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

Merge branch 'fixes' into for-linus

Browse Source 
Conflicts:

	arch/arm/mach-versatile/core.c
This commit is contained in:
Russell King 2008-10-15 23:16:07 +01:00 committed by Russell King
commit 2502991560
4086 changed files with 266808 additions and 154472 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Documentation/00-INDEX
View File

@ -159,8 +159,6 @@ hayes-esp.txt
- info on using the Hayes ESP serial driver.
highuid.txt
- notes on the change from 16 bit to 32 bit user/group IDs.
hpet.txt
- High Precision Event Timer Driver for Linux.
timers/
- info on the timer related topics
hw_random.txt
@ -251,8 +249,6 @@ mono.txt
- how to execute Mono-based .NET binaries with the help of BINFMT_MISC.
moxa-smartio
- file with info on installing/using Moxa multiport serial driver.
mtrr.txt
- how to use PPro Memory Type Range Registers to increase performance.
mutex-design.txt
- info on the generic mutex subsystem.
namespaces/

2
Documentation/DMA-API.txt
View File

@ -337,7 +337,7 @@ With scatterlists, you use the resulting mapping like this:
int i, count = dma_map_sg(dev, sglist, nents, direction);
struct scatterlist *sg;
for (i = 0, sg = sglist; i < count; i++, sg++) {
for_each_sg(sglist, sg, count, i) {
hw_address[i] = sg_dma_address(sg);
hw_len[i] = sg_dma_len(sg);
}

5
Documentation/DocBook/kernel-api.tmpl
View File

@ -283,6 +283,7 @@ X!Earch/x86/kernel/mca_32.c
<chapter id="security">
<title>Security Framework</title>
!Isecurity/security.c
!Esecurity/inode.c
</chapter>
<chapter id="audit">
@ -364,6 +365,10 @@ X!Edrivers/pnp/system.c
!Eblock/blk-barrier.c
!Eblock/blk-tag.c
!Iblock/blk-tag.c
!Eblock/blk-integrity.c
!Iblock/blktrace.c
!Iblock/genhd.c
!Eblock/genhd.c
</chapter>
<chapter id="chrdev">

12
Documentation/DocBook/mac80211.tmpl
View File

@ -145,7 +145,6 @@ usage should require reading the full document.
this though and the recommendation to allow only a single
interface in STA mode at first!
</para>
!Finclude/net/mac80211.h ieee80211_if_types
!Finclude/net/mac80211.h ieee80211_if_init_conf
!Finclude/net/mac80211.h ieee80211_if_conf
</chapter>
@ -177,8 +176,7 @@ usage should require reading the full document.
<title>functions/definitions</title>
!Finclude/net/mac80211.h ieee80211_rx_status
!Finclude/net/mac80211.h mac80211_rx_flags
!Finclude/net/mac80211.h ieee80211_tx_control
!Finclude/net/mac80211.h ieee80211_tx_status_flags
!Finclude/net/mac80211.h ieee80211_tx_info
!Finclude/net/mac80211.h ieee80211_rx
!Finclude/net/mac80211.h ieee80211_rx_irqsafe
!Finclude/net/mac80211.h ieee80211_tx_status
@ -189,12 +187,11 @@ usage should require reading the full document.
!Finclude/net/mac80211.h ieee80211_ctstoself_duration
!Finclude/net/mac80211.h ieee80211_generic_frame_duration
!Finclude/net/mac80211.h ieee80211_get_hdrlen_from_skb
!Finclude/net/mac80211.h ieee80211_get_hdrlen
!Finclude/net/mac80211.h ieee80211_hdrlen
!Finclude/net/mac80211.h ieee80211_wake_queue
!Finclude/net/mac80211.h ieee80211_stop_queue
!Finclude/net/mac80211.h ieee80211_start_queues
!Finclude/net/mac80211.h ieee80211_stop_queues
!Finclude/net/mac80211.h ieee80211_wake_queues
!Finclude/net/mac80211.h ieee80211_stop_queues
</sect1>
</chapter>
@ -230,8 +227,7 @@ usage should require reading the full document.
<title>Multiple queues and QoS support</title>
<para>TBD</para>
!Finclude/net/mac80211.h ieee80211_tx_queue_params
!Finclude/net/mac80211.h ieee80211_tx_queue_stats_data
!Finclude/net/mac80211.h ieee80211_tx_queue
!Finclude/net/mac80211.h ieee80211_tx_queue_stats
</chapter>
<chapter id="AP">

2
Documentation/RCU/checklist.txt
View File

@ -210,7 +210,7 @@ over a rather long period of time, but improvements are always welcome!
number of updates per grace period.
9. All RCU list-traversal primitives, which include
rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
rcu_dereference(), list_for_each_entry_rcu(),
list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
must be either within an RCU read-side critical section or
must be protected by appropriate update-side locks. RCU

16
Documentation/RCU/rcuref.txt
View File

@ -29,9 +29,9 @@ release_referenced() delete()
}
If this list/array is made lock free using RCU as in changing the
write_lock() in add() and delete() to spin_lock and changing read_lock
in search_and_reference to rcu_read_lock(), the atomic_get in
search_and_reference could potentially hold reference to an element which
write_lock() in add() and delete() to spin_lock() and changing read_lock()
in search_and_reference() to rcu_read_lock(), the atomic_inc() in
search_and_reference() could potentially hold reference to an element which
has already been deleted from the list/array. Use atomic_inc_not_zero()
in this scenario as follows:
@ -40,20 +40,20 @@ add() search_and_reference()
{ {
alloc_object rcu_read_lock();
... search_for_element
atomic_set(&el->rc, 1); if (atomic_inc_not_zero(&el->rc)) {
write_lock(&list_lock); rcu_read_unlock();
atomic_set(&el->rc, 1); if (!atomic_inc_not_zero(&el->rc)) {
spin_lock(&list_lock); rcu_read_unlock();
return FAIL;
add_element }
... ...
write_unlock(&list_lock); rcu_read_unlock();
spin_unlock(&list_lock); rcu_read_unlock();
} }
3. 4.
release_referenced() delete()
{ {
... write_lock(&list_lock);
... spin_lock(&list_lock);
if (atomic_dec_and_test(&el->rc)) ...
call_rcu(&el->head, el_free); delete_element
... write_unlock(&list_lock);
... spin_unlock(&list_lock);
} ...
if (atomic_dec_and_test(&el->rc))
call_rcu(&el->head, el_free);

2
Documentation/RCU/whatisRCU.txt
View File

@ -786,8 +786,6 @@ RCU pointer/list traversal:
list_for_each_entry_rcu
hlist_for_each_entry_rcu
list_for_each_rcu (to be deprecated in favor of
list_for_each_entry_rcu)
list_for_each_continue_rcu (to be deprecated in favor of new
list_for_each_entry_continue_rcu)

27
Documentation/SELinux.txt Normal file
View File

@ -0,0 +1,27 @@
If you want to use SELinux, chances are you will want
to use the distro-provided policies, or install the
latest reference policy release from
http://oss.tresys.com/projects/refpolicy
However, if you want to install a dummy policy for
testing, you can do using 'mdp' provided under
scripts/selinux. Note that this requires the selinux
userspace to be installed - in particular you will
need checkpolicy to compile a kernel, and setfiles and
fixfiles to label the filesystem.
1. Compile the kernel with selinux enabled.
2. Type 'make' to compile mdp.
3. Make sure that you are not running with
SELinux enabled and a real policy. If
you are, reboot with selinux disabled
before continuing.
4. Run install_policy.sh:
cd scripts/selinux
sh install_policy.sh
Step 4 will create a new dummy policy valid for your
kernel, with a single selinux user, role, and type.
It will compile the policy, will set your SELINUXTYPE to
dummy in /etc/selinux/config, install the compiled policy
as 'dummy', and relabel your filesystem.

155
Documentation/blackfin/kgdb.txt
View File

@ -1,155 +0,0 @@
A Simple Guide to Configure KGDB
Sonic Zhang <sonic.zhang@analog.com>
Aug. 24th 2006
This KGDB patch enables the kernel developer to do source level debugging on
the kernel for the Blackfin architecture. The debugging works over either the
ethernet interface or one of the uarts. Both software breakpoints and
hardware breakpoints are supported in this version.
http://docs.blackfin.uclinux.org/doku.php?id=kgdb
2 known issues:
1. This bug:
http://blackfin.uclinux.org/tracker/index.php?func=detail&aid=544&group_id=18&atid=145
The GDB client for Blackfin uClinux causes incorrect values of local
variables to be displayed when the user breaks the running of kernel in GDB.
2. Because of a hardware bug in Blackfin 533 v1.0.3:
05000067 - Watchpoints (Hardware Breakpoints) are not supported
Hardware breakpoints cannot be set properly.
Debug over Ethernet:
1. Compile and install the cross platform version of gdb for blackfin, which
can be found at $(BINROOT)/bfin-elf-gdb.
2. Apply this patch to the 2.6.x kernel. Select the menuconfig option under
"Kernel hacking" -> "Kernel debugging" -> "KGDB: kernel debug with remote gdb".
With this selected, option "Full Symbolic/Source Debugging support" and
"Compile the kernel with frame pointers" are also selected.
3. Select option "KGDB: connect over (Ethernet)". Add "kgdboe=@target-IP/,@host-IP/" to
the option "Compiled-in Kernel Boot Parameter" under "Kernel hacking".
4. Connect minicom to the serial port and boot the kernel image.
5. Configure the IP "/> ifconfig eth0 target-IP"
6. Start GDB client "bfin-elf-gdb vmlinux".
7. Connect to the target "(gdb) target remote udp:target-IP:6443".
8. Set software breakpoint "(gdb) break sys_open".
9. Continue "(gdb) c".
10. Run ls in the target console "/> ls".
11. Breakpoint hits. "Breakpoint 1: sys_open(..."
12. Display local variables and function paramters.
(*) This operation gives wrong results, see known issue 1.
13. Single stepping "(gdb) si".
14. Remove breakpoint 1. "(gdb) del 1"
15. Set hardware breakpoint "(gdb) hbreak sys_open".
16. Continue "(gdb) c".
17. Run ls in the target console "/> ls".
18. Hardware breakpoint hits. "Breakpoint 1: sys_open(...".
(*) This hardware breakpoint will not be hit, see known issue 2.
19. Continue "(gdb) c".
20. Interrupt the target in GDB "Ctrl+C".
21. Detach from the target "(gdb) detach".
22. Exit GDB "(gdb) quit".
Debug over the UART:
1. Compile and install the cross platform version of gdb for blackfin, which
can be found at $(BINROOT)/bfin-elf-gdb.
2. Apply this patch to the 2.6.x kernel. Select the menuconfig option under
"Kernel hacking" -> "Kernel debugging" -> "KGDB: kernel debug with remote gdb".
With this selected, option "Full Symbolic/Source Debugging support" and
"Compile the kernel with frame pointers" are also selected.
3. Select option "KGDB: connect over (UART)". Set "KGDB: UART port number" to be
a different one from the console. Don't forget to change the mode of
blackfin serial driver to PIO. Otherwise kgdb works incorrectly on UART.
4. If you want connect to kgdb when the kernel boots, enable
"KGDB: Wait for gdb connection early"
5. Compile kernel.
6. Connect minicom to the serial port of the console and boot the kernel image.
7. Start GDB client "bfin-elf-gdb vmlinux".
8. Set the baud rate in GDB "(gdb) set remotebaud 57600".
9. Connect to the target on the second serial port "(gdb) target remote /dev/ttyS1".
10. Set software breakpoint "(gdb) break sys_open".
11. Continue "(gdb) c".
12. Run ls in the target console "/> ls".
13. A breakpoint is hit. "Breakpoint 1: sys_open(..."
14. All other operations are the same as that in KGDB over Ethernet.
Debug over the same UART as console:
1. Compile and install the cross platform version of gdb for blackfin, which
can be found at $(BINROOT)/bfin-elf-gdb.
2. Apply this patch to the 2.6.x kernel. Select the menuconfig option under
"Kernel hacking" -> "Kernel debugging" -> "KGDB: kernel debug with remote gdb".
With this selected, option "Full Symbolic/Source Debugging support" and
"Compile the kernel with frame pointers" are also selected.
3. Select option "KGDB: connect over UART". Set "KGDB: UART port number" to console.
Don't forget to change the mode of blackfin serial driver to PIO.
Otherwise kgdb works incorrectly on UART.
4. If you want connect to kgdb when the kernel boots, enable
"KGDB: Wait for gdb connection early"
5. Connect minicom to the serial port and boot the kernel image.
6. (Optional) Ask target to wait for gdb connection by entering Ctrl+A. In minicom, you should enter Ctrl+A+A.
7. Start GDB client "bfin-elf-gdb vmlinux".
8. Set the baud rate in GDB "(gdb) set remotebaud 57600".
9. Connect to the target "(gdb) target remote /dev/ttyS0".
10. Set software breakpoint "(gdb) break sys_open".
11. Continue "(gdb) c". Then enter Ctrl+C twice to stop GDB connection.
12. Run ls in the target console "/> ls". Dummy string can be seen on the console.
13. Then connect the gdb to target again. "(gdb) target remote /dev/ttyS0".
Now you will find a breakpoint is hit. "Breakpoint 1: sys_open(..."
14. All other operations are the same as that in KGDB over Ethernet. The only
difference is that after continue command in GDB, please stop GDB
connection by 2 "Ctrl+C"s and connect again after breakpoints are hit or
Ctrl+A is entered.

14
Documentation/block/deadline-iosched.txt
View File

@ -30,12 +30,18 @@ write_expire (in ms)
Similar to read_expire mentioned above, but for writes.
fifo_batch
fifo_batch (number of requests)
----------
When a read request expires its deadline, we must move some requests from
the sorted io scheduler list to the block device dispatch queue. fifo_batch
controls how many requests we move.
Requests are grouped into ``batches'' of a particular data direction (read or
write) which are serviced in increasing sector order. To limit extra seeking,
deadline expiries are only checked between batches. fifo_batch controls the
maximum number of requests per batch.
This parameter tunes the balance between per-request latency and aggregate
throughput. When low latency is the primary concern, smaller is better (where
a value of 1 yields first-come first-served behaviour). Increasing fifo_batch
generally improves throughput, at the cost of latency variation.
writes_starved (number of dispatches)

3
Documentation/cdrom/ide-cd
View File

@ -145,8 +145,7 @@ useful for reading photocds.
To play an audio CD, you should first unmount and remove any data
CDROM. Any of the CDROM player programs should then work (workman,
workbone, cdplayer, etc.). Lacking anything else, you could use the
cdtester program in Documentation/cdrom/sbpcd.
workbone, cdplayer, etc.).
On a few drives, you can read digital audio directly using a program
such as cdda2wav. The only types of drive which I've heard support

10
Documentation/cpu-freq/index.txt
View File

@ -35,11 +35,9 @@ Mailing List
------------
There is a CPU frequency changing CVS commit and general list where
you can report bugs, problems or submit patches. To post a message,
send an email to cpufreq@lists.linux.org.uk, to subscribe go to
http://lists.linux.org.uk/mailman/listinfo/cpufreq. Previous post to the
mailing list are available to subscribers at
http://lists.linux.org.uk/mailman/private/cpufreq/.
send an email to cpufreq@vger.kernel.org, to subscribe go to
http://vger.kernel.org/vger-lists.html#cpufreq and follow the
instructions there.
Links
-----
@ -50,7 +48,7 @@ how to access the CVS repository:
* http://cvs.arm.linux.org.uk/
the CPUFreq Mailing list:
* http://lists.linux.org.uk/mailman/listinfo/cpufreq
* http://vger.kernel.org/vger-lists.html#cpufreq
Clock and voltage scaling for the SA-1100:
* http://www.lartmaker.nl/projects/scaling

29
Documentation/feature-removal-schedule.txt
View File

@ -6,6 +6,24 @@ be removed from this file.
---------------------------
What: old static regulatory information and ieee80211_regdom module parameter
When: 2.6.29
Why: The old regulatory infrastructure has been replaced with a new one
which does not require statically defined regulatory domains. We do
not want to keep static regulatory domains in the kernel due to the
the dynamic nature of regulatory law and localization. We kept around
the old static definitions for the regulatory domains of:
* US
* JP
* EU
and used by default the US when CONFIG_WIRELESS_OLD_REGULATORY was
set. We also kept around the ieee80211_regdom module parameter in case
some applications were relying on it. Changing regulatory domains
can now be done instead by using nl80211, as is done with iw.
Who: Luis R. Rodriguez <lrodriguez@atheros.com>
---------------------------
What: dev->power.power_state
When: July 2007
Why: Broken design for runtime control over driver power states, confusing
@ -232,6 +250,9 @@ What (Why):
- xt_mark match revision 0
(superseded by xt_mark match revision 1)
- xt_recent: the old ipt_recent proc dir
(superseded by /proc/net/xt_recent)
When: January 2009 or Linux 2.7.0, whichever comes first
Why: Superseded by newer revisions or modules
Who: Jan Engelhardt <jengelh@computergmbh.de>
@ -266,14 +287,6 @@ Who: Glauber Costa <gcosta@redhat.com>
---------------------------
What: old style serial driver for ColdFire (CONFIG_SERIAL_COLDFIRE)
When: 2.6.28
Why: This driver still uses the old interface and has been replaced
by CONFIG_SERIAL_MCF.
Who: Sebastian Siewior <sebastian@breakpoint.cc>
---------------------------
What: /sys/o2cb symlink
When: January 2010
Why: /sys/fs/o2cb is the proper location for this information - /sys/o2cb

19
Documentation/filesystems/ext4.txt
View File

@ -32,9 +32,9 @@ Mailing list: linux-ext4@vger.kernel.org
you will need to merge your changes with the version from e2fsprogs
1.41.x.
- Create a new filesystem using the ext4dev filesystem type:
- Create a new filesystem using the ext4 filesystem type:
# mke2fs -t ext4dev /dev/hda1
# mke2fs -t ext4 /dev/hda1
Or configure an existing ext3 filesystem to support extents and set
the test_fs flag to indicate that it's ok for an in-development
@ -47,13 +47,13 @@ Mailing list: linux-ext4@vger.kernel.org
# tune2fs -I 256 /dev/hda1
(Note: we currently do not have tools to convert an ext4dev
(Note: we currently do not have tools to convert an ext4
filesystem back to ext3; so please do not do try this on production
filesystems.)
- Mounting:
# mount -t ext4dev /dev/hda1 /wherever
# mount -t ext4 /dev/hda1 /wherever
- When comparing performance with other filesystems, remember that
ext3/4 by default offers higher data integrity guarantees than most.
@ -177,6 +177,11 @@ barrier=<0|1(*)> This enables/disables the use of write barriers in
your disks are battery-backed in one way or another,
disabling barriers may safely improve performance.
inode_readahead=n This tuning parameter controls the maximum
number of inode table blocks that ext4's inode
table readahead algorithm will pre-read into
the buffer cache. The default value is 32 blocks.
orlov (*) This enables the new Orlov block allocator. It is
enabled by default.
@ -218,6 +223,11 @@ errors=remount-ro(*) Remount the filesystem read-only on an error.
errors=continue Keep going on a filesystem error.
errors=panic Panic and halt the machine if an error occurs.
data_err=ignore(*) Just print an error message if an error occurs
in a file data buffer in ordered mode.
data_err=abort Abort the journal if an error occurs in a file
data buffer in ordered mode.
grpid Give objects the same group ID as their creator.
bsdgroups
@ -252,6 +262,7 @@ stripe=n Number of filesystem blocks that mballoc will try
delalloc (*) Deferring block allocation until write-out time.
nodelalloc Disable delayed allocation. Blocks are allocation
when data is copied from user to page cache.
Data Mode
=========
There are 3 different data modes:

228
Documentation/filesystems/fiemap.txt Normal file
View File

@ -0,0 +1,228 @@
============
Fiemap Ioctl
============
The fiemap ioctl is an efficient method for userspace to get file
extent mappings. Instead of block-by-block mapping (such as bmap), fiemap
returns a list of extents.
Request Basics
--------------
A fiemap request is encoded within struct fiemap:
struct fiemap {
__u64 fm_start; /* logical offset (inclusive) at
* which to start mapping (in) */
__u64 fm_length; /* logical length of mapping which
* userspace cares about (in) */
__u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */
__u32 fm_mapped_extents; /* number of extents that were
* mapped (out) */
__u32 fm_extent_count; /* size of fm_extents array (in) */
__u32 fm_reserved;
struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
};
fm_start, and fm_length specify the logical range within the file
which the process would like mappings for. Extents returned mirror
those on disk - that is, the logical offset of the 1st returned extent
may start before fm_start, and the range covered by the last returned
extent may end after fm_length. All offsets and lengths are in bytes.
Certain flags to modify the way in which mappings are looked up can be
set in fm_flags. If the kernel doesn't understand some particular
flags, it will return EBADR and the contents of fm_flags will contain
the set of flags which caused the error. If the kernel is compatible
with all flags passed, the contents of fm_flags will be unmodified.
It is up to userspace to determine whether rejection of a particular
flag is fatal to it's operation. This scheme is intended to allow the
fiemap interface to grow in the future but without losing
compatibility with old software.
fm_extent_count specifies the number of elements in the fm_extents[] array
that can be used to return extents. If fm_extent_count is zero, then the
fm_extents[] array is ignored (no extents will be returned), and the
fm_mapped_extents count will hold the number of extents needed in
fm_extents[] to hold the file's current mapping. Note that there is
nothing to prevent the file from changing between calls to FIEMAP.
The following flags can be set in fm_flags:
* FIEMAP_FLAG_SYNC
If this flag is set, the kernel will sync the file before mapping extents.
* FIEMAP_FLAG_XATTR
If this flag is set, the extents returned will describe the inodes
extended attribute lookup tree, instead of it's data tree.
Extent Mapping
--------------
Extent information is returned within the embedded fm_extents array
which userspace must allocate along with the fiemap structure. The
number of elements in the fiemap_extents[] array should be passed via
fm_extent_count. The number of extents mapped by kernel will be
returned via fm_mapped_extents. If the number of fiemap_extents
allocated is less than would be required to map the requested range,
the maximum number of extents that can be mapped in the fm_extent[]
array will be returned and fm_mapped_extents will be equal to
fm_extent_count. In that case, the last extent in the array will not
complete the requested range and will not have the FIEMAP_EXTENT_LAST
flag set (see the next section on extent flags).
Each extent is described by a single fiemap_extent structure as
returned in fm_extents.
struct fiemap_extent {
__u64 fe_logical; /* logical offset in bytes for the start of
* the extent */
__u64 fe_physical; /* physical offset in bytes for the start
* of the extent */
__u64 fe_length; /* length in bytes for the extent */
__u64 fe_reserved64[2];
__u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */
__u32 fe_reserved[3];
};
All offsets and lengths are in bytes and mirror those on disk. It is valid
for an extents logical offset to start before the request or it's logical
length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is
returned, fe_logical, fe_physical, and fe_length will be aligned to the
block size of the file system. With the exception of extents flagged as
FIEMAP_EXTENT_MERGED, adjacent extents will not be merged.
The fe_flags field contains flags which describe the extent returned.
A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in
the file so that the process making fiemap calls can determine when no
more extents are available, without having to call the ioctl again.
Some flags are intentionally vague and will always be set in the
presence of other more specific flags. This way a program looking for
a general property does not have to know all existing and future flags
which imply that property.
For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL
are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking
for inline or tail-packed data can key on the specific flag. Software
which simply cares not to try operating on non-aligned extents
however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to
worry about all present and future flags which might imply unaligned
data. Note that the opposite is not true - it would be valid for
FIEMAP_EXTENT_NOT_ALIGNED to appear alone.
* FIEMAP_EXTENT_LAST
This is the last extent in the file. A mapping attempt past this
extent will return nothing.
* FIEMAP_EXTENT_UNKNOWN
The location of this extent is currently unknown. This may indicate
the data is stored on an inaccessible volume or that no storage has
been allocated for the file yet.
* FIEMAP_EXTENT_DELALLOC
- This will also set FIEMAP_EXTENT_UNKNOWN.
Delayed allocation - while there is data for this extent, it's
physical location has not been allocated yet.
* FIEMAP_EXTENT_ENCODED
This extent does not consist of plain filesystem blocks but is
encoded (e.g. encrypted or compressed). Reading the data in this
extent via I/O to the block device will have undefined results.
Note that it is *always* undefined to try to update the data
in-place by writing to the indicated location without the
assistance of the filesystem, or to access the data using the
information returned by the FIEMAP interface while the filesystem
is mounted. In other words, user applications may only read the
extent data via I/O to the block device while the filesystem is
unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is
clear; user applications must not try reading or writing to the
filesystem via the block device under any other circumstances.
* FIEMAP_EXTENT_DATA_ENCRYPTED
- This will also set FIEMAP_EXTENT_ENCODED
The data in this extent has been encrypted by the file system.
* FIEMAP_EXTENT_NOT_ALIGNED
Extent offsets and length are not guaranteed to be block aligned.
* FIEMAP_EXTENT_DATA_INLINE
This will also set FIEMAP_EXTENT_NOT_ALIGNED
Data is located within a meta data block.
* FIEMAP_EXTENT_DATA_TAIL
This will also set FIEMAP_EXTENT_NOT_ALIGNED
Data is packed into a block with data from other files.
* FIEMAP_EXTENT_UNWRITTEN
Unwritten extent - the extent is allocated but it's data has not been
initialized. This indicates the extent's data will be all zero if read
through the filesystem but the contents are undefined if read directly from
the device.
* FIEMAP_EXTENT_MERGED
This will be set when a file does not support extents, i.e., it uses a block
based addressing scheme. Since returning an extent for each block back to
userspace would be highly inefficient, the kernel will try to merge most
adjacent blocks into 'extents'.
VFS -> File System Implementation
---------------------------------
File systems wishing to support fiemap must implement a ->fiemap callback on
their inode_operations structure. The fs ->fiemap call is responsible for
defining it's set of supported fiemap flags, and calling a helper function on
each discovered extent:
struct inode_operations {
...
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
->fiemap is passed struct fiemap_extent_info which describes the
fiemap request:
struct fiemap_extent_info {
unsigned int fi_flags; /* Flags as passed from user */
unsigned int fi_extents_mapped; /* Number of mapped extents */
unsigned int fi_extents_max; /* Size of fiemap_extent array */
struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */
};
It is intended that the file system should not need to access any of this
structure directly.
Flag checking should be done at the beginning of the ->fiemap callback via the
fiemap_check_flags() helper:
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
set of fiemap flags which the fs understands should be passed via fs_flags. If
fiemap_check_flags finds invalid user flags, it will place the bad values in
fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
fiemap_check_flags(), it should immediately exit, returning that error back to
ioctl_fiemap().
For each extent in the request range, the file system should call
the helper function, fiemap_fill_next_extent():
int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
u64 phys, u64 len, u32 flags, u32 dev);
fiemap_fill_next_extent() will use the passed values to populate the
next free extent in the fm_extents array. 'General' extent flags will
automatically be set from specific flags on behalf of the calling file
system so that the userspace API is not broken.
fiemap_fill_next_extent() returns 0 on success, and 1 when the
user-supplied fm_extents array is full. If an error is encountered
while copying the extent to user memory, -EFAULT will be returned.

