Commit graph

210,168 commits

Author SHA1 Message Date
Mike Frysinger
4397c98a8a Input: ad7879 - split bus logic out
The ad7879 driver is using the old bus method of only supporting one
at a time (I2C or SPI). So refactor it like the other input drivers
that support multiple busses simultaneously.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Michael Hennerich <michael.hennerich@analog.com>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
2010-07-03 13:13:03 -07:00
Vince Weaver
f287d332ce perf, x86: Fix incorrect branches event on AMD CPUs
While doing some performance counter validation tests on some
assembly language programs I noticed that the "branches:u"
count was very wrong on AMD machines.

It looks like the wrong event was selected.

Signed-off-by: Vince Weaver <vweaver1@eecs.utk.edu>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Borislav Petkov <borislav.petkov@amd.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: <stable@kernel.org>
LKML-Reference: <alpine.DEB.2.00.1007011526010.23160@cl320.eecs.utk.edu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-07-03 15:19:34 +02:00
David S. Miller
e490c1defe Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6 2010-07-02 22:42:06 -07:00
David S. Miller
8bd39456bd Merge branch 'vhost-net' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost 2010-07-02 22:29:22 -07:00
Rusty Russell
58eba97d07 virtio_net: fix oom handling on tx
virtio net will never try to overflow the TX ring, so the only reason
add_buf may fail is out of memory. Thus, we can not stop the
device until some request completes - there's no guarantee anything
at all is outstanding.

Make the error message clearer as well: error here does not
indicate queue full.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (...and avoid TX_BUSY)
Cc: stable@kernel.org  # .34.x (s/virtqueue_/vi->svq->vq_ops->/)
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 22:27:26 -07:00
Michael S. Tsirkin
1788f49548 virtio_net: do not reschedule rx refill forever
We currently fill all of RX ring, then add_buf
returns ENOSPC, which gets mis-detected as an out of
memory condition and causes us to reschedule the work,
and so on forever. Fix this by oom = err == -ENOMEM;

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: stable@kernel.org # .34.x
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 22:27:25 -07:00
Jon Mason
4a49043223 s2io: resolve statistics issues
This patch resolves a number of issues in the statistics gathering of
the s2io driver.

On Xframe adapters, the received multicast statistics counter includes
pause frames which are not indicated to the driver.  This can cause
issues where the multicast packet count is higher than what has actually
been received, possibly higher than the number of packets received.

The driver software counters are replaced with the adapter hardware
statistics for rx_packets, rx_bytes, and tx_bytes.  It also uses the
overflow registers to determine if the statistics wrapped the 32bit
register (removing the window of having a statistic value less than the
previous call).  rx_length_errors statistic now includes undersized
packets in addition to oversized packets in its counting.  Finally,
rx_crc_errors are now being counted.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 22:27:25 -07:00
David S. Miller
94e6721d9c Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6 2010-07-02 22:04:49 -07:00
Randy Dunlap
e2aec372ff linux/net.h: fix kernel-doc warnings
Fix kernel-doc warnings in linux/net.h:

Warning(include/linux/net.h:151): No description found for parameter 'wq'
Warning(include/linux/net.h:151): Excess struct/union/enum/typedef member 'fasync_list' description in 'socket'
Warning(include/linux/net.h:151): Excess struct/union/enum/typedef member 'wait' description in 'socket'

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:59:08 -07:00
John Fastabend
f0796d5c73 net: decreasing real_num_tx_queues needs to flush qdisc
Reducing real_num_queues needs to flush the qdisc otherwise
skbs with queue_mappings greater then real_num_tx_queues can
be sent to the underlying driver.

The flow for this is,

dev_queue_xmit()
	dev_pick_tx()
		skb_tx_hash()  => hash using real_num_tx_queues
		skb_set_queue_mapping()
	...
	qdisc_enqueue_root() => enqueue skb on txq from hash
...
dev->real_num_tx_queues -= n
...
sch_direct_xmit()
	dev_hard_start_xmit()
		ndo_start_xmit(skb,dev) => skb queue set with old hash

skbs are enqueued on the qdisc with skb->queue_mapping set
0 < queue_mappings < real_num_tx_queues.  When the driver
decreases real_num_tx_queues skb's may be dequeued from the
qdisc with a queue_mapping greater then real_num_tx_queues.

