summaryrefslogtreecommitdiffstats
path: root/kernel/irq/manage.c
Commit message (Collapse)AuthorAgeFilesLines
* Revert "irq: Always set IRQF_ONESHOT if no primary handler is specified"Linus Torvalds2011-08-231-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit f3637a5f2e2eb391ff5757bc83fb5de8f9726464. It turns out that this breaks several drivers, one example being OMAP boards which use the on-board OMAP UARTs and the omap-serial driver that will not boot to userspace after the commit. Paul Walmsley reports that enabling CONFIG_DEBUG_SHIRQ reveals 'IRQ handler type mismatch' errors: IRQ handler type mismatch for IRQ 74 current handler: serial idle ... and the reason is that setting IRQF_ONESHOT will now result in those interrupt handlers having different IRQF flags, and thus being unsharable. So the commit log in the reverted commit: "Since it is required for those users and there is no difference for others it makes sense to add this flag unconditionally." is simply not true: there may not be any difference from a "actions at irq time", but there is a *big* difference wrt this flag testing irq management (see __setup_irq() in kernel/irq/manage.c). One solution may be to stop verifying IRQF_ONESHOT in __setup_irq(), but right now the safe course of action is to revert the change. Let's revisit this in a later merge window. Reported-by: Paul Walmsley <paul@pwsan.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Requested-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Acked-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* irq: Track the owner of irq descriptorSebastian Andrzej Siewior2011-07-281-4/+13
| | | | | | | | | | | | | | | | | | | | Interrupt descriptors can be allocated from modules. The interrupts are used by other modules, but we have no refcount on the module which provides the interrupts and there is no way to establish one on the device level as the interrupt using module is agnostic to the fact that the interrupt is provided by a module rather than by some builtin interrupt controller. To prevent removal of the interrupt providing module, we can track the owner of the interrupt descriptor, which also provides the relevant irq chip functions in the irq descriptor. request/setup_irq() can now acquire a refcount on the owner module to prevent unloading. free_irq() drops the refcount. Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Link: http://lkml.kernel.org/r/20110711101731.GA13804@Chamillionaire.breakpoint.cc Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* irq: Always set IRQF_ONESHOT if no primary handler is specifiedSebastian Andrzej Siewior2011-07-281-0/+1
| | | | | | | | | | | | | If no primary handler is specified then a default one is assigned which always returns IRQ_WAKE_THREAD. This handler requires the IRQF_ONESHOT flag on LEVEL / EIO typed irqs because the source of interrupt is not disabled. Since it is required for those users and there is no difference for others it makes sense to add this flag unconditionally. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: http://lkml.kernel.org/r/1310070737-18514-1-git-send-email-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Prevent potential NULL dereference in irq_set_irq_wake()Jesper Juhl2011-06-101-0/+3
| | | | | | | | | | | | | | | | | | | | | In kernel/irq/manage.c::irq_set_irq_wake() we call irq_get_desc_buslock() which may return NULL, but the code dereferences the result unconditionally. irq_set_irq_wake() has lots of callers - I checked a few and I couldn't find anything that guarantees that they won't call it with some input that will cause irq_get_desc_buslock() to return NULL, so I think it's a good thing to test and -EINVAL was the most sane error code in this situation that I could think of. Not all callers test the return value of irq_set_irq_wake(), but those that do take != 0 to mean error as far as I can see, so they should be fine. I guess those that don't test actually should, but that's a different issue. Signed-off-by: Jesper Juhl <jj@chaosbits.net> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1106092300360.17868@swampdragon.chaosbits.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* irq: Handle spurios irq detection for threaded irqsSebastian Andrzej Siewior2011-06-031-6/+18
| | | | | | | | | | | | | | | | The detection of spurios interrupts is currently limited to first level handler. In force-threaded mode we never notice if the threaded irq does not feel responsible. This patch catches the return value of the threaded handler and forwards it to the spurious detector. If the primary handler returns only IRQ_WAKE_THREAD then the spourious detector ignores it because it gets called again from the threaded handler. [ tglx: Report the erroneous return value early and bail out ] Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Link: http://lkml.kernel.org/r/1306824972-27067-2-git-send-email-sebastian@breakpoint.cc Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Support per-IRQ thread disabling.Paul Mundt2011-04-231-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | This adds support for disabling threading on a per-IRQ basis via the IRQ status instead of the IRQ flow, which is necessary for interrupts that don't follow the natural IRQ flow channels, such as those that are virtually created. The new APIs added are simply: irq_set_thread() irq_set_nothread() which follow the rest of the IRQ status routines. Chained handlers also have IRQ_NOTHREAD set on them automatically, making the lack of threading explicit rather than implicit. Subsequently, the nothread flag can be viewed through the standard genirq debugging facilities. [ tglx: Fixed cleanup fallout ] Signed-off-by: Paul Mundt <lethal@linux-sh.org> Link: http://lkml.kernel.org/r/%3C20110406210135.GF18426%40linux-sh.org%3E Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Fix cpumask leak in __setup_irq()Xiaotian Feng2011-04-021-0/+1
| | | | | | | | The allocated cpumask should be freed in __setup_irq(). Signed-off-by: Xiaotian Feng <dfeng@redhat.com> LKML-Reference: <1301744375-6812-1-git-send-email-dfeng@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Remove compat codeThomas Gleixner2011-03-291-9/+1
| | | | Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Fix harmless typoThomas Gleixner2011-03-291-1/+1
| | | | | | | The late night fixup missed to convert the data type from irq_desc to irq_data, which results in a harmless but annoying warning. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq; Fix cleanup falloutThomas Gleixner2011-03-291-8/+8
| | | | | | | | | I missed the CONFIG_GENERIC_PENDING_IRQ dependency in the affinity related functions and the IRQ_LEVEL propagation into irq_data state. Did not pop up on my main test platforms. :( Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: David Daney <ddaney@caviumnetworks.com>
* genirq: Fix new kernel-doc warningsRandy Dunlap2011-03-281-1/+1
| | | | | | | | | | | | | Fix new irq-related kernel-doc warnings in 2.6.38: Warning(kernel/irq/manage.c:149): No description found for parameter 'mask' Warning(kernel/irq/manage.c:149): Excess function parameter 'cpumask' description in 'irq_set_affinity' Warning(include/linux/irq.h:161): No description found for parameter 'state_use_accessors' Warning(include/linux/irq.h:161): Excess struct/union/enum/typedef member 'state_use_accessor' description in 'irq_data' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> LKML-Reference: <20110318093356.b939558d.randy.dunlap@oracle.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move INPROGRESS, MASKED and DISABLED state flags to irq_dataThomas Gleixner2011-03-281-16/+14
| | | | | | | | We really need these flags for some of the interrupt chips. Move it from internal state to irq_data and provide proper accessors. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: David Daney <ddaney@caviumnetworks.com>
* genirq: Split irq_set_affinity() so it can be called with lock held.David Daney2011-03-271-18/+30
| | | | | | | | | | | | | | | | The .irq_cpu_online() and .irq_cpu_offline() functions may need to adjust affinity, but they are called with the descriptor lock held. Create __irq_set_affinity_locked() which is called with the lock held. Make irq_set_affinity() just a wrapper that acquires the lock. [ tglx: Changed the argument to irq_data, added a !desc check and moved the !irq_set_affinity check where it belongs ] Signed-off-by: David Daney <ddaney@caviumnetworks.com> Cc: linux-mips@linux-mips.org Cc: ralf@linux-mips.org LKML-Reference: <1301081931-11240-4-git-send-email-ddaney@caviumnetworks.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Fix incorrect unlock in __setup_irq()Dan Carpenter2011-03-171-1/+1
| | | | | | | | | | | | goto out_thread is called before we take the lock. It causes a gcc warning: "kernel/irq/manage.c:858: warning: ‘flags’ may be used uninitialized in this function" [ tglx: Moved unlock before free_cpumask_var() ] Signed-off-by: Dan Carpenter <error27@gmail.com> LKML-Reference: <20110317114307.GJ2008@bicker> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Provide forced interrupt threadingThomas Gleixner2011-02-261-4/+63
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a commandline parameter "threadirqs" which forces all interrupts except those marked IRQF_NO_THREAD to run threaded. That's mostly a debug option to allow retrieving better debug data from crashing interrupt handlers. If "threadirqs" is not enabled on the kernel command line, then there is no impact in the interrupt hotpath. Architecture code needs to select CONFIG_IRQ_FORCED_THREADING after marking the interrupts which cant be threaded IRQF_NO_THREAD. All interrupts which have IRQF_TIMER set are implict marked IRQF_NO_THREAD. Also all PER_CPU interrupts are excluded. Forced threading hard interrupts also forces all soft interrupt handling into thread context. When enabled it might slow down things a bit, but for debugging problems in interrupt code it's a reasonable penalty as it does not immediately crash and burn the machine when an interrupt handler is buggy. Some test results on a Core2Duo machine: Cache cold run of: # time git grep irq_desc non-threaded threaded real 1m18.741s 1m19.061s user 0m1.874s 0m1.757s sys 0m5.843s 0m5.427s # iperf -c server non-threaded [ 3] 0.0-10.0 sec 1.09 GBytes 933 Mbits/sec [ 3] 0.0-10.0 sec 1.09 GBytes 934 Mbits/sec [ 3] 0.0-10.0 sec 1.09 GBytes 933 Mbits/sec threaded [ 3] 0.0-10.0 sec 1.09 GBytes 939 Mbits/sec [ 3] 0.0-10.0 sec 1.09 GBytes 934 Mbits/sec [ 3] 0.0-10.0 sec 1.09 GBytes 937 Mbits/sec Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <20110223234956.772668648@linutronix.de>
