i, unsigned int n,
const unsigned long *args)
{
/* Same note as above applies */
BUG_ON(i);
switch (n) {
case 6: regs->gr13 = args[5];
case 5: regs->gr12 = args[4];
case 4: regs->gr11 = args[3];
case 3: regs->gr10 = args[2];
case 2: regs->gr9 = args[1];
case 1: regs->gr8 = args[0];
break;
default:
BUG();
}
}
#endif /* _ASM_SYSCALL_H */

10
arch/frv/include/asm/thread_info.h
View File

@ -109,20 +109,20 @@ register struct thread_info *__current_thread_info asm("gr15");
* - other flags in MSW
*/
#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
#define TIF_SIGPENDING 1 /* signal pending */
#define TIF_NEED_RESCHED 2 /* rescheduling necessary */
#define TIF_SINGLESTEP 3 /* restore singlestep on return to user mode */
#define TIF_IRET 4 /* return with iret */
#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
#define TIF_SIGPENDING 2 /* signal pending */
#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
#define TIF_SINGLESTEP 4 /* restore singlestep on return to user mode */
#define TIF_RESTORE_SIGMASK 5 /* restore signal mask in do_signal() */
#define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling TIF_NEED_RESCHED */
#define TIF_MEMDIE 17 /* OOM killer killed process */
#define TIF_FREEZE 18 /* freezing for suspend */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
#define _TIF_IRET (1 << TIF_IRET)
#define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK)
#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG)
#define _TIF_FREEZE (1 << TIF_FREEZE)

13
arch/frv/kernel/entry.S
View File

@ -886,7 +886,6 @@ system_call:
bnc icc0,#0,__syscall_badsys
ldi @(gr15,#TI_FLAGS),gr4
ori gr4,#_TIF_SYSCALL_TRACE,gr4
andicc gr4,#_TIF_SYSCALL_TRACE,gr0,icc0
bne icc0,#0,__syscall_trace_entry
@ -1150,11 +1149,10 @@ __entry_work_notifysig:
# perform syscall entry tracing
__syscall_trace_entry:
LEDS 0x6320
setlos.p #0,gr8
call do_syscall_trace
call syscall_trace_entry
ldi @(gr28,#REG_SYSCALLNO),gr7
lddi @(gr28,#REG_GR(8)) ,gr8
lddi.p @(gr28,#REG_GR(8)) ,gr8
ori gr8,#0,gr7 ; syscall_trace_entry() returned new syscallno
lddi @(gr28,#REG_GR(10)),gr10
lddi.p @(gr28,#REG_GR(12)),gr12
@ -1169,11 +1167,10 @@ __syscall_exit_work:
beq icc0,#1,__entry_work_pending
movsg psr,gr23
andi gr23,#~PSR_PIL,gr23 ; could let do_syscall_trace() call schedule()
andi gr23,#~PSR_PIL,gr23 ; could let syscall_trace_exit() call schedule()
movgs gr23,psr
setlos.p #1,gr8
call do_syscall_trace
call syscall_trace_exit
bra __entry_resume_userspace
__syscall_badsys:

