23 Jul, 2009
8 commits
-
If skge hardware is capable of waking up the system from sleep,
enable magic packet WoL during driver initialisation.This makes WoL work without calling 'ethtool -s ethX wol g'
for each adapter.Signed-off-by: Rafael J. Wysocki
Tested-by: Michael Guntsche
Acked-by: Stephen Hemminger
Signed-off-by: David S. Miller -
fix this build error when CONFIG_MII is not set
drivers/net/ks8851.c:999: undefined reference to `generic_mii_ioctl'
drivers/net/ks8851.c:1050: undefined reference to `mii_link_ok'
drivers/net/ks8851.c:1056: undefined reference to `mii_nway_restart'
drivers/net/ks8851.c:1044: undefined reference to `mii_ethtool_sset'
drivers/net/ks8851.c:1038: undefined reference to `mii_ethtool_gset'Signed-off-by: Alexander Beregalov
Acked-by: Ben Dooks -
This patch fixes a bug in the non-lro path. Wrong size of received
packet was being passed for updating receive statistics. This patch
is against the net-2.6 git.Signed-off-by: Ajit Khaparde
Signed-off-by: David S. Miller -
Since commit 0b9da337dca972e7a4144e298ec3adb8f244d4a4 ("Rework
ucc_geth driver to use of_mdio infrastructure") the fixed-link
support is broken.This patch fixes the support by removing !ug_info->phy_node check,
and adds a call to of_phy_connect_fixed_link() if a phy is not attached
to the MAC.Also, remove an old fixed-link code that we don't use any longer.
Signed-off-by: Anton Vorontsov
Signed-off-by: Grant Likely
Signed-off-by: David S. Miller -
Since commit fe192a49118f5b1272317d60c7930ece4e13ae49 ("Rework gianfar
driver to use of_mdio infrastructure") the fixed-link support is
broken, the driver oopses at init_phy():Unable to handle kernel paging request for data at address 0x000000e4
Faulting instruction address: 0xc01cf298
Oops: Kernel access of bad area, sig: 11 [#1]
[...]
NIP [c01cf298] init_phy+0x80/0xdc
LR [c01cf250] init_phy+0x38/0xdc
Call Trace:
[cf81fe80] [c01d1cf8] gfar_enet_open+0x6c/0x19c
[cf81fea0] [c024494c] dev_open+0xfc/0x134
[cf81fec0] [c0242edc] dev_change_flags+0x84/0x1ac
[cf81fee0] [c0399ee0] ic_open_devs+0x168/0x2d8
[cf81ff20] [c039b2e8] ip_auto_config+0x90/0x2a4
[cf81ff60] [c0003884] do_one_initcall+0x34/0x1a8This patch fixes the oops, and removes phy_node checks, and adds a call
to of_phy_connect_fixed_link() if a phy isn't attached..Also, remove an old fixed-link code that we don't use any longer.
Signed-off-by: Anton Vorontsov
Signed-off-by: Grant Likely
Signed-off-by: David S. Miller -
Since commit aa73832c5a80d6c52c69b18af858d88fa595dd3c ("Rework
fs_enet driver to use of_mdio infrastructure") the fixed-link support
is broken in the fs_enet driver.This patch fixes the support by removing a check for phy_node, and adding
a call to of_phy_connect_fixed_link().Also set netdev parent device via SET_NETDEV_DEV() call, this is needed
so that OF MDIO core could find a node pointer for a device.Plus, fix "if (IS_ERR(phydev))" check, in case of errors,
of_phy_connect() returns NULL, not ERR_PTR as phy_connect().Signed-off-by: Anton Vorontsov
Signed-off-by: Grant Likely
Signed-off-by: David S. Miller -
Fixed-link support is broken for the ucc_eth, gianfar, and fs_enet
device drivers. The "OF MDIO rework" patches removed most of the
support. Instead of re-adding fixed-link stuff to the drivers, this
patch adds a support function for parsing the fixed-link property
and obtaining a dummy phy to match.Note: the dummy phy handling in arch/powerpc is a bit of a hack and
needs to be reworked. This function is being added now to solve the
regression in the Ethernet drivers, but it should be considered a
temporary measure until the fixed link handling can be reworked.Signed-off-by: Anton Vorontsov
Signed-off-by: Grant Likely
Signed-off-by: David S. Miller
22 Jul, 2009
29 commits
-
Reset rx chain before trying to drain it.