74
Documentation/filesystems/proc.txt
View File

@ -923,45 +923,44 @@ CPUs.
The "procs_blocked" line gives the number of processes currently blocked,
waiting for I/O to complete.
1.9 Ext4 file system parameters
------------------------------
Ext4 file system have one directory per partition under /proc/fs/ext4/
# ls /proc/fs/ext4/hdc/
group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req
stats stream_req
mb_groups:
This file gives the details of multiblock allocator buddy cache of free blocks
Information about mounted ext4 file systems can be found in
/proc/fs/ext4. Each mounted filesystem will have a directory in
/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
/proc/fs/ext4/dm-0). The files in each per-device directory are shown
in Table 1-10, below.
mb_history:
Multiblock allocation history.
Table 1-10: Files in /proc/fs/ext4/<devname>
..............................................................................
File Content
mb_groups details of multiblock allocator buddy cache of free blocks
mb_history multiblock allocation history
stats controls whether the multiblock allocator should start
collecting statistics, which are shown during the unmount
group_prealloc the multiblock allocator will round up allocation
requests to a multiple of this tuning parameter if the
stripe size is not set in the ext4 superblock
max_to_scan The maximum number of extents the multiblock allocator
will search to find the best extent
min_to_scan The minimum number of extents the multiblock allocator
will search to find the best extent
order2_req Tuning parameter which controls the minimum size for
requests (as a power of 2) where the buddy cache is
used
stream_req Files which have fewer blocks than this tunable
parameter will have their blocks allocated out of a
block group specific preallocation pool, so that small
files are packed closely together. Each large file
will have its blocks allocated out of its own unique
preallocation pool.
inode_readahead Tuning parameter which controls the maximum number of
inode table blocks that ext4's inode table readahead
algorithm will pre-read into the buffer cache
..............................................................................
stats:
This file indicate whether the multiblock allocator should start collecting
statistics. The statistics are shown during unmount
group_prealloc:
The multiblock allocator normalize the block allocation request to
group_prealloc filesystem blocks if we don't have strip value set.
The stripe value can be specified at mount time or during mke2fs.
max_to_scan:
How long multiblock allocator can look for a best extent (in found extents)
min_to_scan:
How long multiblock allocator must look for a best extent
order2_req:
Multiblock allocator use 2^N search using buddies only for requests greater
than or equal to order2_req. The request size is specfied in file system
blocks. A value of 2 indicate only if the requests are greater than or equal
to 4 blocks.
stream_req:
Files smaller than stream_req are served by the stream allocator, whose
purpose is to pack requests as close each to other as possible to
produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16
filesystem block size will use group based preallocation.
------------------------------------------------------------------------------
Summary
@ -1332,13 +1331,6 @@ determine whether or not they are still functioning properly.
Because the NMI watchdog shares registers with oprofile, by disabling the NMI
watchdog, oprofile may have more registers to utilize.
maps_protect
------------
Enables/Disables the protection of the per-process proc entries "maps" and
"smaps". When enabled, the contents of these files are visible only to
readers that are allowed to ptrace() the given process.
msgmni
------

300
Documentation/hpet.txt
View File

@ -1,300 +0,0 @@
High Precision Event Timer Driver for Linux
The High Precision Event Timer (HPET) hardware is the future replacement
for the 8254 and Real Time Clock (RTC) periodic timer functionality.
Each HPET can have up to 32 timers. It is possible to configure the
first two timers as legacy replacements for 8254 and RTC periodic timers.
A specification done by Intel and Microsoft can be found at
<http://www.intel.com/technology/architecture/hpetspec.htm>.
The driver supports detection of HPET driver allocation and initialization
of the HPET before the driver module_init routine is called. This enables
platform code which uses timer 0 or 1 as the main timer to intercept HPET
initialization. An example of this initialization can be found in
arch/i386/kernel/time_hpet.c.
The driver provides two APIs which are very similar to the API found in
the rtc.c driver. There is a user space API and a kernel space API.
An example user space program is provided below.
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <string.h>
#include <memory.h>
#include <malloc.h>
#include <time.h>
#include <ctype.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <signal.h>
#include <fcntl.h>
#include <errno.h>
#include <sys/time.h>
#include <linux/hpet.h>
extern void hpet_open_close(int, const char **);
extern void hpet_info(int, const char **);
extern void hpet_poll(int, const char **);
extern void hpet_fasync(int, const char **);
extern void hpet_read(int, const char **);
#include <sys/poll.h>
#include <sys/ioctl.h>
#include <signal.h>
struct hpet_command {
char *command;
void (*func)(int argc, const char ** argv);
} hpet_command[] = {
{
"open-close",
hpet_open_close
},
{
"info",
hpet_info
},
{
"poll",
hpet_poll
},
{
"fasync",
hpet_fasync
},
};
int
main(int argc, const char ** argv)
{
int i;
argc--;
argv++;
if (!argc) {
fprintf(stderr, "-hpet: requires command\n");
return -1;
}
for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
if (!strcmp(argv[0], hpet_command[i].command)) {
argc--;
argv++;
fprintf(stderr, "-hpet: executing %s\n",
hpet_command[i].command);
hpet_command[i].func(argc, argv);
return 0;
}
fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
return -1;
}
void
hpet_open_close(int argc, const char **argv)
{
int fd;
if (argc != 1) {
fprintf(stderr, "hpet_open_close: device-name\n");
return;
}
fd = open(argv[0], O_RDONLY);
if (fd < 0)
fprintf(stderr, "hpet_open_close: open failed\n");
else
close(fd);
return;
}
void
hpet_info(int argc, const char **argv)
{
}
void
hpet_poll(int argc, const char **argv)
{
unsigned long freq;
int iterations, i, fd;
struct pollfd pfd;
struct hpet_info info;
struct timeval stv, etv;
struct timezone tz;
long usec;
if (argc != 3) {
fprintf(stderr, "hpet_poll: device-name freq iterations\n");
return;
}
freq = atoi(argv[1]);
iterations = atoi(argv[2]);
fd = open(argv[0], O_RDONLY);
if (fd < 0) {
fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
return;
}
if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
goto out;
}
if (ioctl(fd, HPET_INFO, &info) < 0) {
fprintf(stderr, "hpet_poll: failed to get info\n");
goto out;
}
fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
goto out;
}
if (ioctl(fd, HPET_IE_ON, 0) < 0) {
fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
goto out;
}
pfd.fd = fd;
pfd.events = POLLIN;
for (i = 0; i < iterations; i++) {
pfd.revents = 0;
gettimeofday(&stv, &tz);
if (poll(&pfd, 1, -1) < 0)
fprintf(stderr, "hpet_poll: poll failed\n");
else {
long data;
gettimeofday(&etv, &tz);
usec = stv.tv_sec * 1000000 + stv.tv_usec;
usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
fprintf(stderr,
"hpet_poll: expired time = 0x%lx\n", usec);
fprintf(stderr, "hpet_poll: revents = 0x%x\n",
pfd.revents);
if (read(fd, &data, sizeof(data)) != sizeof(data)) {
fprintf(stderr, "hpet_poll: read failed\n");
}
else
fprintf(stderr, "hpet_poll: data 0x%lx\n",
data);
}
}
out:
close(fd);
return;
}
static int hpet_sigio_count;
static void
hpet_sigio(int val)
{
fprintf(stderr, "hpet_sigio: called\n");
hpet_sigio_count++;
}
void
hpet_fasync(int argc, const char **argv)
{
unsigned long freq;
int iterations, i, fd, value;
sig_t oldsig;
struct hpet_info info;
hpet_sigio_count = 0;
fd = -1;
if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
return;
}
if (argc != 3) {
fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
goto out;
}
fd = open(argv[0], O_RDONLY);
if (fd < 0) {
fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
return;
}
if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
((value = fcntl(fd, F_GETFL)) == 1) ||
(fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
fprintf(stderr, "hpet_fasync: fcntl failed\n");
goto out;
}
freq = atoi(argv[1]);
iterations = atoi(argv[2]);
if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
goto out;
}
if (ioctl(fd, HPET_INFO, &info) < 0) {
fprintf(stderr, "hpet_fasync: failed to get info\n");
goto out;
}
fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
goto out;
}
if (ioctl(fd, HPET_IE_ON, 0) < 0) {
fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
goto out;
}
for (i = 0; i < iterations; i++) {
(void) pause();
fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
}
out:
signal(SIGIO, oldsig);
if (fd >= 0)
close(fd);
return;
}
The kernel API has three interfaces exported from the driver:
hpet_register(struct hpet_task *tp, int periodic)
hpet_unregister(struct hpet_task *tp)
hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg)
The kernel module using this interface fills in the ht_func and ht_data
members of the hpet_task structure before calling hpet_register.
hpet_control simply vectors to the hpet_ioctl routine and has the same
commands and respective arguments as the user API. hpet_unregister
is used to terminate usage of the HPET timer reserved by hpet_register.

18
Documentation/hwmon/adt7473
View File

@ -14,14 +14,14 @@ Description
This driver implements support for the Analog Devices ADT7473 chip family.
The LM85 uses the 2-wire interface compatible with the SMBUS 2.0
The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
specification. Using an analog to digital converter it measures three (3)
temperatures and two (2) voltages. It has three (3) 16-bit counters for
temperatures and two (2) voltages. It has four (4) 16-bit counters for
measuring fan speed. There are three (3) PWM outputs that can be used
to control fan speed.
A sophisticated control system for the PWM outputs is designed into the
LM85 that allows fan speed to be adjusted automatically based on any of the
ADT7473 that allows fan speed to be adjusted automatically based on any of the
three temperature sensors. Each PWM output is individually adjustable and
programmable. Once configured, the ADT7473 will adjust the PWM outputs in
response to the measured temperatures without further host intervention.
@ -46,14 +46,6 @@ from the raw value to get the temperature value.
The Analog Devices datasheet is very detailed and describes a procedure for
determining an optimal configuration for the automatic PWM control.
Hardware Configurations
-----------------------
The ADT7473 chips have an optional SMBALERT output that can be used to
signal the chipset in case a limit is exceeded or the temperature sensors
fail. Individual sensor interrupts can be masked so they won't trigger
SMBALERT. The SMBALERT output if configured replaces the PWM2 function.
Configuration Notes
-------------------
@ -61,8 +53,8 @@ Besides standard interfaces driver adds the following:
* PWM Control
* pwm#_auto_point1_pwm and pwm#_auto_point1_temp and
* pwm#_auto_point2_pwm and pwm#_auto_point2_temp -
* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
point1: Set the pwm speed at a lower temperature bound.
point2: Set the pwm speed at a higher temperature bound.

12
Documentation/hwmon/sysfs-interface
View File

@ -329,6 +329,10 @@ power[1-*]_average Average power use
Unit: microWatt
RO
power[1-*]_average_interval Power use averaging interval
Unit: milliseconds
RW
power[1-*]_average_highest Historical average maximum power use
Unit: microWatt
RO
@ -353,6 +357,14 @@ power[1-*]_reset_history Reset input_highest, input_lowest,
average_highest and average_lowest.
WO
**********
* Energy *
**********
energy[1-*]_input Cumulative energy use
Unit: microJoule
RO
**********
* Alarms *
**********

4
Documentation/kernel-doc-nano-HOWTO.txt
View File

@ -168,10 +168,10 @@ if ($#ARGV < 0) {
mkdir $ARGV[0],0777;
$state = 0;
while (<STDIN>) {
if (/^\.TH \"[^\"]*\" 4 \"([^\"]*)\"/) {
if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
if ($state == 1) { close OUT }
$state = 1;
$fn = "$ARGV[0]/$1.4";
$fn = "$ARGV[0]/$1.9";
print STDERR "Creating $fn\n";
open OUT, ">$fn" or die "can't open $fn: $!\n";
print OUT $_;

53
Documentation/kernel-parameters.txt
View File

@ -284,6 +284,11 @@ and is between 256 and 4096 characters. It is defined in the file
isolate - enable device isolation (each device, as far
as possible, will get its own protection
domain)
fullflush - enable flushing of IO/TLB entries when
they are unmapped. Otherwise they are
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:
@ -463,12 +468,6 @@ and is between 256 and 4096 characters. It is defined in the file
Range: 0 - 8192
Default: 64
disable_8254_timer
enable_8254_timer
[IA32/X86_64] Disable/Enable interrupt 0 timer routing
over the 8254 in addition to over the IO-APIC. The
kernel tries to set a sensible default.
hpet= [X86-32,HPET] option to control HPET usage
Format: { enable (default) | disable | force }
disable: disable HPET and use PIT instead
@ -659,11 +658,12 @@ and is between 256 and 4096 characters. It is defined in the file
earlyprintk= [X86-32,X86-64,SH,BLACKFIN]
earlyprintk=vga
earlyprintk=serial[,ttySn[,baudrate]]
earlyprintk=dbgp
Append ",keep" to not disable it when the real console
takes over.
Only vga or serial at a time, not both.
Only vga or serial or usb debug port at a time.
Currently only ttyS0 and ttyS1 are supported.
@ -1020,6 +1020,10 @@ and is between 256 and 4096 characters. It is defined in the file
(only serial suported for now)
Format: <serial_device>[,baud]
kmac= [MIPS] korina ethernet MAC address.
Configure the RouterBoard 532 series on-chip
Ethernet adapter MAC address.
l2cr= [PPC]
l3cr= [PPC]
@ -1228,6 +1232,29 @@ and is between 256 and 4096 characters. It is defined in the file
or
memmap=0x10000$0x18690000
memory_corruption_check=0/1 [X86]
Some BIOSes seem to corrupt the first 64k of
memory when doing things like suspend/resume.
Setting this option will scan the memory
looking for corruption. Enabling this will
both detect corruption and prevent the kernel
from using the memory being corrupted.
However, its intended as a diagnostic tool; if
repeatable BIOS-originated corruption always
affects the same memory, you can use memmap=
to prevent the kernel from using that memory.
memory_corruption_check_size=size [X86]
By default it checks for corruption in the low
64k, making this memory unavailable for normal
use. Use this parameter to scan for
corruption in more or less memory.
memory_corruption_check_period=seconds [X86]
By default it checks for corruption every 60
seconds. Use this parameter to check at some
other rate. 0 disables periodic checking.
memtest= [KNL,X86] Enable memtest
Format: <integer>
range: 0,4 : pattern number
@ -1425,6 +1452,12 @@ and is between 256 and 4096 characters. It is defined in the file
nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
nox2apic [X86-64,APIC] Do not enable x2APIC mode.
x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
default x2apic cluster mode on platforms
supporting x2apic.
noltlbs [PPC] Do not use large page/tlb entries for kernel
lowmem mapping on PPC40x.
@ -1882,6 +1915,12 @@ and is between 256 and 4096 characters. It is defined in the file
shapers= [NET]
Maximal number of shapers.
show_msr= [x86] show boot-time MSR settings
Format: { <integer> }
Show boot-time (BIOS-initialized) MSR settings.
The parameter means the number of CPUs to show,
for example 1 means boot CPU only.
sim710= [SCSI,HW]
See header of drivers/scsi/sim710.c.

149
Documentation/laptops/disk-shock-protection.txt Normal file
View File

@ -0,0 +1,149 @@
Hard disk shock protection
==========================
Author: Elias Oltmanns <eo@nebensachen.de>
Last modified: 2008-10-03
0. Contents
-----------
1. Intro
2. The interface
3. References
4. CREDITS
1. Intro
--------
ATA/ATAPI-7 specifies the IDLE IMMEDIATE command with unload feature.
Issuing this command should cause the drive to switch to idle mode and
unload disk heads. This feature is being used in modern laptops in
conjunction with accelerometers and appropriate software to implement
a shock protection facility. The idea is to stop all I/O operations on
the internal hard drive and park its heads on the ramp when critical
situations are anticipated. The desire to have such a feature
available on GNU/Linux systems has been the original motivation to
implement a generic disk head parking interface in the Linux kernel.
Please note, however, that other components have to be set up on your
system in order to get disk shock protection working (see
section 3. References below for pointers to more information about
that).
2. The interface
----------------
For each ATA device, the kernel exports the file
block/*/device/unload_heads in sysfs (here assumed to be mounted under
/sys). Access to /sys/block/*/device/unload_heads is denied with
-EOPNOTSUPP if the device does not support the unload feature.
Otherwise, writing an integer value to this file will take the heads
of the respective drive off the platter and block all I/O operations
for the specified number of milliseconds. When the timeout expires and
no further disk head park request has been issued in the meantime,
normal operation will be resumed. The maximal value accepted for a
timeout is 30000 milliseconds. Exceeding this limit will return
-EOVERFLOW, but heads will be parked anyway and the timeout will be
set to 30 seconds. However, you can always change a timeout to any
value between 0 and 30000 by issuing a subsequent head park request
before the timeout of the previous one has expired. In particular, the
total timeout can exceed 30 seconds and, more importantly, you can
cancel a previously set timeout and resume normal operation
immediately by specifying a timeout of 0. Values below -2 are rejected
with -EINVAL (see below for the special meaning of -1 and -2). If the
timeout specified for a recent head park request has not yet expired,
reading from /sys/block/*/device/unload_heads will report the number
of milliseconds remaining until normal operation will be resumed;
otherwise, reading the unload_heads attribute will return 0.
For example, do the following in order to park the heads of drive
/dev/sda and stop all I/O operations for five seconds:
# echo 5000 > /sys/block/sda/device/unload_heads
A simple
# cat /sys/block/sda/device/unload_heads
will show you how many milliseconds are left before normal operation
will be resumed.
A word of caution: The fact that the interface operates on a basis of
milliseconds may raise expectations that cannot be satisfied in
reality. In fact, the ATA specs clearly state that the time for an
unload operation to complete is vendor specific. The hint in ATA-7
that this will typically be within 500 milliseconds apparently has
been dropped in ATA-8.
There is a technical detail of this implementation that may cause some
confusion and should be discussed here. When a head park request has
been issued to a device successfully, all I/O operations on the
controller port this device is attached to will be deferred. That is
to say, any other device that may be connected to the same port will
be affected too. The only exception is that a subsequent head unload
request to that other device will be executed immediately. Further
operations on that port will be deferred until the timeout specified
for either device on the port has expired. As far as PATA (old style
IDE) configurations are concerned, there can only be two devices
attached to any single port. In SATA world we have port multipliers
which means that a user-issued head parking request to one device may
actually result in stopping I/O to a whole bunch of devices. However,
since this feature is supposed to be used on laptops and does not seem
to be very useful in any other environment, there will be mostly one
device per port. Even if the CD/DVD writer happens to be connected to
the same port as the hard drive, it generally *should* recover just
fine from the occasional buffer under-run incurred by a head park
request to the HD. Actually, when you are using an ide driver rather
than its libata counterpart (i.e. your disk is called /dev/hda
instead of /dev/sda), then parking the heads of one drive (drive X)
will generally not affect the mode of operation of another drive
(drive Y) on the same port as described above. It is only when a port
reset is required to recover from an exception on drive Y that further
I/O operations on that drive (and the reset itself) will be delayed
until drive X is no longer in the parked state.
Finally, there are some hard drives that only comply with an earlier
version of the ATA standard than ATA-7, but do support the unload
feature nonetheless. Unfortunately, there is no safe way Linux can
detect these devices, so you won't be able to write to the
unload_heads attribute. If you know that your device really does
support the unload feature (for instance, because the vendor of your
laptop or the hard drive itself told you so), then you can tell the
kernel to enable the usage of this feature for that drive by writing
the special value -1 to the unload_heads attribute:
# echo -1 > /sys/block/sda/device/unload_heads
will enable the feature for /dev/sda, and giving -2 instead of -1 will
disable it again.
3. References
-------------
There are several laptops from different vendors featuring shock
protection capabilities. As manufacturers have refused to support open
source development of the required software components so far, Linux
support for shock protection varies considerably between different
hardware implementations. Ideally, this section should contain a list
of pointers at different projects aiming at an implementation of shock
protection on different systems. Unfortunately, I only know of a
single project which, although still considered experimental, is fit
for use. Please feel free to add projects that have been the victims
of my ignorance.
- http://www.thinkwiki.org/wiki/HDAPS
See this page for information about Linux support of the hard disk
active protection system as implemented in IBM/Lenovo Thinkpads.
4. CREDITS
----------
This implementation of disk head parking has been inspired by a patch
originally published by Jon Escombe <lists@dresco.co.uk>. My efforts
to develop an implementation of this feature that is fit to be merged
into mainline have been aided by various kernel developers, in
particular by Tejun Heo and Bartlomiej Zolnierkiewicz.

305
Documentation/mtrr.txt
View File

@ -1,305 +0,0 @@
MTRR (Memory Type Range Register) control
3 Jun 1999
Richard Gooch
<rgooch@atnf.csiro.au>
On Intel P6 family processors (Pentium Pro, Pentium II and later)
the Memory Type Range Registers (MTRRs) may be used to control
processor access to memory ranges. This is most useful when you have
a video (VGA) card on a PCI or AGP bus. Enabling write-combining
allows bus write transfers to be combined into a larger transfer
before bursting over the PCI/AGP bus. This can increase performance
of image write operations 2.5 times or more.
The Cyrix 6x86, 6x86MX and M II processors have Address Range
Registers (ARRs) which provide a similar functionality to MTRRs. For
these, the ARRs are used to emulate the MTRRs.
The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
MTRRs. These are supported. The AMD Athlon family provide 8 Intel
style MTRRs.
The Centaur C6 (WinChip) has 8 MCRs, allowing write-combining. These
are supported.
The VIA Cyrix III and VIA C3 CPUs offer 8 Intel style MTRRs.
The CONFIG_MTRR option creates a /proc/mtrr file which may be used
to manipulate your MTRRs. Typically the X server should use
this. This should have a reasonably generic interface so that
similar control registers on other processors can be easily
supported.
There are two interfaces to /proc/mtrr: one is an ASCII interface
which allows you to read and write. The other is an ioctl()
interface. The ASCII interface is meant for administration. The
ioctl() interface is meant for C programs (i.e. the X server). The
interfaces are described below, with sample commands and C code.
===============================================================================
Reading MTRRs from the shell:
% cat /proc/mtrr
reg00: base=0x00000000 ( 0MB), size= 128MB: write-back, count=1
reg01: base=0x08000000 ( 128MB), size= 64MB: write-back, count=1
===============================================================================
Creating MTRRs from the C-shell:
# echo "base=0xf8000000 size=0x400000 type=write-combining" >! /proc/mtrr
or if you use bash:
# echo "base=0xf8000000 size=0x400000 type=write-combining" >| /proc/mtrr
And the result thereof:
% cat /proc/mtrr
reg00: base=0x00000000 ( 0MB), size= 128MB: write-back, count=1
reg01: base=0x08000000 ( 128MB), size= 64MB: write-back, count=1
reg02: base=0xf8000000 (3968MB), size= 4MB: write-combining, count=1
This is for video RAM at base address 0xf8000000 and size 4 megabytes. To
find out your base address, you need to look at the output of your X
server, which tells you where the linear framebuffer address is. A
typical line that you may get is:
(--) S3: PCI: 968 rev 0, Linear FB @ 0xf8000000
Note that you should only use the value from the X server, as it may
move the framebuffer base address, so the only value you can trust is
that reported by the X server.
To find out the size of your framebuffer (what, you don't actually
know?), the following line will tell you:
(--) S3: videoram: 4096k
That's 4 megabytes, which is 0x400000 bytes (in hexadecimal).
A patch is being written for XFree86 which will make this automatic:
in other words the X server will manipulate /proc/mtrr using the
ioctl() interface, so users won't have to do anything. If you use a
commercial X server, lobby your vendor to add support for MTRRs.
===============================================================================
Creating overlapping MTRRs:
%echo "base=0xfb000000 size=0x1000000 type=write-combining" >/proc/mtrr
%echo "base=0xfb000000 size=0x1000 type=uncachable" >/proc/mtrr
And the results: cat /proc/mtrr
reg00: base=0x00000000 ( 0MB), size= 64MB: write-back, count=1
reg01: base=0xfb000000 (4016MB), size= 16MB: write-combining, count=1
reg02: base=0xfb000000 (4016MB), size= 4kB: uncachable, count=1
Some cards (especially Voodoo Graphics boards) need this 4 kB area
excluded from the beginning of the region because it is used for
registers.
NOTE: You can only create type=uncachable region, if the first
region that you created is type=write-combining.
===============================================================================
Removing MTRRs from the C-shell:
% echo "disable=2" >! /proc/mtrr
or using bash:
% echo "disable=2" >| /proc/mtrr
===============================================================================
Reading MTRRs from a C program using ioctl()'s:
/* mtrr-show.c
Source file for mtrr-show (example program to show MTRRs using ioctl()'s)
Copyright (C) 1997-1998 Richard Gooch
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
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.
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., 675 Mass Ave, Cambridge, MA 02139, USA.
Richard Gooch may be reached by email at rgooch@atnf.csiro.au
The postal address is:
Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
*/
/*
This program will use an ioctl() on /proc/mtrr to show the current MTRR
settings. This is an alternative to reading /proc/mtrr.
Written by Richard Gooch 17-DEC-1997
Last updated by Richard Gooch 2-MAY-1998
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <errno.h>
#include <asm/mtrr.h>
#define TRUE 1
#define FALSE 0
#define ERRSTRING strerror (errno)
static char *mtrr_strings[MTRR_NUM_TYPES] =
{
"uncachable", /* 0 */
"write-combining", /* 1 */
"?", /* 2 */
"?", /* 3 */
"write-through", /* 4 */
"write-protect", /* 5 */
"write-back", /* 6 */
};
int main ()
{
int fd;
struct mtrr_gentry gentry;
if ( ( fd = open ("/proc/mtrr", O_RDONLY, 0) ) == -1 )
{
if (errno == ENOENT)
{
fputs ("/proc/mtrr not found: not supported or you don't have a PPro?\n",
stderr);
exit (1);
}
fprintf (stderr, "Error opening /proc/mtrr\t%s\n", ERRSTRING);
exit (2);
}
for (gentry.regnum = 0; ioctl (fd, MTRRIOC_GET_ENTRY, &gentry) == 0;
++gentry.regnum)
{
if (gentry.size < 1)
{
fprintf (stderr, "Register: %u disabled\n", gentry.regnum);
continue;
}
fprintf (stderr, "Register: %u base: 0x%lx size: 0x%lx type: %s\n",
gentry.regnum, gentry.base, gentry.size,
mtrr_strings[gentry.type]);
}
if (errno == EINVAL) exit (0);
fprintf (stderr, "Error doing ioctl(2) on /dev/mtrr\t%s\n", ERRSTRING);
exit (3);
} /* End Function main */
===============================================================================
Creating MTRRs from a C programme using ioctl()'s:
/* mtrr-add.c
Source file for mtrr-add (example programme to add an MTRRs using ioctl())
Copyright (C) 1997-1998 Richard Gooch
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
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.
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., 675 Mass Ave, Cambridge, MA 02139, USA.
Richard Gooch may be reached by email at rgooch@atnf.csiro.au
The postal address is:
Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
*/
/*
This programme will use an ioctl() on /proc/mtrr to add an entry. The first
available mtrr is used. This is an alternative to writing /proc/mtrr.
Written by Richard Gooch 17-DEC-1997
Last updated by Richard Gooch 2-MAY-1998
*/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <errno.h>
#include <asm/mtrr.h>
#define TRUE 1
#define FALSE 0
#define ERRSTRING strerror (errno)
static char *mtrr_strings[MTRR_NUM_TYPES] =
{
"uncachable", /* 0 */
"write-combining", /* 1 */
"?", /* 2 */
"?", /* 3 */
"write-through", /* 4 */
"write-protect", /* 5 */
"write-back", /* 6 */
};
int main (int argc, char **argv)
{
int fd;
struct mtrr_sentry sentry;
if (argc != 4)
{
fprintf (stderr, "Usage:\tmtrr-add base size type\n");
exit (1);
}
sentry.base = strtoul (argv[1], NULL, 0);
sentry.size = strtoul (argv[2], NULL, 0);
for (sentry.type = 0; sentry.type < MTRR_NUM_TYPES; ++sentry.type)
{
if (strcmp (argv[3], mtrr_strings[sentry.type]) == 0) break;
}
if (sentry.type >= MTRR_NUM_TYPES)
{
fprintf (stderr, "Illegal type: \"%s\"\n", argv[3]);
exit (2);
}
if ( ( fd = open ("/proc/mtrr", O_WRONLY, 0) ) == -1 )
{
if (errno == ENOENT)
{
fputs ("/proc/mtrr not found: not supported or you don't have a PPro?\n",
stderr);
exit (3);
}
fprintf (stderr, "Error opening /proc/mtrr\t%s\n", ERRSTRING);
exit (4);
}
if (ioctl (fd, MTRRIOC_ADD_ENTRY, &sentry) == -1)
{
fprintf (stderr, "Error doing ioctl(2) on /dev/mtrr\t%s\n", ERRSTRING);
exit (5);
}
fprintf (stderr, "Sleeping for 5 seconds so you can see the new entry\n");
sleep (5);
close (fd);
fputs ("I've just closed /proc/mtrr so now the new entry should be gone\n",
stderr);
} /* End Function main */
===============================================================================

46
Documentation/networking/LICENSE.qlge Normal file
View File

@ -0,0 +1,46 @@
Copyright (c) 2003-2008 QLogic Corporation
QLogic Linux Networking HBA Driver
This program includes a device driver for Linux 2.6 that may be
distributed with QLogic hardware specific firmware binary file.
You may modify and redistribute the device driver code under the
GNU General Public License as published by the Free Software
Foundation (version 2 or a later version).
You may redistribute the hardware specific firmware binary file
under the following terms:
1. Redistribution of source code (only if applicable),
must retain the above copyright notice, this list of
conditions and the following disclaimer.
2. Redistribution in binary form must reproduce the above
copyright notice, this list of conditions and the
following disclaimer in the documentation and/or other
materials provided with the distribution.
3. The name of QLogic Corporation may not be used to
endorse or promote products derived from this software
without specific prior written permission
REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
COMBINATION WITH THIS PROGRAM.

