The macros ReadMReg and WriteMReg are really just private versions of
the kernel's readl and writel functions. Use the kernel's functions
instead. And since ioremap returns a (void __iomem *) not a (u8 *),
change all the uses of dt3155_lbase to reflect this.
While here, make dt3155_lbase static since it is only used in the
dt3155_drv.c file. Also, remove the global variable dt3155_bbase
since it is not used anywhere in the code.
Where is makes sense, create a local 'mmio' variable instead of using
dt3155_lbase[minor] to make the code more readable.
This change also affects the {Read|Write}I2C functions so they are
also modified as needed.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com> Cc: Scott Smedley <ss@aao.gov.au> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Charles Clément [Mon, 21 Jun 2010 17:39:51 +0000 (10:39 -0700)]
Staging: vt6655: move channel mapping code from card.c to channel.c
Move functions managing the channel mapping to a new channel.c file, as done in
the staging VT6656 driver. The function names contained in card.c were prefixed
with CARD followed by the first letter of the return code, remove this and use
more coherent function names.
John Sheehan [Fri, 18 Jun 2010 17:39:15 +0000 (18:39 +0100)]
Staging: comedi: fix code warnings in s626.c
A patch for s626.c to fix some of the warnings
reported by the checkpatch.pl tool, namely,
-suspect code indent for conditional statements
-please, no space before tabs
Signed-off-by: John Sheehan <john.d.sheehan@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
John Sheehan [Fri, 18 Jun 2010 17:38:01 +0000 (18:38 +0100)]
Staging: comedi: fix code style errors in s626.c
A patch for s626.c to fix errors reported by
checkpatch.pl tool, namely,
-code indent should use tabs where possible
-"foo * bar" should be "foo *bar"
-trailing statements should be on next line
Signed-off-by: John Sheehan <john.d.sheehan@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Henri Häkkinen [Fri, 11 Jun 2010 21:27:36 +0000 (00:27 +0300)]
staging:panel: Fixed coding conventions.
Fixed coding convention issues as reported by checkpatch.pl tool
on the file `panel.c'. Moved LCD special code handling from the
function `lcd_write' into function `handle_lcd_special_code'. Also
moved the handling of INPUT_ST_HIGH and INPUT_ST_FALLING states from
the function `panel_process_input' into functions `input_state_high'
and `input_state_falling'.
Samuel Ortiz [Thu, 10 Jun 2010 14:54:17 +0000 (16:54 +0200)]
Staging: rtl8192e: Do not autoconnect based on probe response
Getting a probe response after sending a probe request to a specific SSID
doesnt mean we're trying to associate with this SSID.
wpa_supplicant should be the only one deciding when to join an SSID, not the
kernel.
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Samuel Ortiz [Thu, 10 Jun 2010 14:54:18 +0000 (16:54 +0200)]
Staging: rtl8192e: Do not send NULL BSSID events when not associated
If we're not associated, we should not send wireless events to let userspace
know that we just left an ESSID, simply because we havent yet joined it.
If we keep on doing that, wpa_supplicant could receive such events while
actually trying to join an ESSID, and thus decide to stop trying. This leads
to a lot of connection failures as this driver seems to be sending GIWAP
events quite a lot.
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Samuel Ortiz [Thu, 10 Jun 2010 14:54:16 +0000 (16:54 +0200)]
Staging: rtl8192e: Do not mess with carrier settings while scanning
Toggling the link carrier is a non sense and is the grossest locking I can
think of. Moreover, it's giving a completely inaccurate status to userspace
who could for example decide to turn the interface down on carrier off
detection.
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
While merging rt30[79]0 support into rt28[67]0, drivers/staging/rt3070/md4.h
has been forgotten, while it isn't referenced from the remaining drivers
anymore; remove it.
Signed-off-by: Stefan Lippers-Hollmann <s.l-h@gmx.de> Acked-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Matti Lammi <mattij.lammi@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Niadh [Sun, 6 Jun 2010 23:09:18 +0000 (00:09 +0100)]
Staging: RT2860 Fixed all errors in mlme.h and all but one in rtmp.h.
I have fixed all errors in mlme.h and fixed all bar one in rtmp.h.
I think I can fix rtmp.h too by moving a brace up two lines, I just dont know if it will work.
If someone can confirm it will work I will change it.
Signed-off-by: Neil Munro <neilmunro@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Bill Pemberton [Thu, 17 Jun 2010 17:10:41 +0000 (13:10 -0400)]
Staging: xgifb: Remove port macros in osdef.h
The port related macros in osdef.h are replaced with calls to out?()
and in?(). This removes the last macros defined in osdef.h, so this
file is no longer needed.