751
arch/frv/kernel/ptrace.c
View File

@ -19,6 +19,9 @@
#include <linux/user.h>
#include <linux/security.h>
#include <linux/signal.h>
#include <linux/regset.h>
#include <linux/elf.h>
#include <linux/tracehook.h>
#include <asm/uaccess.h>
#include <asm/page.h>
@ -32,6 +35,169 @@
* in exit.c or in signal.c.
*/
/*
* retrieve the contents of FRV userspace general registers
*/
static int genregs_get(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
const struct user_int_regs *iregs = &target->thread.user->i;
int ret;
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
iregs, 0, sizeof(*iregs));
if (ret < 0)
return ret;
return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
sizeof(*iregs), -1);
}
/*
* update the contents of the FRV userspace general registers
*/
static int genregs_set(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
struct user_int_regs *iregs = &target->thread.user->i;
unsigned int offs_gr0, offs_gr1;
int ret;
/* not allowed to set PSR or __status */
if (pos < offsetof(struct user_int_regs, psr) + sizeof(long) &&
pos + count > offsetof(struct user_int_regs, psr))
return -EIO;
if (pos < offsetof(struct user_int_regs, __status) + sizeof(long) &&
pos + count > offsetof(struct user_int_regs, __status))
return -EIO;
/* set the control regs */
offs_gr0 = offsetof(struct user_int_regs, gr[0]);
offs_gr1 = offsetof(struct user_int_regs, gr[1]);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
iregs, 0, offs_gr0);
if (ret < 0)
return ret;
/* skip GR0/TBR */
ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
offs_gr0, offs_gr1);
if (ret < 0)
return ret;
/* set the general regs */
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&iregs->gr[1], offs_gr1, sizeof(*iregs));
if (ret < 0)
return ret;
return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
sizeof(*iregs), -1);
}
/*
* retrieve the contents of FRV userspace FP/Media registers
*/
static int fpmregs_get(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
const struct user_fpmedia_regs *fpregs = &target->thread.user->f;
int ret;
ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
fpregs, 0, sizeof(*fpregs));
if (ret < 0)
return ret;
return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
sizeof(*fpregs), -1);
}
/*
* update the contents of the FRV userspace FP/Media registers
*/
static int fpmregs_set(struct task_struct *target,
const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
struct user_fpmedia_regs *fpregs = &target->thread.user->f;
int ret;
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
fpregs, 0, sizeof(*fpregs));
if (ret < 0)
return ret;
return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
sizeof(*fpregs), -1);
}
/*
* determine if the FP/Media registers have actually been used
*/
static int fpmregs_active(struct task_struct *target,
const struct user_regset *regset)
{
return tsk_used_math(target) ? regset->n : 0;
}
/*
* Define the register sets available on the FRV under Linux
*/
enum frv_regset {
REGSET_GENERAL,
REGSET_FPMEDIA,
};
static const struct user_regset frv_regsets[] = {
/*
* General register format is:
* PSR, ISR, CCR, CCCR, LR, LCR, PC, (STATUS), SYSCALLNO, ORIG_G8
* GNER0-1, IACC0, TBR, GR1-63
*/
[REGSET_GENERAL] = {
.core_note_type = NT_PRSTATUS,
.n = ELF_NGREG,
.size = sizeof(long),
.align = sizeof(long),
.get = genregs_get,
.set = genregs_set,
},
/*
* FPU/Media register format is:
* FR0-63, FNER0-1, MSR0-1, ACC0-7, ACCG0-8, FSR
*/
[REGSET_FPMEDIA] = {
.core_note_type = NT_PRFPREG,
.n = sizeof(struct user_fpmedia_regs) / sizeof(long),
.size = sizeof(long),
.align = sizeof(long),
.get = fpmregs_get,
.set = fpmregs_set,
.active = fpmregs_active,
},
};
static const struct user_regset_view user_frv_native_view = {
.name = "frv",
.e_machine = EM_FRV,
.regsets = frv_regsets,
.n = ARRAY_SIZE(frv_regsets),
};
const struct user_regset_view *task_user_regset_view(struct task_struct *task)
{
return &user_frv_native_view;
}
/*
* Get contents of register REGNO in task TASK.
*/
@ -68,41 +234,24 @@ static inline int put_reg(struct task_struct *task, int regno,
}
}
/*
* check that an address falls within the bounds of the target process's memory
* mappings
*/
static inline int is_user_addr_valid(struct task_struct *child,
unsigned long start, unsigned long len)
{
#ifdef CONFIG_MMU
if (start >= PAGE_OFFSET || len > PAGE_OFFSET - start)
return -EIO;
return 0;
#else
struct vm_area_struct *vma;
vma = find_vma(child->mm, start);
if (vma && start >= vma->vm_start && start + len <= vma->vm_end)
return 0;
return -EIO;
#endif
}
/*
* Called by kernel/ptrace.c when detaching..
*
* Control h/w single stepping
*/
void ptrace_disable(struct task_struct *child)
void user_enable_single_step(struct task_struct *child)
{
child->thread.frame0->__status |= REG__STATUS_STEP;
}
void user_disable_single_step(struct task_struct *child)
{
child->thread.frame0->__status &= ~REG__STATUS_STEP;
}
void ptrace_enable(struct task_struct *child)
void ptrace_disable(struct task_struct *child)
{
child->thread.frame0->__status |= REG__STATUS_STEP;
user_disable_single_step(child);
}
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
@ -111,15 +260,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
int ret;
switch (request) {
/* when I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA:
ret = -EIO;
if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
break;
ret = generic_ptrace_peekdata(child, addr, data);
break;
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
tmp = 0;
@ -163,15 +303,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
break;
}
/* when I and D space are separate, this will have to be fixed. */
case PTRACE_POKETEXT: /* write the word at location addr. */
case PTRACE_POKEDATA:
ret = -EIO;
if (is_user_addr_valid(child, addr, sizeof(tmp)) < 0)
break;
ret = generic_ptrace_pokedata(child, addr, data);
break;
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
if ((addr & 3) || addr < 0)
@ -179,7 +310,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
ret = 0;
switch (addr >> 2) {
case 0 ... PT__END-1:
case 0 ... PT__END - 1:
ret = put_reg(child, addr >> 2, data);
break;
@ -189,95 +320,29 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
}
break;
case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
case PTRACE_CONT: /* restart after signal. */
ret = -EIO;
if (!valid_signal(data))
