linux_dsm_epyc7002/kernel/irq/manage.c

954 lines
23 KiB
C
Raw Normal View History

/*
* linux/kernel/irq/manage.c
*
* Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
* Copyright (C) 2005-2006 Thomas Gleixner
*
* This file contains driver APIs to the irq subsystem.
*/
#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include "internals.h"
/**
* synchronize_irq - wait for pending IRQ handlers (on other CPUs)
* @irq: interrupt number to wait for
*
* This function waits for any pending IRQ handlers for this interrupt
* to complete before returning. If you use this function while
* holding a resource the IRQ handler may need you will deadlock.
*
* This function may be called - with care - from IRQ context.
*/
void synchronize_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned int status;
if (!desc)
return;
do {
unsigned long flags;
/*
* Wait until we're out of the critical section. This might
* give the wrong answer due to the lack of memory barriers.
*/
while (desc->status & IRQ_INPROGRESS)
cpu_relax();
/* Ok, that indicated we're done: double-check carefully. */
spin_lock_irqsave(&desc->lock, flags);
status = desc->status;
spin_unlock_irqrestore(&desc->lock, flags);
/* Oops, that failed? */
} while (status & IRQ_INPROGRESS);
/*
* We made sure that no hardirq handler is running. Now verify
* that no threaded handlers are active.
*/
wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
}
EXPORT_SYMBOL(synchronize_irq);
#ifdef CONFIG_SMP
cpumask_var_t irq_default_affinity;
/**
* irq_can_set_affinity - Check if the affinity of a given irq can be set
* @irq: Interrupt to check
*
*/
int irq_can_set_affinity(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
!desc->chip->set_affinity)
return 0;
return 1;
}
static void
irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
{
struct irqaction *action = desc->action;
while (action) {
if (action->thread)
set_cpus_allowed_ptr(action->thread, cpumask);
action = action->next;
}
}
/**
* irq_set_affinity - Set the irq affinity of a given irq
* @irq: Interrupt to set affinity
* @cpumask: cpumask
*
*/
int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
if (!desc->chip->set_affinity)
return -EINVAL;
spin_lock_irqsave(&desc->lock, flags);
#ifdef CONFIG_GENERIC_PENDING_IRQ
x86, irq: Remove IRQ_DISABLED check in process context IRQ move As discussed in the thread here: http://marc.info/?l=linux-kernel&m=123964468521142&w=2 Eric W. Biederman observed: > It looks like some additional bugs have slipped in since last I looked. > > set_irq_affinity does this: > ifdef CONFIG_GENERIC_PENDING_IRQ > if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { > cpumask_copy(desc->affinity, cpumask); > desc->chip->set_affinity(irq, cpumask); > } else { > desc->status |= IRQ_MOVE_PENDING; > cpumask_copy(desc->pending_mask, cpumask); > } > #else > > That IRQ_DISABLED case is a software state and as such it has nothing to > do with how safe it is to move an irq in process context. [...] > > The only reason we migrate MSIs in interrupt context today is that there > wasn't infrastructure for support migration both in interrupt context > and outside of it. Yes. The idea here was to force the MSI migration to happen in process context. One of the patches in the series did disable_irq(dev->irq); irq_set_affinity(dev->irq, cpumask_of(dev->cpu)); enable_irq(dev->irq); with the above patch adding irq/manage code check for interrupt disabled and moving the interrupt in process context. IIRC, there was no IRQ_MOVE_PCNTXT when we were developing this HPET code and we ended up having this ugly hack. IRQ_MOVE_PCNTXT was there when we eventually submitted the patch upstream. But, looks like I did a blind rebasing instead of using IRQ_MOVE_PCNTXT in hpet MSI code. Below patch fixes this. i.e., revert commit 932775a4ab622e3c99bd59f14cc and add PCNTXT to HPET MSI setup. Also removes copying of desc->affinity in generic code as set_affinity routines are doing it internally. Reported-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Li Shaohua" <shaohua.li@intel.com> Cc: Gary Hade <garyhade@us.ibm.com> Cc: "lcm@us.ibm.com" <lcm@us.ibm.com> Cc: suresh.b.siddha@intel.com LKML-Reference: <20090413222058.GB8211@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-14 05:20:58 +07:00