44
Documentation/networking/can.txt
View File

@ -35,8 +35,9 @@ This file contains
6.1 general settings
6.2 local loopback of sent frames
6.3 CAN controller hardware filters
6.4 currently supported CAN hardware
6.5 todo
6.4 The virtual CAN driver (vcan)
6.5 currently supported CAN hardware
6.6 todo
7 Credits
@ -584,7 +585,42 @@ solution for a couple of reasons:
@133MHz with four SJA1000 CAN controllers from 2002 under heavy bus
load without any problems ...
6.4 currently supported CAN hardware (September 2007)
6.4 The virtual CAN driver (vcan)
Similar to the network loopback devices, vcan offers a virtual local
CAN interface. A full qualified address on CAN consists of
- a unique CAN Identifier (CAN ID)
- the CAN bus this CAN ID is transmitted on (e.g. can0)
so in common use cases more than one virtual CAN interface is needed.
The virtual CAN interfaces allow the transmission and reception of CAN
frames without real CAN controller hardware. Virtual CAN network
devices are usually named 'vcanX', like vcan0 vcan1 vcan2 ...
When compiled as a module the virtual CAN driver module is called vcan.ko
Since Linux Kernel version 2.6.24 the vcan driver supports the Kernel
netlink interface to create vcan network devices. The creation and
removal of vcan network devices can be managed with the ip(8) tool:
- Create a virtual CAN network interface:
ip link add type vcan
- Create a virtual CAN network interface with a specific name 'vcan42':
ip link add dev vcan42 type vcan
- Remove a (virtual CAN) network interface 'vcan42':
ip link del vcan42
The tool 'vcan' from the SocketCAN SVN repository on BerliOS is obsolete.
Virtual CAN network device creation in older Kernels:
In Linux Kernel versions < 2.6.24 the vcan driver creates 4 vcan
netdevices at module load time by default. This value can be changed
with the module parameter 'numdev'. E.g. 'modprobe vcan numdev=8'
6.5 currently supported CAN hardware
On the project website http://developer.berlios.de/projects/socketcan
there are different drivers available:
@ -603,7 +639,7 @@ solution for a couple of reasons:
Please check the Mailing Lists on the berlios OSS project website.
6.5 todo (September 2007)
6.6 todo
The configuration interface for CAN network drivers is still an open
issue that has not been finalized in the socketcan project. Also the

54
Documentation/networking/multiqueue.txt
View File

@ -24,4 +24,56 @@ netif_{start|stop|wake}_subqueue() functions to manage each queue while the
device is still operational. netdev->queue_lock is still used when the device
comes online or when it's completely shut down (unregister_netdev(), etc.).
Author: Peter P. Waskiewicz Jr. <peter.p.waskiewicz.jr@intel.com>
Section 2: Qdisc support for multiqueue devices
-----------------------------------------------
Currently two qdiscs are optimized for multiqueue devices. The first is the
default pfifo_fast qdisc. This qdisc supports one qdisc per hardware queue.
A new round-robin qdisc, sch_multiq also supports multiple hardware queues. The
qdisc is responsible for classifying the skb's and then directing the skb's to
bands and queues based on the value in skb->queue_mapping. Use this field in
the base driver to determine which queue to send the skb to.
sch_multiq has been added for hardware that wishes to avoid head-of-line
blocking. It will cycle though the bands and verify that the hardware queue
associated with the band is not stopped prior to dequeuing a packet.
On qdisc load, the number of bands is based on the number of queues on the
hardware. Once the association is made, any skb with skb->queue_mapping set,
will be queued to the band associated with the hardware queue.
Section 3: Brief howto using MULTIQ for multiqueue devices
---------------------------------------------------------------
The userspace command 'tc,' part of the iproute2 package, is used to configure
qdiscs. To add the MULTIQ qdisc to your network device, assuming the device
is called eth0, run the following command:
# tc qdisc add dev eth0 root handle 1: multiq
The qdisc will allocate the number of bands to equal the number of queues that
the device reports, and bring the qdisc online. Assuming eth0 has 4 Tx
queues, the band mapping would look like:
band 0 => queue 0
band 1 => queue 1
band 2 => queue 2
band 3 => queue 3
Traffic will begin flowing through each queue based on either the simple_tx_hash
function or based on netdev->select_queue() if you have it defined.
The behavior of tc filters remains the same. However a new tc action,
skbedit, has been added. Assuming you wanted to route all traffic to a
specific host, for example 192.168.0.3, through a specific queue you could use
this action and establish a filter such as:
tc filter add dev eth0 parent 1: protocol ip prio 1 u32 \
match ip dst 192.168.0.3 \
action skbedit queue_mapping 3
Author: Alexander Duyck <alexander.h.duyck@intel.com>
Original Author: Peter P. Waskiewicz Jr. <peter.p.waskiewicz.jr@intel.com>

175
Documentation/networking/phonet.txt Normal file
View File

@ -0,0 +1,175 @@
Linux Phonet protocol family
============================
Introduction
------------
Phonet is a packet protocol used by Nokia cellular modems for both IPC
and RPC. With the Linux Phonet socket family, Linux host processes can
receive and send messages from/to the modem, or any other external
device attached to the modem. The modem takes care of routing.
Phonet packets can be exchanged through various hardware connections
depending on the device, such as:
- USB with the CDC Phonet interface,
- infrared,
- Bluetooth,
- an RS232 serial port (with a dedicated "FBUS" line discipline),
- the SSI bus with some TI OMAP processors.
Packets format
--------------
Phonet packets have a common header as follows:
struct phonethdr {
uint8_t pn_media; /* Media type (link-layer identifier) */
uint8_t pn_rdev; /* Receiver device ID */
uint8_t pn_sdev; /* Sender device ID */
uint8_t pn_res; /* Resource ID or function */
uint16_t pn_length; /* Big-endian message byte length (minus 6) */
uint8_t pn_robj; /* Receiver object ID */
uint8_t pn_sobj; /* Sender object ID */
};
On Linux, the link-layer header includes the pn_media byte (see below).
The next 7 bytes are part of the network-layer header.
The device ID is split: the 6 higher-order bits consitute the device
address, while the 2 lower-order bits are used for multiplexing, as are
the 8-bit object identifiers. As such, Phonet can be considered as a
network layer with 6 bits of address space and 10 bits for transport
protocol (much like port numbers in IP world).
The modem always has address number zero. All other device have a their
own 6-bit address.
Link layer
----------
Phonet links are always point-to-point links. The link layer header
consists of a single Phonet media type byte. It uniquely identifies the
link through which the packet is transmitted, from the modem's
perspective. Each Phonet network device shall prepend and set the media
type byte as appropriate. For convenience, a common phonet_header_ops
link-layer header operations structure is provided. It sets the
media type according to the network device hardware address.
Linux Phonet network interfaces support a dedicated link layer packets
type (ETH_P_PHONET) which is out of the Ethernet type range. They can
only send and receive Phonet packets.
The virtual TUN tunnel device driver can also be used for Phonet. This
requires IFF_TUN mode, _without_ the IFF_NO_PI flag. In this case,
there is no link-layer header, so there is no Phonet media type byte.
Note that Phonet interfaces are not allowed to re-order packets, so
only the (default) Linux FIFO qdisc should be used with them.
Network layer
-------------
The Phonet socket address family maps the Phonet packet header:
struct sockaddr_pn {
sa_family_t spn_family; /* AF_PHONET */
uint8_t spn_obj; /* Object ID */
uint8_t spn_dev; /* Device ID */
uint8_t spn_resource; /* Resource or function */
uint8_t spn_zero[...]; /* Padding */
};
The resource field is only used when sending and receiving;
It is ignored by bind() and getsockname().
Low-level datagram protocol
---------------------------
Applications can send Phonet messages using the Phonet datagram socket
protocol from the PF_PHONET family. Each socket is bound to one of the
2^10 object IDs available, and can send and receive packets with any
other peer.
struct sockaddr_pn addr = { .spn_family = AF_PHONET, };
ssize_t len;
socklen_t addrlen = sizeof(addr);
int fd;
fd = socket(PF_PHONET, SOCK_DGRAM, 0);
bind(fd, (struct sockaddr *)&addr, sizeof(addr));
/* ... */
sendto(fd, msg, msglen, 0, (struct sockaddr *)&addr, sizeof(addr));
len = recvfrom(fd, buf, sizeof(buf), 0,
(struct sockaddr *)&addr, &addrlen);
This protocol follows the SOCK_DGRAM connection-less semantics.
However, connect() and getpeername() are not supported, as they did
not seem useful with Phonet usages (could be added easily).
Phonet Pipe protocol
--------------------
The Phonet Pipe protocol is a simple sequenced packets protocol
with end-to-end congestion control. It uses the passive listening
socket paradigm. The listening socket is bound to an unique free object
ID. Each listening socket can handle up to 255 simultaneous
connections, one per accept()'d socket.
int lfd, cfd;
lfd = socket(PF_PHONET, SOCK_SEQPACKET, PN_PROTO_PIPE);
listen (lfd, INT_MAX);
/* ... */
cfd = accept(lfd, NULL, NULL);
for (;;)
{
char buf[...];
ssize_t len = read(cfd, buf, sizeof(buf));
/* ... */
write(cfd, msg, msglen);
}
Connections are established between two endpoints by a "third party"
application. This means that both endpoints are passive; so connect()
is not possible.
WARNING:
When polling a connected pipe socket for writability, there is an
intrinsic race condition whereby writability might be lost between the
polling and the writing system calls. In this case, the socket will
block until write because possible again, unless non-blocking mode
becomes enabled.
The pipe protocol provides two socket options at the SOL_PNPIPE level:
PNPIPE_ENCAP accepts one integer value (int) of:
PNPIPE_ENCAP_NONE: The socket operates normally (default).
PNPIPE_ENCAP_IP: The socket is used as a backend for a virtual IP
interface. This requires CAP_NET_ADMIN capability. GPRS data
support on Nokia modems can use this. Note that the socket cannot
be reliably poll()'d or read() from while in this mode.
PNPIPE_IFINDEX is a read-only integer value. It contains the
interface index of the network interface created by PNPIPE_ENCAP,
or zero if encapsulation is off.
Authors
-------
Linux Phonet was initially written by Sakari Ailus.
Other contributors include Mikä Liljeberg, Andras Domokos,
Carlos Chinea and Rémi Denis-Courmont.
Copyright (C) 2008 Nokia Corporation.

194
Documentation/networking/regulatory.txt Normal file
View File

@ -0,0 +1,194 @@
Linux wireless regulatory documentation
---------------------------------------
This document gives a brief review over how the Linux wireless
regulatory infrastructure works.
More up to date information can be obtained at the project's web page:
http://wireless.kernel.org/en/developers/Regulatory
Keeping regulatory domains in userspace
---------------------------------------
Due to the dynamic nature of regulatory domains we keep them
in userspace and provide a framework for userspace to upload
to the kernel one regulatory domain to be used as the central
core regulatory domain all wireless devices should adhere to.
How to get regulatory domains to the kernel
-------------------------------------------
Userspace gets a regulatory domain in the kernel by having
a userspace agent build it and send it via nl80211. Only
expected regulatory domains will be respected by the kernel.
A currently available userspace agent which can accomplish this
is CRDA - central regulatory domain agent. Its documented here:
http://wireless.kernel.org/en/developers/Regulatory/CRDA
Essentially the kernel will send a udev event when it knows
it needs a new regulatory domain. A udev rule can be put in place
to trigger crda to send the respective regulatory domain for a
specific ISO/IEC 3166 alpha2.
Below is an example udev rule which can be used:
# Example file, should be put in /etc/udev/rules.d/regulatory.rules
KERNEL=="regulatory*", ACTION=="change", SUBSYSTEM=="platform", RUN+="/sbin/crda"
The alpha2 is passed as an environment variable under the variable COUNTRY.
Who asks for regulatory domains?
--------------------------------
* Users
Users can use iw:
http://wireless.kernel.org/en/users/Documentation/iw
An example:
# set regulatory domain to "Costa Rica"
iw reg set CR
This will request the kernel to set the regulatory domain to
the specificied alpha2. The kernel in turn will then ask userspace
to provide a regulatory domain for the alpha2 specified by the user
by sending a uevent.
* Wireless subsystems for Country Information elements
The kernel will send a uevent to inform userspace a new
regulatory domain is required. More on this to be added
as its integration is added.
* Drivers
If drivers determine they need a specific regulatory domain
set they can inform the wireless core using regulatory_hint().
They have two options -- they either provide an alpha2 so that
crda can provide back a regulatory domain for that country or
they can build their own regulatory domain based on internal
custom knowledge so the wireless core can respect it.
*Most* drivers will rely on the first mechanism of providing a
regulatory hint with an alpha2. For these drivers there is an additional
check that can be used to ensure compliance based on custom EEPROM
regulatory data. This additional check can be used by drivers by
registering on its struct wiphy a reg_notifier() callback. This notifier
is called when the core's regulatory domain has been changed. The driver
can use this to review the changes made and also review who made them
(driver, user, country IE) and determine what to allow based on its
internal EEPROM data. Devices drivers wishing to be capable of world
roaming should use this callback. More on world roaming will be
added to this document when its support is enabled.
Device drivers who provide their own built regulatory domain
do not need a callback as the channels registered by them are
the only ones that will be allowed and therefore *additional*
cannels cannot be enabled.
Example code - drivers hinting an alpha2:
------------------------------------------
This example comes from the zd1211rw device driver. You can start
by having a mapping of your device's EEPROM country/regulatory
domain value to to a specific alpha2 as follows:
static struct zd_reg_alpha2_map reg_alpha2_map[] = {
{ ZD_REGDOMAIN_FCC, "US" },
{ ZD_REGDOMAIN_IC, "CA" },
{ ZD_REGDOMAIN_ETSI, "DE" }, /* Generic ETSI, use most restrictive */
{ ZD_REGDOMAIN_JAPAN, "JP" },
{ ZD_REGDOMAIN_JAPAN_ADD, "JP" },
{ ZD_REGDOMAIN_SPAIN, "ES" },
{ ZD_REGDOMAIN_FRANCE, "FR" },
Then you can define a routine to map your read EEPROM value to an alpha2,
as follows:
static int zd_reg2alpha2(u8 regdomain, char *alpha2)
{
unsigned int i;
struct zd_reg_alpha2_map *reg_map;
for (i = 0; i < ARRAY_SIZE(reg_alpha2_map); i++) {
reg_map = &reg_alpha2_map[i];
if (regdomain == reg_map->reg) {
alpha2[0] = reg_map->alpha2[0];
alpha2[1] = reg_map->alpha2[1];
return 0;
}
}
return 1;
}
Lastly, you can then hint to the core of your discovered alpha2, if a match
was found. You need to do this after you have registered your wiphy. You
are expected to do this during initialization.
r = zd_reg2alpha2(mac->regdomain, alpha2);
if (!r)
regulatory_hint(hw->wiphy, alpha2, NULL);
Example code - drivers providing a built in regulatory domain:
--------------------------------------------------------------
If you have regulatory information you can obtain from your
driver and you *need* to use this we let you build a regulatory domain
structure and pass it to the wireless core. To do this you should
kmalloc() a structure big enough to hold your regulatory domain
structure and you should then fill it with your data. Finally you simply
call regulatory_hint() with the regulatory domain structure in it.
Bellow is a simple example, with a regulatory domain cached using the stack.
Your implementation may vary (read EEPROM cache instead, for example).
Example cache of some regulatory domain
struct ieee80211_regdomain mydriver_jp_regdom = {
.n_reg_rules = 3,
.alpha2 = "JP",
//.alpha2 = "99", /* If I have no alpha2 to map it to */
.reg_rules = {
/* IEEE 802.11b/g, channels 1..14 */
REG_RULE(2412-20, 2484+20, 40, 6, 20, 0),
/* IEEE 802.11a, channels 34..48 */
REG_RULE(5170-20, 5240+20, 40, 6, 20,
NL80211_RRF_PASSIVE_SCAN),
/* IEEE 802.11a, channels 52..64 */
REG_RULE(5260-20, 5320+20, 40, 6, 20,
NL80211_RRF_NO_IBSS |
NL80211_RRF_DFS),
}
};
Then in some part of your code after your wiphy has been registered:
int r;
struct ieee80211_regdomain *rd;
int size_of_regd;
int num_rules = mydriver_jp_regdom.n_reg_rules;
unsigned int i;
size_of_regd = sizeof(struct ieee80211_regdomain) +
(num_rules * sizeof(struct ieee80211_reg_rule));
rd = kzalloc(size_of_regd, GFP_KERNEL);
if (!rd)
return -ENOMEM;
memcpy(rd, &mydriver_jp_regdom, sizeof(struct ieee80211_regdomain));
for (i=0; i < num_rules; i++) {
memcpy(&rd->reg_rules[i], &mydriver_jp_regdom.reg_rules[i],
sizeof(struct ieee80211_reg_rule));
}
r = regulatory_hint(hw->wiphy, NULL, rd);
if (r) {
kfree(rd);
return r;
}

85
Documentation/networking/tproxy.txt Normal file
View File

@ -0,0 +1,85 @@
Transparent proxy support
=========================
This feature adds Linux 2.2-like transparent proxy support to current kernels.
To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in
your kernel config. You will need policy routing too, so be sure to enable that
as well.
1. Making non-local sockets work
================================
The idea is that you identify packets with destination address matching a local
socket on your box, set the packet mark to a certain value, and then match on that
value using policy routing to have those packets delivered locally:
# iptables -t mangle -N DIVERT
# iptables -t mangle -A PREROUTING -p tcp -m socket -j DIVERT
# iptables -t mangle -A DIVERT -j MARK --set-mark 1
# iptables -t mangle -A DIVERT -j ACCEPT
# ip rule add fwmark 1 lookup 100
# ip route add local 0.0.0.0/0 dev lo table 100
Because of certain restrictions in the IPv4 routing output code you'll have to
modify your application to allow it to send datagrams _from_ non-local IP
addresses. All you have to do is enable the (SOL_IP, IP_TRANSPARENT) socket
option before calling bind:
fd = socket(AF_INET, SOCK_STREAM, 0);
/* - 8< -*/
int value = 1;
setsockopt(fd, SOL_IP, IP_TRANSPARENT, &value, sizeof(value));
/* - 8< -*/
name.sin_family = AF_INET;
name.sin_port = htons(0xCAFE);
name.sin_addr.s_addr = htonl(0xDEADBEEF);
bind(fd, &name, sizeof(name));
A trivial patch for netcat is available here:
http://people.netfilter.org/hidden/tproxy/netcat-ip_transparent-support.patch
2. Redirecting traffic
======================
Transparent proxying often involves "intercepting" traffic on a router. This is
usually done with the iptables REDIRECT target; however, there are serious
limitations of that method. One of the major issues is that it actually
modifies the packets to change the destination address -- which might not be
acceptable in certain situations. (Think of proxying UDP for example: you won't
be able to find out the original destination address. Even in case of TCP
getting the original destination address is racy.)
The 'TPROXY' target provides similar functionality without relying on NAT. Simply
add rules like this to the iptables ruleset above:
# iptables -t mangle -A PREROUTING -p tcp --dport 80 -j TPROXY \
--tproxy-mark 0x1/0x1 --on-port 50080
Note that for this to work you'll have to modify the proxy to enable (SOL_IP,
IP_TRANSPARENT) for the listening socket.
3. Iptables extensions
======================
To use tproxy you'll need to have the 'socket' and 'TPROXY' modules
compiled for iptables. A patched version of iptables is available
here: http://git.balabit.hu/?p=bazsi/iptables-tproxy.git
4. Application support
======================
4.1. Squid
----------
Squid 3.HEAD has support built-in. To use it, pass
'--enable-linux-netfilter' to configure and set the 'tproxy' option on
the HTTP listener you redirect traffic to with the TPROXY iptables
target.
For more information please consult the following page on the Squid
wiki: http://wiki.squid-cache.org/Features/Tproxy4

6
Documentation/pcmcia/driver-changes.txt
View File

@ -1,5 +1,11 @@
This file details changes in 2.6 which affect PCMCIA card driver authors:
* New configuration loop helper (as of 2.6.28)
By calling pcmcia_loop_config(), a driver can iterate over all available
configuration options. During a driver's probe() phase, one doesn't need
to use pcmcia_get_{first,next}_tuple, pcmcia_get_tuple_data and
pcmcia_parse_tuple directly in most if not all cases.
* New release helper (as of 2.6.17)
Instead of calling pcmcia_release_{configuration,io,irq,win}, all that's
necessary now is calling pcmcia_disable_device. As there is no valid

32
Documentation/rfkill.txt
View File

@ -341,6 +341,8 @@ key that does nothing by itself, as well as any hot key that is type-specific
3.1 Guidelines for wireless device drivers
------------------------------------------
(in this text, rfkill->foo means the foo field of struct rfkill).
1. Each independent transmitter in a wireless device (usually there is only one
transmitter per device) should have a SINGLE rfkill class attached to it.
@ -363,10 +365,32 @@ This rule exists because users of the rfkill subsystem expect to get (and set,
when possible) the overall transmitter rfkill state, not of a particular rfkill
line.
5. During suspend, the rfkill class will attempt to soft-block the radio
through a call to rfkill->toggle_radio, and will try to restore its previous
state during resume. After a rfkill class is suspended, it will *not* call
rfkill->toggle_radio until it is resumed.
5. The wireless device driver MUST NOT leave the transmitter enabled during
suspend and hibernation unless:
5.1. The transmitter has to be enabled for some sort of functionality
like wake-on-wireless-packet or autonomous packed forwarding in a mesh
network, and that functionality is enabled for this suspend/hibernation
cycle.
AND
5.2. The device was not on a user-requested BLOCKED state before
the suspend (i.e. the driver must NOT unblock a device, not even
to support wake-on-wireless-packet or remain in the mesh).
In other words, there is absolutely no allowed scenario where a driver can
automatically take action to unblock a rfkill controller (obviously, this deals
with scenarios where soft-blocking or both soft and hard blocking is happening.
Scenarios where hardware rfkill lines are the only ones blocking the
transmitter are outside of this rule, since the wireless device driver does not
control its input hardware rfkill lines in the first place).
6. During resume, rfkill will try to restore its previous state.
7. After a rfkill class is suspended, it will *not* call rfkill->toggle_radio
until it is resumed.
Example of a WLAN wireless driver connected to the rfkill subsystem:
--------------------------------------------------------------------

11
Documentation/s390/CommonIO
View File

@ -70,13 +70,19 @@ Command line parameters
Note: While already known devices can be added to the list of devices to be
ignored, there will be no effect on then. However, if such a device
disappears and then reappears, it will then be ignored.
disappears and then reappears, it will then be ignored. To make
known devices go away, you need the "purge" command (see below).
For example,
"echo add 0.0.a000-0.0.accc, 0.0.af00-0.0.afff > /proc/cio_ignore"
will add 0.0.a000-0.0.accc and 0.0.af00-0.0.afff to the list of ignored
devices.
You can remove already known but now ignored devices via
"echo purge > /proc/cio_ignore"
All devices ignored but still registered and not online (= not in use)
will be deregistered and thus removed from the system.
The devices can be specified either by bus id (0.x.abcd) or, for 2.4 backward
compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
numbers given as 0xabcd will be interpreted as 0.0.abcd.
@ -98,8 +104,7 @@ debugfs entries
handling).
- /sys/kernel/debug/s390dbf/cio_msg/sprintf
Various debug messages from the common I/O-layer, including messages
printed when cio_msg=yes.
Various debug messages from the common I/O-layer.
- /sys/kernel/debug/s390dbf/cio_trace/hex_ascii
Logs the calling of functions in the common I/O-layer and, if applicable,