break;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
child->exit_code = data;
ptrace_disable(child);
wake_up_process(child);
ret = 0;
break;
case PTRACE_GETREGS: /* Get all integer regs from the child. */
return copy_regset_to_user(child, &user_frv_native_view,
REGSET_GENERAL,
0, sizeof(child->thread.user->i),
(void __user *)data);
/* make the child exit. Best I can do is send it a sigkill.
* perhaps it should be put in the status that it wants to
* exit.
*/
case PTRACE_KILL:
ret = 0;
if (child->exit_state == EXIT_ZOMBIE) /* already dead */
break;
child->exit_code = SIGKILL;
clear_tsk_thread_flag(child, TIF_SINGLESTEP);
ptrace_disable(child);
wake_up_process(child);
break;
case PTRACE_SETREGS: /* Set all integer regs in the child. */
return copy_regset_from_user(child, &user_frv_native_view,
REGSET_GENERAL,
0, sizeof(child->thread.user->i),
(const void __user *)data);
case PTRACE_SINGLESTEP: /* set the trap flag. */
ret = -EIO;
if (!valid_signal(data))
break;
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
ptrace_enable(child);
child->exit_code = data;
wake_up_process(child);
ret = 0;
break;
case PTRACE_GETFPREGS: /* Get the child FP/Media state. */
return copy_regset_to_user(child, &user_frv_native_view,
REGSET_FPMEDIA,
0, sizeof(child->thread.user->f),
(void __user *)data);
case PTRACE_DETACH: /* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
case PTRACE_GETREGS: { /* Get all integer regs from the child. */
int i;
for (i = 0; i < PT__GPEND; i++) {
tmp = get_reg(child, i);
if (put_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
data += sizeof(long);
}
ret = 0;
break;
}
case PTRACE_SETREGS: { /* Set all integer regs in the child. */
int i;
for (i = 0; i < PT__GPEND; i++) {
if (get_user(tmp, (unsigned long *) data)) {
ret = -EFAULT;
break;
}
put_reg(child, i, tmp);
data += sizeof(long);
}
ret = 0;
break;
}
case PTRACE_GETFPREGS: { /* Get the child FP/Media state. */
ret = 0;
if (copy_to_user((void *) data,
&child->thread.user->f,
sizeof(child->thread.user->f)))
ret = -EFAULT;
break;
}
case PTRACE_SETFPREGS: { /* Set the child FP/Media state. */
ret = 0;
if (copy_from_user(&child->thread.user->f,
(void *) data,
sizeof(child->thread.user->f)))
ret = -EFAULT;
break;
}
case PTRACE_SETFPREGS: /* Set the child FP/Media state. */
return copy_regset_from_user(child, &user_frv_native_view,
REGSET_FPMEDIA,
0, sizeof(child->thread.user->f),
(const void __user *)data);
case PTRACE_GETFDPIC:
tmp = 0;
@ -300,414 +365,36 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
break;
default:
ret = -EIO;
ret = ptrace_request(child, request, addr, data);
break;
}
return ret;
}
int __nongprelbss kstrace;
static const struct {
const char *name;
unsigned argmask;
} __syscall_name_table[NR_syscalls] = {
[0] = { "restart_syscall" },
[1] = { "exit", 0x000001 },
[2] = { "fork", 0xffffff },
[3] = { "read", 0x000141 },
[4] = { "write", 0x000141 },
[5] = { "open", 0x000235 },
[6] = { "close", 0x000001 },
[7] = { "waitpid", 0x000141 },
[8] = { "creat", 0x000025 },
[9] = { "link", 0x000055 },
[10] = { "unlink", 0x000005 },
[11] = { "execve", 0x000445 },
[12] = { "chdir", 0x000005 },
[13] = { "time", 0x000004 },
[14] = { "mknod", 0x000325 },
[15] = { "chmod", 0x000025 },
[16] = { "lchown", 0x000025 },
[17] = { "break" },
[18] = { "oldstat", 0x000045 },
[19] = { "lseek", 0x000131 },
[20] = { "getpid", 0xffffff },
[21] = { "mount", 0x043555 },
[22] = { "umount", 0x000005 },
[23] = { "setuid", 0x000001 },
[24] = { "getuid", 0xffffff },
[25] = { "stime", 0x000004 },
[26] = { "ptrace", 0x004413 },
[27] = { "alarm", 0x000001 },
[28] = { "oldfstat", 0x000041 },
[29] = { "pause", 0xffffff },
[30] = { "utime", 0x000045 },
[31] = { "stty" },
[32] = { "gtty" },
[33] = { "access", 0x000025 },
[34] = { "nice", 0x000001 },
[35] = { "ftime" },
[36] = { "sync", 0xffffff },
[37] = { "kill", 0x000011 },
[38] = { "rename", 0x000055 },
[39] = { "mkdir", 0x000025 },
[40] = { "rmdir", 0x000005 },
[41] = { "dup", 0x000001 },
[42] = { "pipe", 0x000004 },
[43] = { "times", 0x000004 },
[44] = { "prof" },
[45] = { "brk", 0x000004 },
[46] = { "setgid", 0x000001 },
[47] = { "getgid", 0xffffff },
[48] = { "signal", 0x000041 },
[49] = { "geteuid", 0xffffff },
[50] = { "getegid", 0xffffff },
[51] = { "acct", 0x000005 },
[52] = { "umount2", 0x000035 },
[53] = { "lock" },
[54] = { "ioctl", 0x000331 },
[55] = { "fcntl", 0x000331 },
[56] = { "mpx" },
[57] = { "setpgid", 0x000011 },
[58] = { "ulimit" },
[60] = { "umask", 0x000002 },
[61] = { "chroot", 0x000005 },
[62] = { "ustat", 0x000043 },
[63] = { "dup2", 0x000011 },
[64] = { "getppid", 0xffffff },
[65] = { "getpgrp", 0xffffff },
[66] = { "setsid", 0xffffff },
[67] = { "sigaction" },
[68] = { "sgetmask" },
[69] = { "ssetmask" },
[70] = { "setreuid" },
[71] = { "setregid" },
[72] = { "sigsuspend" },
[73] = { "sigpending" },
[74] = { "sethostname" },
[75] = { "setrlimit" },
[76] = { "getrlimit" },
[77] = { "getrusage" },
[78] = { "gettimeofday" },
[79] = { "settimeofday" },
[80] = { "getgroups" },
[81] = { "setgroups" },
[82] = { "select" },
[83] = { "symlink" },
[84] = { "oldlstat" },
[85] = { "readlink" },
[86] = { "uselib" },
[87] = { "swapon" },
[88] = { "reboot" },
[89] = { "readdir" },
[91] = { "munmap", 0x000034 },
[92] = { "truncate" },
[93] = { "ftruncate" },
[94] = { "fchmod" },
[95] = { "fchown" },
[96] = { "getpriority" },
[97] = { "setpriority" },
[99] = { "statfs" },
[100] = { "fstatfs" },
[102] = { "socketcall" },
[103] = { "syslog" },
[104] = { "setitimer" },
[105] = { "getitimer" },
[106] = { "stat" },
[107] = { "lstat" },
[108] = { "fstat" },
[111] = { "vhangup" },
[114] = { "wait4" },
[115] = { "swapoff" },
[116] = { "sysinfo" },
[117] = { "ipc" },
[118] = { "fsync" },
[119] = { "sigreturn" },
[120] = { "clone" },
[121] = { "setdomainname" },
[122] = { "uname" },
[123] = { "modify_ldt" },
[123] = { "cacheflush" },
[124] = { "adjtimex" },
[125] = { "mprotect" },
[126] = { "sigprocmask" },
[127] = { "create_module" },
[128] = { "init_module" },
[129] = { "delete_module" },
[130] = { "get_kernel_syms" },
[131] = { "quotactl" },
[132] = { "getpgid" },
[133] = { "fchdir" },
[134] = { "bdflush" },
[135] = { "sysfs" },
[136] = { "personality" },
[137] = { "afs_syscall" },
[138] = { "setfsuid" },
[139] = { "setfsgid" },
[140] = { "_llseek", 0x014331 },
[141] = { "getdents" },
[142] = { "_newselect", 0x000141 },