if (desc->status & IRQ_MOVE_PCNTXT)
desc->chip->set_affinity(irq, cpumask);
x86, irq: Remove IRQ_DISABLED check in process context IRQ move As discussed in the thread here: http://marc.info/?l=linux-kernel&m=123964468521142&w=2 Eric W. Biederman observed: > It looks like some additional bugs have slipped in since last I looked. > > set_irq_affinity does this: > ifdef CONFIG_GENERIC_PENDING_IRQ > if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { > cpumask_copy(desc->affinity, cpumask); > desc->chip->set_affinity(irq, cpumask); > } else { > desc->status |= IRQ_MOVE_PENDING; > cpumask_copy(desc->pending_mask, cpumask); > } > #else > > That IRQ_DISABLED case is a software state and as such it has nothing to > do with how safe it is to move an irq in process context. [...] > > The only reason we migrate MSIs in interrupt context today is that there > wasn't infrastructure for support migration both in interrupt context > and outside of it. Yes. The idea here was to force the MSI migration to happen in process context. One of the patches in the series did disable_irq(dev->irq); irq_set_affinity(dev->irq, cpumask_of(dev->cpu)); enable_irq(dev->irq); with the above patch adding irq/manage code check for interrupt disabled and moving the interrupt in process context. IIRC, there was no IRQ_MOVE_PCNTXT when we were developing this HPET code and we ended up having this ugly hack. IRQ_MOVE_PCNTXT was there when we eventually submitted the patch upstream. But, looks like I did a blind rebasing instead of using IRQ_MOVE_PCNTXT in hpet MSI code. Below patch fixes this. i.e., revert commit 932775a4ab622e3c99bd59f14cc and add PCNTXT to HPET MSI setup. Also removes copying of desc->affinity in generic code as set_affinity routines are doing it internally. Reported-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Cc: "Li Shaohua" <shaohua.li@intel.com> Cc: Gary Hade <garyhade@us.ibm.com> Cc: "lcm@us.ibm.com" <lcm@us.ibm.com> Cc: suresh.b.siddha@intel.com LKML-Reference: <20090413222058.GB8211@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-14 05:20:58 +07:00
else {
desc->status |= IRQ_MOVE_PENDING;
cpumask_copy(desc->pending_mask, cpumask);
}
#else
cpumask_copy(desc->affinity, cpumask);
desc->chip->set_affinity(irq, cpumask);
#endif
irq_set_thread_affinity(desc, cpumask);
desc->status |= IRQ_AFFINITY_SET;
spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
#ifndef CONFIG_AUTO_IRQ_AFFINITY
/*
* Generic version of the affinity autoselector.
*/
static int setup_affinity(unsigned int irq, struct irq_desc *desc)
{
if (!irq_can_set_affinity(irq))
return 0;
/*
* Preserve an userspace affinity setup, but make sure that
* one of the targets is online.
*/
if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
if (cpumask_any_and(desc->affinity, cpu_online_mask)
< nr_cpu_ids)
goto set_affinity;
else
desc->status &= ~IRQ_AFFINITY_SET;
}
cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
set_affinity:
desc->chip->set_affinity(irq, desc->affinity);
return 0;
}
#else
static inline int setup_affinity(unsigned int irq, struct irq_desc *d)
{
return irq_select_affinity(irq);
}
#endif
/*
* Called when affinity is set via /proc/irq
*/
int irq_select_affinity_usr(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
int ret;
spin_lock_irqsave(&desc->lock, flags);
ret = setup_affinity(irq, desc);
if (!ret)
irq_set_thread_affinity(desc, desc->affinity);
spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
#else
static inline int setup_affinity(unsigned int irq, struct irq_desc *desc)
{
return 0;
}
#endif
void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
{
if (suspend) {
if (!desc->action || (desc->action->flags & IRQF_TIMER))
return;
desc->status |= IRQ_SUSPENDED;
}
if (!desc->depth++) {
desc->status |= IRQ_DISABLED;
desc->chip->disable(irq);
}
}
/**
* disable_irq_nosync - disable an irq without waiting
* @irq: Interrupt to disable
*
* Disable the selected interrupt line. Disables and Enables are
* nested.
