- 28 Jun, 2006 40 commits
-
-
Kirill Korotaev authored
There is a race between set_cpus_allowed() and move_task_off_dead_cpu(). __migrate_task() doesn't report any err code, so task can be left on its runqueue if its cpus_allowed mask changed so that dest_cpu is not longer a possible target. Also, chaning cpus_allowed mask requires rq->lock being held. Signed-off-by:
Kirill Korotaev <dev@openvz.org> Acked-By:
Ingo Molnar <mingo@elte.hu> Signed-off-by:
Andrew Morton <akpm@osdl.org> Signed-off-by:
Linus Torvalds <torvalds@osdl.org>
-
Steven Rostedt authored
Unless we expect to have more than 2G CPUs, there's no reason to have 'i' as a long long here. Signed-off-by:
Steven Rostedt <rostedt@goodmis.org> Signed-off-by:
-
Con Kolivas authored
The relationship between INTERACTIVE_SLEEP and the ceiling is not perfect and not explicit enough. The sleep boost is not supposed to be any larger than without this code and the comment is not clear enough about what exactly it does, just the reason it does it. Fix it. There is a ceiling to the priority beyond which tasks that only ever sleep for very long periods cannot surpass. Fix it. Prevent the on-runqueue bonus logic from defeating the idle sleep logic. Opportunity to micro-optimise. Signed-off-by:
Con Kolivas <kernel@kolivas.org> Signed-off-by:
Mike Galbraith <efault@gmx.de> Acked-by:
Ken Chen <kenneth.w.chen@intel.com> Signed-off-by:
-
Steven Rostedt authored
Signed-off-by:
-
Chen, Kenneth W authored
Initial report and lock contention fix from Chris Mason: Recent benchmarks showed some performance regressions between 2.6.16 and 2.6.5. We tracked down one of the regressions to lock contention in schedule heavy workloads (~70,000 context switches per second) kernel/sched.c:dependent_sleeper() was responsible for most of the lock contention, hammering on the run queue locks. The patch below is more of a discussion point than a suggested fix (although it does reduce lock contention significantly). The dependent_sleeper code looks very expensive to me, especially for using a spinlock to bounce control between two different siblings in the same cpu. It is further optimized: * perform dependent_sleeper check after next task is determined * convert wake_sleeping_dependent to use trylock * skip smt runqueue check if trylock fails * optimize double_rq_lock now that smt nice is converted to trylock * early exit in searching first SD_SHARE_CPUPOWER domain * speedup fast path of dependent_sleeper [akpm@osdl.org: cleanup] Signed-off-by:
Nick Piggin <npiggin@suse.de> Acked-by:
Chris Mason <mason@suse.com> Signed-off-by:
-
Jim Cromie authored
Replace the temp makefile hacks with proper CONFIG entries, which are also added to Kconfig. Signed-off-by:
Jim Cromie <jim.cromie@gmail.com> Signed-off-by:
-
Jim Cromie authored
Add current pin settings to gpio_dump() output. This adds the last 'word' to the syslog lines, which displays the input and output values that the pin is set to. pc8736x_gpio.0: io00: 0x0044 TS OD PUE EDGE LO DEBOUNCE io:1/1 The 2 values may differ for a number of reasons: 1- the pin output circuitry is diaabled, (as the above 'TS' indicates) 2- it needs a pullup resistor to drive the attached circuit, 3- the external circuit needs a pullup so the open-drain has something to pull-down 4- the pin is wired to Vcc or Ground It might be appropriate to add a WARN for 2,3,4, since they could damage the chip and/or circuit, esp if misconfig goes unnoticed. Signed-off-by:
-
Jim Cromie authored
Hmm. Im somewhat ambivalent about this patch, since with it, driver wont build for vanilla 17 or older. Its also only 1/2 of your suggestion - when I tried it, I was building against vanilla 17, and asm/uaccess.h cause compilation failure. Looking back, Im perplexed as to why linux/io.h didnt cause same failure ?!? use linux/io.h rather than asm/io.h Signed-off-by:
-
Jim Cromie authored
Replace spinlocks guarding gpio config ops with mutexes. This is a me-too patch, and is justifiable insofar as mutexes have stricter semantics and better debugging support, so are preferred where they are applicable. Signed-off-by:
-
Jim Cromie authored
Add a working gpio_current() to pc8736x_gpio.c (the previous implementation just threw a dev_warn), and fix gpio_change() to use gpio_current() rather than the incorrect (and temporary) gpio_get(). Initialize shadow-regs so this all works. Signed-off-by:
-
Jim Cromie authored