* genirq: Allow shared oneshot interruptsThomas Gleixner2011-02-251-6/+4
| | | | | | | | Support ONESHOT on shared interrupts, if all drivers agree on it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <20110223234956.483640430@linutronix.de>
* genirq: Prepare the handling of shared oneshot interruptsThomas Gleixner2011-02-251-6/+48
| | | | | | | | | | | | | | | | | | | | For level type interrupts we need to track how many threads are on flight to avoid useless interrupt storms when not all thread handlers have finished yet. Keep track of the woken threads and only unmask when there are no more threads in flight. Yes, I'm lazy and using a bitfield. But not only because I'm lazy, the main reason is that it's way simpler than using a refcount. A refcount based solution would need to keep track of various things like crashing the irq thread, spurious interrupts coming in, disables/enables, free_irq() and some more. The bitfield keeps the tracking simple and makes things just work. It's also nicely confined to the thread code pathes and does not require additional checks all over the place. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <20110223234956.388095876@linutronix.de>
* genirq: Add missing break in __irq_set_trigger()Thomas Gleixner2011-02-211-0/+1
| | | | | | | | The switch case in __irq_set_trigger() lacks a break, which emits a pr_err unconditionally on success. Reported-by: Lars-Peter Clausen <lars@metafoo.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Use irq_get/put functionsThomas Gleixner2011-02-191-50/+31
| | | | | | | Convert the management functions to use the common irq_get/put function. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Remove real old transition functionsThomas Gleixner2011-02-191-13/+1
| | | | | | These transition helpers are stale for years now. Remove them. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move wakeup state to irq_dataThomas Gleixner2011-02-191-2/+2
| | | | | | | Some irq_chips need to know the state of wakeup mode for setting the trigger type etc. Reflect it in irq_data state. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Add IRQCHIP_SET_TYPE_MASKED flagThomas Gleixner2011-02-191-3/+13
| | | | | | | | | | irq_chips, which require to mask the chip before changing the trigger type should set this flag. So the core takes care of it and the requirement for looking into desc->status in the chip goes away. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Linus Walleij <linus.walleij@stericsson.com> Cc: Lars-Peter Clausen <lars@metafoo.de>
* genirq: Wrap the remaning IRQ_* flagsThomas Gleixner2011-02-191-7/+7
| | | | | | Use wrappers to keep them away from the core code. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Mirror irq trigger type bits in irq_data.stateThomas Gleixner2011-02-191-17/+27
| | | | | | | | | | | | | | | | | That's the data structure chip functions get provided. Also allow them to signal the core code that they updated the flags in irq_data.state by returning IRQ_SET_MASK_OK_NOCOPY. The default is unchanged. The type bits should be accessed via: val = irqd_get_trigger_type(irqdata); and irqd_set_trigger_type(irqdata, val); Coders who access them directly will be tracked down and slapped with stinking trouts. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_AFFINITY_SET to coreThomas Gleixner2011-02-191-4/+7
| | | | | | Keep status in sync until last abuser is gone. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Reuse existing can set affinty checkThomas Gleixner2011-02-191-2/+2
| | | | | | Add a !desc check while at it. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Mirror IRQ_PER_CPU and IRQ_NO_BALANCING in irq_data.stateThomas Gleixner2011-02-191-6/+10
| | | | | | | | | | | | | | That's the right data structure to look at for arch code. Accessor functions are provided. irqd_is_per_cpu(irqdata); irqd_can_balance(irqdata); Coders who access them directly will be tracked down and slapped with stinking trouts. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Remove CHECK_IRQ_PER_CPU from core codeThomas Gleixner2011-02-191-2/+2
| | | | Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Remove CONFIG_IRQ_PER_CPUThomas Gleixner2011-02-191-6/+3
| | | | | | | | The saving of this switch is minimal versus the ifdef mess it creates. Simple enable PER_CPU unconditionally and remove the config switch. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Add IRQ_MOVE_PENDING to irq_data.stateThomas Gleixner2011-02-191-2/+2