* Unlike disable_irq(), this function does not ensure existing
* instances of the IRQ handler have completed before returning.
*
* This function may be called from IRQ context.
*/
void disable_irq_nosync(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
if (!desc)
return;
spin_lock_irqsave(&desc->lock, flags);
__disable_irq(desc, irq, false);
spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL(disable_irq_nosync);
/**
* disable_irq - disable an irq and wait for completion
* @irq: Interrupt to disable
*
* Disable the selected interrupt line. Enables and Disables are
* nested.
* This function waits for any pending IRQ handlers for this interrupt
* to complete before returning. If you use this function while
* holding a resource the IRQ handler may need you will deadlock.
*
* This function may be called - with care - from IRQ context.
*/
void disable_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc)
return;
disable_irq_nosync(irq);
if (desc->action)
synchronize_irq(irq);
}
EXPORT_SYMBOL(disable_irq);
void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
{
if (resume)
desc->status &= ~IRQ_SUSPENDED;
switch (desc->depth) {
case 0:
err_out:
WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
break;
case 1: {
unsigned int status = desc->status & ~IRQ_DISABLED;
if (desc->status & IRQ_SUSPENDED)
goto err_out;
/* Prevent probing on this irq: */
desc->status = status | IRQ_NOPROBE;
check_irq_resend(desc, irq);
/* fall-through */
}
default:
desc->depth--;
}
}
/**
* enable_irq - enable handling of an irq
* @irq: Interrupt to enable
*
* Undoes the effect of one call to disable_irq(). If this
* matches the last disable, processing of interrupts on this
* IRQ line is re-enabled.
*
* This function may be called from IRQ context.
*/
void enable_irq(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
if (!desc)
return;
spin_lock_irqsave(&desc->lock, flags);
__enable_irq(desc, irq, false);
spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL(enable_irq);
static int set_irq_wake_real(unsigned int irq, unsigned int on)
{
struct irq_desc *desc = irq_to_desc(irq);
int ret = -ENXIO;
if (desc->chip->set_wake)
ret = desc->chip->set_wake(irq, on);
return ret;
}
/**
* set_irq_wake - control irq power management wakeup
* @irq: interrupt to control
* @on: enable/disable power management wakeup
*
* Enable/disable power management wakeup mode, which is
* disabled by default. Enables and disables must match,
* just as they match for non-wakeup mode support.
*
* Wakeup mode lets this IRQ wake the system from sleep
* states like "suspend to RAM".
*/
int set_irq_wake(unsigned int irq, unsigned int on)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
int ret = 0;
/* wakeup-capable irqs can be shared between drivers that
* don't need to have the same sleep mode behaviors.
*/
spin_lock_irqsave(&desc->lock, flags);
if (on) {
if (desc->wake_depth++ == 0) {
ret = set_irq_wake_real(irq, on);
if (ret)
desc->wake_depth = 0;
else
desc->status |= IRQ_WAKEUP;
}
} else {
if (desc->wake_depth == 0) {
WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
} else if (--desc->wake_depth == 0) {
ret = set_irq_wake_real(irq, on);
if (ret)
desc->wake_depth = 1;
else
desc->status &= ~IRQ_WAKEUP;
}
}
spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
EXPORT_SYMBOL(set_irq_wake);
/*
* Internal function that tells the architecture code whether a
* particular irq has been exclusively allocated or is available
* for driver use.