Shut interrupts off last, incase there's something to report.Signed-off-by: Mike McCormack
Acked-by: Stephen Hemminger
Signed-off-by: David S. Miller -
The values in the advertising field are typically ADVERTISED_xxx, not
SUPPORTED_xxx. Both SUPPORTED_10000baseT_Full and
ADVERTISED_1000baseT_Full have the same value.The semantic match that finds this problem is as follows:
(http://www.emn.fr/x-info/coccinelle/)//
@@
struct ethtool_cmd E;
@@
*E.advertising = SUPPORTED_10000baseT_Full
//Signed-off-by: Julia Lawall
Signed-off-by: David S. Miller -
If the NULL test is necessary, then the dereference should be moved below
the NULL test.The semantic patch that makes this change is as follows:
(http://www.emn.fr/x-info/coccinelle/)//
@@
type T;
expression E,E1;
identifier i,fld;
statement S;
@@- T i = E->fld;
+ T i;
... when != E=E1
when != i
if (E == NULL||...) S
+ i = E->fld;
//Signed-off-by: Julia Lawall
Signed-off-by: David S. Miller -
If the NULL test is necessary, then the dereferences should be moved below
the NULL test.The semantic patch that makes this change is as follows:
(http://www.emn.fr/x-info/coccinelle/)//
@@
type T;
expression E,E1;
identifier i,fld;
statement S;
@@- T i = E->fld;
+ T i;
... when != E=E1
when != i
BUG_ON (E == NULL||...);
+ i = E->fld;
//Signed-off-by: Julia Lawall
Signed-off-by: David S. Miller -
Firmware V4 on CF8381 reports region code shifted by 1 byte to left.
The following patch checks for this and handles it properly.Signed-off-by: Marek Vasut
Signed-off-by: John W. Linville -
Two users of ar9170 devices have now reported their cards
have been programmed with a regulatory domain of 0x8000.
This is not a valid regulatory domain as such these users were
unable to use these devices. Since this doesn't seem to be
a device EEPROM corruption we must treat it specially. It
may have been possible the manufacturer intended to use 0x0
as the regulatory domain and that would ultimately yield
to US but since we cannot get confirmationf or this we
default this special case to one of our world regulatory
domains, specifically 0x64.Reported-by: DavidFreeman on #linux-wireless
Reported-by: Joerg Albert
Cc: Christian Lamparter ,
Cc: Stephen Chen
Cc: David Quan
Cc: Tony Yang
Signed-off-by: Luis R. Rodriguez
Signed-off-by: John W. Linville -
Fix a potential NULL dereference bug during
error handling in p54spi_probe.This bug was discovered by smatch:
(http://repo.or.cz/w/smatch.git).Signed-off-by: Dan Carpenter
Signed-off-by: Christian Lamparter
Signed-off-by: John W. Linville -
Fix another polarity error introduced by the rfkill rewrite,
this time in acer_rfkill_set().Signed-off-by: Alan Jenkins
Signed-off-by: John W. Linville -
Signed-off-by: Evgeniy Polyakov
Signed-off-by: David S. Miller -
Many Nokia handsets support a Phonet interface to the cellular modem
via a vendor-specific USB interface. CDC Phonet follows the
Communications Device Class model, with one control interface, and
and a pair of inactive and active data alternative interface. The later
has two bulk endpoint, one per direction.This was tested against Nokia E61, Nokia N95, and the existing Phonet
gadget function for the Linux composite USB gadget framework.Signed-off-by: Rémi Denis-Courmont
Signed-off-by: David S. Miller -
Set the driver data before using it. Fixes an oops when doing rmmod.