387
Documentation/scheduler/sched-design-CFS.txt
View File

@ -1,151 +1,242 @@
This is the CFS scheduler.
80% of CFS's design can be summed up in a single sentence: CFS basically
models an "ideal, precise multi-tasking CPU" on real hardware.
"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100%
physical power and which can run each task at precise equal speed, in
parallel, each at 1/nr_running speed. For example: if there are 2 tasks
running then it runs each at 50% physical power - totally in parallel.
On real hardware, we can run only a single task at once, so while that
one task runs, the other tasks that are waiting for the CPU are at a
disadvantage - the current task gets an unfair amount of CPU time. In
CFS this fairness imbalance is expressed and tracked via the per-task
p->wait_runtime (nanosec-unit) value. "wait_runtime" is the amount of
time the task should now run on the CPU for it to become completely fair
and balanced.
( small detail: on 'ideal' hardware, the p->wait_runtime value would
always be zero - no task would ever get 'out of balance' from the
'ideal' share of CPU time. )
CFS's task picking logic is based on this p->wait_runtime value and it
is thus very simple: it always tries to run the task with the largest
p->wait_runtime value. In other words, CFS tries to run the task with
the 'gravest need' for more CPU time. So CFS always tries to split up
CPU time between runnable tasks as close to 'ideal multitasking
hardware' as possible.
Most of the rest of CFS's design just falls out of this really simple
concept, with a few add-on embellishments like nice levels,
multiprocessing and various algorithm variants to recognize sleepers.
In practice it works like this: the system runs a task a bit, and when
the task schedules (or a scheduler tick happens) the task's CPU usage is
'accounted for': the (small) time it just spent using the physical CPU
is deducted from p->wait_runtime. [minus the 'fair share' it would have
gotten anyway]. Once p->wait_runtime gets low enough so that another
task becomes the 'leftmost task' of the time-ordered rbtree it maintains
(plus a small amount of 'granularity' distance relative to the leftmost
task so that we do not over-schedule tasks and trash the cache) then the
new leftmost task is picked and the current task is preempted.
The rq->fair_clock value tracks the 'CPU time a runnable task would have
fairly gotten, had it been runnable during that time'. So by using
rq->fair_clock values we can accurately timestamp and measure the
'expected CPU time' a task should have gotten. All runnable tasks are
sorted in the rbtree by the "rq->fair_clock - p->wait_runtime" key, and
CFS picks the 'leftmost' task and sticks to it. As the system progresses
forwards, newly woken tasks are put into the tree more and more to the
right - slowly but surely giving a chance for every task to become the
'leftmost task' and thus get on the CPU within a deterministic amount of
time.
Some implementation details:
- the introduction of Scheduling Classes: an extensible hierarchy of
scheduler modules. These modules encapsulate scheduling policy
details and are handled by the scheduler core without the core
code assuming about them too much.
- sched_fair.c implements the 'CFS desktop scheduler': it is a
replacement for the vanilla scheduler's SCHED_OTHER interactivity
code.
I'd like to give credit to Con Kolivas for the general approach here:
he has proven via RSDL/SD that 'fair scheduling' is possible and that
it results in better desktop scheduling. Kudos Con!
The CFS patch uses a completely different approach and implementation
from RSDL/SD. My goal was to make CFS's interactivity quality exceed
that of RSDL/SD, which is a high standard to meet :-) Testing
feedback is welcome to decide this one way or another. [ and, in any
case, all of SD's logic could be added via a kernel/sched_sd.c module
as well, if Con is interested in such an approach. ]
CFS's design is quite radical: it does not use runqueues, it uses a
time-ordered rbtree to build a 'timeline' of future task execution,
and thus has no 'array switch' artifacts (by which both the vanilla
scheduler and RSDL/SD are affected).
CFS uses nanosecond granularity accounting and does not rely on any
jiffies or other HZ detail. Thus the CFS scheduler has no notion of
'timeslices' and has no heuristics whatsoever. There is only one
central tunable (you have to switch on CONFIG_SCHED_DEBUG):
/proc/sys/kernel/sched_granularity_ns
which can be used to tune the scheduler from 'desktop' (low
latencies) to 'server' (good batching) workloads. It defaults to a
setting suitable for desktop workloads. SCHED_BATCH is handled by the
CFS scheduler module too.
Due to its design, the CFS scheduler is not prone to any of the
'attacks' that exist today against the heuristics of the stock
scheduler: fiftyp.c, thud.c, chew.c, ring-test.c, massive_intr.c all
work fine and do not impact interactivity and produce the expected
behavior.
the CFS scheduler has a much stronger handling of nice levels and
SCHED_BATCH: both types of workloads should be isolated much more
agressively than under the vanilla scheduler.
( another detail: due to nanosec accounting and timeline sorting,
sched_yield() support is very simple under CFS, and in fact under
CFS sched_yield() behaves much better than under any other
scheduler i have tested so far. )
- sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler
way than the vanilla scheduler does. It uses 100 runqueues (for all
100 RT priority levels, instead of 140 in the vanilla scheduler)
and it needs no expired array.
- reworked/sanitized SMP load-balancing: the runqueue-walking
assumptions are gone from the load-balancing code now, and
iterators of the scheduling modules are used. The balancing code got
quite a bit simpler as a result.
=============
CFS Scheduler
=============
Group scheduler extension to CFS
================================
1. OVERVIEW
Normally the scheduler operates on individual tasks and strives to provide
fair CPU time to each task. Sometimes, it may be desirable to group tasks
and provide fair CPU time to each such task group. For example, it may
be desirable to first provide fair CPU time to each user on the system
and then to each task belonging to a user.
CFS stands for "Completely Fair Scheduler," and is the new "desktop" process
scheduler implemented by Ingo Molnar and merged in Linux 2.6.23. It is the
replacement for the previous vanilla scheduler's SCHED_OTHER interactivity
code.
CONFIG_FAIR_GROUP_SCHED strives to achieve exactly that. It lets
SCHED_NORMAL/BATCH tasks be be grouped and divides CPU time fairly among such
groups. At present, there are two (mutually exclusive) mechanisms to group
tasks for CPU bandwidth control purpose:
80% of CFS's design can be summed up in a single sentence: CFS basically models
an "ideal, precise multi-tasking CPU" on real hardware.
- Based on user id (CONFIG_FAIR_USER_SCHED)
In this option, tasks are grouped according to their user id.
- Based on "cgroup" pseudo filesystem (CONFIG_FAIR_CGROUP_SCHED)
This options lets the administrator create arbitrary groups
of tasks, using the "cgroup" pseudo filesystem. See
Documentation/cgroups.txt for more information about this
filesystem.
"Ideal multi-tasking CPU" is a (non-existent :-)) CPU that has 100% physical
power and which can run each task at precise equal speed, in parallel, each at
1/nr_running speed. For example: if there are 2 tasks running, then it runs
each at 50% physical power --- i.e., actually in parallel.
On real hardware, we can run only a single task at once, so we have to
introduce the concept of "virtual runtime." The virtual runtime of a task
specifies when its next timeslice would start execution on the ideal
multi-tasking CPU described above. In practice, the virtual runtime of a task
is its actual runtime normalized to the total number of running tasks.
2. FEW IMPLEMENTATION DETAILS
In CFS the virtual runtime is expressed and tracked via the per-task
p->se.vruntime (nanosec-unit) value. This way, it's possible to accurately
timestamp and measure the "expected CPU time" a task should have gotten.
[ small detail: on "ideal" hardware, at any time all tasks would have the same
p->se.vruntime value --- i.e., tasks would execute simultaneously and no task
would ever get "out of balance" from the "ideal" share of CPU time. ]
CFS's task picking logic is based on this p->se.vruntime value and it is thus
very simple: it always tries to run the task with the smallest p->se.vruntime
value (i.e., the task which executed least so far). CFS always tries to split
up CPU time between runnable tasks as close to "ideal multitasking hardware" as
possible.
Most of the rest of CFS's design just falls out of this really simple concept,
with a few add-on embellishments like nice levels, multiprocessing and various
algorithm variants to recognize sleepers.
3. THE RBTREE
CFS's design is quite radical: it does not use the old data structures for the
runqueues, but it uses a time-ordered rbtree to build a "timeline" of future
task execution, and thus has no "array switch" artifacts (by which both the
previous vanilla scheduler and RSDL/SD are affected).
CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic
increasing value tracking the smallest vruntime among all tasks in the
runqueue. The total amount of work done by the system is tracked using
min_vruntime; that value is used to place newly activated entities on the left
side of the tree as much as possible.
The total number of running tasks in the runqueue is accounted through the
rq->cfs.load value, which is the sum of the weights of the tasks queued on the
runqueue.
CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
p->se.vruntime key (there is a subtraction using rq->cfs.min_vruntime to
account for possible wraparounds). CFS picks the "leftmost" task from this
tree and sticks to it.
As the system progresses forwards, the executed tasks are put into the tree
more and more to the right --- slowly but surely giving a chance for every task
to become the "leftmost task" and thus get on the CPU within a deterministic
amount of time.
Summing up, CFS works like this: it runs a task a bit, and when the task
schedules (or a scheduler tick happens) the task's CPU usage is "accounted
for": the (small) time it just spent using the physical CPU is added to
p->se.vruntime. Once p->se.vruntime gets high enough so that another task
becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a
small amount of "granularity" distance relative to the leftmost task so that we
do not over-schedule tasks and trash the cache), then the new leftmost task is
picked and the current task is preempted.
4. SOME FEATURES OF CFS
CFS uses nanosecond granularity accounting and does not rely on any jiffies or
other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the
way the previous scheduler had, and has no heuristics whatsoever. There is
only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
/proc/sys/kernel/sched_granularity_ns
which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
"server" (i.e., good batching) workloads. It defaults to a setting suitable
for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too.
Due to its design, the CFS scheduler is not prone to any of the "attacks" that
exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c,
chew.c, ring-test.c, massive_intr.c all work fine and do not impact
interactivity and produce the expected behavior.
The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH
than the previous vanilla scheduler: both types of workloads are isolated much
more aggressively.
SMP load-balancing has been reworked/sanitized: the runqueue-walking
assumptions are gone from the load-balancing code now, and iterators of the
scheduling modules are used. The balancing code got quite a bit simpler as a
result.
5. Scheduling policies
CFS implements three scheduling policies:
- SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling
policy that is used for regular tasks.
- SCHED_BATCH: Does not preempt nearly as often as regular tasks
would, thereby allowing tasks to run longer and make better use of
caches but at the cost of interactivity. This is well suited for
batch jobs.
- SCHED_IDLE: This is even weaker than nice 19, but its not a true
idle timer scheduler in order to avoid to get into priority
inversion problems which would deadlock the machine.
SCHED_FIFO/_RR are implemented in sched_rt.c and are as specified by
POSIX.
The command chrt from util-linux-ng 2.13.1.1 can set all of these except
SCHED_IDLE.
6. SCHEDULING CLASSES
The new CFS scheduler has been designed in such a way to introduce "Scheduling
Classes," an extensible hierarchy of scheduler modules. These modules
encapsulate scheduling policy details and are handled by the scheduler core
without the core code assuming too much about them.
sched_fair.c implements the CFS scheduler described above.
sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than
the previous vanilla scheduler did. It uses 100 runqueues (for all 100 RT
priority levels, instead of 140 in the previous scheduler) and it needs no
expired array.
Scheduling classes are implemented through the sched_class structure, which
contains hooks to functions that must be called whenever an interesting event
occurs.
This is the (partial) list of the hooks:
- enqueue_task(...)
Called when a task enters a runnable state.
It puts the scheduling entity (task) into the red-black tree and
increments the nr_running variable.
- dequeue_tree(...)
When a task is no longer runnable, this function is called to keep the
corresponding scheduling entity out of the red-black tree. It decrements
the nr_running variable.
- yield_task(...)
This function is basically just a dequeue followed by an enqueue, unless the
compat_yield sysctl is turned on; in that case, it places the scheduling
entity at the right-most end of the red-black tree.
- check_preempt_curr(...)
This function checks if a task that entered the runnable state should
preempt the currently running task.
- pick_next_task(...)
This function chooses the most appropriate task eligible to run next.
- set_curr_task(...)
This function is called when a task changes its scheduling class or changes
its task group.
- task_tick(...)
This function is mostly called from time tick functions; it might lead to
process switch. This drives the running preemption.
- task_new(...)
The core scheduler gives the scheduling module an opportunity to manage new
task startup. The CFS scheduling module uses it for group scheduling, while
the scheduling module for a real-time task does not use it.
7. GROUP SCHEDULER EXTENSIONS TO CFS
Normally, the scheduler operates on individual tasks and strives to provide
fair CPU time to each task. Sometimes, it may be desirable to group tasks and
provide fair CPU time to each such task group. For example, it may be
desirable to first provide fair CPU time to each user on the system and then to
each task belonging to a user.
CONFIG_GROUP_SCHED strives to achieve exactly that. It lets tasks to be
grouped and divides CPU time fairly among such groups.
CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
SCHED_RR) tasks.
CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
SCHED_BATCH) tasks.
At present, there are two (mutually exclusive) mechanisms to group tasks for
CPU bandwidth control purposes:
- Based on user id (CONFIG_USER_SCHED)
With this option, tasks are grouped according to their user id.
- Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
This options needs CONFIG_CGROUPS to be defined, and lets the administrator
create arbitrary groups of tasks, using the "cgroup" pseudo filesystem. See
Documentation/cgroups.txt for more information about this filesystem.
Only one of these options to group tasks can be chosen and not both.
Group scheduler tunables:
When CONFIG_FAIR_USER_SCHED is defined, a directory is created in sysfs for
each new user and a "cpu_share" file is added in that directory.
When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
user and a "cpu_share" file is added in that directory.
# cd /sys/kernel/uids
# cat 512/cpu_share # Display user 512's CPU share
@ -155,16 +246,14 @@ each new user and a "cpu_share" file is added in that directory.
2048
#
CPU bandwidth between two users are divided in the ratio of their CPU shares.
For ex: if you would like user "root" to get twice the bandwidth of user
"guest", then set the cpu_share for both the users such that "root"'s
cpu_share is twice "guest"'s cpu_share
CPU bandwidth between two users is divided in the ratio of their CPU shares.
For example: if you would like user "root" to get twice the bandwidth of user
"guest," then set the cpu_share for both the users such that "root"'s cpu_share
is twice "guest"'s cpu_share.
When CONFIG_FAIR_CGROUP_SCHED is defined, a "cpu.shares" file is created
for each group created using the pseudo filesystem. See example steps
below to create task groups and modify their CPU share using the "cgroups"
pseudo filesystem
When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
group created using the pseudo filesystem. See example steps below to create
task groups and modify their CPU share using the "cgroups" pseudo filesystem.
# mkdir /dev/cpuctl
# mount -t cgroup -ocpu none /dev/cpuctl

36
Documentation/scsi/scsi_fc_transport.txt
View File

@ -436,6 +436,42 @@ Other:
was updated to remove all vports for the fc_host as well.
Transport supplied functions
----------------------------
The following functions are supplied by the FC-transport for use by LLDs.
fc_vport_create - create a vport
fc_vport_terminate - detach and remove a vport
Details:
/**
* fc_vport_create - Admin App or LLDD requests creation of a vport
* @shost: scsi host the virtual port is connected to.
* @ids: The world wide names, FC4 port roles, etc for
* the virtual port.
*
* Notes:
* This routine assumes no locks are held on entry.
*/
struct fc_vport *
fc_vport_create(struct Scsi_Host *shost, struct fc_vport_identifiers *ids)
/**
* fc_vport_terminate - Admin App or LLDD requests termination of a vport
* @vport: fc_vport to be terminated
*
* Calls the LLDD vport_delete() function, then deallocates and removes
* the vport from the shost and object tree.
*
* Notes:
* This routine assumes no locks are held on entry.
*/
int
fc_vport_terminate(struct fc_vport *vport)
Credits
=======
The following people have contributed to this document:

62
Documentation/sound/alsa/ALSA-Configuration.txt
View File

@ -746,8 +746,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
Module snd-hda-intel
--------------------
Module for Intel HD Audio (ICH6, ICH6M, ESB2, ICH7, ICH8),
ATI SB450, SB600, RS600,
Module for Intel HD Audio (ICH6, ICH6M, ESB2, ICH7, ICH8, ICH9, ICH10,
PCH, SCH),
ATI SB450, SB600, R600, RS600, RS690, RS780, RV610, RV620,
RV630, RV635, RV670, RV770,
VIA VT8251/VT8237A,
SIS966, ULI M5461
@ -807,6 +809,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ALC260
hp HP machines
hp-3013 HP machines (3013-variant)
hp-dc7600 HP DC7600
fujitsu Fujitsu S7020
acer Acer TravelMate
will Will laptops (PB V7900)
@ -828,8 +831,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
hippo Hippo (ATI) with jack detection, Sony UX-90s
hippo_1 Hippo (Benq) with jack detection
sony-assamd Sony ASSAMD
toshiba-s06 Toshiba S06
toshiba-rx1 Toshiba RX1
ultra Samsung Q1 Ultra Vista model
lenovo-3000 Lenovo 3000 y410
nec NEC Versa S9100
basic fixed pin assignment w/o SPDIF
auto auto-config reading BIOS (default)
@ -838,6 +844,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
3stack 3-stack model
toshiba Toshiba A205
acer Acer laptops
acer-aspire Acer Aspire One
dell Dell OEM laptops (Vostro 1200)
zepto Zepto laptops
test for testing/debugging purpose, almost all controls can
@ -847,6 +854,9 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
ALC269
basic Basic preset
quanta Quanta FL1
eeepc-p703 ASUS Eeepc P703 P900A
eeepc-p901 ASUS Eeepc P901 S101
ALC662/663
3stack-dig 3-stack (2-channel) with SPDIF
@ -856,10 +866,17 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
lenovo-101e Lenovo laptop
eeepc-p701 ASUS Eeepc P701
eeepc-ep20 ASUS Eeepc EP20
ecs ECS/Foxconn mobo
m51va ASUS M51VA
g71v ASUS G71V
h13 ASUS H13
g50v ASUS G50V
asus-mode1 ASUS
asus-mode2 ASUS
asus-mode3 ASUS
asus-mode4 ASUS
asus-mode5 ASUS
asus-mode6 ASUS
auto auto-config reading BIOS (default)
ALC882/885
@ -891,12 +908,14 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
lenovo-101e Lenovo 101E
lenovo-nb0763 Lenovo NB0763
lenovo-ms7195-dig Lenovo MS7195
lenovo-sky Lenovo Sky
haier-w66 Haier W66
3stack-hp HP machines with 3stack (Lucknow, Samba boards)
6stack-dell Dell machines with 6stack (Inspiron 530)
mitac Mitac 8252D
clevo-m720 Clevo M720 laptop series
fujitsu-pi2515 Fujitsu AMILO Pi2515
3stack-6ch-intel Intel DG33* boards
auto auto-config reading BIOS (default)
ALC861/660
@ -929,7 +948,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
allout 5-jack in back, 2-jack in front, SPDIF out
auto auto-config reading BIOS (default)
AD1882
AD1882 / AD1882A
3stack 3-stack mode (default)
6stack 6-stack mode
@ -1079,7 +1098,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
register value without FIFO size correction as the current
DMA pointer. position_fix=2 will make the driver to use
the position buffer instead of reading SD_LPIB register.
(Usually SD_LPLIB register is more accurate than the
(Usually SD_LPIB register is more accurate than the
position buffer.)
NB: If you get many "azx_get_response timeout" messages at
@ -1166,6 +1185,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* Event Electronics, EZ8
* Digigram VX442
* Lionstracs, Mediastaton
* Terrasoniq TS 88
model - Use the given board model, one of the following:
delta1010, dio2496, delta66, delta44, audiophile, delta410,
@ -1200,7 +1220,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* TerraTec Phase 22
* TerraTec Phase 28
* AudioTrak Prodigy 7.1
* AudioTrak Prodigy 7.1LT
* AudioTrak Prodigy 7.1 LT
* AudioTrak Prodigy 7.1 XT
* AudioTrak Prodigy 7.1 HIFI
* AudioTrak Prodigy 7.1 HD2
* AudioTrak Prodigy 192
* Pontis MS300
* Albatron K8X800 Pro II
@ -1211,12 +1234,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* Shuttle SN25P
* Onkyo SE-90PCI
* Onkyo SE-200PCI
* ESI Juli@
* Hercules Fortissimo IV
* EGO-SYS WaveTerminal 192M
model - Use the given board model, one of the following:
revo51, revo71, amp2000, prodigy71, prodigy71lt,
prodigy192, aureon51, aureon71, universe, ap192,
k8x800, phase22, phase28, ms300, av710, se200pci,
se90pci
prodigy71xt, prodigy71hifi, prodigyhd2, prodigy192,
juli, aureon51, aureon71, universe, ap192, k8x800,
phase22, phase28, ms300, av710, se200pci, se90pci,
fortissimo4, sn25p, WT192M
This module supports multiple cards and autoprobe.
@ -1255,7 +1282,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
Module for AC'97 motherboards from Intel and compatibles.
* Intel i810/810E, i815, i820, i830, i84x, MX440
ICH5, ICH6, ICH7, ESB2
ICH5, ICH6, ICH7, 6300ESB, ESB2
* SiS 7012 (SiS 735)
* NVidia NForce, NForce2, NForce3, MCP04, CK804
CK8, CK8S, MCP501
@ -1951,6 +1978,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
* CHIC True Sound 4Dwave
* Shark Predator4D-PCI
* Jaton SonicWave 4D
* SiS SI7018 PCI Audio
* Hoontech SoundTrack Digital 4DWave NX
pcm_channels - max channels (voices) reserved for PCM
wavetable_size - max wavetable size in kB (4-?kb)
@ -1966,12 +1995,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
vid - Vendor ID for the device (optional)
pid - Product ID for the device (optional)
nrpacks - Max. number of packets per URB (default: 8)
async_unlink - Use async unlink mode (default: yes)
device_setup - Device specific magic number (optional)
- Influence depends on the device
- Default: 0x0000
ignore_ctl_error - Ignore any USB-controller regarding mixer
interface (default: no)
This module supports multiple devices, autoprobe and hotplugging.
NB: nrpacks parameter can be modified dynamically via sysfs.
Don't put the value over 20. Changing via sysfs has no sanity
check.
NB: async_unlink=0 would cause Oops. It remains just for
debugging purpose (if any).
NB: ignore_ctl_error=1 may help when you get an error at accessing
the mixer element such as URB error -22. This happens on some
buggy USB device or the controller.
Module snd-usb-caiaq
--------------------
@ -2078,7 +2120,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
-------------------
Module for sound cards based on the Asus AV100/AV200 chips,
i.e., Xonar D1, DX, D2 and D2X.
i.e., Xonar D1, DX, D2, D2X and HDAV1.3 (Deluxe).
This module supports autoprobe and multiple cards.

73
Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
View File

@ -5073,8 +5073,7 @@ struct _snd_pcm_runtime {
with <constant>SNDRV_DMA_TYPE_CONTINUOUS</constant> type and the
<function>snd_dma_continuous_data(GFP_KERNEL)</function> device pointer,
where <constant>GFP_KERNEL</constant> is the kernel allocation flag to
use. For the SBUS, <constant>SNDRV_DMA_TYPE_SBUS</constant> and
<function>snd_dma_sbus_data(sbus_dev)</function> are used instead.
use.
For the PCI scatter-gather buffers, use
<constant>SNDRV_DMA_TYPE_DEV_SG</constant> with
<function>snd_dma_pci_data(pci)</function>
@ -6135,44 +6134,58 @@ struct _snd_pcm_runtime {
</para>
</section>
<section id="useful-functions-snd-assert">
<title><function>snd_assert()</function></title>
<para>
<function>snd_assert()</function> macro is similar with the
normal <function>assert()</function> macro. For example,
<informalexample>
<programlisting>
<![CDATA[
snd_assert(pointer != NULL, return -EINVAL);
]]>
</programlisting>
</informalexample>
</para>
<para>
The first argument is the expression to evaluate, and the
second argument is the action if it fails. When
<constant>CONFIG_SND_DEBUG</constant>, is set, it will show an
error message such as <computeroutput>BUG? (xxx)</computeroutput>
together with stack trace.
</para>
<para>
When no debug flag is set, this macro is ignored.
</para>
</section>
<section id="useful-functions-snd-bug">
<title><function>snd_BUG()</function></title>
<para>
It shows the <computeroutput>BUG?</computeroutput> message and
stack trace as well as <function>snd_assert</function> at the point.
stack trace as well as <function>snd_BUG_ON</function> at the point.
It's useful to show that a fatal error happens there.
</para>
<para>
When no debug flag is set, this macro is ignored.
</para>
</section>
<section id="useful-functions-snd-bug-on">
<title><function>snd_BUG_ON()</function></title>
<para>
<function>snd_BUG_ON()</function> macro is similar with
<function>WARN_ON()</function> macro. For example,
<informalexample>
<programlisting>
<![CDATA[
snd_BUG_ON(!pointer);
]]>
</programlisting>
</informalexample>
or it can be used as the condition,
<informalexample>
<programlisting>
<![CDATA[
if (snd_BUG_ON(non_zero_is_bug))
return -EINVAL;
]]>
</programlisting>
</informalexample>
</para>
<para>
The macro takes an conditional expression to evaluate.
When <constant>CONFIG_SND_DEBUG</constant>, is set, the
expression is actually evaluated. If it's non-zero, it shows
the warning message such as
<computeroutput>BUG? (xxx)</computeroutput>
normally followed by stack trace. It returns the evaluated
value.
When no <constant>CONFIG_SND_DEBUG</constant> is set, this
macro always returns zero.
</para>
</section>
</chapter>

309
Documentation/sparc/sbus_drivers.txt
View File

@ -1,309 +0,0 @@
Writing SBUS Drivers
David S. Miller (davem@redhat.com)
The SBUS driver interfaces of the Linux kernel have been
revamped completely for 2.4.x for several reasons. Foremost were
performance and complexity concerns. This document details these
new interfaces and how they are used to write an SBUS device driver.
SBUS drivers need to include <asm/sbus.h> to get access
to functions and structures described here.
Probing and Detection
Each SBUS device inside the machine is described by a
structure called "struct sbus_dev". Likewise, each SBUS bus
found in the system is described by a "struct sbus_bus". For
each SBUS bus, the devices underneath are hung in a tree-like
fashion off of the bus structure.
The SBUS device structure contains enough information
for you to implement your device probing algorithm and obtain
the bits necessary to run your device. The most commonly
used members of this structure, and their typical usage,
will be detailed below.
Here is a piece of skeleton code for performing a device
probe in an SBUS driver under Linux:
static int __devinit mydevice_probe_one(struct sbus_dev *sdev)
{
struct mysdevice *mp = kzalloc(sizeof(*mp), GFP_KERNEL);
if (!mp)
return -ENODEV;
...
dev_set_drvdata(&sdev->ofdev.dev, mp);
return 0;
...
}
static int __devinit mydevice_probe(struct of_device *dev,
const struct of_device_id *match)
{
struct sbus_dev *sdev = to_sbus_device(&dev->dev);
return mydevice_probe_one(sdev);
}
static int __devexit mydevice_remove(struct of_device *dev)
{
struct sbus_dev *sdev = to_sbus_device(&dev->dev);
struct mydevice *mp = dev_get_drvdata(&dev->dev);
return mydevice_remove_one(sdev, mp);
}
static struct of_device_id mydevice_match[] = {
{
.name = "mydevice",
},
{},
};
MODULE_DEVICE_TABLE(of, mydevice_match);
static struct of_platform_driver mydevice_driver = {
.match_table = mydevice_match,
.probe = mydevice_probe,
.remove = __devexit_p(mydevice_remove),
.driver = {
.name = "mydevice",
},
};
static int __init mydevice_init(void)
{
return of_register_driver(&mydevice_driver, &sbus_bus_type);
}
static void __exit mydevice_exit(void)
{
of_unregister_driver(&mydevice_driver);
}
module_init(mydevice_init);
module_exit(mydevice_exit);
The mydevice_match table is a series of entries which
describes what SBUS devices your driver is meant for. In the
simplest case you specify a string for the 'name' field. Every
SBUS device with a 'name' property matching your string will
be passed one-by-one to your .probe method.
You should store away your device private state structure
pointer in the drvdata area so that you can retrieve it later on
in your .remove method.
Any memory allocated, registers mapped, IRQs registered,
etc. must be undone by your .remove method so that all resources
of your device are released by the time it returns.
You should _NOT_ use the for_each_sbus(), for_each_sbusdev(),
and for_all_sbusdev() interfaces. They are deprecated, will be
removed, and no new driver should reference them ever.
Mapping and Accessing I/O Registers
Each SBUS device structure contains an array of descriptors
which describe each register set. We abuse struct resource for that.
They each correspond to the "reg" properties provided by the OBP firmware.
Before you can access your device's registers you must map
them. And later if you wish to shutdown your driver (for module
unload or similar) you must unmap them. You must treat them as
a resource, which you allocate (map) before using and free up
(unmap) when you are done with it.
The mapping information is stored in an opaque value
typed as an "unsigned long". This is the type of the return value
of the mapping interface, and the arguments to the unmapping
interface. Let's say you want to map the first set of registers.
Perhaps part of your driver software state structure looks like:
struct mydevice {
unsigned long control_regs;
...
struct sbus_dev *sdev;
...
};
At initialization time you then use the sbus_ioremap
interface to map in your registers, like so:
static void init_one_mydevice(struct sbus_dev *sdev)
{
struct mydevice *mp;
...
mp->control_regs = sbus_ioremap(&sdev->resource[0], 0,
CONTROL_REGS_SIZE, "mydevice regs");
if (!mp->control_regs) {
/* Failure, cleanup and return. */
}
}
Second argument to sbus_ioremap is an offset for
cranky devices with broken OBP PROM. The sbus_ioremap uses only
a start address and flags from the resource structure.
Therefore it is possible to use the same resource to map
several sets of registers or even to fabricate a resource
structure if driver gets physical address from some private place.
This practice is discouraged though. Use whatever OBP PROM
provided to you.
And here is how you might unmap these registers later at
driver shutdown or module unload time, using the sbus_iounmap
interface:
static void mydevice_unmap_regs(struct mydevice *mp)
{
sbus_iounmap(mp->control_regs, CONTROL_REGS_SIZE);
}
Finally, to actually access your registers there are 6
interface routines at your disposal. Accesses are byte (8 bit),
word (16 bit), or longword (32 bit) sized. Here they are:
u8 sbus_readb(unsigned long reg) /* read byte */
u16 sbus_readw(unsigned long reg) /* read word */
u32 sbus_readl(unsigned long reg) /* read longword */
void sbus_writeb(u8 value, unsigned long reg) /* write byte */
void sbus_writew(u16 value, unsigned long reg) /* write word */
void sbus_writel(u32 value, unsigned long reg) /* write longword */
So, let's say your device has a control register of some sort
at offset zero. The following might implement resetting your device:
#define CONTROL 0x00UL
#define CONTROL_RESET 0x00000001 /* Reset hardware */
static void mydevice_reset(struct mydevice *mp)
{
sbus_writel(CONTROL_RESET, mp->regs + CONTROL);
}
Or perhaps there is a data port register at an offset of
16 bytes which allows you to read bytes from a fifo in the device:
#define DATA 0x10UL
static u8 mydevice_get_byte(struct mydevice *mp)
{
return sbus_readb(mp->regs + DATA);
}
It's pretty straightforward, and clueful readers may have
noticed that these interfaces mimick the PCI interfaces of the
Linux kernel. This was not by accident.
WARNING:
DO NOT try to treat these opaque register mapping
values as a memory mapped pointer to some structure
which you can dereference.
It may be memory mapped, it may not be. In fact it
could be a physical address, or it could be the time
of day xor'd with 0xdeadbeef. :-)
Whatever it is, it's an implementation detail. The
interface was done this way to shield the driver
author from such complexities.
Doing DVMA
SBUS devices can perform DMA transactions in a way similar
to PCI but dissimilar to ISA, e.g. DMA masters supply address.
In contrast to PCI, however, that address (a bus address) is
translated by IOMMU before a memory access is performed and therefore
it is virtual. Sun calls this procedure DVMA.
Linux supports two styles of using SBUS DVMA: "consistent memory"
and "streaming DVMA". CPU view of consistent memory chunk is, well,
consistent with a view of a device. Think of it as an uncached memory.
Typically this way of doing DVMA is not very fast and drivers use it
mostly for control blocks or queues. On some CPUs we cannot flush or
invalidate individual pages or cache lines and doing explicit flushing
over ever little byte in every control block would be wasteful.
Streaming DVMA is a preferred way to transfer large amounts of data.
This process works in the following way:
1. a CPU stops accessing a certain part of memory,
flushes its caches covering that memory;
2. a device does DVMA accesses, then posts an interrupt;
3. CPU invalidates its caches and starts to access the memory.
A single streaming DVMA operation can touch several discontiguous
regions of a virtual bus address space. This is called a scatter-gather
DVMA.
[TBD: Why do not we neither Solaris attempt to map disjoint pages
into a single virtual chunk with the help of IOMMU, so that non SG
DVMA masters would do SG? It'd be very helpful for RAID.]
In order to perform a consistent DVMA a driver does something
like the following:
char *mem; /* Address in the CPU space */
u32 busa; /* Address in the SBus space */
mem = (char *) sbus_alloc_consistent(sdev, MYMEMSIZE, &busa);
Then mem is used when CPU accesses this memory and u32
is fed to the device so that it can do DVMA. This is typically
done with an sbus_writel() into some device register.
Do not forget to free the DVMA resources once you are done:
sbus_free_consistent(sdev, MYMEMSIZE, mem, busa);
Streaming DVMA is more interesting. First you allocate some
memory suitable for it or pin down some user pages. Then it all works
like this:
char *mem = argumen1;
unsigned int size = argument2;
u32 busa; /* Address in the SBus space */
*mem = 1; /* CPU can access */
busa = sbus_map_single(sdev, mem, size);
if (busa == 0) .......
/* Tell the device to use busa here */
/* CPU cannot access the memory without sbus_dma_sync_single() */
sbus_unmap_single(sdev, busa, size);
if (*mem == 0) .... /* CPU can access again */
It is possible to retain mappings and ask the device to
access data again and again without calling sbus_unmap_single.
However, CPU caches must be invalidated with sbus_dma_sync_single
before such access.
[TBD but what about writeback caches here... do we have any?]
There is an equivalent set of functions doing the same thing
only with several memory segments at once for devices capable of
scatter-gather transfers. Use the Source, Luke.
Examples
drivers/net/sunhme.c
This is a complicated driver which illustrates many concepts
discussed above and plus it handles both PCI and SBUS boards.
drivers/scsi/esp.c
Check it out for scatter-gather DVMA.
drivers/sbus/char/bpp.c
A non-DVMA device.
drivers/net/sunlance.c
Lance driver abuses consistent mappings for data transfer.
It is a nifty trick which we do not particularly recommend...
Just check it out and know that it's legal.