[143] = { "flock" },
[144] = { "msync" },
[145] = { "readv" },
[146] = { "writev" },
[147] = { "getsid", 0x000001 },
[148] = { "fdatasync", 0x000001 },
[149] = { "_sysctl", 0x000004 },
[150] = { "mlock" },
[151] = { "munlock" },
[152] = { "mlockall" },
[153] = { "munlockall" },
[154] = { "sched_setparam" },
[155] = { "sched_getparam" },
[156] = { "sched_setscheduler" },
[157] = { "sched_getscheduler" },
[158] = { "sched_yield" },
[159] = { "sched_get_priority_max" },
[160] = { "sched_get_priority_min" },
[161] = { "sched_rr_get_interval" },
[162] = { "nanosleep", 0x000044 },
[163] = { "mremap" },
[164] = { "setresuid" },
[165] = { "getresuid" },
[166] = { "vm86" },
[167] = { "query_module" },
[168] = { "poll" },
[169] = { "nfsservctl" },
[170] = { "setresgid" },
[171] = { "getresgid" },
[172] = { "prctl", 0x333331 },
[173] = { "rt_sigreturn", 0xffffff },
[174] = { "rt_sigaction", 0x001441 },
[175] = { "rt_sigprocmask", 0x001441 },
[176] = { "rt_sigpending", 0x000014 },
[177] = { "rt_sigtimedwait", 0x001444 },
[178] = { "rt_sigqueueinfo", 0x000411 },
[179] = { "rt_sigsuspend", 0x000014 },
[180] = { "pread", 0x003341 },
[181] = { "pwrite", 0x003341 },
[182] = { "chown", 0x000115 },
[183] = { "getcwd" },
[184] = { "capget" },
[185] = { "capset" },
[186] = { "sigaltstack" },
[187] = { "sendfile" },
[188] = { "getpmsg" },
[189] = { "putpmsg" },
[190] = { "vfork", 0xffffff },
[191] = { "ugetrlimit" },
[192] = { "mmap2", 0x313314 },
[193] = { "truncate64" },
[194] = { "ftruncate64" },
[195] = { "stat64", 0x000045 },
[196] = { "lstat64", 0x000045 },
[197] = { "fstat64", 0x000041 },
[198] = { "lchown32" },
[199] = { "getuid32", 0xffffff },
[200] = { "getgid32", 0xffffff },
[201] = { "geteuid32", 0xffffff },
[202] = { "getegid32", 0xffffff },
[203] = { "setreuid32" },
[204] = { "setregid32" },
[205] = { "getgroups32" },
[206] = { "setgroups32" },
[207] = { "fchown32" },
[208] = { "setresuid32" },
[209] = { "getresuid32" },
[210] = { "setresgid32" },
[211] = { "getresgid32" },
[212] = { "chown32" },
[213] = { "setuid32" },
[214] = { "setgid32" },
[215] = { "setfsuid32" },
[216] = { "setfsgid32" },
[217] = { "pivot_root" },
[218] = { "mincore" },
[219] = { "madvise" },
[220] = { "getdents64" },
[221] = { "fcntl64" },
[223] = { "security" },
[224] = { "gettid" },
[225] = { "readahead" },
[226] = { "setxattr" },
[227] = { "lsetxattr" },
[228] = { "fsetxattr" },
[229] = { "getxattr" },
[230] = { "lgetxattr" },
[231] = { "fgetxattr" },
[232] = { "listxattr" },
[233] = { "llistxattr" },
[234] = { "flistxattr" },
[235] = { "removexattr" },
[236] = { "lremovexattr" },
[237] = { "fremovexattr" },
[238] = { "tkill" },
[239] = { "sendfile64" },
[240] = { "futex" },
[241] = { "sched_setaffinity" },
[242] = { "sched_getaffinity" },
[243] = { "set_thread_area" },
[244] = { "get_thread_area" },
[245] = { "io_setup" },
[246] = { "io_destroy" },
[247] = { "io_getevents" },
[248] = { "io_submit" },
[249] = { "io_cancel" },
[250] = { "fadvise64" },
[252] = { "exit_group", 0x000001 },
[253] = { "lookup_dcookie" },
[254] = { "epoll_create" },
[255] = { "epoll_ctl" },
[256] = { "epoll_wait" },
[257] = { "remap_file_pages" },
[258] = { "set_tid_address" },
[259] = { "timer_create" },
[260] = { "timer_settime" },
[261] = { "timer_gettime" },
[262] = { "timer_getoverrun" },
[263] = { "timer_delete" },
[264] = { "clock_settime" },
[265] = { "clock_gettime" },
[266] = { "clock_getres" },
[267] = { "clock_nanosleep" },
[268] = { "statfs64" },
[269] = { "fstatfs64" },
[270] = { "tgkill" },
[271] = { "utimes" },
[272] = { "fadvise64_64" },
[273] = { "vserver" },
[274] = { "mbind" },
[275] = { "get_mempolicy" },
[276] = { "set_mempolicy" },
[277] = { "mq_open" },
[278] = { "mq_unlink" },
[279] = { "mq_timedsend" },
[280] = { "mq_timedreceive" },
[281] = { "mq_notify" },
[282] = { "mq_getsetattr" },
[283] = { "sys_kexec_load" },
};
asmlinkage void do_syscall_trace(int leaving)
/*
* handle tracing of system call entry
* - return the revised system call number or ULONG_MAX to cause ENOSYS
*/
asmlinkage unsigned long syscall_trace_entry(void)
{
#if 0
unsigned long *argp;
const char *name;
unsigned argmask;
char buffer[16];
if (!kstrace)
return;
if (!current->mm)
return;
if (__frame->gr7 == __NR_close)
return;
#if 0
if (__frame->gr7 != __NR_mmap2 &&
__frame->gr7 != __NR_vfork &&
__frame->gr7 != __NR_execve &&
__frame->gr7 != __NR_exit)
return;
#endif
argmask = 0;
name = NULL;
if (__frame->gr7 < NR_syscalls) {
name = __syscall_name_table[__frame->gr7].name;
argmask = __syscall_name_table[__frame->gr7].argmask;
}
if (!name) {
sprintf(buffer, "sys_%lx", __frame->gr7);
name = buffer;
__frame->__status |= REG__STATUS_SYSC_ENTRY;
if (tracehook_report_syscall_entry(__frame)) {
/* tracing decided this syscall should not happen, so
* We'll return a bogus call number to get an ENOSYS
* error, but leave the original number in
* __frame->syscallno
*/
return ULONG_MAX;
}
if (!leaving) {
if (!argmask) {
printk(KERN_CRIT "[%d] %s(%lx,%lx,%lx,%lx,%lx,%lx)\n",
current->pid,
name,
__frame->gr8,
__frame->gr9,
__frame->gr10,
__frame->gr11,
__frame->gr12,
__frame->gr13);
}
else if (argmask == 0xffffff) {
printk(KERN_CRIT "[%d] %s()\n",
current->pid,
name);
}
else {
printk(KERN_CRIT "[%d] %s(",
current->pid,
name);
argp = &__frame->gr8;
do {
switch (argmask & 0xf) {
case 1:
printk("%ld", (long) *argp);
break;
case 2:
printk("%lo", *argp);
break;
case 3:
printk("%lx", *argp);
break;
case 4:
printk("%p", (void *) *argp);
break;
case 5:
printk("\"%s\"", (char *) *argp);
break;
}
argp++;
argmask >>= 4;
if (argmask)
printk(",");
} while (argmask);
printk(")\n");
}
}
else {
if ((int)__frame->gr8 > -4096 && (int)__frame->gr8 < 4096)
printk(KERN_CRIT "[%d] %s() = %ld\n", current->pid, name, __frame->gr8);
else
printk(KERN_CRIT "[%d] %s() = %lx\n", current->pid, name, __frame->gr8);
}
return;
#endif
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
/* we need to indicate entry or exit to strace */
if (leaving)
__frame->__status |= REG__STATUS_SYSC_EXIT;
else
__frame->__status |= REG__STATUS_SYSC_ENTRY;
ptrace_notify(SIGTRAP);
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
return __frame->syscallno;
}
/*
* handle tracing of system call exit
*/
asmlinkage void syscall_trace_exit(void)
{
__frame->__status |= REG__STATUS_SYSC_EXIT;
tracehook_report_syscall_exit(__frame, 0);
}