Signed-off-by: Finn Thain
Signed-off-by: David S. Miller -
A pointer to mac_sonic_probe is passed to the core via
platform_driver_register and so the function must not disappear when the
.init sections are discarded. Otherwise (if also having HOTPLUG=y)
unbinding and binding a device to the driver via sysfs will result in an
oops as does a device being registered late.Various other functions that are called by mac_sonic_probe need to move
to .devinit.text, too.An alternative to this patch is using platform_driver_probe instead of
platform_driver_register plus removing the pointer to the probe function
from the struct platform_driver.Signed-off-by: Uwe Kleine-König
Tested-by: Finn Thain
Signed-off-by: David S. Miller -
This patch fixes a double free corruption in __cfg80211_scan_done:
================================================
BUG kmalloc-512: Object already free
------------------------------------------------INFO: Allocated in load_elf_binary+0x18b/0x19af age=6
INFO: Freed in load_elf_binary+0x104e/0x19af age=5
INFO: Slab 0xffffea0001bae4c0 objects=14 used=7
INFO: Object 0xffff88007e8a9918 @offset=6424 fp=0xffff88007e8a9488Bytes b4 0xffff88007e8a9908: 00 00 00 00 00 00 00 00 5a 5a
[...]
Pid: 28705, comm: rmmod Tainted: P C 2.6.31-rc2-wl #1
Call Trace:
[] print_trailer+0x14e/0x16e
[] object_err+0x42/0x61
[] __slab_free+0x2af/0x396
[] ? wiphy_unregister+0x92/0x142 [cfg80211]
[] kfree+0x13c/0x17a
[] ? wiphy_unregister+0x92/0x142 [cfg80211]
[] wiphy_unregister+0x92/0x142 [cfg80211]
[] ieee80211_unregister_hw+0xc8/0xff [mac80211]
[] p54_unregister_common+0x31/0x66 [p54common]
[...]
FIX kmalloc-512: Object at 0xffff88007e8a9918 not freedThe code path which leads to the *funny* double free:
request = rdev->scan_req;
dev = dev_get_by_index(&init_net, request->ifidx);
/*
* the driver was unloaded recently and
* therefore dev_get_by_index will return NULL!
*/
if (!dev)
goto out;
[...]
rdev->scan_req = NULL; /* not executed... */
[...]
out:
kfree(request);Signed-off-by: Christian Lamparter
Signed-off-by: John W. Linville -
Some drivers don't need the return value of rfkill_set_hw_state(),
so it should not be marked as __must_check.Signed-off-by: Alan Jenkins
Acked-by: Johannes Berg
Signed-off-by: John W. Linville -
For AP mode we must tune ANI specially for 2 GHz and
for 5 GHz. We mask in only the flags we want to toggle
on ath9k_hw_ani_control() through the ah->ani_function
bitmask, this will take care of ignoring changes during
ANI reset which we were disabling before.Testedy-by: Steven Luo
Cc: Bennyam Malavazi
Cc: Jouni Malinen
Signed-off-by: Luis R. Rodriguez
Signed-off-by: John W. Linville -
The commit below changed the semantics of rt2x00_check_rev so that it no
longer checked the bottom 4 bits of the rev were non-zero. During that
conversion this part of the check was not propogated to the rt2500usb
initialisation.commit 358623c22c9fd837b3b1b444377037f72553dc9f
Author: Ivo van Doorn
Date: Tue May 5 19:46:08 2009 +0200rt2x00: Simplify rt2x00_check_rev
Without this check rt73 devices are miss recognised as rt2500 devices and
two drivers are loaded. Preventing the device being used. Reinstate this
check.Signed-off-by: Andy Whitcroft
Signed-off-by: John W. Linville -
Potential memory leak via msg pointer in nl80211_get_key() function.