*/
int can_request_irq(unsigned int irq, unsigned long irqflags)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
if (!desc)
return 0;
if (desc->status & IRQ_NOREQUEST)
return 0;
action = desc->action;
if (action)
if (irqflags & action->flags & IRQF_SHARED)
action = NULL;
return !action;
}
void compat_irq_chip_set_default_handler(struct irq_desc *desc)
{
/*
* If the architecture still has not overriden
* the flow handler then zap the default. This
* should catch incorrect flow-type setting.
*/
if (desc->handle_irq == &handle_bad_irq)
desc->handle_irq = NULL;
}
int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
unsigned long flags)
{
int ret;
struct irq_chip *chip = desc->chip;
if (!chip || !chip->set_type) {
/*
* IRQF_TRIGGER_* but the PIC does not support multiple
* flow-types?
*/
pr_debug("No set_type function for IRQ %d (%s)\n", irq,
chip ? (chip->name ? : "unknown") : "unknown");
return 0;
}
/* caller masked out all except trigger mode flags */
ret = chip->set_type(irq, flags);
if (ret)
pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
(int)flags, irq, chip->set_type);
else {
if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
flags |= IRQ_LEVEL;
/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
desc->status |= flags;
}
return ret;
}
static int irq_wait_for_interrupt(struct irqaction *action)
{
while (!kthread_should_stop()) {
set_current_state(TASK_INTERRUPTIBLE);
if (test_and_clear_bit(IRQTF_RUNTHREAD,
&action->thread_flags)) {
__set_current_state(TASK_RUNNING);
return 0;
}
schedule();
}
return -1;
}
/*
* Interrupt handler thread
*/
static int irq_thread(void *data)
{
struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
struct irqaction *action = data;
struct irq_desc *desc = irq_to_desc(action->irq);
int wake;
sched_setscheduler(current, SCHED_FIFO, &param);
current->irqaction = action;
while (!irq_wait_for_interrupt(action)) {
atomic_inc(&desc->threads_active);
spin_lock_irq(&desc->lock);
if (unlikely(desc->status & IRQ_DISABLED)) {
/*
* CHECKME: We might need a dedicated
* IRQ_THREAD_PENDING flag here, which
* retriggers the thread in check_irq_resend()
* but AFAICT IRQ_PENDING should be fine as it
* retriggers the interrupt itself --- tglx
*/
desc->status |= IRQ_PENDING;
spin_unlock_irq(&desc->lock);
} else {
spin_unlock_irq(&desc->lock);
action->thread_fn(action->irq, action->dev_id);
}
wake = atomic_dec_and_test(&desc->threads_active);
if (wake && waitqueue_active(&desc->wait_for_threads))
wake_up(&desc->wait_for_threads);
}
/*
* Clear irqaction. Otherwise exit_irq_thread() would make
* fuzz about an active irq thread going into nirvana.
*/
current->irqaction = NULL;
return 0;
}
/*
* Called from do_exit()
*/
void exit_irq_thread(void)
{
struct task_struct *tsk = current;
if (!tsk->irqaction)
return;
printk(KERN_ERR
"exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
/*
* Set the THREAD DIED flag to prevent further wakeups of the
* soon to be gone threaded handler.
*/
set_bit(IRQTF_DIED, &tsk->irqaction->flags);
}
/*
* Internal function to register an irqaction - typically used to
* allocate special interrupts that are part of the architecture.
*/
static int
__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
{
struct irqaction *old, **old_ptr;
const char *old_name = NULL;
unsigned long flags;
int shared = 0;
int ret;
if (!desc)
return -EINVAL;
if (desc->chip == &no_irq_chip)
return -ENOSYS;
/*
* Some drivers like serial.c use request_irq() heavily,
* so we have to be careful not to interfere with a
* running system.
*/
if (new->flags & IRQF_SAMPLE_RANDOM) {
/*
* This function might sleep, we want to call it first,
* outside of the atomic block.
* Yes, this might clear the entropy pool if the wrong
* driver is attempted to be loaded, without actually
* installing a new handler, but is this really a problem,
* only the sysadmin is able to do this.