10
arch/frv/kernel/signal.c
View File

@ -21,6 +21,7 @@
#include <linux/unistd.h>
#include <linux/personality.h>
#include <linux/freezer.h>
#include <linux/tracehook.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
@ -516,6 +517,9 @@ static void do_signal(void)
* clear the TIF_RESTORE_SIGMASK flag */
if (test_thread_flag(TIF_RESTORE_SIGMASK))
clear_thread_flag(TIF_RESTORE_SIGMASK);
tracehook_signal_handler(signr, &info, &ka, __frame,
test_thread_flag(TIF_SINGLESTEP));
}
return;
@ -564,4 +568,10 @@ asmlinkage void do_notify_resume(__u32 thread_info_flags)
if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK))
do_signal();
/* deal with notification on about to resume userspace execution */
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(__frame);
}
} /* end do_notify_resume() */

6
arch/frv/kernel/uaccess.c
View File

@ -23,8 +23,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
char *p, ch;
long err = -EFAULT;
if (count < 0)
BUG();
BUG_ON(count < 0);
p = dst;
@ -76,8 +75,7 @@ long strnlen_user(const char __user *src, long count)
long err = 0;
char ch;
if (count < 0)
BUG();
BUG_ON(count < 0);
#ifndef CONFIG_MMU
if ((unsigned long) src < memory_start)

6
arch/frv/mb93090-mb00/pci-dma-nommu.c
View File

@ -116,8 +116,7 @@ EXPORT_SYMBOL(dma_free_coherent);
dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
enum dma_data_direction direction)
{
if (direction == DMA_NONE)
BUG();
BUG_ON(direction == DMA_NONE);
frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
@ -151,8 +150,7 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
frv_cache_wback_inv(sg_dma_address(&sg[i]),
sg_dma_address(&sg[i]) + sg_dma_len(&sg[i]));
if (direction == DMA_NONE)
BUG();
BUG_ON(direction == DMA_NONE);
return nents;
}

6
arch/frv/mb93090-mb00/pci-dma.c
View File

@ -48,8 +48,7 @@ EXPORT_SYMBOL(dma_free_coherent);
dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
enum dma_data_direction direction)
{
if (direction == DMA_NONE)
BUG();
BUG_ON(direction == DMA_NONE);
frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
@ -81,8 +80,7 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
void *vaddr;
int i;
if (direction == DMA_NONE)
BUG();
BUG_ON(direction == DMA_NONE);
dampr2 = __get_DAMPR(2);

1
arch/h8300/include/asm/flat.h
View File

@ -5,7 +5,6 @@
#ifndef __H8300_FLAT_H__
#define __H8300_FLAT_H__
#define flat_stack_align(sp) /* nothing needed */
#define flat_argvp_envp_on_stack() 1
#define flat_old_ram_flag(flags) 1
#define flat_reloc_valid(reloc, size) ((reloc) <= (size))

3
arch/ia64/hp/sim/hpsim_irq.c
View File

@ -21,9 +21,10 @@ hpsim_irq_noop (unsigned int irq)
{
}
static void
static int
hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b)
{
return 0;
}
static struct hw_interrupt_type irq_type_hp_sim = {

6
arch/ia64/include/asm/kvm_host.h
View File

@ -371,6 +371,7 @@ struct kvm_vcpu_arch {
int last_run_cpu;
int vmm_tr_slot;
int vm_tr_slot;
int sn_rtc_tr_slot;
#define KVM_MP_STATE_RUNNABLE 0
#define KVM_MP_STATE_UNINITIALIZED 1
@ -465,6 +466,7 @@ struct kvm_arch {
unsigned long vmm_init_rr;
int online_vcpus;
int is_sn2;
struct kvm_ioapic *vioapic;
struct kvm_vm_stat stat;
@ -472,6 +474,7 @@ struct kvm_arch {
struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
int iommu_flags;
struct hlist_head irq_ack_notifier_list;
unsigned long irq_sources_bitmap;
@ -578,6 +581,8 @@ struct kvm_vmm_info{
kvm_vmm_entry *vmm_entry;
kvm_tramp_entry *tramp_entry;
unsigned long vmm_ivt;
unsigned long patch_mov_ar;
unsigned long patch_mov_ar_sn2;
};
int kvm_highest_pending_irq(struct kvm_vcpu *vcpu);
@ -585,7 +590,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu);
int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
void kvm_sal_emul(struct kvm_vcpu *vcpu);
static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {}
#endif /* __ASSEMBLY__*/
#endif

2
arch/ia64/include/asm/pgtable.h
View File

@ -146,6 +146,8 @@
#define PAGE_GATE __pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_X_RX)
#define PAGE_KERNEL __pgprot(__DIRTY_BITS | _PAGE_PL_0 | _PAGE_AR_RWX)
#define PAGE_KERNELRX __pgprot(__ACCESS_BITS | _PAGE_PL_0 | _PAGE_AR_RX)
#define PAGE_KERNEL_UC __pgprot(__DIRTY_BITS | _PAGE_PL_0 | _PAGE_AR_RWX | \
_PAGE_MA_UC)
# ifndef __ASSEMBLY__

5
arch/ia64/kernel/acpi.c
View File

@ -636,7 +636,7 @@ void __init acpi_numa_arch_fixup(void)
* success: return IRQ number (>=0)
* failure: return < 0
*/
int acpi_register_gsi(u32 gsi, int triggering, int polarity)
int acpi_register_gsi(struct device *dev, u32 gsi, int triggering, int polarity)
{
if (acpi_irq_model == ACPI_IRQ_MODEL_PLATFORM)
return gsi;
@ -678,7 +678,8 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
fadt = (struct acpi_table_fadt *)fadt_header;
acpi_register_gsi(fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW);
acpi_register_gsi(NULL, fadt->sci_interrupt, ACPI_LEVEL_SENSITIVE,
ACPI_ACTIVE_LOW);
return 0;
}

10
arch/ia64/kernel/iosapic.c
View File

@ -329,7 +329,7 @@ unmask_irq (unsigned int irq)
}
static void
static int
iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
{
#ifdef CONFIG_SMP
@ -343,15 +343,15 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
cpu = cpumask_first_and(cpu_online_mask, mask);
if (cpu >= nr_cpu_ids)
return;
return -1;
if (irq_prepare_move(irq, cpu))
return;
return -1;
dest = cpu_physical_id(cpu);
if (!iosapic_intr_info[irq].count)
return; /* not an IOSAPIC interrupt */
return -1; /* not an IOSAPIC interrupt */
set_irq_affinity_info(irq, dest, redir);
@ -376,7 +376,9 @@ iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
iosapic_write(iosapic, IOSAPIC_RTE_HIGH(rte_index), high32);
iosapic_write(iosapic, IOSAPIC_RTE_LOW(rte_index), low32);
}
#endif
return 0;
}
/*

3
arch/ia64/kernel/irq_ia64.c
View File

@ -610,6 +610,9 @@ static struct irqaction ipi_irqaction = {
.name = "IPI"
};
/*
* KVM uses this interrupt to force a cpu out of guest mode
*/
static struct irqaction resched_irqaction = {
.handler = dummy_handler,
.flags = IRQF_DISABLED,