This fixes a case in ixgbe where this was occurring with DCB
and FCoE. Because the driver is using queue_mapping to map
skbs to tx descriptor rings we can potentially map skbs to
rings that no longer exist.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:59:07 -07:00
John Fastabend
4ef6acff83 sched: qdisc_reset_all_tx is calling qdisc_reset without qdisc_lock
When calling qdisc_reset() the qdisc lock needs to be held.  In
this case there is at least one driver i4l which is using this
without holding the lock.  Add the locking here.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:59:07 -07:00
Breno Leitao
7ae80abdba qlge: fix a eeh handler to not add a pending timer
On some ocasions the function qlge_io_resume() tries to add a
pending timer, which causes the system to hit the BUG() on
add_timer() function.

This patch removes the timer during the EEH recovery.

Signed-off-by: Breno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: Ron Mercer <ron.mercer@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:59:06 -07:00
Breno Leitao
72046d84f0 qlge: Replacing add_timer() to mod_timer()
Currently qlge driver calls add_timer() instead of mod_timer().
This patch changes add_timer() to mod_timer(), which seems a better
solution.

Signed-off-by: Breno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: Ron Mercer <ron.mercer@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:59:05 -07:00
Ben Hutchings
0dacca73a3 usbnet: Set parent device early for netdev_printk()
netdev_printk() follows the net_device's parent device pointer, so
we must set that earlier than we previously did.

Reported-by: Luís Picciochi Oliveira <pitxyoki@gmail.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:49:02 -07:00
Ben Hutchings
7b00ac51ff net: Revert "rndis_host: Poll status channel before control channel"
This reverts commit c17b274dc2.

That change was reported to break rndis_wlan support for the WUSB54GS.

Reported-by: Luís Picciochi Oliveira <pitxyoki@gmail.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-02 21:47:54 -07:00
Dan Williams
3e6b02d9f5 of/dma: fix build breakage in ppc4xx adma driver
Convert ppc4xx adma driver to use new node pointer location

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Anatolij Gustschin <agust@denx.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2010-07-02 15:46:17 -06:00
Mauro Carvalho Chehab
67c8931677 MAINTAINERS: Add an entry for i7core_edac
While here, fixes the mailing list for i5400_edac

Acked-by: Doug Thompson <dougthompson@xmission.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2010-07-02 18:04:38 -03:00
Mauro Carvalho Chehab
2d95d8158b i7core_edac: Avoid doing multiple probes for the same card
As Nehalem/Nehalem-EP/Westmere devices uses several devices for the same
functionality (memory controller), the default way of proping devices doesn't
work. So, instead of a per-device probe, all devices should be probed at once.

This means that we should block any new attempt of probe, otherwise, it will
try to register the same device several times.

Acked-by: Doug Thompson <dougthompson@xmission.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2010-07-02 18:04:29 -03:00
Mauro Carvalho Chehab
bda142890e i7core_edac: Properly discover the first QPI device
On Nehalem/Nehalem-EP/Westmere, the first QPI device is the last PCI bus.
The last bus is generally at 0x3f or 0xff, but there are also other systems
using different setups. For example, HP Z800 has 0x7f as the last bus.

This patch adds a logic to discover the last bus, dynamically detecting it
at runtime.

Acked-by: Doug Thompson <dougthompson@xmission.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
2010-07-02 18:04:05 -03:00
Wey-Yi Guy
c8312facd9 iwlwifi: adding enhance sensitivity table entries
For newer devices (6000g2a and 6000g2b), the sensitivity table send to
uCode require additional table entries to help sensitivity calibration.

All the additional entries has fix data for now, but do expect the value
will be change in the future when device become more stable.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
2010-07-02 11:11:17 -07:00
Wey-Yi Guy
bf3c7fddf9 iwlwifi: generic parameter define for _agn device
Code clean up to change name from having 5000 as part of name which easy
to confuse and think it is for 5000 series devices to more
generic _agn name since it is being used by multiple _agn devices.

