Commit graph

134,929 commits

Author SHA1 Message Date
Stefan Richter
b2268830f5 firewire: net: throttle TX queue before running out of tlabels
This prevents firewire-net from submitting write requests in fast
succession until failure due to all 64 transaction labels were used up
for unfinished split transactions.  The netif_stop/wake_queue API is
used for this purpose.

Without this stop/wake mechanism, datagrams were simply lost whenever
the tlabel pool was exhausted.  Plus, tlabel exhaustion by firewire-net
also prevented other unrelated outbound transactions to be initiated.

The chosen queue depth was checked by me to hit the maximum possible
throughput with an OS X peer whose receive DMA is good enough to never
reject requests due to busy inbound request FIFO.  Current Linux peers
show a mixed picture of -5%...+15% change in bandwidth; their current
bottleneck are RCODE_BUSY situations (fewer or more, depending on TX
queue depth) due to too small AR buffer in firewire-ohci.

Maxim Levitsky tested this change with similar watermarks with a Linux
peer and some pending firewire-ohci improvements that address the
RCODE_BUSY problem and confirmed that these TX queue limits are good.

Note:  This removes some netif_wake_queue from reception code paths.
They were apparently copy&paste artefacts from a nonsensical
netif_wake_queue use in the older eth1394 driver.  This belongs only
into the transmit path.

Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Tested-by: Maxim Levitsky <maximlevitsky@gmail.com>
2010-11-17 00:08:49 +01:00
Stefan Richter
48553011ce firewire: net: replace lists by counters
The current transmit code does not at all make use of
  - fwnet_device.packet_list
and only very limited use of
  - fwnet_device.broadcasted_list,
  - fwnet_device.queued_packets.
Their current function is to track whether the TX soft-IRQ finished
dealing with an skb when the AT-req tasklet takes over, and to discard
pending tx datagrams (if there are any) when the local node is removed.

The latter does actually contain a race condition bug with TX soft-IRQ
and AT-req tasklet.

Instead of these lists and the corresponding link in fwnet_packet_task,
  - a flag in fwnet_packet_task to track whether fwnet_tx is done,
  - a counter of queued datagrams in fwnet_device
do the job as well.

The above mentioned theoretic race condition is resolved by letting
fwnet_remove sleep until all datagrams were flushed.  It may sleep
almost arbitrarily long since fwnet_remove is executed in the context of
a multithreaded (concurrency managed) workqueue.

The type of max_payload is changed to u16 here to avoid waste in struct
fwnet_packet_task.  This value cannot exceed 4096 per IEEE 1394:2008
table 16-18 (or 32678 per specification of packet headers, if there is
ever going to be something else than beta mode).

Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
2010-11-17 00:08:48 +01:00
Stefan Richter
7ee11fa8d0 firewire: net: fix memory leaks
a) fwnet_transmit_packet_done used to poison ptask->pt_link by list_del.
If fwnet_send_packet checked later whether it was responsible to clean
up (in the border case that the TX soft IRQ was outpaced by the AT-req
tasklet on another CPU), it missed this because ptask->pt_link was no
longer shown as empty.

b) If fwnet_write_complete got an rcode other than RCODE_COMPLETE, we
missed to free the skb and ptask entirely.

Also, count stats.tx_dropped and stats.tx_errors when rcode != 0.

Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
2010-11-17 00:08:48 +01:00
Stefan Richter
902bca00dc firewire: net: count stats.tx_packets and stats.tx_bytes
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
2010-11-17 00:08:48 +01:00
Jeremy Fitzhardinge
e04195644e xen/events: use locked set|clear_bit() for cpu_evtchn_mask
The per-cpu event channel masks can be updated unlocked from multiple
CPUs, so use the locked variant.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
2010-11-16 14:58:50 -08:00
Jan Beulich
1c6969ec8e xen/evtchn: clear secondary CPUs' cpu_evtchn_mask[] after restore
To bind all event channels to CPU#0, it is not sufficient to set all
of its cpu_evtchn_mask[] bits; all other CPUs also need to get their
bits cleared. Otherwise, evtchn_do_upcall() will start handling
interrupts on CPUs they're not intended to run on, which can be
particularly bad for per-CPU ones.