10
Documentation/timers/00-INDEX Normal file
View File

@ -0,0 +1,10 @@
00-INDEX
- this file
highres.txt
- High resolution timers and dynamic ticks design notes
hpet.txt
- High Precision Event Timer Driver for Linux
hrtimers.txt
- subsystem for high-resolution kernel timers
timer_stats.txt
- timer usage statistics

299
Documentation/timers/hpet.txt Normal file
View File

@ -0,0 +1,299 @@
High Precision Event Timer Driver for Linux
The High Precision Event Timer (HPET) hardware follows a specification
by Intel and Microsoft which can be found at
http://www.intel.com/technology/architecture/hpetspec.htm
Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
and up to 32 comparators. Normally three or more comparators are provided,
each of which can generate oneshot interupts and at least one of which has
additional hardware to support periodic interrupts. The comparators are
also called "timers", which can be misleading since usually timers are
independent of each other ... these share a counter, complicating resets.
HPET devices can support two interrupt routing modes. In one mode, the
comparators are additional interrupt sources with no particular system
role. Many x86 BIOS writers don't route HPET interrupts at all, which
prevents use of that mode. They support the other "legacy replacement"
mode where the first two comparators block interrupts from 8254 timers
and from the RTC.
The driver supports detection of HPET driver allocation and initialization
of the HPET before the driver module_init routine is called. This enables
platform code which uses timer 0 or 1 as the main timer to intercept HPET
initialization. An example of this initialization can be found in
arch/x86/kernel/hpet.c.
The driver provides a userspace API which resembles the API found in the
RTC driver framework. An example user space program is provided below.
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <string.h>
#include <memory.h>
#include <malloc.h>
#include <time.h>
#include <ctype.h>
#include <sys/types.h>
#include <sys/wait.h>
#include <signal.h>
#include <fcntl.h>
#include <errno.h>
#include <sys/time.h>
#include <linux/hpet.h>
extern void hpet_open_close(int, const char **);
extern void hpet_info(int, const char **);
extern void hpet_poll(int, const char **);
extern void hpet_fasync(int, const char **);
extern void hpet_read(int, const char **);
#include <sys/poll.h>
#include <sys/ioctl.h>
#include <signal.h>
struct hpet_command {
char *command;
void (*func)(int argc, const char ** argv);
} hpet_command[] = {
{
"open-close",
hpet_open_close
},
{
"info",
hpet_info
},
{
"poll",
hpet_poll
},
{
"fasync",
hpet_fasync
},
};
int
main(int argc, const char ** argv)
{
int i;
argc--;
argv++;
if (!argc) {
fprintf(stderr, "-hpet: requires command\n");
return -1;
}
for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
if (!strcmp(argv[0], hpet_command[i].command)) {
argc--;
argv++;
fprintf(stderr, "-hpet: executing %s\n",
hpet_command[i].command);
hpet_command[i].func(argc, argv);
return 0;
}
fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
return -1;
}
void
hpet_open_close(int argc, const char **argv)
{
int fd;
if (argc != 1) {
fprintf(stderr, "hpet_open_close: device-name\n");
return;
}
fd = open(argv[0], O_RDONLY);
if (fd < 0)
fprintf(stderr, "hpet_open_close: open failed\n");
else
close(fd);
return;
}
void
hpet_info(int argc, const char **argv)
{
}
void
hpet_poll(int argc, const char **argv)
{
unsigned long freq;
int iterations, i, fd;
struct pollfd pfd;
struct hpet_info info;
struct timeval stv, etv;
struct timezone tz;
long usec;
if (argc != 3) {
fprintf(stderr, "hpet_poll: device-name freq iterations\n");
return;
}
freq = atoi(argv[1]);
iterations = atoi(argv[2]);
fd = open(argv[0], O_RDONLY);
if (fd < 0) {
fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
return;
}
if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
goto out;
}
if (ioctl(fd, HPET_INFO, &info) < 0) {
fprintf(stderr, "hpet_poll: failed to get info\n");
goto out;
}
fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
goto out;
}
if (ioctl(fd, HPET_IE_ON, 0) < 0) {
fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
goto out;
}
pfd.fd = fd;
pfd.events = POLLIN;
for (i = 0; i < iterations; i++) {
pfd.revents = 0;
gettimeofday(&stv, &tz);
if (poll(&pfd, 1, -1) < 0)
fprintf(stderr, "hpet_poll: poll failed\n");
else {
long data;
gettimeofday(&etv, &tz);
usec = stv.tv_sec * 1000000 + stv.tv_usec;
usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
fprintf(stderr,
"hpet_poll: expired time = 0x%lx\n", usec);
fprintf(stderr, "hpet_poll: revents = 0x%x\n",
pfd.revents);
if (read(fd, &data, sizeof(data)) != sizeof(data)) {
fprintf(stderr, "hpet_poll: read failed\n");
}
else
fprintf(stderr, "hpet_poll: data 0x%lx\n",
data);
}
}
out:
close(fd);
return;
}
static int hpet_sigio_count;
static void
hpet_sigio(int val)
{
fprintf(stderr, "hpet_sigio: called\n");
hpet_sigio_count++;
}
void
hpet_fasync(int argc, const char **argv)
{
unsigned long freq;
int iterations, i, fd, value;
sig_t oldsig;
struct hpet_info info;
hpet_sigio_count = 0;
fd = -1;
if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
return;
}
if (argc != 3) {
fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
goto out;
}
fd = open(argv[0], O_RDONLY);
if (fd < 0) {
fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
return;
}
if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
((value = fcntl(fd, F_GETFL)) == 1) ||
(fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
fprintf(stderr, "hpet_fasync: fcntl failed\n");
goto out;
}
freq = atoi(argv[1]);
iterations = atoi(argv[2]);
if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
goto out;
}
if (ioctl(fd, HPET_INFO, &info) < 0) {
fprintf(stderr, "hpet_fasync: failed to get info\n");
goto out;
}
fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
goto out;
}
if (ioctl(fd, HPET_IE_ON, 0) < 0) {
fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
goto out;
}
for (i = 0; i < iterations; i++) {
(void) pause();
fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
}
out:
signal(SIGIO, oldsig);
if (fd >= 0)
close(fd);
return;
}

1
Documentation/video4linux/CARDLIST.bttv
View File

@ -150,3 +150,4 @@
149 -> Typhoon TV-Tuner PCI (50684)
150 -> Geovision GV-600 [008a:763c]
151 -> Kozumi KTV-01C
152 -> Encore ENL TV-FM-2 [1000:1801]

2
Documentation/video4linux/CARDLIST.cx23885
View File

@ -9,3 +9,5 @@
8 -> Hauppauge WinTV-HVR1700 [0070:8101]
9 -> Hauppauge WinTV-HVR1400 [0070:8010]
10 -> DViCO FusionHDTV7 Dual Express [18ac:d618]
11 -> DViCO FusionHDTV DVB-T Dual Express [18ac:db78]
12 -> Leadtek Winfast PxDVR3200 H [107d:6681]

8
Documentation/video4linux/CARDLIST.cx88
View File

@ -66,3 +66,11 @@
65 -> DViCO FusionHDTV 7 Gold [18ac:d610]
66 -> Prolink Pixelview MPEG 8000GT [1554:4935]
67 -> Kworld PlusTV HD PCI 120 (ATSC 120) [17de:08c1]
68 -> Hauppauge WinTV-HVR4000 DVB-S/S2/T/Hybrid [0070:6900,0070:6904,0070:6902]
69 -> Hauppauge WinTV-HVR4000(Lite) DVB-S/S2 [0070:6905,0070:6906]
70 -> TeVii S460 DVB-S/S2 [d460:9022]
71 -> Omicom SS4 DVB-S/S2 PCI [A044:2011]
72 -> TBS 8920 DVB-S/S2 [8920:8888]
73 -> TeVii S420 DVB-S [d420:9022]
74 -> Prolink Pixelview Global Extreme [1554:4976]
75 -> PROF 7300 DVB-S/S2 [B033:3033]

4
Documentation/video4linux/CARDLIST.em28xx
View File

@ -1,5 +1,5 @@
0 -> Unknown EM2800 video grabber (em2800) [eb1a:2800]
1 -> Unknown EM2750/28xx video grabber (em2820/em2840) [eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2870,eb1a:2881,eb1a:2883]
1 -> Unknown EM2750/28xx video grabber (em2820/em2840) [eb1a:2820,eb1a:2860,eb1a:2861,eb1a:2870,eb1a:2881,eb1a:2883]
2 -> Terratec Cinergy 250 USB (em2820/em2840) [0ccd:0036]
3 -> Pinnacle PCTV USB 2 (em2820/em2840) [2304:0208]
4 -> Hauppauge WinTV USB 2 (em2820/em2840) [2040:4200,2040:4201]
@ -12,7 +12,7 @@
11 -> Terratec Hybrid XS (em2880) [0ccd:0042]
12 -> Kworld PVR TV 2800 RF (em2820/em2840)
13 -> Terratec Prodigy XS (em2880) [0ccd:0047]
14 -> Pixelview Prolink PlayTV USB 2.0 (em2820/em2840)
14 -> Pixelview Prolink PlayTV USB 2.0 (em2820/em2840) [eb1a:2821]
15 -> V-Gear PocketTV (em2800)
16 -> Hauppauge WinTV HVR 950 (em2883) [2040:6513,2040:6517,2040:651b,2040:651f]
17 -> Pinnacle PCTV HD Pro Stick (em2880) [2304:0227]

8
Documentation/video4linux/CARDLIST.saa7134
View File

@ -76,7 +76,7 @@
75 -> AVerMedia AVerTVHD MCE A180 [1461:1044]
76 -> SKNet MonsterTV Mobile [1131:4ee9]
77 -> Pinnacle PCTV 40i/50i/110i (saa7133) [11bd:002e]
78 -> ASUSTeK P7131 Dual [1043:4862,1043:4857]
78 -> ASUSTeK P7131 Dual [1043:4862]
79 -> Sedna/MuchTV PC TV Cardbus TV/Radio (ITO25 Rev:2B)
80 -> ASUS Digimatrix TV [1043:0210]
81 -> Philips Tiger reference design [1131:2018]
@ -145,3 +145,9 @@
144 -> Beholder BeholdTV M6 Extra [5ace:6193]
145 -> AVerMedia MiniPCI DVB-T Hybrid M103 [1461:f636]
146 -> ASUSTeK P7131 Analog
147 -> Asus Tiger 3in1 [1043:4878]
148 -> Encore ENLTV-FM v5.3 [1a7f:2008]
149 -> Avermedia PCI pure analog (M135A) [1461:f11d]
150 -> Zogis Real Angel 220
151 -> ADS Tech Instant HDTV [1421:0380]
152 -> Asus Tiger Rev:1.00 [1043:4857]

1
Documentation/video4linux/CARDLIST.tuner
View File

@ -74,3 +74,4 @@ tuner=72 - Thomson FE6600
tuner=73 - Samsung TCPG 6121P30A
tuner=75 - Philips TEA5761 FM Radio
tuner=76 - Xceive 5000 tuner
tuner=77 - TCL tuner MF02GIP-5N-E

28
Documentation/video4linux/gspca.txt
View File

@ -7,6 +7,7 @@ The modules are:
xxxx vend:prod
----
spca501 0000:0000 MystFromOri Unknow Camera
m5602 0402:5602 ALi Video Camera Controller
spca501 040a:0002 Kodak DVC-325
spca500 040a:0300 Kodak EZ200
zc3xx 041e:041e Creative WebCam Live!
@ -42,6 +43,7 @@ zc3xx 0458:7007 Genius VideoCam V2
zc3xx 0458:700c Genius VideoCam V3
zc3xx 0458:700f Genius VideoCam Web V2
sonixj 0458:7025 Genius Eye 311Q
sonixj 0458:702e Genius Slim 310 NB
sonixj 045e:00f5 MicroSoft VX3000
sonixj 045e:00f7 MicroSoft VX1000
ov519 045e:028c Micro$oft xbox cam
@ -81,7 +83,7 @@ spca561 046d:092b Labtec Webcam Plus
spca561 046d:092c Logitech QC chat Elch2
spca561 046d:092d Logitech QC Elch2
spca561 046d:092e Logitech QC Elch2
spca561 046d:092f Logitech QC Elch2
spca561 046d:092f Logitech QuickCam Express Plus
sunplus 046d:0960 Logitech ClickSmart 420
sunplus 0471:0322 Philips DMVC1300K
zc3xx 0471:0325 Philips SPC 200 NC
@ -96,6 +98,29 @@ sunplus 04a5:3003 Benq DC 1300
sunplus 04a5:3008 Benq DC 1500
sunplus 04a5:300a Benq DC 3410
spca500 04a5:300c Benq DC 1016
finepix 04cb:0104 Fujifilm FinePix 4800
finepix 04cb:0109 Fujifilm FinePix A202
finepix 04cb:010b Fujifilm FinePix A203
finepix 04cb:010f Fujifilm FinePix A204
finepix 04cb:0111 Fujifilm FinePix A205
finepix 04cb:0113 Fujifilm FinePix A210
finepix 04cb:0115 Fujifilm FinePix A303
finepix 04cb:0117 Fujifilm FinePix A310
finepix 04cb:0119 Fujifilm FinePix F401
finepix 04cb:011b Fujifilm FinePix F402
finepix 04cb:011d Fujifilm FinePix F410
finepix 04cb:0121 Fujifilm FinePix F601
finepix 04cb:0123 Fujifilm FinePix F700
finepix 04cb:0125 Fujifilm FinePix M603
finepix 04cb:0127 Fujifilm FinePix S300
finepix 04cb:0129 Fujifilm FinePix S304
finepix 04cb:012b Fujifilm FinePix S500
finepix 04cb:012d Fujifilm FinePix S602
finepix 04cb:012f Fujifilm FinePix S700
finepix 04cb:0131 Fujifilm FinePix unknown model
finepix 04cb:013b Fujifilm FinePix unknown model
finepix 04cb:013d Fujifilm FinePix unknown model
finepix 04cb:013f Fujifilm FinePix F420
sunplus 04f1:1001 JVC GC A50
spca561 04fc:0561 Flexcam 100
sunplus 04fc:500c Sunplus CA500C
@ -181,6 +206,7 @@ pac207 093a:2468 PAC207
pac207 093a:2470 Genius GF112
pac207 093a:2471 Genius VideoCam ge111
pac207 093a:2472 Genius VideoCam ge110
pac207 093a:2476 Genius e-Messenger 112
pac7311 093a:2600 PAC7311 Typhoon
pac7311 093a:2601 Philips SPC 610 NC
pac7311 093a:2603 PAC7312

12
Documentation/video4linux/m5602.txt Normal file
View File

@ -0,0 +1,12 @@
This document describes the ALi m5602 bridge connected
to the following supported sensors:
OmniVision OV9650,
Samsung s5k83a,
Samsung s5k4aa,
Micron mt9m111,
Pixel plus PO1030
This driver mimics the windows drivers, which have a braindead implementation sending bayer-encoded frames at VGA resolution.
In a perfect world we should be able to reprogram the m5602 and the connected sensor in hardware instead, supporting a range of resolutions and pixelformats
Anyway, have fun and please report any bugs to m560x-driver-devel@lists.sourceforge.net

120
Documentation/video4linux/soc-camera.txt Normal file
View File

@ -0,0 +1,120 @@
Soc-Camera Subsystem
====================
Terminology
-----------
The following terms are used in this document:
- camera / camera device / camera sensor - a video-camera sensor chip, capable
of connecting to a variety of systems and interfaces, typically uses i2c for
control and configuration, and a parallel or a serial bus for data.
- camera host - an interface, to which a camera is connected. Typically a
specialised interface, present on many SoCs, e.g., PXA27x and PXA3xx, SuperH,
AVR32, i.MX27, i.MX31.
- camera host bus - a connection between a camera host and a camera. Can be
parallel or serial, consists of data and control lines, e.g., clock, vertical
and horizontal synchronization signals.
Purpose of the soc-camera subsystem
-----------------------------------
The soc-camera subsystem provides a unified API between camera host drivers and
camera sensor drivers. It implements a V4L2 interface to the user, currently
only the mmap method is supported.
This subsystem has been written to connect drivers for System-on-Chip (SoC)
video capture interfaces with drivers for CMOS camera sensor chips to enable
the reuse of sensor drivers with various hosts. The subsystem has been designed
to support multiple camera host interfaces and multiple cameras per interface,
although most applications have only one camera sensor.
Existing drivers
----------------
As of 2.6.27-rc4 there are two host drivers in the mainline: pxa_camera.c for
PXA27x SoCs and sh_mobile_ceu_camera.c for SuperH SoCs, and four sensor drivers:
mt9m001.c, mt9m111.c, mt9v022.c and a generic soc_camera_platform.c driver. This
list is not supposed to be updated, look for more examples in your tree.
Camera host API
---------------
A host camera driver is registered using the
soc_camera_host_register(struct soc_camera_host *);
function. The host object can be initialized as follows:
static struct soc_camera_host pxa_soc_camera_host = {
.drv_name = PXA_CAM_DRV_NAME,
.ops = &pxa_soc_camera_host_ops,
};
All camera host methods are passed in a struct soc_camera_host_ops:
static struct soc_camera_host_ops pxa_soc_camera_host_ops = {
.owner = THIS_MODULE,
.add = pxa_camera_add_device,
.remove = pxa_camera_remove_device,
.suspend = pxa_camera_suspend,
.resume = pxa_camera_resume,
.set_fmt_cap = pxa_camera_set_fmt_cap,
.try_fmt_cap = pxa_camera_try_fmt_cap,
.init_videobuf = pxa_camera_init_videobuf,
.reqbufs = pxa_camera_reqbufs,
.poll = pxa_camera_poll,
.querycap = pxa_camera_querycap,
.try_bus_param = pxa_camera_try_bus_param,
.set_bus_param = pxa_camera_set_bus_param,
};
.add and .remove methods are called when a sensor is attached to or detached
from the host, apart from performing host-internal tasks they shall also call
sensor driver's .init and .release methods respectively. .suspend and .resume
methods implement host's power-management functionality and its their
responsibility to call respective sensor's methods. .try_bus_param and
.set_bus_param are used to negotiate physical connection parameters between the
host and the sensor. .init_videobuf is called by soc-camera core when a
video-device is opened, further video-buffer management is implemented completely
by the specific camera host driver. The rest of the methods are called from
respective V4L2 operations.
Camera API
----------
Sensor drivers can use struct soc_camera_link, typically provided by the
platform, and used to specify to which camera host bus the sensor is connected,
and arbitrarily provide platform .power and .reset methods for the camera.
soc_camera_device_register() and soc_camera_device_unregister() functions are
used to add a sensor driver to or remove one from the system. The registration
function takes a pointer to struct soc_camera_device as the only parameter.
This struct can be initialized as follows:
/* link to driver operations */
icd->ops = &mt9m001_ops;
/* link to the underlying physical (e.g., i2c) device */
icd->control = &client->dev;
/* window geometry */
icd->x_min = 20;
icd->y_min = 12;
icd->x_current = 20;
icd->y_current = 12;
icd->width_min = 48;
icd->width_max = 1280;
icd->height_min = 32;
icd->height_max = 1024;
icd->y_skip_top = 1;
/* camera bus ID, typically obtained from platform data */
icd->iface = icl->bus_id;
struct soc_camera_ops provides .probe and .remove methods, which are called by
the soc-camera core, when a camera is matched against or removed from a camera
host bus, .init, .release, .suspend, and .resume are called from the camera host
driver as discussed above. Other members of this struct provide respective V4L2
functionality.
struct soc_camera_device also links to an array of struct soc_camera_data_format,
listing pixel formats, supported by the camera.
--
Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>

4
Documentation/x86/00-INDEX Normal file
View File

@ -0,0 +1,4 @@
00-INDEX
- this file
mtrr.txt
- how to use x86 Memory Type Range Registers to increase performance