No functional changes.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:11:06 -07:00
Wey-Yi Guy
4bf49a90bc iwlwifi: debugfs file for txfifo command testing
Add debugfs file for REPLY_TXFIFO_FLUSH host command testing.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:10:57 -07:00
Wey-Yi Guy
6555063666 iwlwifi: add support for device tx flush request
"Flush" request can come from two different sources, it can either from
mac80211, or from device when the operation is needed. Here
adding the support for device issue "flush" request.

When receive tx complete with status is TX_STATUS_FAIL_RFKILL_FLUSH,
issue REPLY_TXFIFO_FLUSH command to uCode to flush out all the tx frames
in queues.

In this condition, since mac80211 has no knowledge of "flush" operation,
driver need to stop all the tx queues and wait for the operation
completed before wake up the queues for frames transmission.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:10:45 -07:00
Wey-Yi Guy
716c74b007 iwlwifi: add mac80211 flush callback support
Adding flush callback support in the driver. Two type of flush can be
issued by mac80211:
1. drop = true: frame drop is ok, issue REPLY_TXFIFO_FLUSH host command
to uCode to drop all the frames in tx fifo queues; then return the
control back to mac80211
2. drop = false: wait for either all the frames in tx fifo queues been
transmitted, or timeout; then return the control back to mac80211

If the flush request coming from mac80211, mac80211 will make sure there
are no additional frames push down to driver before flush operation is
completed.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:10:33 -07:00
Wey-Yi Guy
947279eefb iwlwifi: tx fifo queue flush command
Add host command and structure for tx fifo queue flush

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:10:15 -07:00
Wey-Yi Guy
ad8d8333b1 iwlwifi: add debug print for parsing firmware TLV
When parsing TLV during loading firmware, if encounter any TLV error,
log the error message to help debugging.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:10:01 -07:00
Wey-Yi Guy
c04f9f2203 iwlwifi: fix fw_restart module parameter
fw_restart module parameter was broken by the recent check for stuck
queue patch, driver check the fx_restart module parameter
before reload the firmware; but the stuck queue timer kick in after
firmware error and reload the firmware even fw_restart=0. In this case,
driver should not reload the firmware, it is important to help debugging
uCode error.

The only case we can ignore the module parameter is when user request
firmware reload from debugfs, which can bypass the checking and perform
firmware reload all the time.

Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
2010-07-02 11:08:52 -07:00
Ming Lei
ecc3d5ae17 minstrel_ht: fix check for downgrading of top2 rate
The check should be against current top2 rate, instead of
current top rate.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Acked-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:40 -04:00
Ming Lei
009271f918 minstrel_ht: fix updating rate with best probability
The throughput should be considered when updating rate
with best probability.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Acked-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:39 -04:00
Felix Fietkau
8e67ca7c92 ath9k: fix crash with WEP in ad-hoc mode
Commit eed8e22f01 added support for using
multicast key lookup to support per-vif/sta keys for AP and ad-hoc.
Unfortunately, it also introduced a crash in ad-hoc mode when the sta
pointer is NULL, which happens when setting up an interface with WEP
keys. This patch fixes it by falling back to the assigned key index.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Reported-by: Senthil Balasubramanian <senthilkumar@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:38 -04:00
Felix Fietkau
347809fc2c ath9k: fix false positives in the baseband hang check
ath9k_hw_check_alive() occasionally returns false, as the hardware
is still processing data in a specific state. Fix this issue by
repeating the test a few times with longer delay inbetween attempts.
This gets rid of excessive hardware resets that appear frequently on
some AR9132 based devices, but could also happen on AR9280.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Reported-by: Björn Smedman <bjorn.smedman@venatech.se>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:38 -04:00
Felix Fietkau
54bd5006b0 ath9k_hw: clean up the noise floor calibration code to reduce code duplication
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:37 -04:00
Felix Fietkau
f2552e2837 ath9k_hw: sanitize noise floor values properly on all chips
This refactors the noise floor range checks to make them generic,
and adds proper ranges for each supported chip type.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:36 -04:00
Felix Fietkau
ba17bc5e55 ath9k_hw: sync initvals for ar9001 and ar9002 with Atheros
This includes the following changes/fixes:

 - a bugfix for stuck beacon issues
 - timing changes for improved performance
 - AGC setting improvements
 - fixes for high temperature issues on some chips

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:35 -04:00
Felix Fietkau
2e1f25662b ath9k_hw: reformat the ar5008, ar9001 and ar9002 initvals to match ar9003
This format is generated by the initval tool, available at:
git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/initvals-tool.git

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:34 -04:00
Felix Fietkau
f504f5f63a ath9k_hw: fix a few inconsistencies in initval array names
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
2010-07-02 13:44:33 -04:00
Reinette Chatre
e4c064728c iwlwifi: remove key information during device restart
When there is a firmware error or the firmware is reloaded for some other
reason we currently clear all station information, including keys
associated with them. A problem is that we do not clear some other
information regarding keys that are not stored in the station structs.