[ linux-2.6.18-xen.hg 7de7453dee36 ]

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
2010-11-16 14:58:47 -08:00
Alan Stern
c08512c761 USB: improve uses of usb_mark_last_busy
This patch (as1434) cleans up the uses of usb_mark_last_busy() in
usbcore.  The function will be called when a device is resumed and
whenever a usage count is decremented.  A call that was missing from
the hub driver is added: A hub is used whenever one of its ports gets
suspended (this prevents hubs from suspending immediately after their
last child).

In addition, the call to disable autosuspend support for new devices
by default is moved from usb_detect_quirks() (where it doesn't really
belong) into usb_new_device() along with all the other runtime-PM
initializations.  Finally, an extra pm_runtime_get_noresume() is added
to prevent new devices from autosuspending while they are being
registered.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 14:04:22 -08:00
Alan Stern
fcc4a01eb8 USB: use the runtime-PM autosuspend implementation
This patch (as1428) converts USB over to the new runtime-PM core
autosuspend framework.  One slightly awkward aspect of the conversion
is that USB devices will now have two suspend-delay attributes: the
old power/autosuspend file and the new power/autosuspend_delay_ms
file.  One expresses the delay time in seconds and the other in
milliseconds, but otherwise they do the same thing.  The old attribute
can be deprecated and then removed eventually.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 14:03:41 -08:00
Ming Lei
6ddf27cdbc USB: make usb_mark_last_busy use pm_runtime_mark_last_busy
Since the runtime-PM core already defines a .last_busy field in
device.power, this patch uses it to replace the .last_busy field
defined in usb_device and uses pm_runtime_mark_last_busy to implement
usb_mark_last_busy.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 14:02:54 -08:00
Alan Stern
045cac6b3b USB: use sysfs_merge_group for power attributes
This patch (as1426) makes use of the new sysfs_merge_group() and
sysfs_unmerge_group() routines to simplify the handling of power
attributes for USB devices.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 14:02:00 -08:00
Ming Lei
63defa73c8 USB: use the no_callbacks flag for interfaces
Call pm_runtime_no_callbacks to set no_callbacks flag for USB
interfaces.  Since interfaces cannot be power-managed separately from
their parent devices, there's no reason for the runtime-PM core to
invoke any callbacks for them.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 14:02:00 -08:00
Toshiharu Okada
f646cf9452 USB device driver of Topcliff PCH
This patch adds the USB device driver of EG20T(Topcliff) PCH.

EG20T PCH is the platform controller hub that is going to be used in
Intel's upcoming general embedded platform. All IO peripherals in
EG20T PCH are actually devices sitting on AMBA bus.
EG20T PCH has USB device I/F. Using this I/F, it is able to access system
devices connected to USB device.

Signed-off-by: Toshiharu Okada <toshiharu-linux@dsn.okisemi.com>
Acked-by: Michał Nazarewicz <m.nazarewicz@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:57:25 -08:00
Michal Nazarewicz
d8df0b611c usb: gadget: f_fs: remove custom printk() wrappers
This commit removes custom printk() wrappers from the f_fs.c
file.  They served little purpose above what pr_*() family of
macros provides.  Only FVDBG() has been left but renamed to
pr_vdebug() to match other uses.

Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:55:19 -08:00
Michal Nazarewicz
5ab54cf7ac usb: gadget: FunctionFS: fix typos and coding style
This commit changes FunctionFS as to make it more compliant
with coding style as well as fixes several typos.

Signed-off-by: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:54:46 -08:00
Joe Perches
7189ba939e drivers/uwb: Use printf extension %pR for struct resource
Using %pR standardizes the struct resource output.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:54:18 -08:00
Joe Perches
cc7e6056f4 drivers/usb/gadget: Remove unnecessary semicolons
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:54:18 -08:00
Joe Perches
ce7eb32fc2 drivers/usb/host/uhci-hcd.c: Remove unnecessary casts of pci_get_drvdata
Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:54:18 -08:00
Deepak Sikri
c8c38de9d8 USB host: Adding USB ehci & ohci support for spear platform
This patch adds support for ehci and ohci controller in the SPEAr platform.