900
Documentation/x86/boot.txt Normal file
View File

@ -0,0 +1,900 @@
THE LINUX/x86 BOOT PROTOCOL
---------------------------
On the x86 platform, the Linux kernel uses a rather complicated boot
convention. This has evolved partially due to historical aspects, as
well as the desire in the early days to have the kernel itself be a
bootable image, the complicated PC memory model and due to changed
expectations in the PC industry caused by the effective demise of
real-mode DOS as a mainstream operating system.
Currently, the following versions of the Linux/x86 boot protocol exist.
Old kernels: zImage/Image support only. Some very early kernels
may not even support a command line.
Protocol 2.00: (Kernel 1.3.73) Added bzImage and initrd support, as
well as a formalized way to communicate between the
boot loader and the kernel. setup.S made relocatable,
although the traditional setup area still assumed
writable.
Protocol 2.01: (Kernel 1.3.76) Added a heap overrun warning.
Protocol 2.02: (Kernel 2.4.0-test3-pre3) New command line protocol.
Lower the conventional memory ceiling. No overwrite
of the traditional setup area, thus making booting
safe for systems which use the EBDA from SMM or 32-bit
BIOS entry points. zImage deprecated but still
supported.
Protocol 2.03: (Kernel 2.4.18-pre1) Explicitly makes the highest possible
initrd address available to the bootloader.
Protocol 2.04: (Kernel 2.6.14) Extend the syssize field to four bytes.
Protocol 2.05: (Kernel 2.6.20) Make protected mode kernel relocatable.
Introduce relocatable_kernel and kernel_alignment fields.
Protocol 2.06: (Kernel 2.6.22) Added a field that contains the size of
the boot command line.
Protocol 2.07: (Kernel 2.6.24) Added paravirtualised boot protocol.
Introduced hardware_subarch and hardware_subarch_data
and KEEP_SEGMENTS flag in load_flags.
Protocol 2.08: (Kernel 2.6.26) Added crc32 checksum and ELF format
payload. Introduced payload_offset and payload length
fields to aid in locating the payload.
Protocol 2.09: (Kernel 2.6.26) Added a field of 64-bit physical
pointer to single linked list of struct setup_data.
**** MEMORY LAYOUT
The traditional memory map for the kernel loader, used for Image or
zImage kernels, typically looks like:
| |
0A0000 +------------------------+
| Reserved for BIOS | Do not use. Reserved for BIOS EBDA.
09A000 +------------------------+
| Command line |
| Stack/heap | For use by the kernel real-mode code.
098000 +------------------------+
| Kernel setup | The kernel real-mode code.
090200 +------------------------+
| Kernel boot sector | The kernel legacy boot sector.
090000 +------------------------+
| Protected-mode kernel | The bulk of the kernel image.
010000 +------------------------+
| Boot loader | <- Boot sector entry point 0000:7C00
001000 +------------------------+
| Reserved for MBR/BIOS |
000800 +------------------------+
| Typically used by MBR |
000600 +------------------------+
| BIOS use only |
000000 +------------------------+
When using bzImage, the protected-mode kernel was relocated to
0x100000 ("high memory"), and the kernel real-mode block (boot sector,
setup, and stack/heap) was made relocatable to any address between
0x10000 and end of low memory. Unfortunately, in protocols 2.00 and
2.01 the 0x90000+ memory range is still used internally by the kernel;
the 2.02 protocol resolves that problem.
It is desirable to keep the "memory ceiling" -- the highest point in
low memory touched by the boot loader -- as low as possible, since
some newer BIOSes have begun to allocate some rather large amounts of
memory, called the Extended BIOS Data Area, near the top of low
memory. The boot loader should use the "INT 12h" BIOS call to verify
how much low memory is available.
Unfortunately, if INT 12h reports that the amount of memory is too
low, there is usually nothing the boot loader can do but to report an
error to the user. The boot loader should therefore be designed to
take up as little space in low memory as it reasonably can. For
zImage or old bzImage kernels, which need data written into the
0x90000 segment, the boot loader should make sure not to use memory
above the 0x9A000 point; too many BIOSes will break above that point.
For a modern bzImage kernel with boot protocol version >= 2.02, a
memory layout like the following is suggested:
~ ~
| Protected-mode kernel |
100000 +------------------------+
| I/O memory hole |
0A0000 +------------------------+
| Reserved for BIOS | Leave as much as possible unused
~ ~
| Command line | (Can also be below the X+10000 mark)
X+10000 +------------------------+
| Stack/heap | For use by the kernel real-mode code.
X+08000 +------------------------+
| Kernel setup | The kernel real-mode code.
| Kernel boot sector | The kernel legacy boot sector.
X +------------------------+
| Boot loader | <- Boot sector entry point 0000:7C00
001000 +------------------------+
| Reserved for MBR/BIOS |
000800 +------------------------+
| Typically used by MBR |
000600 +------------------------+
| BIOS use only |
000000 +------------------------+
... where the address X is as low as the design of the boot loader
permits.
**** THE REAL-MODE KERNEL HEADER
In the following text, and anywhere in the kernel boot sequence, "a
sector" refers to 512 bytes. It is independent of the actual sector
size of the underlying medium.
The first step in loading a Linux kernel should be to load the
real-mode code (boot sector and setup code) and then examine the
following header at offset 0x01f1. The real-mode code can total up to
32K, although the boot loader may choose to load only the first two
sectors (1K) and then examine the bootup sector size.
The header looks like:
Offset Proto Name Meaning
/Size
01F1/1 ALL(1 setup_sects The size of the setup in sectors
01F2/2 ALL root_flags If set, the root is mounted readonly
01F4/4 2.04+(2 syssize The size of the 32-bit code in 16-byte paras
01F8/2 ALL ram_size DO NOT USE - for bootsect.S use only
01FA/2 ALL vid_mode Video mode control
01FC/2 ALL root_dev Default root device number
01FE/2 ALL boot_flag 0xAA55 magic number
0200/2 2.00+ jump Jump instruction
0202/4 2.00+ header Magic signature "HdrS"
0206/2 2.00+ version Boot protocol version supported
0208/4 2.00+ realmode_swtch Boot loader hook (see below)
020C/2 2.00+ start_sys The load-low segment (0x1000) (obsolete)
020E/2 2.00+ kernel_version Pointer to kernel version string
0210/1 2.00+ type_of_loader Boot loader identifier
0211/1 2.00+ loadflags Boot protocol option flags
0212/2 2.00+ setup_move_size Move to high memory size (used with hooks)
0214/4 2.00+ code32_start Boot loader hook (see below)
0218/4 2.00+ ramdisk_image initrd load address (set by boot loader)
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
0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line
022C/4 2.03+ initrd_addr_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
0235/3 N/A pad2 Unused
0238/4 2.06+ cmdline_size Maximum size of the kernel command line
023C/4 2.07+ hardware_subarch Hardware subarchitecture
0240/8 2.07+ hardware_subarch_data Subarchitecture-specific data
0248/4 2.08+ payload_offset Offset of kernel payload
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
(1) For backwards compatibility, if the setup_sects field contains 0, the
real value is 4.
(2) For boot protocol prior to 2.04, the upper two bytes of the syssize
field are unusable, which means the size of a bzImage kernel
cannot be determined.
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:
Image type = zImage
initrd not supported
Real-mode kernel must be located at 0x90000.
Otherwise, the "version" field contains the protocol version,
e.g. protocol version 2.01 will contain 0x0201 in this field. When
setting fields in the header, you must make sure only to set fields
supported by the protocol version in use.
**** DETAILS OF HEADER FIELDS
For each field, some are information from the kernel to the bootloader
("read"), some are expected to be filled out by the bootloader
("write"), and some are expected to be read and modified by the
bootloader ("modify").
All general purpose boot loaders should write the fields marked
(obligatory). Boot loaders who want to load the kernel at a
nonstandard address should fill in the fields marked (reloc); other
boot loaders can ignore those fields.
The byte order of all fields is littleendian (this is x86, after all.)
Field name: setup_sects
Type: read
Offset/size: 0x1f1/1
Protocol: ALL
The size of the setup code in 512-byte sectors. If this field is
0, the real value is 4. The real-mode code consists of the boot
sector (always one 512-byte sector) plus the setup code.
Field name: root_flags
Type: modify (optional)
Offset/size: 0x1f2/2
Protocol: ALL
If this field is nonzero, the root defaults to readonly. The use of
this field is deprecated; use the "ro" or "rw" options on the
command line instead.
Field name: syssize
Type: read
Offset/size: 0x1f4/4 (protocol 2.04+) 0x1f4/2 (protocol ALL)
Protocol: 2.04+
The size of the protected-mode code in units of 16-byte paragraphs.
For protocol versions older than 2.04 this field is only two bytes
wide, and therefore cannot be trusted for the size of a kernel if
the LOAD_HIGH flag is set.
Field name: ram_size
Type: kernel internal
Offset/size: 0x1f8/2
Protocol: ALL
This field is obsolete.
Field name: vid_mode
Type: modify (obligatory)
Offset/size: 0x1fa/2
Please see the section on SPECIAL COMMAND LINE OPTIONS.
Field name: root_dev
Type: modify (optional)
Offset/size: 0x1fc/2
Protocol: ALL
The default root device device number. The use of this field is
deprecated, use the "root=" option on the command line instead.
Field name: boot_flag
Type: read
Offset/size: 0x1fe/2
Protocol: ALL
Contains 0xAA55. This is the closest thing old Linux kernels have
to a magic number.
Field name: jump
Type: read
Offset/size: 0x200/2
Protocol: 2.00+
Contains an x86 jump instruction, 0xEB followed by a signed offset
relative to byte 0x202. This can be used to determine the size of
the header.
Field name: header
Type: read
Offset/size: 0x202/4
Protocol: 2.00+
Contains the magic number "HdrS" (0x53726448).
Field name: version
Type: read
Offset/size: 0x206/2
Protocol: 2.00+
Contains the boot protocol version, in (major << 8)+minor format,
e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version
10.17.
Field name: readmode_swtch
Type: modify (optional)
Offset/size: 0x208/4
Protocol: 2.00+
Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
Field name: start_sys
Type: read
Offset/size: 0x20c/2
Protocol: 2.00+
The load low segment (0x1000). Obsolete.
Field name: kernel_version
Type: read
Offset/size: 0x20e/2
Protocol: 2.00+
If set to a nonzero value, contains a pointer to a NUL-terminated
human-readable kernel version number string, less 0x200. This can
be used to display the kernel version to the user. This value
should be less than (0x200*setup_sects).
For example, if this value is set to 0x1c00, the kernel version
number string can be found at offset 0x1e00 in the kernel file.
This is a valid value if and only if the "setup_sects" field
contains the value 15 or higher, as:
0x1c00 < 15*0x200 (= 0x1e00) but
0x1c00 >= 14*0x200 (= 0x1c00)
0x1c00 >> 9 = 14, so the minimum value for setup_secs is 15.
Field name: type_of_loader
Type: write (obligatory)
Offset/size: 0x210/1
Protocol: 2.00+
If your boot loader has an assigned id (see table below), enter
0xTV here, where T is an identifier for the boot loader and V is
a version number. Otherwise, enter 0xFF here.
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
5 ELILO
7 GRuB
8 U-BOOT
9 Xen
A Gujin
B Qemu
Please contact <hpa@zytor.com> if you need a bootloader ID
value assigned.
Field name: loadflags
Type: modify (obligatory)
Offset/size: 0x211/1
Protocol: 2.00+
This field is a bitmask.
Bit 0 (read): LOADED_HIGH
- If 0, the protected-mode code is loaded at 0x10000.
- If 1, the protected-mode code is loaded at 0x100000.
Bit 5 (write): QUIET_FLAG
- If 0, print early messages.
- If 1, suppress early messages.
This requests to the kernel (decompressor and early
kernel) to not write early messages that require
accessing the display hardware directly.
Bit 6 (write): KEEP_SEGMENTS
Protocol: 2.07+
- If 0, reload the segment registers in the 32bit entry point.
- If 1, do not reload the segment registers in the 32bit entry point.
Assume that %cs %ds %ss %es are all set to flat segments with
a base of 0 (or the equivalent for their environment).
Bit 7 (write): CAN_USE_HEAP
Set this bit to 1 to indicate that the value entered in the
heap_end_ptr is valid. If this field is clear, some setup code
functionality will be disabled.
Field name: setup_move_size
Type: modify (obligatory)
Offset/size: 0x212/2
Protocol: 2.00-2.01
When using protocol 2.00 or 2.01, if the real mode kernel is not
loaded at 0x90000, it gets moved there later in the loading
sequence. Fill in this field if you want additional data (such as
the kernel command line) moved in addition to the real-mode kernel
itself.
The unit is bytes starting with the beginning of the boot sector.
This field is can be ignored when the protocol is 2.02 or higher, or
if the real-mode code is loaded at 0x90000.
Field name: code32_start
Type: modify (optional, reloc)
Offset/size: 0x214/4
Protocol: 2.00+
The address to jump to in protected mode. This defaults to the load
address of the kernel, and can be used by the boot loader to
determine the proper load address.
This field can be modified for two purposes:
1. as a boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
2. if a bootloader which does not install a hook loads a
relocatable kernel at a nonstandard address it will have to modify
this field to point to the load address.
Field name: ramdisk_image
Type: write (obligatory)
Offset/size: 0x218/4
Protocol: 2.00+
The 32-bit linear address of the initial ramdisk or ramfs. Leave at
zero if there is no initial ramdisk/ramfs.
Field name: ramdisk_size
Type: write (obligatory)
Offset/size: 0x21c/4
Protocol: 2.00+
Size of the initial ramdisk or ramfs. Leave at zero if there is no
initial ramdisk/ramfs.
Field name: bootsect_kludge
Type: kernel internal
Offset/size: 0x220/4
Protocol: 2.00+
This field is obsolete.
Field name: heap_end_ptr
Type: write (obligatory)
Offset/size: 0x224/2
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: cmd_line_ptr
Type: write (obligatory)
Offset/size: 0x228/4
Protocol: 2.02+
Set this field to the linear address of the kernel command line.
The kernel command line can be located anywhere between the end of
the setup heap and 0xA0000; it does not have to be located in the
same 64K segment as the real-mode code itself.
Fill in this field even if your boot loader does not support a
command line, in which case you can point this to an empty string
(or better yet, to the string "auto".) If this field is left at
zero, the kernel will assume that your boot loader does not support
the 2.02+ protocol.
Field name: initrd_addr_max
Type: read
Offset/size: 0x22c/4
Protocol: 2.03+
The maximum address that may be occupied by the initial
ramdisk/ramfs contents. For boot protocols 2.02 or earlier, this
field is not present, and the maximum address is 0x37FFFFFF. (This
address is defined as the address of the highest safe byte, so if
your ramdisk is exactly 131072 bytes long and this field is
0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
Field name: kernel_alignment
Type: read (reloc)
Offset/size: 0x230/4
Protocol: 2.05+
Alignment unit required by the kernel (if relocatable_kernel is true.)
Field name: relocatable_kernel
Type: read (reloc)
Offset/size: 0x234/1
Protocol: 2.05+
If this field is nonzero, the protected-mode part of the kernel can
be loaded at any address that satisfies the kernel_alignment field.
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: cmdline_size
Type: read
Offset/size: 0x238/4
Protocol: 2.06+
The maximum size of the command line without the terminating
zero. This means that the command line can contain at most
cmdline_size characters. With protocol version 2.05 and earlier, the
maximum size was 255.
Field name: hardware_subarch
Type: write (optional, defaults to x86/PC)
Offset/size: 0x23c/4
Protocol: 2.07+
In a paravirtualized environment the hardware low level architectural
pieces such as interrupt handling, page table handling, and
accessing process control registers needs to be done differently.
This field allows the bootloader to inform the kernel we are in one
one of those environments.
0x00000000 The default x86/PC environment
0x00000001 lguest
0x00000002 Xen
Field name: hardware_subarch_data
Type: write (subarch-dependent)
Offset/size: 0x240/8
Protocol: 2.07+
A pointer to data that is specific to hardware subarch
This field is currently unused for the default x86/PC environment,
do not modify.
Field name: payload_offset
Type: read
Offset/size: 0x248/4
Protocol: 2.08+
If non-zero then this field contains the offset from the end of the
real-mode code to the payload.
The payload may be compressed. The format of both the compressed and
uncompressed data should be determined using the standard magic
numbers. Currently only gzip compressed ELF is used.
Field name: payload_length
Type: read
Offset/size: 0x24c/4
Protocol: 2.08+
The length of the payload.
Field name: setup_data
Type: write (special)
Offset/size: 0x250/8
Protocol: 2.09+
The 64-bit physical pointer to NULL terminated single linked list of
struct setup_data. This is used to define a more extensible boot
parameters passing mechanism. The definition of struct setup_data is
as follow:
struct setup_data {
u64 next;
u32 type;
u32 len;
u8 data[0];
};
Where, the next is a 64-bit physical pointer to the next node of
linked list, the next field of the last node is 0; the type is used
to identify the contents of data; the len is the length of data
field; the data holds the real payload.
This list may be modified at a number of points during the bootup
process. Therefore, when modifying this list one should always make
sure to consider the case where the linked list already contains
entries.
**** THE IMAGE CHECKSUM
From boot protocol version 2.08 onwards the CRC-32 is calculated over
the entire file using the characteristic polynomial 0x04C11DB7 and an
initial remainder of 0xffffffff. The checksum is appended to the
file; therefore the CRC of the file up to the limit specified in the
syssize field of the header is always 0.
**** THE KERNEL COMMAND LINE
The kernel command line has become an important way for the boot
loader to communicate with the kernel. Some of its options are also
relevant to the boot loader itself, see "special command line options"
below.
The kernel command line is a null-terminated string. The maximum
length can be retrieved from the field cmdline_size. Before protocol
version 2.06, the maximum was 255 characters. A string that is too
long will be automatically truncated by the kernel.
If the boot protocol version is 2.02 or later, the address of the
kernel command line is given by the header field cmd_line_ptr (see
above.) This address can be anywhere between the end of the setup
heap and 0xA0000.
If the protocol version is *not* 2.02 or higher, the kernel
command line is entered using the following protocol:
At offset 0x0020 (word), "cmd_line_magic", enter the magic
number 0xA33F.
At offset 0x0022 (word), "cmd_line_offset", enter the offset
of the kernel command line (relative to the start of the
real-mode kernel).
The kernel command line *must* be within the memory region
covered by setup_move_size, so you may need to adjust this
field.
**** MEMORY LAYOUT OF THE REAL-MODE CODE
The real-mode code requires a stack/heap to be set up, as well as
memory allocated for the kernel command line. This needs to be done
in the real-mode accessible memory in bottom megabyte.
It should be noted that modern machines often have a sizable Extended
BIOS Data Area (EBDA). As a result, it is advisable to use as little
of the low megabyte as possible.
Unfortunately, under the following circumstances the 0x90000 memory
segment has to be used:
- When loading a zImage kernel ((loadflags & 0x01) == 0).
- When loading a 2.01 or earlier boot protocol kernel.
-> For the 2.00 and 2.01 boot protocols, the real-mode code
can be loaded at another address, but it is internally
relocated to 0x90000. For the "old" protocol, the
real-mode code must be loaded at 0x90000.
When loading at 0x90000, avoid using memory above 0x9a000.
For boot protocol 2.02 or higher, the command line does not have to be
located in the same 64K segment as the real-mode setup code; it is
thus permitted to give the stack/heap the full 64K segment and locate
the command line above it.
The kernel command line should not be located below the real-mode
code, nor should it be located in high memory.
**** SAMPLE BOOT CONFIGURATION
As a sample configuration, assume the following layout of the real
mode segment:
When loading below 0x90000, use the entire segment:
0x0000-0x7fff Real mode kernel
0x8000-0xdfff Stack and heap
0xe000-0xffff Kernel command line
When loading at 0x90000 OR the protocol version is 2.01 or earlier:
0x0000-0x7fff Real mode kernel
0x8000-0x97ff Stack and heap
0x9800-0x9fff Kernel command line
Such a boot loader should enter the following fields in the header:
unsigned long base_ptr; /* base address for real-mode segment */
if ( setup_sects == 0 ) {
setup_sects = 4;
}
if ( protocol >= 0x0200 ) {
type_of_loader = <type code>;
if ( loading_initrd ) {
ramdisk_image = <initrd_address>;
ramdisk_size = <initrd_size>;
}
if ( protocol >= 0x0202 && loadflags & 0x01 )
heap_end = 0xe000;
else
heap_end = 0x9800;
if ( protocol >= 0x0201 ) {
heap_end_ptr = heap_end - 0x200;
loadflags |= 0x80; /* CAN_USE_HEAP */
}
if ( protocol >= 0x0202 ) {
cmd_line_ptr = base_ptr + heap_end;
strcpy(cmd_line_ptr, cmdline);
} else {
cmd_line_magic = 0xA33F;
cmd_line_offset = heap_end;
setup_move_size = heap_end + strlen(cmdline)+1;
strcpy(base_ptr+cmd_line_offset, cmdline);
}
} else {
/* Very old kernel */
heap_end = 0x9800;
cmd_line_magic = 0xA33F;
cmd_line_offset = heap_end;
/* A very old kernel MUST have its real-mode code
loaded at 0x90000 */
if ( base_ptr != 0x90000 ) {
/* Copy the real-mode kernel */
memcpy(0x90000, base_ptr, (setup_sects+1)*512);
base_ptr = 0x90000; /* Relocated */
}
strcpy(0x90000+cmd_line_offset, cmdline);
/* It is recommended to clear memory up to the 32K mark */
memset(0x90000 + (setup_sects+1)*512, 0,
(64-(setup_sects+1))*512);
}
**** LOADING THE REST OF THE KERNEL
The 32-bit (non-real-mode) kernel starts at offset (setup_sects+1)*512
in the kernel file (again, if setup_sects == 0 the real value is 4.)
It should be loaded at address 0x10000 for Image/zImage kernels and
0x100000 for bzImage kernels.
The kernel is a bzImage kernel if the protocol >= 2.00 and the 0x01
bit (LOAD_HIGH) in the loadflags field is set:
is_bzImage = (protocol >= 0x0200) && (loadflags & 0x01);
load_address = is_bzImage ? 0x100000 : 0x10000;
Note that Image/zImage kernels can be up to 512K in size, and thus use
the entire 0x10000-0x90000 range of memory. This means it is pretty
much a requirement for these kernels to load the real-mode part at
0x90000. bzImage kernels allow much more flexibility.
**** SPECIAL COMMAND LINE OPTIONS
If the command line provided by the boot loader is entered by the
user, the user may expect the following command line options to work.
They should normally not be deleted from the kernel command line even
though not all of them are actually meaningful to the kernel. Boot
loader authors who need additional command line options for the boot
loader itself should get them registered in
Documentation/kernel-parameters.txt to make sure they will not
conflict with actual kernel options now or in the future.
vga=<mode>
<mode> here is either an integer (in C notation, either
decimal, octal, or hexadecimal) or one of the strings
"normal" (meaning 0xFFFF), "ext" (meaning 0xFFFE) or "ask"
(meaning 0xFFFD). This value should be entered into the
vid_mode field, as it is used by the kernel before the command
line is parsed.
mem=<size>
<size> is an integer in C notation optionally followed by
(case insensitive) K, M, G, T, P or E (meaning << 10, << 20,
<< 30, << 40, << 50 or << 60). This specifies the end of
memory to the kernel. This affects the possible placement of
an initrd, since an initrd should be placed near end of
memory. Note that this is an option to *both* the kernel and
the bootloader!
initrd=<file>
An initrd should be loaded. The meaning of <file> is
obviously bootloader-dependent, and some boot loaders
(e.g. LILO) do not have such a command.
In addition, some boot loaders add the following options to the
user-specified command line:
BOOT_IMAGE=<file>
The boot image which was loaded. Again, the meaning of <file>
is obviously bootloader-dependent.
auto
The kernel was booted without explicit user intervention.
If these options are added by the boot loader, it is highly
recommended that they are located *first*, before the user-specified
or configuration-specified command line. Otherwise, "init=/bin/sh"
gets confused by the "auto" option.
**** RUNNING THE KERNEL
The kernel is started by jumping to the kernel entry point, which is
located at *segment* offset 0x20 from the start of the real mode
kernel. This means that if you loaded your real-mode kernel code at
0x90000, the kernel entry point is 9020:0000.
At entry, ds = es = ss should point to the start of the real-mode
kernel code (0x9000 if the code is loaded at 0x90000), sp should be
set up properly, normally pointing to the top of the heap, and
interrupts should be disabled. Furthermore, to guard against bugs in
the kernel, it is recommended that the boot loader sets fs = gs = ds =
es = ss.
In our example from above, we would do:
/* Note: in the case of the "old" kernel protocol, base_ptr must
be == 0x90000 at this point; see the previous sample code */
seg = base_ptr >> 4;
cli(); /* Enter with interrupts disabled! */
/* Set up the real-mode kernel stack */
_SS = seg;
_SP = heap_end;
_DS = _ES = _FS = _GS = seg;
jmp_far(seg+0x20, 0); /* Run the kernel */
If your boot sector accesses a floppy drive, it is recommended to
switch off the floppy motor before running the kernel, since the
kernel boot leaves interrupts off and thus the motor will not be
switched off, especially if the loaded kernel has the floppy driver as
a demand-loaded module!
**** ADVANCED BOOT LOADER HOOKS
If the boot loader runs in a particularly hostile environment (such as
LOADLIN, which runs under DOS) it may be impossible to follow the
standard memory location requirements. Such a boot loader may use the
following hooks that, if set, are invoked by the kernel at the
appropriate time. The use of these hooks should probably be
considered an absolutely last resort!
IMPORTANT: All the hooks are required to preserve %esp, %ebp, %esi and
%edi across invocation.
realmode_swtch:
A 16-bit real mode far subroutine invoked immediately before
entering protected mode. The default routine disables NMI, so
your routine should probably do so, too.
code32_start:
A 32-bit flat-mode routine *jumped* to immediately after the
transition to protected mode, but before the kernel is
uncompressed. No segments, except CS, are guaranteed to be
set up (current kernels do, but older ones do not); you should
set them up to BOOT_DS (0x18) yourself.
After completing your hook, you should jump to the address
that was in this field before your boot loader overwrote it
(relocated, if appropriate.)
**** 32-bit BOOT PROTOCOL
For machine with some new BIOS other than legacy BIOS, such as EFI,
LinuxBIOS, etc, and kexec, the 16-bit real mode setup code in kernel
based on legacy BIOS can not be used, so a 32-bit boot protocol needs
to be defined.
In 32-bit boot protocol, the first step in loading a Linux kernel
should be to setup the boot parameters (struct boot_params,
traditionally known as "zero page"). The memory for struct boot_params
should be allocated and initialized to all zero. Then the setup header
from offset 0x01f1 of kernel image on should be loaded into struct
boot_params and examined. The end of setup header can be calculated as
follow:
0x0202 + byte value at offset 0x0201
In addition to read/modify/write the setup header of the struct
boot_params as that of 16-bit boot protocol, the boot loader should
also fill the additional fields of the struct boot_params as that
described in zero-page.txt.
After setupping the struct boot_params, the boot loader can load the
32/64-bit kernel in the same way as that of 16-bit boot protocol.
In 32-bit boot protocol, the kernel is started by jumping to the
32-bit kernel entry point, which is the start address of loaded
32/64-bit kernel.
At entry, the CPU must be in 32-bit protected mode with paging
disabled; a GDT must be loaded with the descriptors for selectors
__BOOT_CS(0x10) and __BOOT_DS(0x18); both descriptors must be 4G flat
segment; __BOOS_CS must have execute/read permission, and __BOOT_DS
must have read/write permission; CS must be __BOOT_CS and DS, ES, SS
must be __BOOT_DS; interrupt must be disabled; %esi must hold the base
address of the struct boot_params; %ebp, %edi and %ebx must be zero.