The consequence of this is that when the device is reconfigured after the
firmware reload we can, among other things, run out of key indices.

This fixes:
https://bugzilla.kernel.org/show_bug.cgi?id=16232
http://bugzilla.intellinuxwireless.org/show_bug.cgi?id=2221

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
2010-07-02 10:44:19 -07:00
Linus Torvalds
123f94f22e Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Cure nr_iowait_cpu() users
  init: Fix comment
  init, sched: Fix race between init and kthreadd
2010-07-02 09:52:58 -07:00
Linus Torvalds
4b78c119f0 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp:
  amd64_edac: Fix syndrome calculation on K8
2010-07-02 09:52:31 -07:00
Borislav Petkov
41c310447f amd64_edac: Fix syndrome calculation on K8
When calculating the DCT channel from the syndrome we need to know the
syndrome type (x4 vs x8). On F10h, this is read out from extended PCI
cfg space register F3x180 while on K8 we only support x4 syndromes and
don't have extended PCI config space anyway.

Make the code accessing F3x180 F10h only and fall back to x4 syndromes
on everything else.

Cc: <stable@kernel.org> # .33.x .34.x
Reported-by: Jeffrey Merkey <jeffmerkey@gmail.com>
Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
2010-07-02 17:32:34 +02:00
Conny Seidel
167a58f10d perf tools: Fix fallback to cplus_demangle() when bfd_demangle() is not available
make version 3.80 doesn't support "else ifdef" on the same line, also it
doesn't support unindented nested constructs.

Build fails with:
Makefile:608: Extraneous text after `else' directive
Makefile:611: *** only one `else' per conditional.  Stop.

This patch fixes the build for make 3.80.

Cc: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <1277990366-1462-1-git-send-email-conny.seidel@amd.com>
Signed-off-by: Conny Seidel <conny.seidel@.amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-07-02 10:01:58 -03:00
Catalin Marinas
246cf9c26b kbuild: Warn on selecting symbols with unmet direct dependencies
The "select" statement in Kconfig files allows the enabling of options
even if they have unmet direct dependencies (i.e. "depends on" expands
to "no"). Currently, the "depends on" clauses are used in calculating
the visibility but they do not affect the reverse dependencies in any
way.

The patch introduces additional tracking of the "depends on" statements
and prints a warning on selecting an option if its direct dependencies
are not met.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Michal Marek <mmarek@suse.cz>
2010-07-02 14:53:09 +02:00
Martin Ettl
5e8e1cc0a1 scripts/dtc: Fix a resource leak
during a check of the current git head of the linux kernel with the
static code analysis tool cppcheck
(http://sourceforge.net/apps/mediawiki/cppcheck/index.php?title=Main_Page)
the tool discovered a resource leak in linux-2.6/scripts/dtc/fstree.c.

Please refer the attached patch, that fixes the issue.

Fixes https://bugzilla.kernel.org/show_bug.cgi?id=15363
Signed-off-by: Martin Ettl <ettl.martin@gmx.de>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michal Marek <mmarek@suse.cz>
2010-07-02 13:51:11 +02:00
Michal Marek
62052be3a7 Merge branch 'setlocalversion-speedup' into kbuild/rc-fixes
Conflicts:
	Makefile
2010-07-02 11:56:52 +02:00
Catalin Marinas
42c4dafe80 ARM: 6202/1: Do not ARM_DMA_MEM_BUFFERABLE on RealView boards with L210/L220
RealView boards with certain revisions of the L210/L220 cache controller
may have issues (hardware deadlock) with the mandatory barriers (DSB
followed by an L2 cache sync) when ARM_DMA_MEM_BUFFERABLE is enabled.
The patch disables ARM_DMA_MEM_BUFFERABLE for these boards.