Use of dev_dbg() and friends is considered good practice. dev_dbg() needs a struct device *devp, but nsc_gpio is only a helper module, so it doesnt have/need its own. To provide devp to the user-modules (scx200 & pc8736x _gpio), we add it to the vtable, and set it during init. Also squeeze nsc_gpio_dump()'s format a little. [ 199.259879] pc8736x_gpio.0: io09: 0x0044 TS OD PUE EDGE LO DEBOUNCE Signed-off-by:
-
Jim Cromie authored
Adds platform-device to (just introduced) driver, and uses it to replace many printks with dev_dbg() etc. This could trivially be merged into previous patch, but this way matches better with the corresponding patch that does the same change to scx200_gpio. Signed-off-by:
-
Jim Cromie authored
Add the brand new pc8736x_gpio driver. This is mostly based upon scx200_gpio.c, but the platform_dev is treated separately, since its fairly big too. Signed-off-by:
-
Jim Cromie authored
Since the meaning of config-bits is the same for scx200 and pc8736x _gpios, we can share a function to deliver this to user. Since it is called via the vtable, its also completely replaceable. For now, we keep using printk... Signed-off-by:
-
Jim Cromie authored
Now that the read(), write() file-ops are dispatching gpio-ops via the vtable, they are generic, and can be moved 'verbatim' to the nsc_gpio common-support module. After the move, various symbols are renamed to update 'scx200_' to 'nsc_', and headers are adjusted accordingly. Signed-off-by:
-
Jim Cromie authored
Add the nsc_gpio common-support module as an empty shell. Next patch starts the migration of the common gpio support routines. Signed-off-by:
-
Jim Cromie authored
Now actually call the gpio operations thru the vtable. Signed-off-by:
-
Jim Cromie authored
Abstract the gpio operations into a new nsc_gpio_ops vtable. Signed-off-by:
-
Jim Cromie authored
[PATCH] chardev: GPIO for SCx200 & PC-8736x: refactor scx200_probe to better segregate _gpio initialization Pull shadow-reg initialization into separate function now, rather than doing it 2x later (scx200, pc8736x). When we revisit 2nd drvr below, it will be to reimplement an init function, rather than another refactor. Signed-off-by:
-
Jim Cromie authored
Add a new driver command: 'v' which calls gpio_dump() on the pin. The output goes to the log, like all other INFO messages in the original driver. Giving the user control over the feedback they 'need' is construed to be a user-friendly feature, and allows us (later) to dial down many INFO messages to DEBUG log-level. Signed-off-by:
-
Jim Cromie authored
Shrink scx200_gpio_dump() to a single printk with ternary ops. The function is still ifdef'd out, this is corrected in next patch, when it is actually used. The patch 'inadvertently' changed loglevel from DEBUG to INFO. This is Good, because in next patch, its wired to a 'command' which the user can invoke when they want. When they do so, its because they want INFO to support their developement effort, and we want to give it to them without compiling a DEBUG version of the driver. Signed-off-by:
-
Jim Cromie authored
Per kernel headers, device minor numbers are unsigned ints. Do the same in this driver. Signed-off-by:
-
Jim Cromie authored
Add a platform-device to scx200_gpio, and use its struct device dev member (ie: devp) in dev_dbg() once. There are 2 alternatives here (Im soliciting guidance/commentary): - use isa_device, if/when its added to the kernel. - alter scx200.c to EXPORT_GPL its private devp so that both scx200_gpio, and the (to be added) nsc_gpio module can use it. Since the available devp is in 'grandparent', this seems like too much 'action at a distance'. Signed-off-by:
-
Jim Cromie authored
Adopt many modern 2.6 coding practices, ala LDD3, chapter 3. Changes are limited to initialization calls from module init, ie: cdev_init, cdev_add, *_chrdev_region, mkdev. Signed-off-by:
-
Jim Cromie authored
GPIO SUPPORT FOR SCx200 & PC8736x The patch-set reworks the 2.4 vintage scx200_gpio driver for modern 2.6, and refactors GPIO support to reuse it in a new driver for the GPIO on PC-8736x chips. Its handy for the Soekris.com net-4801, which has both chips. These patches have been seen recently on Kernel-Mentors, and then Kernel-Newbies ML, where Jesper Juhl kindly reviewed it. His feedback has been incorporated. Thanks Jesper ! Its also gone to soekris-tech@soekris.com for possible testing by linux folks, I've gotten 1 promise so far. Theyre mostly BSD folk over there, but we'll see.. Device-file & Sysfs The driver preserves the existing device-file interface, including the write/cmd set, but adds v to 