| | | | | | | | | | | | chip implementations need to know about it. Keep status in sync until all users are fixed. Accessor function: irqd_is_setaffinity_pending(irqdata) Coders who access them directly will be tracked down and slapped with stinking trouts. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_WAKEUP to coreThomas Gleixner2011-02-191-2/+2
| | | | | | No users outside of core. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_SUSPENDED to coreThomas Gleixner2011-02-191-4/+4
| | | | | | No users outside of core. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_MASKED to coreThomas Gleixner2011-02-191-2/+3
| | | | | | Keep status in sync until all users are fixed. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_PENDING flag to coreThomas Gleixner2011-02-191-2/+3
| | | | | | Keep status in sync until all users are fixed. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_DISABLED to coreThomas Gleixner2011-02-191-2/+2
| | | | | | Keep status in sync until all abusers are fixed. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_REPLAY and IRQ_WAITING to coreThomas Gleixner2011-02-191-2/+2
| | | | | | No users outside of core. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_ONESHOT to coreThomas Gleixner2011-02-191-4/+4
| | | | | | No users outside of core. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Add IRQ_INPROGRESS to coreThomas Gleixner2011-02-191-8/+9
| | | | | | | | | | | | | We need to maintain the flag for now in both fields status and istate. Add a CONFIG_GENERIC_HARDIRQS_NO_COMPAT switch to allow testing w/o the status one. Wrap the access to status IRQ_INPROGRESS in a inline which can be turned of with CONFIG_GENERIC_HARDIRQS_NO_COMPAT along with the define. There is no reason that anything outside of core looks at this. That needs some modifications, but we'll get there. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_SPURIOUS_DISABLED to core stateThomas Gleixner2011-02-191-5/+4
| | | | | | No users outside. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Move IRQ_AUTODETECT to internal stateThomas Gleixner2011-02-191-1/+2
| | | | | | No users outside of core Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Fixup core code namespace falloutThomas Gleixner2011-02-191-1/+1
| | | | Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Consolidate IRQ_DISABLEDThomas Gleixner2011-02-191-6/+3
| | | | | | Handle IRQ_DISABLED consistent. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Remove default magicThomas Gleixner2011-02-191-2/+2
| | | | | | | | | Now that everything uses the wrappers, we can remove the default functions. None of those functions is performance critical. That makes the IRQ_MASKED flag tracking fully consistent. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Consolidate disable/enableThomas Gleixner2011-02-191-1/+1
| | | | | | Create irq_disable/enable and use them to keep the flags consistent. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Consolidate startup/shutdown of interruptsThomas Gleixner2011-02-191-9/+5
| | | | | | | | | | Aside of duplicated code some of the startup/shutdown sites do not handle the MASKED/DISABLED flags and the depth field at all. Move that to a helper function and take care of it there. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <20110202212551.787481468@linutronix.de>
* genirq: Remove bogus conditionalThomas Gleixner2011-02-191-4/+1
| | | | | | | | | | The if (chip->irq_shutdown) check will always evaluate to true, as we fill in chip->irq_shutdown with default_shutdown in irq_chip_set_defaults() if the chip does not provide its own function. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <20110202212551.667607458@linutronix.de>
* genirq: Remove redundant thread affinity settingThomas Gleixner2011-02-191-2/+0
| | | | | | Thread affinity is already set by setup_affinity(). Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Do not copy affinity before setThomas Gleixner2011-02-191-13/+34
| | | | | | | | | | | | | | | | While rumaging through arch code I found that there are a few workarounds which deal with the fact that the initial affinity setting from request_irq() copies the mask into irq_data->affinity before the chip code is called. In the normal path we unconditionally copy the mask when the chip code returns 0. Copy after the code is called and add a return code IRQ_SET_MASK_OK_NOCOPY for the chip functions, which prevents the copy. That way we see the real mask when the chip function decided to truncate it further as some arches do. IRQ_SET_MASK_OK is 0, which is the current behaviour. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Always apply cpu online maskThomas Gleixner2011-02-191-6/+6
| | | | | | | | If the affinity had been set by the user, then a later request_irq() will honour that setting. But online cpus can have changed. So apply the online mask and for this case as well. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* genirq: Rremove redundant checkThomas Gleixner2011-02-191-1/+2
| | | | | | | IRQ_NO_BALANCING is already checked in irq_can_set_affinity() above, no need to check it again. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
OpenPOWER on IntegriCloud