Changes since V2:
added clear_tt_buffer_complete in ehci_spear_hc_driver

Signed-off-by: Deepak Sikri <deepak.sikri@st.com>
Signed-off-by: Viresh Kumar <viresh.kumar@st.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-11-16 13:53:29 -08:00
Mohammed Shafi Shajakhan
28d9cc7f21 ath9k_htc: Use macro for caldata array size
The calibration data variable size is based on the number of
channels available in the ath9k driver.

Signed-off-by: Mohammed Shafi Shajakhan <mshajakhan@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:39:09 -05:00
Stanislaw Gruszka
ef1b21f7eb iwlwifi: kill elapsed_jiffies
Subtract of jiffies is fine even if one variable overwrap.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:39:09 -05:00
Stanislaw Gruszka
70f3876f09 iwlagn: simplify iwlagn_tx_skb
We can simplify length calculation in iwlagn_tx_skb, that function
is enough complex, without fuzz it more than necessary.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:39:09 -05:00
Stanislaw Gruszka
2cb7865648 iwl3945: remove unused len_org variable
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Acked-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:39:09 -05:00
Felix Fietkau
4e8c14e958 ath9k_hw: add a private op for configuring radar pulse detection
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:08 -05:00
Felix Fietkau
82b873afe8 ath9k: clean up tx buffer setup
Merge ath_tx_send_normal and ath_tx_send_ht_normal.
Move the paprd state initialization and sequence number assignment
to reduce the number of redundant checks.

This not only simplifies buffer allocation error handling, but also
removes a small inconsistency in the buffer HT flag.
This flag should only be set if the frame is also a QoS data frame.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:08 -05:00
Felix Fietkau
61117f01e7 ath9k: remove the tx info padding byte abuse
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:07 -05:00
Felix Fietkau
f0c255a07f ath9k: handle tx underrun in the driver instead of rate control
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:07 -05:00
Felix Fietkau
1d666d8e05 ath9k: remove the unnecessary private xretry tx flag
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:07 -05:00
Ben Greear
7afbb2f070 ath5k: Cleanup opmode setting logic.
An earlier review suggested moving the code in a small
method that was only called once inline.  This patch
accomplishes that.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Acked-by: Bruno Randolf <br1@einfach.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:07 -05:00
Senthil Balasubramanian
6ee63f55c7 ath9k_hw: Fix low throughput issue with AR93xx
TX underruns were noticed when RTS/CTS preceded aggregates.
This issue was noticed in ar93xx family of chipsets only.
The workaround involves padding the RTS or CTS length up
to the min packet length of 256 bytes required by the
hardware by adding delimiters to the fist descriptor of
the aggregate.

Signed-off-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:07 -05:00
Vasanthakumar Thiagarajan
39ec2997c3 ath9k: Fix bug in delimiter padding computation
There is a roundng error in delimiter padding computation
which causes severe throughput drop with some of AR9003.

signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Cc:stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:07 -05:00
Vasanthakumar Thiagarajan
bc2068020b ath9k_hw: Add helper function for interpolation
Also round off interpolated values this would improve power
accuracy by 0.5dB in some cases.

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Vasanthakumar Thiagarajan
15cbbc44cc ath9k_hw: Improve power control accuracy for AR9003
It is done for 5Ghz by adding three temperature slopes.

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Vasanthakumar Thiagarajan
f4475a6e52 ath9k_hw: Enable strong signal detection for AR9003
Attenuation from eeprom is configured into attenuator control
register.

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Vasanthakumar Thiagarajan
52a0e2477d ath9k_hw: Fix XPABIAS level configuration for AR9003
Improper configuration of 0x16288 and 0x16290 would affect transmission.

Cc:stable@kernel.org
Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Senthil Balasubramanian
3092354970 ath9k_hw: add eeprom templates for ar9003 family chipsets
We are currently using the default eeprom default and it doesn't
work properly for all ar9003 family chipsets. So add eeprom
templates for different versisons and select the eeprom table
based on the template version programmed in the eeprom.

Signed-off-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Senthil Balasubramanian
3ceb801bff ath9k_hw: Fix paprd training frame failure.
paprd training frame fails in some rates. Fix the rate mask.