*/
rand_initialize_irq(irq);
}
/*
* Threaded handler ?
*/
if (new->thread_fn) {
struct task_struct *t;
t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
new->name);
if (IS_ERR(t))
return PTR_ERR(t);
/*
* We keep the reference to the task struct even if
* the thread dies to avoid that the interrupt code
* references an already freed task_struct.
*/
get_task_struct(t);
new->thread = t;
wake_up_process(t);
}
/*
* The following block of code has to be executed atomically
*/
spin_lock_irqsave(&desc->lock, flags);
old_ptr = &desc->action;
old = *old_ptr;
if (old) {
/*
* Can't share interrupts unless both agree to and are
* the same type (level, edge, polarity). So both flag
* fields must have IRQF_SHARED set and the bits which
* set the trigger type must match.
*/
if (!((old->flags & new->flags) & IRQF_SHARED) ||
((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) {
old_name = old->name;
goto mismatch;
}
#if defined(CONFIG_IRQ_PER_CPU)
/* All handlers must agree on per-cpuness */
if ((old->flags & IRQF_PERCPU) !=
(new->flags & IRQF_PERCPU))
goto mismatch;
#endif
/* add new interrupt at end of irq queue */
do {
old_ptr = &old->next;
old = *old_ptr;
} while (old);
shared = 1;
}
if (!shared) {
irq_chip_set_defaults(desc->chip);
init_waitqueue_head(&desc->wait_for_threads);
/* Setup the type (level, edge polarity) if configured: */
if (new->flags & IRQF_TRIGGER_MASK) {
ret = __irq_set_trigger(desc, irq,
new->flags & IRQF_TRIGGER_MASK);
if (ret)
goto out_thread;
} else
compat_irq_chip_set_default_handler(desc);
#if defined(CONFIG_IRQ_PER_CPU)
if (new->flags & IRQF_PERCPU)
desc->status |= IRQ_PER_CPU;
#endif
desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING |
IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED);
if (!(desc->status & IRQ_NOAUTOEN)) {
desc->depth = 0;
desc->status &= ~IRQ_DISABLED;
desc->chip->startup(irq);
} else
/* Undo nested disables: */
desc->depth = 1;
/* Exclude IRQ from balancing if requested */
if (new->flags & IRQF_NOBALANCING)
desc->status |= IRQ_NO_BALANCING;
/* Set default affinity mask once everything is setup */
setup_affinity(irq, desc);
} else if ((new->flags & IRQF_TRIGGER_MASK)
&& (new->flags & IRQF_TRIGGER_MASK)
!= (desc->status & IRQ_TYPE_SENSE_MASK)) {
/* hope the handler works with the actual trigger mode... */
pr_warning("IRQ %d uses trigger mode %d; requested %d\n",
irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK),
(int)(new->flags & IRQF_TRIGGER_MASK));
}
*old_ptr = new;
/* Reset broken irq detection when installing new handler */
desc->irq_count = 0;
desc->irqs_unhandled = 0;
/*
* Check whether we disabled the irq via the spurious handler
* before. Reenable it and give it another chance.
*/
if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) {
desc->status &= ~IRQ_SPURIOUS_DISABLED;
__enable_irq(desc, irq, false);
}
spin_unlock_irqrestore(&desc->lock, flags);
new->irq = irq;
register_irq_proc(irq, desc);
new->dir = NULL;
register_handler_proc(irq, new);
return 0;
mismatch:
#ifdef CONFIG_DEBUG_SHIRQ
if (!(new->flags & IRQF_PROBE_SHARED)) {
printk(KERN_ERR "IRQ handler type mismatch for IRQ %d\n", irq);
if (old_name)
printk(KERN_ERR "current handler: %s\n", old_name);
dump_stack();
}
#endif
ret = -EBUSY;
out_thread:
spin_unlock_irqrestore(&desc->lock, flags);
if (new->thread) {
struct task_struct *t = new->thread;
new->thread = NULL;
if (likely(!test_bit(IRQTF_DIED, &new->thread_flags)))
kthread_stop(t);
put_task_struct(t);
}
return ret;
}
/**
* setup_irq - setup an interrupt
* @irq: Interrupt line to setup
* @act: irqaction for the interrupt
*
* Used to statically setup interrupts in the early boot process.