16
arch/ia64/kernel/msi_ia64.c
View File

@ -12,7 +12,7 @@
static struct irq_chip ia64_msi_chip;
#ifdef CONFIG_SMP
static void ia64_set_msi_irq_affinity(unsigned int irq,
static int ia64_set_msi_irq_affinity(unsigned int irq,
const cpumask_t *cpu_mask)
{
struct msi_msg msg;
@ -20,10 +20,10 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
int cpu = first_cpu(*cpu_mask);
if (!cpu_online(cpu))
return;
return -1;
if (irq_prepare_move(irq, cpu))
return;
return -1;
read_msi_msg(irq, &msg);
@ -39,6 +39,8 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
write_msi_msg(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
return 0;
}
#endif /* CONFIG_SMP */
@ -130,17 +132,17 @@ void arch_teardown_msi_irq(unsigned int irq)
#ifdef CONFIG_DMAR
#ifdef CONFIG_SMP
static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
{
struct irq_cfg *cfg = irq_cfg + irq;
struct msi_msg msg;
int cpu = cpumask_first(mask);
if (!cpu_online(cpu))
return;
return -1;
if (irq_prepare_move(irq, cpu))
return;
return -1;
dmar_msi_read(irq, &msg);
@ -151,6 +153,8 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
dmar_msi_write(irq, &msg);
cpumask_copy(irq_desc[irq].affinity, mask);
return 0;
}
#endif /* CONFIG_SMP */

2
arch/ia64/kvm/Kconfig
View File

@ -23,7 +23,7 @@ if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM && EXPERIMENTAL
depends on HAVE_KVM && MODULES && EXPERIMENTAL
# for device assignment:
depends on PCI
select PREEMPT_NOTIFIERS