'view' the pin-settings & configs by inducing, via gpio_dump(), a dev_info() call. Its a fairly crappy way to get status, but it sticks to the syslog approach, conservatively. Allowing users to voluntarily trigger logging is good, it gives them a familiar way to confirm their app's control & use of the pins, and I've thus reduced the pin-mode-updates from dev_info to dev_dbg. I've recently bolted on a proto sysfs interface for both new drivers. Im not including those patches here; they (the patch + doc-pre-patch) are still quite raw (and unreviewed on KNML), and since they 'invent' a convention for GPIO, a proper vetting is needed. Since this patchset is much bigger than my previous ones, Id like to keep things simpler, and address it 1st, before bolting on more stuff. The driver-split The Geode CPU and the PC-87366 Super-IO chip have GPIO units which share a common pin-architecture (same pin features, with same bits controlling), but with different addressing mechanics and port organizations. The vintage driver expresses the pin capabilities with pin-mode commands [OoPpTt],etc that change the pin configurations, and since the 2 chips share pin-arch, we can reuse the read(), write() commands, once the implementation is suitably adjusted. The patchset adds a vtable: struct nsc_gpio_ops, to abstract the existing gpio operations, then adjusts fileops.write() code to invoke operations via that vtable. Driver specific open()s set private_data to the vtable so its available for use by write(). The vtable gets the gpio_dump() too, since its user-friendly, and (could be construed as) part of the current device-file interface. To support use of dev_dbg() in write() & _dump(), the vtable gets a dev ptr too, set by both scx200 & pc8736x _gpio drivers. heres how the pins are presented in syslog: [ 1890.176223] scx200_gpio.0: io00: 0x0044 TS OD PUE EDGE LO DEBOUNCE [ 1890.287223] scx200_gpio.0: io01: 0x0003 OE PP PUD EDGE LO nsc_gpio.c: new file is new home of several file-ops methods, which are modified to get their vtable from filp->private_data, and use it where needed. scx200_gpio.c: keeps some of its existing gpio routines, but now wires them up via the vtable (they're invoked by nsc_gpio.c:nsc_gpio_write() thru this vtable). A driver-spcific open() initializes filp->private_data with the vtable. Once the split is clean, and the scx200_gpio driver is working, we copy and modify the function and variable names, and rework the access-method bodies for the different addressing scheme. Heres a working overview of the patchset: # series file for GPIO # Spring Cleaning gpio-scx/patch.preclean # scripts/Lindent fixes, editor-ctrl comments # API Modernization gpio-scx/patch.api26 # what I learned from LDD3 gpio-scx/patch.platform-dev-2 # get pdev, support for dev_dbg() gpio-scx/patch.unsigned-minor # fix to match std practice # Debuggability gpio-scx/patch.dump-diet # shrink gpio_dump() gpio-scx/patch.viewpins # add new 'command' to call dump() gpio-scx/patch.init-refactor # pull shadow-register init to sub # Access-Abstraction (add vtable) gpio-scx/patch.access-vtable # introduce nsg_gpio_ops vtable, w dump gpio-scx/patch.vtable-calls # add & use the vtable in scx200_gpio gpio-scx/patch.nscgpio-shell # add empty driver for common-fops # move code under abstraction gpio-scx/patch.migrate-fops # move file-ops methods from scx200_gpio gpio-scx/patch.common-dump # mv scx200.c:scx200_gpio_dump() to nsc_gpio.c gpio-scx/patch.add-pc8736x-gpio # add new driver, like old, w chip adapt # gpio-scx/patch.add-DEBUG # enable all dev_dbg()s # Cleanups # finish printk -> dev_dbg() etc gpio-scx/patch.pdev-pc8736x # new drvr needs pdev too, gpio-scx/patch.devdbg-nscgpio # add device to 'vtable', use in dev_dbg() # gpio-scx/patch.pin-config-view # another 'c' 'command' # gpio-scx/quiet-getset # take out excess dbg stuff (pretty quiet now) gpio-scx/patch.shadow-current # imitate scx200_gpio's shadow regs in pc87* # post KMentors-post patches .. gpio-scx/patch.mutexes # use mutexes for config-locks gpio-scx/patch.viewpins-values # extend dump to obsolete separate 'c' cmd gpio-scx/patch.kconfig # add stuff for kbuild # TBC # combine api26 with pdev, which is just one step. # merge c&v commands to single do-all-fn # delay viewpins, dump-diet should also un-ifdef it too. diff.sys-gpio-rollup-1 This patch: Removed editor format-control comments, and used scripts/Lindent to clean up whitespace, then deleted the bogus chunks :-( Signed-off-by:
-
Chandra Seetharaman authored