900
Documentation/x86/i386/boot.txt
View File

@ -1,900 +0,0 @@
THE LINUX/x86 BOOT PROTOCOL
---------------------------
On the x86 platform, the Linux kernel uses a rather complicated boot
convention. This has evolved partially due to historical aspects, as
well as the desire in the early days to have the kernel itself be a
bootable image, the complicated PC memory model and due to changed
expectations in the PC industry caused by the effective demise of
real-mode DOS as a mainstream operating system.
Currently, the following versions of the Linux/x86 boot protocol exist.
Old kernels: zImage/Image support only. Some very early kernels
may not even support a command line.
Protocol 2.00: (Kernel 1.3.73) Added bzImage and initrd support, as
well as a formalized way to communicate between the
boot loader and the kernel. setup.S made relocatable,
although the traditional setup area still assumed
writable.
Protocol 2.01: (Kernel 1.3.76) Added a heap overrun warning.
Protocol 2.02: (Kernel 2.4.0-test3-pre3) New command line protocol.
Lower the conventional memory ceiling. No overwrite
of the traditional setup area, thus making booting
safe for systems which use the EBDA from SMM or 32-bit
BIOS entry points. zImage deprecated but still
supported.
Protocol 2.03: (Kernel 2.4.18-pre1) Explicitly makes the highest possible
initrd address available to the bootloader.
Protocol 2.04: (Kernel 2.6.14) Extend the syssize field to four bytes.
Protocol 2.05: (Kernel 2.6.20) Make protected mode kernel relocatable.
Introduce relocatable_kernel and kernel_alignment fields.
Protocol 2.06: (Kernel 2.6.22) Added a field that contains the size of
the boot command line.
Protocol 2.07: (Kernel 2.6.24) Added paravirtualised boot protocol.
Introduced hardware_subarch and hardware_subarch_data
and KEEP_SEGMENTS flag in load_flags.
Protocol 2.08: (Kernel 2.6.26) Added crc32 checksum and ELF format
payload. Introduced payload_offset and payload length
fields to aid in locating the payload.
Protocol 2.09: (Kernel 2.6.26) Added a field of 64-bit physical
pointer to single linked list of struct setup_data.
**** MEMORY LAYOUT
The traditional memory map for the kernel loader, used for Image or
zImage kernels, typically looks like:
| |
0A0000 +------------------------+
| Reserved for BIOS | Do not use. Reserved for BIOS EBDA.
09A000 +------------------------+
| Command line |
| Stack/heap | For use by the kernel real-mode code.
098000 +------------------------+
| Kernel setup | The kernel real-mode code.
090200 +------------------------+
| Kernel boot sector | The kernel legacy boot sector.
090000 +------------------------+
| Protected-mode kernel | The bulk of the kernel image.
010000 +------------------------+
| Boot loader | <- Boot sector entry point 0000:7C00
001000 +------------------------+
| Reserved for MBR/BIOS |
000800 +------------------------+
| Typically used by MBR |
000600 +------------------------+
| BIOS use only |
000000 +------------------------+
When using bzImage, the protected-mode kernel was relocated to
0x100000 ("high memory"), and the kernel real-mode block (boot sector,
setup, and stack/heap) was made relocatable to any address between
0x10000 and end of low memory. Unfortunately, in protocols 2.00 and
2.01 the 0x90000+ memory range is still used internally by the kernel;
the 2.02 protocol resolves that problem.
It is desirable to keep the "memory ceiling" -- the highest point in
low memory touched by the boot loader -- as low as possible, since
some newer BIOSes have begun to allocate some rather large amounts of
memory, called the Extended BIOS Data Area, near the top of low
memory. The boot loader should use the "INT 12h" BIOS call to verify
how much low memory is available.
Unfortunately, if INT 12h reports that the amount of memory is too
low, there is usually nothing the boot loader can do but to report an
error to the user. The boot loader should therefore be designed to
take up as little space in low memory as it reasonably can. For
zImage or old bzImage kernels, which need data written into the
0x90000 segment, the boot loader should make sure not to use memory
above the 0x9A000 point; too many BIOSes will break above that point.
For a modern bzImage kernel with boot protocol version >= 2.02, a
memory layout like the following is suggested:
~ ~
| Protected-mode kernel |
100000 +------------------------+
| I/O memory hole |
0A0000 +------------------------+
| Reserved for BIOS | Leave as much as possible unused
~ ~
| Command line | (Can also be below the X+10000 mark)
X+10000 +------------------------+
| Stack/heap | For use by the kernel real-mode code.
X+08000 +------------------------+
| Kernel setup | The kernel real-mode code.
| Kernel boot sector | The kernel legacy boot sector.
X +------------------------+
| Boot loader | <- Boot sector entry point 0000:7C00
001000 +------------------------+
| Reserved for MBR/BIOS |
000800 +------------------------+
| Typically used by MBR |
000600 +------------------------+
| BIOS use only |
000000 +------------------------+
... where the address X is as low as the design of the boot loader
permits.
**** THE REAL-MODE KERNEL HEADER
In the following text, and anywhere in the kernel boot sequence, "a
sector" refers to 512 bytes. It is independent of the actual sector
size of the underlying medium.
The first step in loading a Linux kernel should be to load the
real-mode code (boot sector and setup code) and then examine the
following header at offset 0x01f1. The real-mode code can total up to
32K, although the boot loader may choose to load only the first two
sectors (1K) and then examine the bootup sector size.
The header looks like:
Offset Proto Name Meaning
/Size
01F1/1 ALL(1 setup_sects The size of the setup in sectors
01F2/2 ALL root_flags If set, the root is mounted readonly
01F4/4 2.04+(2 syssize The size of the 32-bit code in 16-byte paras
01F8/2 ALL ram_size DO NOT USE - for bootsect.S use only
01FA/2 ALL vid_mode Video mode control
01FC/2 ALL root_dev Default root device number
01FE/2 ALL boot_flag 0xAA55 magic number
0200/2 2.00+ jump Jump instruction
0202/4 2.00+ header Magic signature "HdrS"
0206/2 2.00+ version Boot protocol version supported
0208/4 2.00+ realmode_swtch Boot loader hook (see below)
020C/2 2.00+ start_sys The load-low segment (0x1000) (obsolete)
020E/2 2.00+ kernel_version Pointer to kernel version string
0210/1 2.00+ type_of_loader Boot loader identifier
0211/1 2.00+ loadflags Boot protocol option flags
0212/2 2.00+ setup_move_size Move to high memory size (used with hooks)
0214/4 2.00+ code32_start Boot loader hook (see below)
0218/4 2.00+ ramdisk_image initrd load address (set by boot loader)
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
0228/4 2.02+ cmd_line_ptr 32-bit pointer to the kernel command line
022C/4 2.03+ initrd_addr_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
0235/3 N/A pad2 Unused
0238/4 2.06+ cmdline_size Maximum size of the kernel command line
023C/4 2.07+ hardware_subarch Hardware subarchitecture
0240/8 2.07+ hardware_subarch_data Subarchitecture-specific data
0248/4 2.08+ payload_offset Offset of kernel payload
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
(1) For backwards compatibility, if the setup_sects field contains 0, the
real value is 4.
(2) For boot protocol prior to 2.04, the upper two bytes of the syssize
field are unusable, which means the size of a bzImage kernel
cannot be determined.
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:
Image type = zImage
initrd not supported
Real-mode kernel must be located at 0x90000.
Otherwise, the "version" field contains the protocol version,
e.g. protocol version 2.01 will contain 0x0201 in this field. When
setting fields in the header, you must make sure only to set fields
supported by the protocol version in use.
**** DETAILS OF HEADER FIELDS
For each field, some are information from the kernel to the bootloader
("read"), some are expected to be filled out by the bootloader
("write"), and some are expected to be read and modified by the
bootloader ("modify").
All general purpose boot loaders should write the fields marked
(obligatory). Boot loaders who want to load the kernel at a
nonstandard address should fill in the fields marked (reloc); other
boot loaders can ignore those fields.
The byte order of all fields is littleendian (this is x86, after all.)
Field name: setup_sects
Type: read
Offset/size: 0x1f1/1
Protocol: ALL
The size of the setup code in 512-byte sectors. If this field is
0, the real value is 4. The real-mode code consists of the boot
sector (always one 512-byte sector) plus the setup code.
Field name: root_flags
Type: modify (optional)
Offset/size: 0x1f2/2
Protocol: ALL
If this field is nonzero, the root defaults to readonly. The use of
this field is deprecated; use the "ro" or "rw" options on the
command line instead.
Field name: syssize
Type: read
Offset/size: 0x1f4/4 (protocol 2.04+) 0x1f4/2 (protocol ALL)
Protocol: 2.04+
The size of the protected-mode code in units of 16-byte paragraphs.
For protocol versions older than 2.04 this field is only two bytes
wide, and therefore cannot be trusted for the size of a kernel if
the LOAD_HIGH flag is set.
Field name: ram_size
Type: kernel internal
Offset/size: 0x1f8/2
Protocol: ALL
This field is obsolete.
Field name: vid_mode
Type: modify (obligatory)
Offset/size: 0x1fa/2
Please see the section on SPECIAL COMMAND LINE OPTIONS.
Field name: root_dev
Type: modify (optional)
Offset/size: 0x1fc/2
Protocol: ALL
The default root device device number. The use of this field is
deprecated, use the "root=" option on the command line instead.
Field name: boot_flag
Type: read
Offset/size: 0x1fe/2
Protocol: ALL
Contains 0xAA55. This is the closest thing old Linux kernels have
to a magic number.
Field name: jump
Type: read
Offset/size: 0x200/2
Protocol: 2.00+
Contains an x86 jump instruction, 0xEB followed by a signed offset
relative to byte 0x202. This can be used to determine the size of
the header.
Field name: header
Type: read
Offset/size: 0x202/4
Protocol: 2.00+
Contains the magic number "HdrS" (0x53726448).
Field name: version
Type: read
Offset/size: 0x206/2
Protocol: 2.00+
Contains the boot protocol version, in (major << 8)+minor format,
e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version
10.17.
Field name: readmode_swtch
Type: modify (optional)
Offset/size: 0x208/4
Protocol: 2.00+
Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
Field name: start_sys
Type: read
Offset/size: 0x20c/4
Protocol: 2.00+
The load low segment (0x1000). Obsolete.
Field name: kernel_version
Type: read
Offset/size: 0x20e/2
Protocol: 2.00+
If set to a nonzero value, contains a pointer to a NUL-terminated
human-readable kernel version number string, less 0x200. This can
be used to display the kernel version to the user. This value
should be less than (0x200*setup_sects).
For example, if this value is set to 0x1c00, the kernel version
number string can be found at offset 0x1e00 in the kernel file.
This is a valid value if and only if the "setup_sects" field
contains the value 15 or higher, as:
0x1c00 < 15*0x200 (= 0x1e00) but
0x1c00 >= 14*0x200 (= 0x1c00)
0x1c00 >> 9 = 14, so the minimum value for setup_secs is 15.
Field name: type_of_loader
Type: write (obligatory)
Offset/size: 0x210/1
Protocol: 2.00+
If your boot loader has an assigned id (see table below), enter
0xTV here, where T is an identifier for the boot loader and V is
a version number. Otherwise, enter 0xFF here.
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
5 ELILO
7 GRuB
8 U-BOOT
9 Xen
A Gujin
B Qemu
Please contact <hpa@zytor.com> if you need a bootloader ID
value assigned.
Field name: loadflags
Type: modify (obligatory)
Offset/size: 0x211/1
Protocol: 2.00+
This field is a bitmask.
Bit 0 (read): LOADED_HIGH
- If 0, the protected-mode code is loaded at 0x10000.
- If 1, the protected-mode code is loaded at 0x100000.
Bit 5 (write): QUIET_FLAG
- If 0, print early messages.
- If 1, suppress early messages.
This requests to the kernel (decompressor and early
kernel) to not write early messages that require
accessing the display hardware directly.
Bit 6 (write): KEEP_SEGMENTS
Protocol: 2.07+
- If 0, reload the segment registers in the 32bit entry point.
- If 1, do not reload the segment registers in the 32bit entry point.
Assume that %cs %ds %ss %es are all set to flat segments with
a base of 0 (or the equivalent for their environment).
Bit 7 (write): CAN_USE_HEAP
Set this bit to 1 to indicate that the value entered in the
heap_end_ptr is valid. If this field is clear, some setup code
functionality will be disabled.
Field name: setup_move_size
Type: modify (obligatory)
Offset/size: 0x212/2
Protocol: 2.00-2.01
When using protocol 2.00 or 2.01, if the real mode kernel is not
loaded at 0x90000, it gets moved there later in the loading
sequence. Fill in this field if you want additional data (such as
the kernel command line) moved in addition to the real-mode kernel
itself.
The unit is bytes starting with the beginning of the boot sector.
This field is can be ignored when the protocol is 2.02 or higher, or
if the real-mode code is loaded at 0x90000.
Field name: code32_start
Type: modify (optional, reloc)
Offset/size: 0x214/4
Protocol: 2.00+
The address to jump to in protected mode. This defaults to the load
address of the kernel, and can be used by the boot loader to
determine the proper load address.
This field can be modified for two purposes:
1. as a boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
2. if a bootloader which does not install a hook loads a
relocatable kernel at a nonstandard address it will have to modify
this field to point to the load address.
Field name: ramdisk_image
Type: write (obligatory)
Offset/size: 0x218/4
Protocol: 2.00+
The 32-bit linear address of the initial ramdisk or ramfs. Leave at
zero if there is no initial ramdisk/ramfs.
Field name: ramdisk_size
Type: write (obligatory)
Offset/size: 0x21c/4
Protocol: 2.00+
Size of the initial ramdisk or ramfs. Leave at zero if there is no
initial ramdisk/ramfs.
Field name: bootsect_kludge
Type: kernel internal
Offset/size: 0x220/4
Protocol: 2.00+
This field is obsolete.
Field name: heap_end_ptr
Type: write (obligatory)
Offset/size: 0x224/2
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: cmd_line_ptr
Type: write (obligatory)
Offset/size: 0x228/4
Protocol: 2.02+
Set this field to the linear address of the kernel command line.
The kernel command line can be located anywhere between the end of
the setup heap and 0xA0000; it does not have to be located in the
same 64K segment as the real-mode code itself.
Fill in this field even if your boot loader does not support a
command line, in which case you can point this to an empty string
(or better yet, to the string "auto".) If this field is left at
zero, the kernel will assume that your boot loader does not support
the 2.02+ protocol.
Field name: initrd_addr_max
Type: read
Offset/size: 0x22c/4
Protocol: 2.03+
The maximum address that may be occupied by the initial
ramdisk/ramfs contents. For boot protocols 2.02 or earlier, this
field is not present, and the maximum address is 0x37FFFFFF. (This
address is defined as the address of the highest safe byte, so if
your ramdisk is exactly 131072 bytes long and this field is
0x37FFFFFF, you can start your ramdisk at 0x37FE0000.)
Field name: kernel_alignment
Type: read (reloc)
Offset/size: 0x230/4
Protocol: 2.05+
Alignment unit required by the kernel (if relocatable_kernel is true.)
Field name: relocatable_kernel
Type: read (reloc)
Offset/size: 0x234/1
Protocol: 2.05+
If this field is nonzero, the protected-mode part of the kernel can
be loaded at any address that satisfies the kernel_alignment field.
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: cmdline_size
Type: read
Offset/size: 0x238/4
Protocol: 2.06+
The maximum size of the command line without the terminating
zero. This means that the command line can contain at most
cmdline_size characters. With protocol version 2.05 and earlier, the
maximum size was 255.
Field name: hardware_subarch
Type: write (optional, defaults to x86/PC)
Offset/size: 0x23c/4
Protocol: 2.07+
In a paravirtualized environment the hardware low level architectural
pieces such as interrupt handling, page table handling, and
accessing process control registers needs to be done differently.
This field allows the bootloader to inform the kernel we are in one
one of those environments.
0x00000000 The default x86/PC environment
0x00000001 lguest
0x00000002 Xen
Field name: hardware_subarch_data
Type: write (subarch-dependent)
Offset/size: 0x240/8
Protocol: 2.07+
A pointer to data that is specific to hardware subarch
This field is currently unused for the default x86/PC environment,
do not modify.
Field name: payload_offset
Type: read
Offset/size: 0x248/4
Protocol: 2.08+
If non-zero then this field contains the offset from the end of the
real-mode code to the payload.
The payload may be compressed. The format of both the compressed and
uncompressed data should be determined using the standard magic
numbers. Currently only gzip compressed ELF is used.
Field name: payload_length
Type: read
Offset/size: 0x24c/4
Protocol: 2.08+
The length of the payload.
Field name: setup_data
Type: write (special)
Offset/size: 0x250/8
Protocol: 2.09+
The 64-bit physical pointer to NULL terminated single linked list of
struct setup_data. This is used to define a more extensible boot
parameters passing mechanism. The definition of struct setup_data is
as follow:
struct setup_data {
u64 next;
u32 type;
u32 len;
u8 data[0];
};
Where, the next is a 64-bit physical pointer to the next node of
linked list, the next field of the last node is 0; the type is used
to identify the contents of data; the len is the length of data
field; the data holds the real payload.
This list may be modified at a number of points during the bootup
process. Therefore, when modifying this list one should always make
sure to consider the case where the linked list already contains
entries.
**** THE IMAGE CHECKSUM
From boot protocol version 2.08 onwards the CRC-32 is calculated over
the entire file using the characteristic polynomial 0x04C11DB7 and an
initial remainder of 0xffffffff. The checksum is appended to the
file; therefore the CRC of the file up to the limit specified in the
syssize field of the header is always 0.
**** THE KERNEL COMMAND LINE
The kernel command line has become an important way for the boot
loader to communicate with the kernel. Some of its options are also
relevant to the boot loader itself, see "special command line options"
below.
The kernel command line is a null-terminated string. The maximum
length can be retrieved from the field cmdline_size. Before protocol
version 2.06, the maximum was 255 characters. A string that is too
long will be automatically truncated by the kernel.
If the boot protocol version is 2.02 or later, the address of the
kernel command line is given by the header field cmd_line_ptr (see
above.) This address can be anywhere between the end of the setup
heap and 0xA0000.
If the protocol version is *not* 2.02 or higher, the kernel
command line is entered using the following protocol:
At offset 0x0020 (word), "cmd_line_magic", enter the magic
number 0xA33F.
At offset 0x0022 (word), "cmd_line_offset", enter the offset
of the kernel command line (relative to the start of the
real-mode kernel).
The kernel command line *must* be within the memory region
covered by setup_move_size, so you may need to adjust this
field.
**** MEMORY LAYOUT OF THE REAL-MODE CODE
The real-mode code requires a stack/heap to be set up, as well as
memory allocated for the kernel command line. This needs to be done
in the real-mode accessible memory in bottom megabyte.
It should be noted that modern machines often have a sizable Extended
BIOS Data Area (EBDA). As a result, it is advisable to use as little
of the low megabyte as possible.
Unfortunately, under the following circumstances the 0x90000 memory
segment has to be used:
- When loading a zImage kernel ((loadflags & 0x01) == 0).
- When loading a 2.01 or earlier boot protocol kernel.
-> For the 2.00 and 2.01 boot protocols, the real-mode code
can be loaded at another address, but it is internally
relocated to 0x90000. For the "old" protocol, the
real-mode code must be loaded at 0x90000.
When loading at 0x90000, avoid using memory above 0x9a000.
For boot protocol 2.02 or higher, the command line does not have to be
located in the same 64K segment as the real-mode setup code; it is
thus permitted to give the stack/heap the full 64K segment and locate
the command line above it.
The kernel command line should not be located below the real-mode
code, nor should it be located in high memory.
**** SAMPLE BOOT CONFIGURATION
As a sample configuration, assume the following layout of the real
mode segment:
When loading below 0x90000, use the entire segment:
0x0000-0x7fff Real mode kernel
0x8000-0xdfff Stack and heap
0xe000-0xffff Kernel command line
When loading at 0x90000 OR the protocol version is 2.01 or earlier:
0x0000-0x7fff Real mode kernel
0x8000-0x97ff Stack and heap
0x9800-0x9fff Kernel command line
Such a boot loader should enter the following fields in the header:
unsigned long base_ptr; /* base address for real-mode segment */
if ( setup_sects == 0 ) {
setup_sects = 4;
}
if ( protocol >= 0x0200 ) {
type_of_loader = <type code>;
if ( loading_initrd ) {
ramdisk_image = <initrd_address>;
ramdisk_size = <initrd_size>;
}
if ( protocol >= 0x0202 && loadflags & 0x01 )
heap_end = 0xe000;
else
heap_end = 0x9800;
if ( protocol >= 0x0201 ) {
heap_end_ptr = heap_end - 0x200;
loadflags |= 0x80; /* CAN_USE_HEAP */
}
if ( protocol >= 0x0202 ) {
cmd_line_ptr = base_ptr + heap_end;
strcpy(cmd_line_ptr, cmdline);
} else {
cmd_line_magic = 0xA33F;
cmd_line_offset = heap_end;
setup_move_size = heap_end + strlen(cmdline)+1;
strcpy(base_ptr+cmd_line_offset, cmdline);
}
} else {
/* Very old kernel */
heap_end = 0x9800;
cmd_line_magic = 0xA33F;
cmd_line_offset = heap_end;
/* A very old kernel MUST have its real-mode code
loaded at 0x90000 */
if ( base_ptr != 0x90000 ) {
/* Copy the real-mode kernel */
memcpy(0x90000, base_ptr, (setup_sects+1)*512);
base_ptr = 0x90000; /* Relocated */
}
strcpy(0x90000+cmd_line_offset, cmdline);
/* It is recommended to clear memory up to the 32K mark */
memset(0x90000 + (setup_sects+1)*512, 0,
(64-(setup_sects+1))*512);
}
**** LOADING THE REST OF THE KERNEL
The 32-bit (non-real-mode) kernel starts at offset (setup_sects+1)*512
in the kernel file (again, if setup_sects == 0 the real value is 4.)
It should be loaded at address 0x10000 for Image/zImage kernels and
0x100000 for bzImage kernels.
The kernel is a bzImage kernel if the protocol >= 2.00 and the 0x01
bit (LOAD_HIGH) in the loadflags field is set:
is_bzImage = (protocol >= 0x0200) && (loadflags & 0x01);
load_address = is_bzImage ? 0x100000 : 0x10000;
Note that Image/zImage kernels can be up to 512K in size, and thus use
the entire 0x10000-0x90000 range of memory. This means it is pretty
much a requirement for these kernels to load the real-mode part at
0x90000. bzImage kernels allow much more flexibility.
**** SPECIAL COMMAND LINE OPTIONS
If the command line provided by the boot loader is entered by the
user, the user may expect the following command line options to work.
They should normally not be deleted from the kernel command line even
though not all of them are actually meaningful to the kernel. Boot
loader authors who need additional command line options for the boot
loader itself should get them registered in
Documentation/kernel-parameters.txt to make sure they will not
conflict with actual kernel options now or in the future.
vga=<mode>
<mode> here is either an integer (in C notation, either
decimal, octal, or hexadecimal) or one of the strings
"normal" (meaning 0xFFFF), "ext" (meaning 0xFFFE) or "ask"
(meaning 0xFFFD). This value should be entered into the
vid_mode field, as it is used by the kernel before the command
line is parsed.
mem=<size>
<size> is an integer in C notation optionally followed by
(case insensitive) K, M, G, T, P or E (meaning << 10, << 20,
<< 30, << 40, << 50 or << 60). This specifies the end of
memory to the kernel. This affects the possible placement of
an initrd, since an initrd should be placed near end of
memory. Note that this is an option to *both* the kernel and
the bootloader!
initrd=<file>
An initrd should be loaded. The meaning of <file> is
obviously bootloader-dependent, and some boot loaders
(e.g. LILO) do not have such a command.
In addition, some boot loaders add the following options to the
user-specified command line:
BOOT_IMAGE=<file>
The boot image which was loaded. Again, the meaning of <file>
is obviously bootloader-dependent.
auto
The kernel was booted without explicit user intervention.
If these options are added by the boot loader, it is highly
recommended that they are located *first*, before the user-specified
or configuration-specified command line. Otherwise, "init=/bin/sh"
gets confused by the "auto" option.
**** RUNNING THE KERNEL
The kernel is started by jumping to the kernel entry point, which is
located at *segment* offset 0x20 from the start of the real mode
kernel. This means that if you loaded your real-mode kernel code at
0x90000, the kernel entry point is 9020:0000.
At entry, ds = es = ss should point to the start of the real-mode
kernel code (0x9000 if the code is loaded at 0x90000), sp should be
set up properly, normally pointing to the top of the heap, and
interrupts should be disabled. Furthermore, to guard against bugs in
the kernel, it is recommended that the boot loader sets fs = gs = ds =
es = ss.
In our example from above, we would do:
/* Note: in the case of the "old" kernel protocol, base_ptr must
be == 0x90000 at this point; see the previous sample code */
seg = base_ptr >> 4;
cli(); /* Enter with interrupts disabled! */
/* Set up the real-mode kernel stack */
_SS = seg;
_SP = heap_end;
_DS = _ES = _FS = _GS = seg;
jmp_far(seg+0x20, 0); /* Run the kernel */
If your boot sector accesses a floppy drive, it is recommended to
switch off the floppy motor before running the kernel, since the
kernel boot leaves interrupts off and thus the motor will not be
switched off, especially if the loaded kernel has the floppy driver as
a demand-loaded module!
**** ADVANCED BOOT LOADER HOOKS
If the boot loader runs in a particularly hostile environment (such as
LOADLIN, which runs under DOS) it may be impossible to follow the
standard memory location requirements. Such a boot loader may use the
following hooks that, if set, are invoked by the kernel at the
appropriate time. The use of these hooks should probably be
considered an absolutely last resort!
IMPORTANT: All the hooks are required to preserve %esp, %ebp, %esi and
%edi across invocation.
realmode_swtch:
A 16-bit real mode far subroutine invoked immediately before
entering protected mode. The default routine disables NMI, so
your routine should probably do so, too.
code32_start:
A 32-bit flat-mode routine *jumped* to immediately after the
transition to protected mode, but before the kernel is
uncompressed. No segments, except CS, are guaranteed to be
set up (current kernels do, but older ones do not); you should
set them up to BOOT_DS (0x18) yourself.
After completing your hook, you should jump to the address
that was in this field before your boot loader overwrote it
(relocated, if appropriate.)
**** 32-bit BOOT PROTOCOL
For machine with some new BIOS other than legacy BIOS, such as EFI,
LinuxBIOS, etc, and kexec, the 16-bit real mode setup code in kernel
based on legacy BIOS can not be used, so a 32-bit boot protocol needs
to be defined.
In 32-bit boot protocol, the first step in loading a Linux kernel
should be to setup the boot parameters (struct boot_params,
traditionally known as "zero page"). The memory for struct boot_params
should be allocated and initialized to all zero. Then the setup header
from offset 0x01f1 of kernel image on should be loaded into struct
boot_params and examined. The end of setup header can be calculated as
follow:
0x0202 + byte value at offset 0x0201
In addition to read/modify/write the setup header of the struct
boot_params as that of 16-bit boot protocol, the boot loader should
also fill the additional fields of the struct boot_params as that
described in zero-page.txt.
After setupping the struct boot_params, the boot loader can load the
32/64-bit kernel in the same way as that of 16-bit boot protocol.
In 32-bit boot protocol, the kernel is started by jumping to the
32-bit kernel entry point, which is the start address of loaded
32/64-bit kernel.
At entry, the CPU must be in 32-bit protected mode with paging
disabled; a GDT must be loaded with the descriptors for selectors
__BOOT_CS(0x10) and __BOOT_DS(0x18); both descriptors must be 4G flat
segment; __BOOS_CS must have execute/read permission, and __BOOT_DS
must have read/write permission; CS must be __BOOT_CS and DS, ES, SS
must be __BOOT_DS; interrupt must be disabled; %esi must hold the base
address of the struct boot_params; %ebp, %edi and %ebx must be zero.

305
Documentation/x86/mtrr.txt Normal file
View File

@ -0,0 +1,305 @@
MTRR (Memory Type Range Register) control
3 Jun 1999
Richard Gooch
<rgooch@atnf.csiro.au>
On Intel P6 family processors (Pentium Pro, Pentium II and later)
the Memory Type Range Registers (MTRRs) may be used to control
processor access to memory ranges. This is most useful when you have
a video (VGA) card on a PCI or AGP bus. Enabling write-combining
allows bus write transfers to be combined into a larger transfer
before bursting over the PCI/AGP bus. This can increase performance
of image write operations 2.5 times or more.
The Cyrix 6x86, 6x86MX and M II processors have Address Range
Registers (ARRs) which provide a similar functionality to MTRRs. For
these, the ARRs are used to emulate the MTRRs.
The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
MTRRs. These are supported. The AMD Athlon family provide 8 Intel
style MTRRs.
The Centaur C6 (WinChip) has 8 MCRs, allowing write-combining. These
are supported.
The VIA Cyrix III and VIA C3 CPUs offer 8 Intel style MTRRs.
The CONFIG_MTRR option creates a /proc/mtrr file which may be used
to manipulate your MTRRs. Typically the X server should use
this. This should have a reasonably generic interface so that
similar control registers on other processors can be easily
supported.
There are two interfaces to /proc/mtrr: one is an ASCII interface
which allows you to read and write. The other is an ioctl()
interface. The ASCII interface is meant for administration. The
ioctl() interface is meant for C programs (i.e. the X server). The
interfaces are described below, with sample commands and C code.
===============================================================================
Reading MTRRs from the shell:
% cat /proc/mtrr
reg00: base=0x00000000 ( 0MB), size= 128MB: write-back, count=1
reg01: base=0x08000000 ( 128MB), size= 64MB: write-back, count=1
===============================================================================
Creating MTRRs from the C-shell:
# echo "base=0xf8000000 size=0x400000 type=write-combining" >! /proc/mtrr
or if you use bash:
# echo "base=0xf8000000 size=0x400000 type=write-combining" >| /proc/mtrr
And the result thereof:
% cat /proc/mtrr
reg00: base=0x00000000 ( 0MB), size= 128MB: write-back, count=1
reg01: base=0x08000000 ( 128MB), size= 64MB: write-back, count=1
reg02: base=0xf8000000 (3968MB), size= 4MB: write-combining, count=1
This is for video RAM at base address 0xf8000000 and size 4 megabytes. To
find out your base address, you need to look at the output of your X
server, which tells you where the linear framebuffer address is. A
typical line that you may get is:
(--) S3: PCI: 968 rev 0, Linear FB @ 0xf8000000
Note that you should only use the value from the X server, as it may
move the framebuffer base address, so the only value you can trust is
that reported by the X server.
To find out the size of your framebuffer (what, you don't actually
know?), the following line will tell you:
(--) S3: videoram: 4096k
That's 4 megabytes, which is 0x400000 bytes (in hexadecimal).
A patch is being written for XFree86 which will make this automatic:
in other words the X server will manipulate /proc/mtrr using the
ioctl() interface, so users won't have to do anything. If you use a
commercial X server, lobby your vendor to add support for MTRRs.
===============================================================================
Creating overlapping MTRRs:
%echo "base=0xfb000000 size=0x1000000 type=write-combining" >/proc/mtrr
%echo "base=0xfb000000 size=0x1000 type=uncachable" >/proc/mtrr
And the results: cat /proc/mtrr
reg00: base=0x00000000 ( 0MB), size= 64MB: write-back, count=1
reg01: base=0xfb000000 (4016MB), size= 16MB: write-combining, count=1
reg02: base=0xfb000000 (4016MB), size= 4kB: uncachable, count=1
Some cards (especially Voodoo Graphics boards) need this 4 kB area
excluded from the beginning of the region because it is used for
registers.
NOTE: You can only create type=uncachable region, if the first
region that you created is type=write-combining.
===============================================================================
Removing MTRRs from the C-shell:
% echo "disable=2" >! /proc/mtrr
or using bash:
% echo "disable=2" >| /proc/mtrr
===============================================================================
Reading MTRRs from a C program using ioctl()'s:
/* mtrr-show.c
Source file for mtrr-show (example program to show MTRRs using ioctl()'s)
Copyright (C) 1997-1998 Richard Gooch
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
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.
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., 675 Mass Ave, Cambridge, MA 02139, USA.
Richard Gooch may be reached by email at rgooch@atnf.csiro.au
The postal address is:
Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
*/
/*
This program will use an ioctl() on /proc/mtrr to show the current MTRR
settings. This is an alternative to reading /proc/mtrr.
Written by Richard Gooch 17-DEC-1997
Last updated by Richard Gooch 2-MAY-1998
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <errno.h>
#include <asm/mtrr.h>
#define TRUE 1
#define FALSE 0
#define ERRSTRING strerror (errno)
static char *mtrr_strings[MTRR_NUM_TYPES] =
{
"uncachable", /* 0 */
"write-combining", /* 1 */
"?", /* 2 */
"?", /* 3 */
"write-through", /* 4 */
"write-protect", /* 5 */
"write-back", /* 6 */
};
int main ()
{
int fd;
struct mtrr_gentry gentry;
if ( ( fd = open ("/proc/mtrr", O_RDONLY, 0) ) == -1 )
{
if (errno == ENOENT)
{
fputs ("/proc/mtrr not found: not supported or you don't have a PPro?\n",
stderr);
exit (1);
}
fprintf (stderr, "Error opening /proc/mtrr\t%s\n", ERRSTRING);
exit (2);
}
for (gentry.regnum = 0; ioctl (fd, MTRRIOC_GET_ENTRY, &gentry) == 0;
++gentry.regnum)
{
if (gentry.size < 1)
{
fprintf (stderr, "Register: %u disabled\n", gentry.regnum);
continue;
}
fprintf (stderr, "Register: %u base: 0x%lx size: 0x%lx type: %s\n",
gentry.regnum, gentry.base, gentry.size,
mtrr_strings[gentry.type]);
}
if (errno == EINVAL) exit (0);
fprintf (stderr, "Error doing ioctl(2) on /dev/mtrr\t%s\n", ERRSTRING);
exit (3);
} /* End Function main */
===============================================================================
Creating MTRRs from a C programme using ioctl()'s:
/* mtrr-add.c
Source file for mtrr-add (example programme to add an MTRRs using ioctl())
Copyright (C) 1997-1998 Richard Gooch
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
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.
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., 675 Mass Ave, Cambridge, MA 02139, USA.
Richard Gooch may be reached by email at rgooch@atnf.csiro.au
The postal address is:
Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
*/
/*
This programme will use an ioctl() on /proc/mtrr to add an entry. The first
available mtrr is used. This is an alternative to writing /proc/mtrr.
Written by Richard Gooch 17-DEC-1997
Last updated by Richard Gooch 2-MAY-1998
*/
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/ioctl.h>
#include <errno.h>
#include <asm/mtrr.h>
#define TRUE 1
#define FALSE 0
#define ERRSTRING strerror (errno)
static char *mtrr_strings[MTRR_NUM_TYPES] =
{
"uncachable", /* 0 */
"write-combining", /* 1 */
"?", /* 2 */
"?", /* 3 */
"write-through", /* 4 */
"write-protect", /* 5 */
"write-back", /* 6 */
};
int main (int argc, char **argv)
{
int fd;
struct mtrr_sentry sentry;
if (argc != 4)
{
fprintf (stderr, "Usage:\tmtrr-add base size type\n");
exit (1);
}
sentry.base = strtoul (argv[1], NULL, 0);
sentry.size = strtoul (argv[2], NULL, 0);
for (sentry.type = 0; sentry.type < MTRR_NUM_TYPES; ++sentry.type)
{
if (strcmp (argv[3], mtrr_strings[sentry.type]) == 0) break;
}
if (sentry.type >= MTRR_NUM_TYPES)
{
fprintf (stderr, "Illegal type: \"%s\"\n", argv[3]);
exit (2);
}
if ( ( fd = open ("/proc/mtrr", O_WRONLY, 0) ) == -1 )
{
if (errno == ENOENT)
{
fputs ("/proc/mtrr not found: not supported or you don't have a PPro?\n",
stderr);
exit (3);
}
fprintf (stderr, "Error opening /proc/mtrr\t%s\n", ERRSTRING);
exit (4);
}
if (ioctl (fd, MTRRIOC_ADD_ENTRY, &sentry) == -1)
{
fprintf (stderr, "Error doing ioctl(2) on /dev/mtrr\t%s\n", ERRSTRING);
exit (5);
}
fprintf (stderr, "Sleeping for 5 seconds so you can see the new entry\n");
sleep (5);
close (fd);
fputs ("I've just closed /proc/mtrr so now the new entry should be gone\n",
stderr);
} /* End Function main */
===============================================================================

54
Documentation/x86/pat.txt
View File

@ -14,6 +14,10 @@ PAT allows for different types of memory attributes. The most commonly used
ones that will be supported at this time are Write-back, Uncached,
Write-combined and Uncached Minus.
PAT APIs
--------
There are many different APIs in the kernel that allows setting of memory
attributes at the page level. In order to avoid aliasing, these interfaces
should be used thoughtfully. Below is a table of interfaces available,
@ -26,38 +30,38 @@ address range to avoid any aliasing.
API | RAM | ACPI,... | Reserved/Holes |
-----------------------|----------|------------|------------------|
| | | |
ioremap | -- | UC | UC |
ioremap | -- | UC- | UC- |
| | | |
ioremap_cache | -- | WB | WB |
| | | |
ioremap_nocache | -- | UC | UC |
ioremap_nocache | -- | UC- | UC- |
| | | |
ioremap_wc | -- | -- | WC |
| | | |
set_memory_uc | UC | -- | -- |
set_memory_uc | UC- | -- | -- |
set_memory_wb | | | |
| | | |
set_memory_wc | WC | -- | -- |
set_memory_wb | | | |
| | | |
pci sysfs resource | -- | -- | UC |
pci sysfs resource | -- | -- | UC- |
| | | |
pci sysfs resource_wc | -- | -- | WC |
is IORESOURCE_PREFETCH| | | |
| | | |
pci proc | -- | -- | UC |
pci proc | -- | -- | UC- |
!PCIIOC_WRITE_COMBINE | | | |
| | | |
pci proc | -- | -- | WC |
PCIIOC_WRITE_COMBINE | | | |
| | | |
/dev/mem | -- | UC | UC |
/dev/mem | -- | WB/WC/UC- | WB/WC/UC- |
read-write | | | |
| | | |
/dev/mem | -- | UC | UC |
/dev/mem | -- | UC- | UC- |
mmap SYNC flag | | | |
| | | |
/dev/mem | -- | WB/WC/UC | WB/WC/UC |
/dev/mem | -- | WB/WC/UC- | WB/WC/UC- |
mmap !SYNC flag | |(from exist-| (from exist- |
and | | ing alias)| ing alias) |
any alias to this area| | | |
@ -68,7 +72,7 @@ pci proc | -- | -- | WC |
and | | | |
MTRR says WB | | | |
| | | |
/dev/mem | -- | -- | UC_MINUS |
/dev/mem | -- | -- | UC- |
mmap !SYNC flag | | | |
no alias to this area | | | |
and | | | |
@ -98,3 +102,35 @@ types.
Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
PAT debugging
-------------
With CONFIG_DEBUG_FS enabled, PAT memtype list can be examined by
# mount -t debugfs debugfs /sys/kernel/debug
# cat /sys/kernel/debug/x86/pat_memtype_list
PAT memtype list:
uncached-minus @ 0x7fadf000-0x7fae0000
uncached-minus @ 0x7fb19000-0x7fb1a000
uncached-minus @ 0x7fb1a000-0x7fb1b000
uncached-minus @ 0x7fb1b000-0x7fb1c000
uncached-minus @ 0x7fb1c000-0x7fb1d000
uncached-minus @ 0x7fb1d000-0x7fb1e000
uncached-minus @ 0x7fb1e000-0x7fb25000
uncached-minus @ 0x7fb25000-0x7fb26000
uncached-minus @ 0x7fb26000-0x7fb27000
uncached-minus @ 0x7fb27000-0x7fb28000
uncached-minus @ 0x7fb28000-0x7fb2e000
uncached-minus @ 0x7fb2e000-0x7fb2f000
uncached-minus @ 0x7fb2f000-0x7fb30000
uncached-minus @ 0x7fb31000-0x7fb32000
uncached-minus @ 0x80000000-0x90000000
This list shows physical address ranges and various PAT settings used to
access those physical address ranges.
Another, more verbose way of getting PAT related debug messages is with
"debugpat" boot parameter. With this parameter, various debug messages are
printed to dmesg log.