263
arch/ia64/kvm/kvm-ia64.c
View File

@ -41,6 +41,9 @@
#include <asm/div64.h>
#include <asm/tlb.h>
#include <asm/elf.h>
#include <asm/sn/addrs.h>
#include <asm/sn/clksupport.h>
#include <asm/sn/shub_mmr.h>
#include "misc.h"
#include "vti.h"
@ -65,6 +68,16 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ NULL }
};
static unsigned long kvm_get_itc(struct kvm_vcpu *vcpu)
{
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
if (vcpu->kvm->arch.is_sn2)
return rtc_time();
else
#endif
return ia64_getreg(_IA64_REG_AR_ITC);
}
static void kvm_flush_icache(unsigned long start, unsigned long len)
{
int l;
@ -119,8 +132,7 @@ void kvm_arch_hardware_enable(void *garbage)
unsigned long saved_psr;
int slot;
pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
PAGE_KERNEL));
pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL));
local_irq_save(saved_psr);
slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
local_irq_restore(saved_psr);
@ -283,6 +295,18 @@ static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
static int __apic_accept_irq(struct kvm_vcpu *vcpu, uint64_t vector)
{
struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
if (!test_and_set_bit(vector, &vpd->irr[0])) {
vcpu->arch.irq_new_pending = 1;
kvm_vcpu_kick(vcpu);
return 1;
}
return 0;
}
/*
* offset: address offset to IPI space.
* value: deliver value.
@ -292,20 +316,20 @@ static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm,
{
switch (dm) {
case SAPIC_FIXED:
kvm_apic_set_irq(vcpu, vector, 0);
break;
case SAPIC_NMI:
kvm_apic_set_irq(vcpu, 2, 0);
vector = 2;
break;
case SAPIC_EXTINT:
kvm_apic_set_irq(vcpu, 0, 0);
vector = 0;
break;
case SAPIC_INIT:
case SAPIC_PMI:
default:
printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n");
break;
return;
}
__apic_accept_irq(vcpu, vector);
}
static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
@ -413,6 +437,23 @@ static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
static int kvm_sn2_setup_mappings(struct kvm_vcpu *vcpu)
{
unsigned long pte, rtc_phys_addr, map_addr;
int slot;
map_addr = KVM_VMM_BASE + (1UL << KVM_VMM_SHIFT);
rtc_phys_addr = LOCAL_MMR_OFFSET | SH_RTC;
pte = pte_val(mk_pte_phys(rtc_phys_addr, PAGE_KERNEL_UC));
slot = ia64_itr_entry(0x3, map_addr, pte, PAGE_SHIFT);
vcpu->arch.sn_rtc_tr_slot = slot;
if (slot < 0) {
printk(KERN_ERR "Mayday mayday! RTC mapping failed!\n");
slot = 0;
}
return slot;
}
int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
@ -426,7 +467,7 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
if (irqchip_in_kernel(vcpu->kvm)) {
vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
vcpu_now_itc = kvm_get_itc(vcpu) + vcpu->arch.itc_offset;
if (time_after(vcpu_now_itc, vpd->itm)) {
vcpu->arch.timer_check = 1;
@ -447,10 +488,10 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
hrtimer_cancel(p_ht);
vcpu->arch.ht_active = 0;
if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests) ||
kvm_cpu_has_pending_timer(vcpu))
if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
return -EINTR;
@ -551,22 +592,35 @@ static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu)
if (r < 0)
goto out;
vcpu->arch.vm_tr_slot = r;
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
if (kvm->arch.is_sn2) {
r = kvm_sn2_setup_mappings(vcpu);
if (r < 0)
goto out;
}
#endif
r = 0;
out:
return r;
}
static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot);
ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot);
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
if (kvm->arch.is_sn2)
ia64_ptr_entry(0x3, vcpu->arch.sn_rtc_tr_slot);
#endif
}
static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
{
unsigned long psr;
int r;
int cpu = smp_processor_id();
if (vcpu->arch.last_run_cpu != cpu ||
@ -578,36 +632,27 @@ static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
vcpu->arch.host_rr6 = ia64_get_rr(RR6);
vti_set_rr6(vcpu->arch.vmm_rr);
return kvm_insert_vmm_mapping(vcpu);
local_irq_save(psr);
r = kvm_insert_vmm_mapping(vcpu);
local_irq_restore(psr);
return r;
}
static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
{
kvm_purge_vmm_mapping(vcpu);
vti_set_rr6(vcpu->arch.host_rr6);
}
static int vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
union context *host_ctx, *guest_ctx;
int r;
/*Get host and guest context with guest address space.*/
host_ctx = kvm_get_host_context(vcpu);
guest_ctx = kvm_get_guest_context(vcpu);
r = kvm_vcpu_pre_transition(vcpu);
if (r < 0)
goto out;
kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
kvm_vcpu_post_transition(vcpu);
r = 0;
out:
return r;
}
static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
/*
* down_read() may sleep and return with interrupts enabled
*/
down_read(&vcpu->kvm->slots_lock);
again:
if (signal_pending(current)) {
@ -616,26 +661,31 @@ again:
goto out;
}
/*
* down_read() may sleep and return with interrupts enabled
*/
down_read(&vcpu->kvm->slots_lock);
preempt_disable();
local_irq_disable();
vcpu->guest_mode = 1;
/*Get host and guest context with guest address space.*/
host_ctx = kvm_get_host_context(vcpu);
guest_ctx = kvm_get_guest_context(vcpu);
clear_bit(KVM_REQ_KICK, &vcpu->requests);
r = kvm_vcpu_pre_transition(vcpu);
if (r < 0)
goto vcpu_run_fail;
up_read(&vcpu->kvm->slots_lock);
kvm_guest_enter();
r = vti_vcpu_run(vcpu, kvm_run);
if (r < 0) {
local_irq_enable();
preempt_enable();
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
goto out;
}
/*
* Transition to the guest
*/
kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
kvm_vcpu_post_transition(vcpu);
vcpu->arch.launched = 1;
vcpu->guest_mode = 0;
set_bit(KVM_REQ_KICK, &vcpu->requests);
local_irq_enable();
/*
@ -646,9 +696,10 @@ again:
*/
barrier();
kvm_guest_exit();
up_read(&vcpu->kvm->slots_lock);
preempt_enable();
down_read(&vcpu->kvm->slots_lock);
r = kvm_handle_exit(kvm_run, vcpu);
if (r > 0) {
@ -657,12 +708,20 @@ again:
}
out:
up_read(&vcpu->kvm->slots_lock);
if (r > 0) {
kvm_resched(vcpu);
down_read(&vcpu->kvm->slots_lock);
goto again;
}
return r;
vcpu_run_fail:
local_irq_enable();
preempt_enable();
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
goto out;
}
static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
@ -788,6 +847,9 @@ struct kvm *kvm_arch_create_vm(void)
if (IS_ERR(kvm))
return ERR_PTR(-ENOMEM);
kvm->arch.is_sn2 = ia64_platform_is("sn2");
kvm_init_vm(kvm);
kvm->arch.online_vcpus = 0;
@ -884,7 +946,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
RESTORE_REGS(saved_gp);
vcpu->arch.irq_new_pending = 1;
vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC);
vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu);
set_bit(KVM_REQ_RESUME, &vcpu->requests);
vcpu_put(vcpu);
@ -1043,10 +1105,6 @@ static void kvm_free_vmm_area(void)
}
}
static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
}
static int vti_init_vpd(struct kvm_vcpu *vcpu)
{
int i;
@ -1165,7 +1223,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
regs->cr_iip = PALE_RESET_ENTRY;
/*Initialize itc offset for vcpus*/
itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
itc_offset = 0UL - kvm_get_itc(vcpu);
for (i = 0; i < kvm->arch.online_vcpus; i++) {
v = (struct kvm_vcpu *)((char *)vcpu +
sizeof(struct kvm_vcpu_data) * i);
@ -1237,6 +1295,7 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
local_irq_save(psr);
r = kvm_insert_vmm_mapping(vcpu);
local_irq_restore(psr);
if (r)
goto fail;
r = kvm_vcpu_init(vcpu, vcpu->kvm, id);
@ -1254,13 +1313,11 @@ static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
goto uninit;
kvm_purge_vmm_mapping(vcpu);
local_irq_restore(psr);
return 0;
uninit:
kvm_vcpu_uninit(vcpu);
fail:
local_irq_restore(psr);
return r;
}
@ -1291,7 +1348,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->kvm = kvm;
cpu = get_cpu();
vti_vcpu_load(vcpu, cpu);
r = vti_vcpu_setup(vcpu, id);
put_cpu();
@ -1427,7 +1483,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
}
for (i = 0; i < 4; i++)
regs->insvc[i] = vcpu->arch.insvc[i];
regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC);
regs->saved_itc = vcpu->arch.itc_offset + kvm_get_itc(vcpu);
SAVE_REGS(xtp);
SAVE_REGS(metaphysical_rr0);
SAVE_REGS(metaphysical_rr4);
@ -1574,6 +1630,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
void kvm_arch_flush_shadow(struct kvm *kvm)
{
kvm_flush_remote_tlbs(kvm);
}
long kvm_arch_dev_ioctl(struct file *filp,
@ -1616,8 +1673,37 @@ out:
return 0;
}
/*
* On SN2, the ITC isn't stable, so copy in fast path code to use the
* SN2 RTC, replacing the ITC based default verion.
*/
static void kvm_patch_vmm(struct kvm_vmm_info *vmm_info,
struct module *module)
{
unsigned long new_ar, new_ar_sn2;
unsigned long module_base;
if (!ia64_platform_is("sn2"))
return;
module_base = (unsigned long)module->module_core;
new_ar = kvm_vmm_base + vmm_info->patch_mov_ar - module_base;
new_ar_sn2 = kvm_vmm_base + vmm_info->patch_mov_ar_sn2 - module_base;
printk(KERN_INFO "kvm: Patching ITC emulation to use SGI SN2 RTC "
"as source\n");
/*
* Copy the SN2 version of mov_ar into place. They are both
* the same size, so 6 bundles is sufficient (6 * 0x10).
*/
memcpy((void *)new_ar, (void *)new_ar_sn2, 0x60);
}
static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
struct module *module)
struct module *module)
{
unsigned long module_base;
unsigned long vmm_size;
@ -1639,6 +1725,7 @@ static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
return -EFAULT;
memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size);
kvm_patch_vmm(vmm_info, module);
kvm_flush_icache(kvm_vmm_base, vmm_size);
/*Recalculate kvm_vmm_info based on new VMM*/
@ -1792,38 +1879,24 @@ void kvm_arch_hardware_unsetup(void)
{
}
static void vcpu_kick_intr(void *info)
{
#ifdef DEBUG
struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu);
#endif
}
void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
int ipi_pcpu = vcpu->cpu;
int cpu = get_cpu();
int me;
int cpu = vcpu->cpu;
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
if (vcpu->guest_mode && cpu != ipi_pcpu)
smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
me = get_cpu();
if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu))
if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
smp_send_reschedule(cpu);
put_cpu();
}
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
{
struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
if (!test_and_set_bit(vec, &vpd->irr[0])) {
vcpu->arch.irq_new_pending = 1;
kvm_vcpu_kick(vcpu);
return 1;
}
return 0;
return __apic_accept_irq(vcpu, irq->vector);
}
int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
@ -1836,20 +1909,18 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
return 0;
}
struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
unsigned long bitmap)
int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
{
struct kvm_vcpu *lvcpu = kvm->vcpus[0];
int i;
return vcpu1->arch.xtp - vcpu2->arch.xtp;
}
for (i = 1; i < kvm->arch.online_vcpus; i++) {
if (!kvm->vcpus[i])
continue;
if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
lvcpu = kvm->vcpus[i];
}
return lvcpu;
int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, int dest, int dest_mode)
{
struct kvm_lapic *target = vcpu->arch.apic;
return (dest_mode == 0) ?
kvm_apic_match_physical_addr(target, dest) :
kvm_apic_match_logical_addr(target, dest);
}
static int find_highest_bits(int *dat)
@ -1888,6 +1959,12 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
return 0;
}
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
{
/* do real check here */
return 1;
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
return vcpu->arch.timer_fired;
@ -1918,6 +1995,7 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
long psr;
local_irq_save(psr);
r = kvm_insert_vmm_mapping(vcpu);
local_irq_restore(psr);
if (r)
goto fail;
@ -1930,7 +2008,6 @@ static int vcpu_reset(struct kvm_vcpu *vcpu)
kvm_purge_vmm_mapping(vcpu);
r = 0;
fail:
local_irq_restore(psr);
return r;
}