Make use the of newly defined hotplug version of cpu_notifier functionality wherever appropriate. Signed-off-by:
Chandra Seetharaman <sekharan@us.ibm.com> Cc: Ashok Raj <ashok.raj@intel.com> Signed-off-by:
-
Chandra Seetharaman authored
Define new macros register_hotcpu_notifier() and unregister_hotcpu_notifier() that redefines register_cpu_notifier() and unregister_cpu_notifier() for use only when HOTPLUG_CPU is defined. Signed-off-by:
-
Chandra Seetharaman authored
Make notifier_calls associated with cpu_notifier as __cpuinit. __cpuinit makes sure that the function is init time only unless CONFIG_HOTPLUG_CPU is defined. [akpm@osdl.org: section fix] Signed-off-by:
-
Chandra Seetharaman authored
Make notifier_blocks associated with cpu_notifier as __cpuinitdata. __cpuinitdata makes sure that the data is init time only unless CONFIG_HOTPLUG_CPU is defined. Signed-off-by:
-
Chandra Seetharaman authored
CPUs come online only at init time (unless CONFIG_HOTPLUG_CPU is defined). So, cpu_notifier functionality need to be available only at init time. This patch makes register_cpu_notifier() available only at init time, unless CONFIG_HOTPLUG_CPU is defined. This patch exports register_cpu_notifier() and unregister_cpu_notifier() only if CONFIG_HOTPLUG_CPU is defined. Signed-off-by:
-
Chandra Seetharaman authored
This patch reverts notifier_block changes made in 2.6.17 Signed-off-by:
-
Chandra Seetharaman authored
In 2.6.17, there was a problem with cpu_notifiers and XFS. I provided a band-aid solution to solve that problem. In the process, i undid all the changes you both were making to ensure that these notifiers were available only at init time (unless CONFIG_HOTPLUG_CPU is defined). We deferred the real fix to 2.6.18. Here is a set of patches that fixes the XFS problem cleanly and makes the cpu notifiers available only at init time (unless CONFIG_HOTPLUG_CPU is defined). If CONFIG_HOTPLUG_CPU is defined then cpu notifiers are available at run time. This patch reverts the notifier_call changes made in 2.6.17 Signed-off-by:
-
Sonny Rao authored
We need to serialize access to the global rtc_idr even in this error path. Signed-off-by:
Sonny Rao <sonny@burdell.org> Acked-by:
Alessandro Zummo <a.zummo@towertech.it> Signed-off-by:
-
Alan Cox authored
There are two locking sets involved. One locks the board mappings and the other is the tty open/close locking. The low level code was clearly designed to be ported to OS's with spin locks already so pretty much comes out in the wash Signed-off-by:
Alan Cox <alan@redhat.com> Signed-off-by:
-
akpm@osdl.org authored
Corey Minyard <minyard@acm.org> The kthread used to speed up polling for IPMI was using udelay in its busy-wait polling loop when the lower-level state machine told it to do a short delay. This just used CPU and didn't help scheduling, thus causing bad problems with other tasks. Call schedule() instead. Signed-off-by:
Corey Minyard <minyard@acm.org> Acked-by:
Matt Domsch <Matt_Domsch@dell.com> Signed-off-by:
-
Paul E. McKenney authored
Add operations for the call_rcu_bh() variant of RCU. Also add an rcu_batches_completed_bh() function, which is needed by rcutorture. Signed-off-by:
Paul E. McKenney <paulmck@us.ibm.com> Signed-off-by:
-
Paul E. McKenney authored
Add an ops vector to rcutorture, and add the ops for Classic RCU. Update the rcutorture documentation to reflect slight change to the dmesg formats. Signed-off-by:
-
Paul E. McKenney authored
This just catches the RCU torture documentation up with the recent fixes that test RCU for architectures that turn of the scheduling-clock interrupt for idle CPUs and the addition of a SUCCESS/FAILURE indication, fixing up an obsolete comment as well. Signed-off-by:
-
Randy Dunlap authored
Fix kernel-doc parameters in kernel/ Warning(/var/linsrc/linux-2617-g9//kernel/auditsc.c:1376): No description found for parameter 'u_abs_timeout' Warning(/var/linsrc/linux-2617-g9//kernel/auditsc.c:1420): No description found for parameter 'u_msg_prio' Warning(/var/linsrc/linux-2617-g9//kernel/auditsc.c:1420): No description found for parameter 'u_abs_timeout' Warning(/var/linsrc/linux-2617-g9//kernel/acct.c:526): No description found for parameter 'pacct' Signed-off-by:
Randy Dunlap <rdunlap@xenotime.net> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by:
-
Paul Fulghum authored
Fix TCSBRK comment to prevent confusion or accidental removal. Signed-off-by:
Paul Fulghum <paulkf@microgate.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by:
-