Signed-off-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Senthil Balasubramanian
ef5a6a7573 ath9k_hw: Initialize 2GHz CTL properly.
The last 2GHz CTL was not being initialized, so power was being
set to 0 instead of 30dbm. Initialize to 30 like other CTLs.

Signed-off-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:06 -05:00
Senthil Balasubramanian
b3dd6bc1f0 ath9k_hw: Add new member into the eeprom structure.
Add eeprom base extension structures which are needed for
AR938x caliberation changes and gain calculation.

Signed-off-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:05 -05:00
Senthil Balasubramanian
a9d85fbd3e ath9k_hw: Fix a reset failure on AR9382 (2x2).
AR9382 needs to be configured for the correct chain mask before
running AGC/TxIQ caliberation. Otherwise reset would fail.

Signed-off-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:05 -05:00
Bruno Randolf
72a801103f ath5k: Add support for antenna configuration
Support setting the antenna configuration via cfg/mac80211. At the moment only
allow the simple pre-defined configurations we already have (fixed antenna A/B
or diversity), but more advanced settings are possible to implement.

Signed-off-by: Bruno Randolf <br1@einfach.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:05 -05:00
Joe Perches
0e67d6cb75 drivers/net/wireless/b43legacy/main.c: Use printf extension %pV
Using %pV reduces the number of printk calls and
eliminates any possible message interleaving from
other printk calls.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:05 -05:00
Joe Perches
5b736d42bc drivers/net/wireless/b43/main.c: Use printf extension %pV
Using %pV reduces the number of printk calls and
eliminates any possible message interleaving from
other printk calls.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:04 -05:00
Joe Perches
7e559ec31c drivers/net/wireless/ath/debug.c: Use printf extension %pV
Using %pV reduces the number of printk calls and
eliminates any possible message interleaving from
other printk calls.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:04 -05:00
Jussi Kivilinna
5cb56af29b rndis_wlan: workaround poor scanning with BCM4320a
BCM4320a devices seem to sometimes do scanning pretty poorly. This can be
workaround by issuing new scan every second, while not yet connected. By this
new scanning method device catches beacons much faster. Fixes bug #20822.

Reported-by: Luís Picciochi <Pitxyoki@gmail.com>
Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:04 -05:00
Jussi Kivilinna
b5257c952d rndis_wlan: workaround device not returning bss for currently connected AP
BCM4320a devices do not return bss for currently connected AP in bss-list,
althought this is required by NDIS specs. Missing bss leads to warning at
net/wireless/sme.c:__cfg80211_connect_result(), WARN_ON(!bss).

Workaround this by crafting bss manually with information we can read from
device. Workaround is only used when device bss-list does not return current
bss, and so is only used with BCM4320a devices and not newer BCM4320b ones.

Fixes bug #20152.

Reported-by: Luís Picciochi <Pitxyoki@gmail.com>
Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:04 -05:00
Rafał Miłecki
ca4a083191 ssb: return -ENOMEM on alloc fail (instead of CRC check's result)
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:03 -05:00
Rafał Miłecki
54435f9ec8 ssb: workarounds: be verbose about hacking SPROM revision, don't duplicate code
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:03 -05:00
Brian Cavagnolo
d1f9e41d1d mwl8k: use const struct fw pointers throughout
This eliminates compiler warnings by doing things how the
firmware class expects.

Signed-off-by: Brian Cavagnolo <brian@cozybit.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:03 -05:00
Brian Cavagnolo
9902047100 mwl8k: make initial firmware load asynchronous
Introduce a firmware loading state machine to manage the process
of loading firmware asynchronously and completing initialization
upon success.  The state machine attempts to load the preferred
firmware image.  If that fails, and if an alternative firmware
image is available, it will attempt to load that one.

Signed-off-by: Brian Cavagnolo <brian@cozybit.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:03 -05:00
Brian Cavagnolo
952a0e963f mwl8k: add API version checking for AP firmware
The AP firmware specifies an API version in the GET_HW_SPEC
command response.  Currently, the driver only supports AP
firmware for the 8366, and only supports API v1.  In the future,
if higher API version firmwares emerge (possibly for different
chips), different ops can be selected based on the reported API
version.

Signed-off-by: Brian Cavagnolo <brian@cozybit.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-11-16 16:37:03 -05:00