Daniel Seither [Mon, 21 Jun 2010 23:25:54 +0000 (01:25 +0200)]
Staging: batman-adv: record route for ICMP messages
The standard layer 3 ping utility can use the record route (RR) option
of IP to collect route data for sent ping messages (ping -R). This
patch introduces comparable functionality for batman-adv ICMP messages.
The patch adds a second batman ICMP packet format (icmp_packet_rr) such
that up to 17 MAC addresses can be recorded (sufficient for up to 8
hops per direction). When no RR is wanted, the old icmp_packet without
the RR overhead can be sent.
Signed-off-by: Daniel Seither <post@tiwoc.de> Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Simon Wunderlich [Mon, 21 Jun 2010 23:25:53 +0000 (01:25 +0200)]
Staging: batman-adv: bonding and interface alternating
This patch adds interface alternating to the new bonding feature. By
default, we now try to avoid forwarding packets on the receiving
interface, instead choosing alternative interfaces. This feature
works only on nodes which have multiple interfaces connected to the
mesh. This approach should reduce problems of the half-duplex nature
of WiFi Hardware and thus increase performance.
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de> Acked-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Simon Wunderlich [Mon, 21 Jun 2010 23:25:52 +0000 (01:25 +0200)]
Staging: batman-adv: Add bonding functionality
This patch introduces bonding functionality to batman-advanced, targeted
for the 0.3 release. As we are able to route the payload traffic as we
want, we may use multiple interfaces on multihomed hosts to transfer data
to achieve higher bandwidth. This can be considered as "light Multi Path
Routing" for single hop connections.
To detect which interfaces of a peer node belong to the same host, a
new flag PRIMARIES_FIRST_HOP is introduced. This flag is set on the first hop
of OGMs of the primary (first) interface, which is broadcasted on all
interfaces. When receiving such an OGM, we can learn which interfaces
belong to the same host (by assigning them to the primary originator).
Bonding works by sending packets in a round-robin fashion to the available
interfaces of a neighbor host, if multiple interfaces are available. The
neighbor interfaces should be almost equally good to reach.
To avoid interferences (i.e. sending on the same channel), only neighbor
interfaces with different mac addresses and different outgoing interfaces
are considered as candidates.
Bonding is deactivated by default, and can be activated by
echo 1 > /sys/class/net/bat0/mesh/bonding
for each individual node.
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Rework on top of current version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Simon Wunderlich [Mon, 21 Jun 2010 23:25:51 +0000 (01:25 +0200)]
Staging: batman-adv: 32bit sequence number and TTL for broadcasts
This patch changes the sequence number range from 8 or 16 bit to 32 bit.
This should avoid problems with the sequence number sliding window algorithm
which we had seen in the past for broadcast floods or malicious packet
injections. We can not assure 100% security with this patch, but it is quite
an improvement over the old 16 bit sequence numbers:
* expected window size can be increased (4096 -> 65536)
* 64k packets in the right order would now be needed to cause a loop,
which seems practically impossible.
Furthermore, a TTL field has been added to the broadcast packet type, just to
make sure.
These changes required to increase the compatibility level once again.
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Change atomic64_* back to atomic_*, Rework on
top of current version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Linus Lüssing [Mon, 21 Jun 2010 23:25:49 +0000 (01:25 +0200)]
Staging: batman-adv: permit setting ogm interval to JITTER*2
When trying to set the originator interval to 40ms, we are asked to set
it to a minimum value of 40ms. This patch permits setting an
originator interval of JITTER*2 (40ms by default) now.