28
arch/ia64/kvm/kvm_fw.c
View File

@ -21,6 +21,9 @@
#include <linux/kvm_host.h>
#include <linux/smp.h>
#include <asm/sn/addrs.h>
#include <asm/sn/clksupport.h>
#include <asm/sn/shub_mmr.h>
#include "vti.h"
#include "misc.h"
@ -188,12 +191,35 @@ static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu)
return result;
}
/*
* On the SGI SN2, the ITC isn't stable. Emulation backed by the SN2
* RTC is used instead. This function patches the ratios from SAL
* to match the RTC before providing them to the guest.
*/
static void sn2_patch_itc_freq_ratios(struct ia64_pal_retval *result)
{
struct pal_freq_ratio *ratio;
unsigned long sal_freq, sal_drift, factor;
result->status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM,
&sal_freq, &sal_drift);
ratio = (struct pal_freq_ratio *)&result->v2;
factor = ((sal_freq * 3) + (sn_rtc_cycles_per_second / 2)) /
sn_rtc_cycles_per_second;
ratio->num = 3;
ratio->den = factor;
}
static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
{
struct ia64_pal_retval result;
PAL_CALL(result, PAL_FREQ_RATIOS, 0, 0, 0);
if (vcpu->kvm->arch.is_sn2)
sn2_patch_itc_freq_ratios(&result);
return result;
}

6
arch/ia64/kvm/lapic.h
View File

@ -20,6 +20,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu);
int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, int dest, int dest_mode);
int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
#define kvm_apic_present(x) (true)
#endif

30
arch/ia64/kvm/optvfault.S
View File

@ -11,6 +11,7 @@
#include <asm/asmmacro.h>
#include <asm/processor.h>
#include <asm/kvm_host.h>
#include "vti.h"
#include "asm-offsets.h"
@ -140,6 +141,35 @@ GLOBAL_ENTRY(kvm_asm_mov_from_ar)
;;
END(kvm_asm_mov_from_ar)
/*
* Special SGI SN2 optimized version of mov_from_ar using the SN2 RTC
* clock as it's source for emulating the ITC. This version will be
* copied on top of the original version if the host is determined to
* be an SN2.
*/
GLOBAL_ENTRY(kvm_asm_mov_from_ar_sn2)
add r18=VMM_VCPU_ITC_OFS_OFFSET, r21
movl r19 = (KVM_VMM_BASE+(1<<KVM_VMM_SHIFT))
add r16=VMM_VCPU_LAST_ITC_OFFSET,r21
extr.u r17=r25,6,7
mov r24=b0
;;
ld8 r18=[r18]
ld8 r19=[r19]
addl r20=@gprel(asm_mov_to_reg),gp
;;
add r19=r19,r18
shladd r17=r17,4,r20
;;
adds r30=kvm_resume_to_guest-asm_mov_to_reg,r20
st8 [r16] = r19
mov b0=r17
br.sptk.few b0
;;
END(kvm_asm_mov_from_ar_sn2)
// mov r1=rr[r3]
GLOBAL_ENTRY(kvm_asm_mov_from_rr)

5
arch/ia64/kvm/process.c
View File

@ -652,20 +652,25 @@ void kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
unsigned long isr, unsigned long iim)
{
struct kvm_vcpu *v = current_vcpu;
long psr;
if (ia64_psr(regs)->cpl == 0) {
/* Allow hypercalls only when cpl = 0. */
if (iim == DOMN_PAL_REQUEST) {
local_irq_save(psr);
set_pal_call_data(v);
vmm_transition(v);
get_pal_call_result(v);
vcpu_increment_iip(v);
local_irq_restore(psr);
return;
} else if (iim == DOMN_SAL_REQUEST) {
local_irq_save(psr);
set_sal_call_data(v);
vmm_transition(v);
get_sal_call_result(v);
vcpu_increment_iip(v);
local_irq_restore(psr);
return;
}
}

20
arch/ia64/kvm/vcpu.c
View File

@ -788,13 +788,29 @@ void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
setfpreg(reg, val, regs); /* FIXME: handle NATs later*/
}
/*
* The Altix RTC is mapped specially here for the vmm module
*/
#define SN_RTC_BASE (u64 *)(KVM_VMM_BASE+(1UL<<KVM_VMM_SHIFT))
static long kvm_get_itc(struct kvm_vcpu *vcpu)
{
#if defined(CONFIG_IA64_SGI_SN2) || defined(CONFIG_IA64_GENERIC)
struct kvm *kvm = (struct kvm *)KVM_VM_BASE;
if (kvm->arch.is_sn2)
return (*SN_RTC_BASE);
else
#endif
return ia64_getreg(_IA64_REG_AR_ITC);
}
/************************************************************************
* lsapic timer
***********************************************************************/
u64 vcpu_get_itc(struct kvm_vcpu *vcpu)
{
unsigned long guest_itc;
guest_itc = VMX(vcpu, itc_offset) + ia64_getreg(_IA64_REG_AR_ITC);
guest_itc = VMX(vcpu, itc_offset) + kvm_get_itc(vcpu);
if (guest_itc >= VMX(vcpu, last_itc)) {
VMX(vcpu, last_itc) = guest_itc;
@ -809,7 +825,7 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
struct kvm_vcpu *v;
struct kvm *kvm;
int i;
long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC);
long itc_offset = val - kvm_get_itc(vcpu);
unsigned long vitv = VCPU(vcpu, itv);
kvm = (struct kvm *)KVM_VM_BASE;

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