0
Documentation/x86/i386/usb-legacy-support.txt → Documentation/x86/usb-legacy-support.txt
View File

4
Documentation/x86/x86_64/boot-options.txt
View File

@ -54,10 +54,6 @@ APICs
apicmaintimer. Useful when your PIT timer is totally
broken.
disable_8254_timer / enable_8254_timer
Enable interrupt 0 timer routing over the 8254 in addition to over
the IO-APIC. The kernel tries to set a sensible default.
Early Console
syntax: earlyprintk=vga

0
Documentation/x86/i386/zero-page.txt → Documentation/x86/zero-page.txt
View File

897
MAINTAINERS
View File

File diff suppressed because it is too large Load Diff

2
Makefile
View File

@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 27
EXTRAVERSION = -rc9
EXTRAVERSION =
NAME = Rotary Wombat
# *DOCUMENTATION*

14
arch/Kconfig
View File

@ -13,6 +13,20 @@ config OPROFILE
If unsure, say N.
config OPROFILE_IBS
bool "OProfile AMD IBS support (EXPERIMENTAL)"
default n
depends on OPROFILE && SMP && X86
help
Instruction-Based Sampling (IBS) is a new profiling
technique that provides rich, precise program performance
information. IBS is introduced by AMD Family10h processors
(AMD Opteron Quad-Core processor “Barcelona”) to overcome
the limitations of conventional performance counter
sampling.
If unsure, say N.
config HAVE_OPROFILE
def_bool n

4
arch/alpha/Kconfig
View File

@ -5,6 +5,7 @@
config ALPHA
bool
default y
select HAVE_AOUT
select HAVE_IDE
select HAVE_OPROFILE
help
@ -68,9 +69,6 @@ config AUTO_IRQ_AFFINITY
depends on SMP
default y
config ARCH_SUPPORTS_AOUT
def_bool y
source "init/Kconfig"

4
arch/alpha/include/asm/statfs.h
View File

@ -1,6 +1,10 @@
#ifndef _ALPHA_STATFS_H
#define _ALPHA_STATFS_H
/* Alpha is the only 64-bit platform with 32-bit statfs. And doesn't
even seem to implement statfs64 */
#define __statfs_word __u32
#include <asm-generic/statfs.h>
#endif

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

@ -149,6 +149,9 @@ smp_callin(void)
atomic_inc(&init_mm.mm_count);
current->active_mm = &init_mm;
/* inform the notifiers about the new cpu */
notify_cpu_starting(cpuid);
/* Must have completely accurate bogos. */
local_irq_enable();

4
arch/arm/Kconfig
View File

@ -8,6 +8,7 @@ mainmenu "Linux Kernel Configuration"
config ARM
bool
default y
select HAVE_AOUT
select HAVE_IDE
select RTC_LIB
select SYS_SUPPORTS_APM_EMULATION
@ -140,9 +141,6 @@ config GENERIC_CALIBRATE_DELAY
bool
default y
config ARCH_SUPPORTS_AOUT
def_bool y
config ARCH_MAY_HAVE_PC_FDC
bool

34
arch/arm/include/asm/statfs.h
View File

@ -1,42 +1,12 @@
#ifndef _ASMARM_STATFS_H
#define _ASMARM_STATFS_H
#ifndef __KERNEL_STRICT_NAMES
# include <linux/types.h>
typedef __kernel_fsid_t fsid_t;
#endif
struct statfs {
__u32 f_type;
__u32 f_bsize;
__u32 f_blocks;
__u32 f_bfree;
__u32 f_bavail;
__u32 f_files;
__u32 f_ffree;
__kernel_fsid_t f_fsid;
__u32 f_namelen;
__u32 f_frsize;
__u32 f_spare[5];
};
/*
* With EABI there is 4 bytes of padding added to this structure.
* Let's pack it so the padding goes away to simplify dual ABI support.
* Note that user space does NOT have to pack this structure.
*/
struct statfs64 {
__u32 f_type;
__u32 f_bsize;
__u64 f_blocks;
__u64 f_bfree;
__u64 f_bavail;
__u64 f_files;
__u64 f_ffree;
__kernel_fsid_t f_fsid;
__u32 f_namelen;
__u32 f_frsize;
__u32 f_spare[5];
} __attribute__ ((packed,aligned(4)));
#define ARCH_PACK_STATFS64 __attribute__((packed,aligned(4)))
#include <asm-generic/statfs.h>
#endif

17
arch/arm/kernel/dma.c
View File

@ -25,23 +25,6 @@ EXPORT_SYMBOL(dma_spin_lock);
static dma_t dma_chan[MAX_DMA_CHANNELS];
/*
* Get dma list for /proc/dma
*/
int get_dma_list(char *buf)
{
dma_t *dma;
char *p = buf;
int i;
for (i = 0, dma = dma_chan; i < MAX_DMA_CHANNELS; i++, dma++)
if (dma->lock)
p += sprintf(p, "%2d: %14s %s\n", i,
dma->d_ops->type, dma->device_id);
return p - buf;
}
/*
* Request DMA channel
*

1
arch/arm/kernel/smp.c
View File

@ -277,6 +277,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
/*
* Enable local interrupts.
*/
notify_cpu_starting(cpu);
local_irq_enable();
local_fiq_enable();

2
arch/arm/mach-kirkwood/db88f6281-bp-setup.c
View File

@ -25,7 +25,7 @@
#include "common.h"
static struct mv643xx_eth_platform_data db88f6281_ge00_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
static struct mv_sata_platform_data db88f6281_sata_data = {

2
arch/arm/mach-kirkwood/rd88f6192-nas-setup.c
View File

@ -30,7 +30,7 @@
#define RD88F6192_GPIO_USB_VBUS 10
static struct mv643xx_eth_platform_data rd88f6192_ge00_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
static struct mv_sata_platform_data rd88f6192_sata_data = {

2
arch/arm/mach-kirkwood/rd88f6281-setup.c
View File

@ -69,7 +69,7 @@ static struct platform_device rd88f6281_nand_flash = {
};
static struct mv643xx_eth_platform_data rd88f6281_ge00_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
.speed = SPEED_1000,
.duplex = DUPLEX_FULL,
};

2
arch/arm/mach-loki/lb88rc8480-setup.c
View File

@ -67,7 +67,7 @@ static struct platform_device lb88rc8480_boot_flash = {
};
static struct mv643xx_eth_platform_data lb88rc8480_ge0_data = {
.phy_addr = 1,
.phy_addr = MV643XX_ETH_PHY_ADDR(1),
.mac_addr = { 0x00, 0x50, 0x43, 0x11, 0x22, 0x33 },
};

6
arch/arm/mach-mv78xx0/common.c
View File

@ -335,6 +335,7 @@ void __init mv78xx0_ge00_init(struct mv643xx_eth_platform_data *eth_data)
struct mv643xx_eth_shared_platform_data mv78xx0_ge01_shared_data = {
.t_clk = 0,
.dram = &mv78xx0_mbus_dram_info,
.shared_smi = &mv78xx0_ge00_shared,
};
static struct resource mv78xx0_ge01_shared_resources[] = {
@ -375,7 +376,6 @@ static struct platform_device mv78xx0_ge01 = {
void __init mv78xx0_ge01_init(struct mv643xx_eth_platform_data *eth_data)
{
eth_data->shared = &mv78xx0_ge01_shared;
eth_data->shared_smi = &mv78xx0_ge00_shared;
mv78xx0_ge01.dev.platform_data = eth_data;
platform_device_register(&mv78xx0_ge01_shared);
@ -389,6 +389,7 @@ void __init mv78xx0_ge01_init(struct mv643xx_eth_platform_data *eth_data)
struct mv643xx_eth_shared_platform_data mv78xx0_ge10_shared_data = {
.t_clk = 0,
.dram = &mv78xx0_mbus_dram_info,
.shared_smi = &mv78xx0_ge00_shared,
};
static struct resource mv78xx0_ge10_shared_resources[] = {
@ -429,7 +430,6 @@ static struct platform_device mv78xx0_ge10 = {
void __init mv78xx0_ge10_init(struct mv643xx_eth_platform_data *eth_data)
{
eth_data->shared = &mv78xx0_ge10_shared;
eth_data->shared_smi = &mv78xx0_ge00_shared;
mv78xx0_ge10.dev.platform_data = eth_data;
platform_device_register(&mv78xx0_ge10_shared);
@ -443,6 +443,7 @@ void __init mv78xx0_ge10_init(struct mv643xx_eth_platform_data *eth_data)
struct mv643xx_eth_shared_platform_data mv78xx0_ge11_shared_data = {
.t_clk = 0,
.dram = &mv78xx0_mbus_dram_info,
.shared_smi = &mv78xx0_ge00_shared,
};
static struct resource mv78xx0_ge11_shared_resources[] = {
@ -483,7 +484,6 @@ static struct platform_device mv78xx0_ge11 = {
void __init mv78xx0_ge11_init(struct mv643xx_eth_platform_data *eth_data)
{
eth_data->shared = &mv78xx0_ge11_shared;
eth_data->shared_smi = &mv78xx0_ge00_shared;
mv78xx0_ge11.dev.platform_data = eth_data;
platform_device_register(&mv78xx0_ge11_shared);

8
arch/arm/mach-mv78xx0/db78x00-bp-setup.c
View File

@ -19,19 +19,19 @@
#include "common.h"
static struct mv643xx_eth_platform_data db78x00_ge00_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
static struct mv643xx_eth_platform_data db78x00_ge01_data = {
.phy_addr = 9,
.phy_addr = MV643XX_ETH_PHY_ADDR(9),
};
static struct mv643xx_eth_platform_data db78x00_ge10_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
};
static struct mv643xx_eth_platform_data db78x00_ge11_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
};
static struct mv_sata_platform_data db78x00_sata_data = {

2
arch/arm/mach-orion5x/db88f5281-setup.c
View File

@ -285,7 +285,7 @@ subsys_initcall(db88f5281_pci_init);
* Ethernet
****************************************************************************/
static struct mv643xx_eth_platform_data db88f5281_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
/*****************************************************************************

2
arch/arm/mach-orion5x/dns323-setup.c
View File

@ -79,7 +79,7 @@ subsys_initcall(dns323_pci_init);
*/
static struct mv643xx_eth_platform_data dns323_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
/****************************************************************************

2
arch/arm/mach-orion5x/include/mach/orion5x.h
View File

@ -157,9 +157,11 @@
#define CPU_CONF ORION5X_BRIDGE_REG(0x100)
#define CPU_CTRL ORION5X_BRIDGE_REG(0x104)
#define CPU_RESET_MASK ORION5X_BRIDGE_REG(0x108)
#define WDT_RESET 0x0002
#define CPU_SOFT_RESET ORION5X_BRIDGE_REG(0x10c)
#define POWER_MNG_CTRL_REG ORION5X_BRIDGE_REG(0x11C)
#define BRIDGE_CAUSE ORION5X_BRIDGE_REG(0x110)
#define WDT_INT_REQ 0x0008
#define BRIDGE_MASK ORION5X_BRIDGE_REG(0x114)
#define BRIDGE_INT_TIMER0 0x0002
#define BRIDGE_INT_TIMER1 0x0004

2
arch/arm/mach-orion5x/kurobox_pro-setup.c
View File

@ -161,7 +161,7 @@ subsys_initcall(kurobox_pro_pci_init);
****************************************************************************/
static struct mv643xx_eth_platform_data kurobox_pro_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
/*****************************************************************************

2
arch/arm/mach-orion5x/mss2-setup.c
View File

@ -109,7 +109,7 @@ subsys_initcall(mss2_pci_init);
****************************************************************************/
static struct mv643xx_eth_platform_data mss2_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
/*****************************************************************************

2
arch/arm/mach-orion5x/mv2120-setup.c
View File

@ -39,7 +39,7 @@
* Ethernet
****************************************************************************/
static struct mv643xx_eth_platform_data mv2120_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
static struct mv_sata_platform_data mv2120_sata_data = {

2
arch/arm/mach-orion5x/rd88f5181l-fxo-setup.c
View File

@ -88,7 +88,7 @@ static struct orion5x_mpp_mode rd88f5181l_fxo_mpp_modes[] __initdata = {
};
static struct mv643xx_eth_platform_data rd88f5181l_fxo_eth_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
.speed = SPEED_1000,
.duplex = DUPLEX_FULL,
};

2
arch/arm/mach-orion5x/rd88f5181l-ge-setup.c
View File

@ -89,7 +89,7 @@ static struct orion5x_mpp_mode rd88f5181l_ge_mpp_modes[] __initdata = {
};
static struct mv643xx_eth_platform_data rd88f5181l_ge_eth_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
.speed = SPEED_1000,
.duplex = DUPLEX_FULL,
};

2
arch/arm/mach-orion5x/rd88f5182-setup.c
View File

@ -221,7 +221,7 @@ subsys_initcall(rd88f5182_pci_init);
****************************************************************************/
static struct mv643xx_eth_platform_data rd88f5182_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
/*****************************************************************************

3
arch/arm/mach-orion5x/ts78xx-setup.c
View File

@ -103,8 +103,7 @@ static struct platform_device ts78xx_nor_boot_flash = {
* Ethernet
****************************************************************************/
static struct mv643xx_eth_platform_data ts78xx_eth_data = {
.phy_addr = 0,
.force_phy_addr = 1,
.phy_addr = MV643XX_ETH_PHY_ADDR(0),
};
/*****************************************************************************

2
arch/arm/mach-orion5x/tsx09-common.c
View File

@ -49,7 +49,7 @@ void qnap_tsx09_power_off(void)
****************************************************************************/
struct mv643xx_eth_platform_data qnap_tsx09_eth_data = {
.phy_addr = 8,
.phy_addr = MV643XX_ETH_PHY_ADDR(8),
};
static int __init qnap_tsx09_parse_hex_nibble(char n)

2
arch/arm/mach-orion5x/wnr854t-setup.c
View File

@ -92,7 +92,7 @@ static struct platform_device wnr854t_nor_flash = {
};
static struct mv643xx_eth_platform_data wnr854t_eth_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
.speed = SPEED_1000,
.duplex = DUPLEX_FULL,
};

2
arch/arm/mach-orion5x/wrt350n-v2-setup.c
View File

@ -100,7 +100,7 @@ static struct platform_device wrt350n_v2_nor_flash = {
};
static struct mv643xx_eth_platform_data wrt350n_v2_eth_data = {
.phy_addr = -1,
.phy_addr = MV643XX_ETH_PHY_NONE,
.speed = SPEED_1000,
.duplex = DUPLEX_FULL,
};

2
arch/arm/mach-pxa/cm-x270.c
View File

@ -162,7 +162,7 @@ static void __init cmx270_init_rtc(void)
platform_device_register(&cmx270_rtc_device);
}
#else
static inline void cmx2xx_init_rtc(void) {}
static inline void cmx270_init_rtc(void) {}
#endif
/* 2700G graphics */

2
arch/arm/mach-pxa/include/mach/camera.h
View File

@ -36,8 +36,6 @@
struct pxacamera_platform_data {
int (*init)(struct device *);
int (*power)(struct device *, int);
int (*reset)(struct device *, int);
unsigned long flags;
unsigned long mclk_10khz;

9
arch/arm/mach-pxa/include/mach/reset.h
View File

@ -10,9 +10,12 @@
extern unsigned int reset_status;
extern void clear_reset_status(unsigned int mask);
/*
* register GPIO as reset generator
/**
* init_gpio_reset() - register GPIO as reset generator
*
* @gpio - gpio nr
* @output - set gpio as out/low instead of input during normal work
*/
extern int init_gpio_reset(int gpio);
extern int init_gpio_reset(int gpio, int output);
#endif /* __ASM_ARCH_RESET_H */

9
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 init_gpio_reset(int gpio, int output)
{
int rc;
@ -30,9 +30,12 @@ int init_gpio_reset(int gpio)
goto out;
}
rc = gpio_direction_input(gpio);
if (output)
rc = gpio_direction_output(gpio, 0);
else
rc = gpio_direction_input(gpio);
if (rc) {
printk(KERN_ERR "Can't configure reset_gpio for input\n");
printk(KERN_ERR "Can't configure reset_gpio\n");
gpio_free(gpio);
goto out;
}

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

@ -618,7 +618,7 @@ static void spitz_restart(char mode)
static void __init common_init(void)
{
init_gpio_reset(SPITZ_GPIO_ON_RESET);
init_gpio_reset(SPITZ_GPIO_ON_RESET, 1);
pm_power_off = spitz_poweroff;
arm_pm_restart = spitz_restart;

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

@ -781,7 +781,7 @@ 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);
init_gpio_reset(TOSA_GPIO_ON_RESET, 0);
pm_power_off = tosa_poweroff;
arm_pm_restart = tosa_restart;

54
arch/arm/mach-pxa/viper.c
View File

@ -204,25 +204,54 @@ static void viper_set_core_cpu_voltage(unsigned long khz, int force)
/* Interrupt handling */
static unsigned long viper_irq_enabled_mask;
static const int viper_isa_irqs[] = { 3, 4, 5, 6, 7, 10, 11, 12, 9, 14, 15 };
static const int viper_isa_irq_map[] = {
0, /* ISA irq #0, invalid */
0, /* ISA irq #1, invalid */
0, /* ISA irq #2, invalid */
1 << 0, /* ISA irq #3 */
1 << 1, /* ISA irq #4 */
1 << 2, /* ISA irq #5 */
1 << 3, /* ISA irq #6 */
1 << 4, /* ISA irq #7 */
0, /* ISA irq #8, invalid */
1 << 8, /* ISA irq #9 */
1 << 5, /* ISA irq #10 */
1 << 6, /* ISA irq #11 */
1 << 7, /* ISA irq #12 */
0, /* ISA irq #13, invalid */
1 << 9, /* ISA irq #14 */
1 << 10, /* ISA irq #15 */
};
static inline int viper_irq_to_bitmask(unsigned int irq)
{
return viper_isa_irq_map[irq - PXA_ISA_IRQ(0)];
}
static inline int viper_bit_to_irq(int bit)
{
return viper_isa_irqs[bit] + PXA_ISA_IRQ(0);
}
static void viper_ack_irq(unsigned int irq)
{
int viper_irq = irq - PXA_ISA_IRQ(0);
int viper_irq = viper_irq_to_bitmask(irq);
if (viper_irq < 8)
VIPER_LO_IRQ_STATUS = 1 << viper_irq;
if (viper_irq & 0xff)
VIPER_LO_IRQ_STATUS = viper_irq;
else
VIPER_HI_IRQ_STATUS = 1 << (viper_irq - 8);
VIPER_HI_IRQ_STATUS = (viper_irq >> 8);
}
static void viper_mask_irq(unsigned int irq)
{
viper_irq_enabled_mask &= ~(1 << (irq - PXA_ISA_IRQ(0)));
viper_irq_enabled_mask &= ~(viper_irq_to_bitmask(irq));
}
static void viper_unmask_irq(unsigned int irq)
{
viper_irq_enabled_mask |= (1 << (irq - PXA_ISA_IRQ(0)));
viper_irq_enabled_mask |= viper_irq_to_bitmask(irq);
}
static inline unsigned long viper_irq_pending(void)
@ -237,8 +266,12 @@ static void viper_irq_handler(unsigned int irq, struct irq_desc *desc)
pending = viper_irq_pending();
do {
/* we're in a chained irq handler,
* so ack the interrupt by hand */
GEDR(VIPER_CPLD_GPIO) = GPIO_bit(VIPER_CPLD_GPIO);
if (likely(pending)) {
irq = PXA_ISA_IRQ(0) + __ffs(pending);
irq = viper_bit_to_irq(__ffs(pending));
generic_handle_irq(irq);
}
pending = viper_irq_pending();
@ -254,15 +287,14 @@ static struct irq_chip viper_irq_chip = {
static void __init viper_init_irq(void)
{
const int isa_irqs[] = { 3, 4, 5, 6, 7, 10, 11, 12, 9, 14, 15 };
int irq;
int level;
int isa_irq;
pxa25x_init_irq();
/* setup ISA IRQs */
for (irq = 0; irq < ARRAY_SIZE(isa_irqs); irq++) {
isa_irq = isa_irqs[irq];
for (level = 0; level < ARRAY_SIZE(viper_isa_irqs); level++) {
isa_irq = viper_bit_to_irq(level);
set_irq_chip(isa_irq, &viper_irq_chip);
set_irq_handler(isa_irq, handle_edge_irq);
set_irq_flags(isa_irq, IRQF_VALID | IRQF_PROBE);

2
arch/arm/mach-versatile/core.c
View File

@ -28,8 +28,8 @@
#include <linux/amba/clcd.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
#include <linux/io.h>
#include <linux/cnt32_to_63.h>
#include <linux/io.h>
#include <asm/system.h>
#include <mach/hardware.h>

21
arch/arm/plat-omap/devices.c
View File

@ -438,16 +438,8 @@ static inline void omap_init_uwire(void) {}
#if defined(CONFIG_OMAP_WATCHDOG) || defined(CONFIG_OMAP_WATCHDOG_MODULE)
#ifdef CONFIG_ARCH_OMAP24XX
#define OMAP_WDT_BASE 0x48022000
#else
#define OMAP_WDT_BASE 0xfffeb000
#endif
static struct resource wdt_resources[] = {
{
.start = OMAP_WDT_BASE,
.end = OMAP_WDT_BASE + 0x4f,
.flags = IORESOURCE_MEM,
},
};
@ -461,6 +453,19 @@ static struct platform_device omap_wdt_device = {
static void omap_init_wdt(void)
{
if (cpu_is_omap16xx())
wdt_resources[0].start = 0xfffeb000;
else if (cpu_is_omap2420())
wdt_resources[0].start = 0x48022000; /* WDT2 */
else if (cpu_is_omap2430())
wdt_resources[0].start = 0x49016000; /* WDT2 */
else if (cpu_is_omap343x())
wdt_resources[0].start = 0x48314000; /* WDT2 */
else
return;
wdt_resources[0].end = wdt_resources[0].start + 0x4f;
(void) platform_device_register(&omap_wdt_device);
}
#else

2
arch/arm/plat-omap/include/mach/mtd-xip.h
View File

@ -3,7 +3,7 @@
*
* Do not include this file directly. It's included from linux/mtd/xip.h
*
* Author: Vladimir Barinov <vbarinov@ru.mvista.com>
* Author: Vladimir Barinov <vbarinov@embeddedalley.com>
*
* (c) 2005 MontaVista Software, Inc. This file is licensed under the
* terms of the GNU General Public License version 2. This program is

19
arch/avr32/boards/atngw100/setup.c
View File

@ -9,6 +9,7 @@
*/
#include <linux/clk.h>
#include <linux/etherdevice.h>
#include <linux/gpio.h>
#include <linux/irq.h>
#include <linux/i2c.h>
#include <linux/i2c-gpio.h>
@ -53,8 +54,11 @@ static struct spi_board_info spi0_board_info[] __initdata = {
};
static struct mci_platform_data __initdata mci0_data = {
.detect_pin = GPIO_PIN_PC(25),
.wp_pin = GPIO_PIN_PE(0),
.slot[0] = {
.bus_width = 4,
.detect_pin = GPIO_PIN_PC(25),
.wp_pin = GPIO_PIN_PE(0),
},
};
/*
@ -190,7 +194,7 @@ static int __init atngw100_init(void)
* PB28/EXTINT3 doesn't; it should be SMBALERT# (for PMBus),
* but it's not available off-board.
*/
at32_select_periph(GPIO_PIN_PB(28), 0, AT32_GPIOF_PULLUP);
at32_select_periph(GPIO_PIOB_BASE, 1 << 28, 0, AT32_GPIOF_PULLUP);
at32_select_gpio(i2c_gpio_data.sda_pin,
AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
at32_select_gpio(i2c_gpio_data.scl_pin,
@ -204,6 +208,15 @@ postcore_initcall(atngw100_init);
static int __init atngw100_arch_init(void)
{
/* PB30 is the otherwise unused jumper on the mainboard, with an
* external pullup; the jumper grounds it. Use it however you
* like, including letting U-Boot or Linux tweak boot sequences.
*/
at32_select_gpio(GPIO_PIN_PB(30), 0);
gpio_request(GPIO_PIN_PB(30), "j15");
gpio_direction_input(GPIO_PIN_PB(30));
gpio_export(GPIO_PIN_PB(30), false);
/* set_irq_type() after the arch_initcall for EIC has run, and
* before the I2C subsystem could try using this IRQ.
*/

23
arch/avr32/boards/atstk1000/atstk1002.c
View File

@ -232,7 +232,7 @@ static void __init atstk1002_setup_extdac(void)
goto err_set_clk;
}
at32_select_periph(GPIO_PIN_PA(30), GPIO_PERIPH_A, 0);
at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
at73c213_data.dac_clk = gclk;
err_set_clk:
@ -264,16 +264,20 @@ void __init setup_board(void)
#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
static struct mci_platform_data __initdata mci0_data = {
.slot[0] = {
.bus_width = 4,
/* MMC card detect requires MACB0 *NOT* be used */
#ifdef CONFIG_BOARD_ATSTK1002_SW6_CUSTOM
static struct mci_platform_data __initdata mci0_data = {
.detect_pin = GPIO_PIN_PC(14), /* gpio30/sdcd */
.wp_pin = GPIO_PIN_PC(15), /* gpio31/sdwp */
};
#define MCI_PDATA &mci0_data
.detect_pin = GPIO_PIN_PC(14), /* gpio30/sdcd */
.wp_pin = GPIO_PIN_PC(15), /* gpio31/sdwp */
#else
#define MCI_PDATA NULL
.detect_pin = -ENODEV,
.wp_pin = -ENODEV,
#endif /* SW6 for sd{cd,wp} routing */
},
};
#endif /* SW2 for MMC signal routing */
@ -326,13 +330,14 @@ static int __init atstk1002_init(void)
at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
#endif
#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
at32_add_device_mci(0, MCI_PDATA);
at32_add_device_mci(0, &mci0_data);
#endif
#ifdef CONFIG_BOARD_ATSTK1002_SW5_CUSTOM
set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
#else
at32_add_device_lcdc(0, &atstk1000_lcdc_data,
fbmem_start, fbmem_size, 0);
fbmem_start, fbmem_size,
ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL);
#endif
at32_add_device_usba(0, NULL);
#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM

15
arch/avr32/boards/atstk1000/atstk1003.c
View File

@ -19,6 +19,7 @@
#include <linux/spi/spi.h>
#include <asm/setup.h>
#include <asm/atmel-mci.h>
#include <mach/at32ap700x.h>
#include <mach/board.h>
@ -66,6 +67,16 @@ static struct spi_board_info spi1_board_info[] __initdata = { {
} };
#endif
#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
static struct mci_platform_data __initdata mci0_data = {
.slot[0] = {
.bus_width = 4,
.detect_pin = -ENODEV,
.wp_pin = -ENODEV,
},
};
#endif
#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
static void __init atstk1003_setup_extdac(void)
{
@ -84,7 +95,7 @@ static void __init atstk1003_setup_extdac(void)
goto err_set_clk;
}
at32_select_periph(GPIO_PIN_PA(30), GPIO_PERIPH_A, 0);
at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
at73c213_data.dac_clk = gclk;
err_set_clk:
@ -154,7 +165,7 @@ static int __init atstk1003_init(void)
at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
#endif
#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
at32_add_device_mci(0, NULL);
at32_add_device_mci(0, &mci0_data);
#endif
at32_add_device_usba(0, NULL);
#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM

18
arch/avr32/boards/atstk1000/atstk1004.c
View File

@ -21,6 +21,7 @@
#include <video/atmel_lcdc.h>
#include <asm/setup.h>
#include <asm/atmel-mci.h>
#include <mach/at32ap700x.h>
#include <mach/board.h>
@ -71,6 +72,16 @@ static struct spi_board_info spi1_board_info[] __initdata = { {
} };
#endif
#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
static struct mci_platform_data __initdata mci0_data = {
.slot[0] = {
.bus_width = 4,
.detect_pin = -ENODEV,
.wp_pin = -ENODEV,
},
};
#endif
#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
static void __init atstk1004_setup_extdac(void)
{
@ -89,7 +100,7 @@ static void __init atstk1004_setup_extdac(void)
goto err_set_clk;
}
at32_select_periph(GPIO_PIN_PA(30), GPIO_PERIPH_A, 0);
at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
at73c213_data.dac_clk = gclk;
err_set_clk:
@ -137,10 +148,11 @@ static int __init atstk1004_init(void)
at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
#endif
#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
at32_add_device_mci(0, NULL);
at32_add_device_mci(0, &mci0_data);
#endif
at32_add_device_lcdc(0, &atstk1000_lcdc_data,
fbmem_start, fbmem_size, 0);
fbmem_start, fbmem_size,
ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL);
at32_add_device_usba(0, NULL);
#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
at32_add_device_ssc(0, ATMEL_SSC_TX);

20
arch/avr32/include/asm/a.out.h
View File

@ -1,20 +0,0 @@
#ifndef __ASM_AVR32_A_OUT_H
#define __ASM_AVR32_A_OUT_H
struct exec
{
unsigned long a_info; /* Use macros N_MAGIC, etc for access */
unsigned a_text; /* length of text, in bytes */
unsigned a_data; /* length of data, in bytes */
unsigned a_bss; /* length of uninitialized data area for file, in bytes */
unsigned a_syms; /* length of symbol table data in file, in bytes */
unsigned a_entry; /* start address */
unsigned a_trsize; /* length of relocation info for text, in bytes */
unsigned a_drsize; /* length of relocation info for data, in bytes */
};
#define N_TRSIZE(a) ((a).a_trsize)
#define N_DRSIZE(a) ((a).a_drsize)
#define N_SYMSIZE(a) ((a).a_syms)
#endif /* __ASM_AVR32_A_OUT_H */

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