Signed-off-by: Linus Lüssing <linus.luessing@web.de> Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de> Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Sven Eckelmann [Mon, 21 Jun 2010 23:25:48 +0000 (01:25 +0200)]
Staging: batman-adv: Ignore debugfs on kernels without debugfs support
All code for debugfs is ignored when the creation of the batman-adv root
directory in debugfs fails. It must also be ignored when the
debugfs_create_dir tells us that debugfs is not implemented to prevent
possible crashes in the future.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Joe Perches [Mon, 21 Jun 2010 23:25:46 +0000 (01:25 +0200)]
Staging: batman-adv: Convert MAC_FMT to %pM
Remove the last uses of MAC_FMT
Signed-off-by: Joe Perches <joe@perches.com>
[sven.eckelmann@gmx.de: Adapted for current batman-adv version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Marek Lindner [Mon, 21 Jun 2010 23:25:45 +0000 (01:25 +0200)]
Staging: batman-adv: remove superfluous hint to "translation table"
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
[sven.eckelmann@gmx.de: Rework on top of current version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Sven Eckelmann [Mon, 21 Jun 2010 23:25:43 +0000 (01:25 +0200)]
Staging: batman-adv: Move tables from sysfs to debugfs
Files which represent more than a single attribute aren't allowed in
sysfs. As we have some files which aren't essential and are lists or
tables aggregated from data from different places inside batman-adv, we
must place them in a filesystem without such a restriction.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Sven Eckelmann [Mon, 21 Jun 2010 23:25:42 +0000 (01:25 +0200)]
Staging: batman-adv: Move device for icmp injection to debugfs
batctl uses /dev/batman-adv to send special batman-adv icmp packets to
other nodes in the mesh. To get it working with multiple batX devices we
must ensure that every mesh device can have their own socket which is
used to inject those packets in exactly one mesh.
The current implementation still doesn't allow to use complete separated
meshes as we rely on structures which are not part of the private data
of a batman device.
Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Staging: batman-adv: convert vis_interval into define
vis_interval does not neccesarily needs to be a variable, as there is
no way to change it anyway (and probably no need to). We can therefore
remove yet another global variable.
Thanks Marek for pointing this out.
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
[sven.eckelmann@gmx.de: Rework on top of current version] Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
batman-adv is receiving and sending the packets of its own ether type
on a very early/low level. Therefore we need to add explicit hooks to
give netfilter/ebtables a chance to filter them.
Reported-by: Antonio Quartulli <ordex@ritirata.org> Signed-off-by: Linus Lüssing <linus.luessing@web.de> Signed-off-by: Sven Eckelmann <sven.eckelmann@gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Marin Mitov [Sun, 6 Jun 2010 11:16:07 +0000 (14:16 +0300)]
Staging: dt3155v4l: correcting a pointer mismatch bug and cleanups
The third argument of dma_alloc_coherent() is of type dma_addr_t and is defined
as u64 for x86_64, while the member 'device_base' of struct dma_coherent_mem is
defined as u32.
While at it, clean up the code. Now if dev->dma_mem != NULL all the fields/members
are already properly initialized.
Dan Carpenter [Mon, 7 Jun 2010 21:44:57 +0000 (23:44 +0200)]
Staging: otus: fix strcpy() overflow
wrq->name is only 16 characters long but "IEEE 802.11-MIMO" is 16
characters + a NULL character, so it's too long. This patch changes it
to "IEEE 802.11abgn".
Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Joe Perches [Mon, 7 Jun 2010 19:11:35 +0000 (12:11 -0700)]
Staging: otus: TODO: Don't bother, for documentation purposes only
On Mon, 2010-06-07 at 12:02 -0700, Luis R. Rodriguez wrote:
> this driver is unmaintained and its only purpose is as a
> source of documentation for developers working on ar9170 and carl9170.
> Once carl9170 gets 11n support and merged upstream then this driver
> can be removed.
Then the TODO file should be updated.
Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Karl Relton [Thu, 3 Jun 2010 22:04:06 +0000 (23:04 +0100)]
Staging: wlan-ng: Switch from wext to cfg80211
Switch driver over from wext to cfg80211 interface.
Some Notes:
- This patch moves the driver wholesale from wext to cfg80211. Wext
support is still provided through the cfg80211 provided wext
compatability layer.
- Currently only infrastructure mode is implemented. Ad hoc mode is not
yet implemented, but can be added.
- It does not support connecting to a specified bssid, instead roaming
is handled by the card itself. This matches the behaviour of the
existing driver.
- It has been tested using NetworkManager (via wpa_supplicant)
configured to use the wext compatability layer, and then again with the
native nl80211 layer.
Signed-off-by: Karl Relton <karllinuxtest.relton@ntlworld.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Ben Hutchings [Tue, 25 May 2010 03:25:57 +0000 (04:25 +0100)]
Staging: rtl8192su: Fix procfs code for interfaces not named wlan0
The current code creates directories in procfs named after interfaces,
but doesn't handle renaming. This can result in name collisions and
consequent WARNINGs. It also means that the interface name cannot
reliably be used to remove the directory - in fact the current code
doesn't even try, and always uses "wlan0"!
Since the name of a proc_dir_entry is embedded in it, use that when
removing it.
Add a netdev notifier to catch interface renaming, and remove and
re-add the directory at this point.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
projects / mirror_ubuntu-hirsute-kernel.git / log