Signed-off-by: Niko Jokinen
Signed-off-by: Luciano Coelho
Signed-off-by: John W. Linville -
When rtl8187 is unloaded and CONFIG_RTL8187_LEDS is set, the kernel
may oops when the module is unloaded as the workqueue for led_on was
not being cancelled.This patch fixes the problem reported in
http://marc.info/?l=linux-wireless&m=124742957615781&w=2.Reported-by: Gábor Stefanik
Signed-off-by: Larry Finger
Signed-off-by: John W. Linville -
Pavel Roskin reported some issues with using AP mode without
nohwcrypt=1. Most likely this is similar to the problem fixed
some time ago in ath9k by 3f53dd64f192450cb331c0fecfc26ca952fb242f,
"ath9k: Fix hw crypto configuration for TKIP in AP mode."That only affects TKIP but it's easiest to just disable that and
WEP too until we get a proper fix in.Signed-off-by: Bob Copeland
Signed-off-by: John W. Linville -
For forwarded frames, we save the precursor address in addr1 in case it
needs to be used to send a Path Error. mesh_path_discard_frame,
however, was using addr2 instead of addr1 to send Path Error frames, so
correct that and also make the comment regarding this more clear.Signed-off-by: Andrey Yurovsky
Signed-off-by: John W. Linville -
Once the "data" pointer is freed, we can't be iterating
to the next item in the list any more so we need to use
list_for_each_entry_safe with a temporary variable.Signed-off-by: Johannes Berg
Signed-off-by: John W. Linville -
If you rmmod the module while associated, frames might
be transmitted during unregistration -- which will crash
if the hwsim%d interface is unregistered first, so only
do that after all the virtual wiphys are gone.Signed-off-by: Johannes Berg
Signed-off-by: John W. Linville -
The point of this function is to set the software and hardware state at
the same time. When I tried to use it, I found it was only setting the
software state.Signed-off-by: Alan Jenkins
Reviewed-by: Johannes Berg
Signed-off-by: John W. Linville -
The location of the 802.11 header is calculated incorrectly due to a
wrong placement of parentheses. Found by kmemcheck.Signed-off-by: Pavel Roskin
Signed-off-by: John W. Linville -
Apparently there actually _are_ tools that try to set
this in sysfs even though it wasn't supposed to be used
this way without claiming first. Guess what: now that
I've cleaned it all up it doesn't matter and we can
simply allow setting the soft-block state in sysfs.Signed-off-by: Johannes Berg
Tested-By: Darren Salt
Signed-off-by: John W. Linville -
My kvm instance was complaining a lot about sleeping
in atomic contexts in the mesh code, and it turns out
that both mesh_path_add() and mpp_path_add() need to
be able to sleep (they even use synchronize_rcu()!).
I put in a might_sleep() to annotate that, but I see
no way, at least right now, of actually making sure
those functions are only called from process context
since they are both called during TX and RX and the
mesh code itself even calls them with rcu_read_lock()
"held".Therefore, let's disable it completely for now.
It's possible that I'm only seeing this because the
hwsim's beaconing is broken and thus the peers aren't
discovered right away, but it is possible that this
happens even if beaconing is working, for a peer that
doesn't exist or so.It should be possible to solve this by deferring the
freeing of the tables to call_rcu() instead of using
synchronize_rcu(), and also using atomic allocations,
but maybe it makes more sense to rework the code to
not call these from atomic contexts and defer more of
the work to the workqueue. Right now, I can't work on
either of those solutions though.Signed-off-by: Johannes Berg
Signed-off-by: John W. Linville -
The byte count table is only used for aggregation. Updating it
in other cases caused fragmented frames to be dropped.This fixes http://www.intellinuxwireless.org/bugzilla/show_bug.cgi?id=2004
Signed-off-by: Reinette Chatre
Signed-off-by: John W. Linville -
This changes the power_level file to adhere to the "one value
per file" sysfs rule. The user will know which power level was
requested as it will be the number just written to this file. It
is thus not necessary to create a new sysfs file for this value.In addition it fixes a problem where powertop's parsing expects
this value to be the first value in this file without any descriptions.Signed-off-by: Reinette Chatre
cc: stable@kernel.org
Signed-off-by: John W. Linville -
The driver private data is now based on wiphy. So we should not
touch the private data after wiphy_free() is called. The patch
fixes the potential NULL pointer dereference by making the
iwm_wdev_free() the last one on the interface removal path.Signed-off-by: Zhu Yi
Signed-off-by: John W. Linville
21 Jul, 2009
3 commits
-
This patch fixes a problem when a device is stopped while in the
bus-off state. Then the carrier remains off forever.Signed-off-by: Kurt Van Dijck
Signed-off-by: Wolfgang Grandegger
Signed-off-by: David S. Miller -
If dev_alloc_skb() failed in can_restart(), the device was left behind
in the bus-off state. This patch restarts the device nevertheless.Signed-off-by: Kurt Van Dijck
Signed-off-by: Wolfgang Grandegger
Signed-off-by: David S. Miller -
Remove duplicated #include('s) in
drivers/net/can/sja1000/sja1000.cSigned-off-by: Huang Weiyi
Signed-off-by: Wolfgang Grandegger
Signed-off-by: David S. Miller