Tested-by: Linus Walleij <linus.walleij@stericsson.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-07-02 10:10:20 +01:00
Catalin Marinas
2503a5ecd8 ARM: 6201/1: RealView: Do not use outer_sync() on ARM11MPCore boards with L220
RealView boards with certain revisions of the L220 cache controller (ARM11*
processors only) may have issues (hardware deadlock) with the recent changes to
the mb() barrier implementation (DSB followed by an L2 cache sync). The patch
redefines the RealView ARM11MPCore mandatory barriers without the outer_sync()
call.

Cc: <stable@kernel.org>
Tested-by: Linus Walleij <linus.walleij@stericsson.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-07-02 10:10:09 +01:00
Tejun Heo
c7fc77f78f workqueue: remove WQ_SINGLE_CPU and use WQ_UNBOUND instead
WQ_SINGLE_CPU combined with @max_active of 1 is used to achieve full
ordering among works queued to a workqueue.  The same can be achieved
using WQ_UNBOUND as unbound workqueues always use the gcwq for
WORK_CPU_UNBOUND.  As @max_active is always one and benefits from cpu
locality isn't accessible anyway, serving them with unbound workqueues
should be fine.

Drop WQ_SINGLE_CPU support and use WQ_UNBOUND instead.  Note that most
single thread workqueue users will be converted to use multithread or
non-reentrant instead and only the ones which require strict ordering
will keep using WQ_UNBOUND + @max_active of 1.

Signed-off-by: Tejun Heo <tj@kernel.org>
2010-07-02 11:00:08 +02:00
Tejun Heo
f34217977d workqueue: implement unbound workqueue
This patch implements unbound workqueue which can be specified with
WQ_UNBOUND flag on creation.  An unbound workqueue has the following
properties.

* It uses a dedicated gcwq with a pseudo CPU number WORK_CPU_UNBOUND.
  This gcwq is always online and disassociated.

* Workers are not bound to any CPU and not concurrency managed.  Works
  are dispatched to workers as soon as possible and the only applied
  limitation is @max_active.  IOW, all unbound workqeueues are
  implicitly high priority.

Unbound workqueues can be used as simple execution context provider.
Contexts unbound to any cpu are served as soon as possible.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: David Howells <dhowells@redhat.com>
2010-07-02 11:00:02 +02:00
Tejun Heo
bdbc5dd7de workqueue: prepare for WQ_UNBOUND implementation
In preparation of WQ_UNBOUND addition, make the following changes.

* Add WORK_CPU_* constants for pseudo cpu id numbers used (currently
  only WORK_CPU_NONE) and use them instead of NR_CPUS.  This is to
  allow another pseudo cpu id for unbound cpu.

* Reorder WQ_* flags.

* Make workqueue_struct->cpu_wq a union which contains a percpu
  pointer, regular pointer and an unsigned long value and use
  kzalloc/kfree() in UP allocation path.  This will be used to
  implement unbound workqueues which will use only one cwq on SMPs.

* Move alloc_cwqs() allocation after initialization of wq fields, so
  that alloc_cwqs() has access to wq->flags.

* Trivial relocation of wq local variables in freeze functions.

These changes don't cause any functional change.

Signed-off-by: Tejun Heo <tj@kernel.org>
2010-07-02 10:59:57 +02:00
Tejun Heo
ad72cf9885 libata: take advantage of cmwq and remove concurrency limitations
libata has two concurrency related limitations.

a. ata_wq which is used for polling PIO has single thread per CPU.  If
   there are multiple devices doing polling PIO on the same CPU, they
   can't be executed simultaneously.

b. ata_aux_wq which is used for SCSI probing has single thread.  In
   cases where SCSI probing is stalled for extended period of time
   which is possible for ATAPI devices, this will stall all probing.

#a is solved by increasing maximum concurrency of ata_wq.  Please note
that polling PIO might be used under allocation path and thus needs to
be served by a separate wq with a rescuer.

#b is solved by using the default wq instead and achieving exclusion
via per-port mutex.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Jeff Garzik <jgarzik@pobox.com>
2010-07-02 10:59:24 +02:00