*/
int setup_irq(unsigned int irq, struct irqaction *act)
{
struct irq_desc *desc = irq_to_desc(irq);
return __setup_irq(irq, desc, act);
}
EXPORT_SYMBOL_GPL(setup_irq);
/*
* Internal function to unregister an irqaction - used to free
* regular and special interrupts that are part of the architecture.
*/
static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action, **action_ptr;
struct task_struct *irqthread;
unsigned long flags;
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
if (!desc)
return NULL;
spin_lock_irqsave(&desc->lock, flags);
/*
* There can be multiple actions per IRQ descriptor, find the right
* one based on the dev_id:
*/
action_ptr = &desc->action;
for (;;) {
action = *action_ptr;
if (!action) {
WARN(1, "Trying to free already-free IRQ %d\n", irq);
spin_unlock_irqrestore(&desc->lock, flags);
return NULL;
}
if (action->dev_id == dev_id)
break;
action_ptr = &action->next;
}
[PATCH] uml: add and use generic hw_controller_type->release With Chris Wedgwood <cw@f00f.org> Currently UML must explicitly call the UML-specific free_irq_by_irq_and_dev() for each free_irq call it's done. This is needed because ->shutdown and/or ->disable are only called when the last "action" for that irq is removed. Instead, for UML shared IRQs (UML IRQs are very often, if not always, shared), for each dev_id some setup is done, which must be cleared on the release of that fd. For instance, for each open console a new instance (i.e. new dev_id) of the same IRQ is requested(). Exactly, a fd is stored in an array (pollfds), which is after read by a host thread and passed to poll(). Each event registered by poll() triggers an interrupt. So, for each free_irq() we must remove the corresponding host fd from the table, which we do via this -release() method. In this patch we add an appropriate hook for this, and remove all uses of it by pointing the hook to the said procedure; this is safe to do since the said procedure. Also some cosmetic improvements are included. This is heavily based on some work by Chris Wedgwood, which however didn't get the patch merged for something I'd call a "misunderstanding" (the need for this patch wasn't cleanly explained, thus adding the generic hook was felt as undesirable). Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> CC: Ingo Molnar <mingo@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 07:16:19 +07:00
/* Found it - now remove it from the list of entries: */
*action_ptr = action->next;
/* Currently used only by UML, might disappear one day: */
#ifdef CONFIG_IRQ_RELEASE_METHOD
if (desc->chip->release)
desc->chip->release(irq, dev_id);
#endif
[PATCH] uml: add and use generic hw_controller_type->release With Chris Wedgwood <cw@f00f.org> Currently UML must explicitly call the UML-specific free_irq_by_irq_and_dev() for each free_irq call it's done. This is needed because ->shutdown and/or ->disable are only called when the last "action" for that irq is removed. Instead, for UML shared IRQs (UML IRQs are very often, if not always, shared), for each dev_id some setup is done, which must be cleared on the release of that fd. For instance, for each open console a new instance (i.e. new dev_id) of the same IRQ is requested(). Exactly, a fd is stored in an array (pollfds), which is after read by a host thread and passed to poll(). Each event registered by poll() triggers an interrupt. So, for each free_irq() we must remove the corresponding host fd from the table, which we do via this -release() method. In this patch we add an appropriate hook for this, and remove all uses of it by pointing the hook to the said procedure; this is safe to do since the said procedure. Also some cosmetic improvements are included. This is heavily based on some work by Chris Wedgwood, which however didn't get the patch merged for something I'd call a "misunderstanding" (the need for this patch wasn't cleanly explained, thus adding the generic hook was felt as undesirable). Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> CC: Ingo Molnar <mingo@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 07:16:19 +07:00
/* If this was the last handler, shut down the IRQ line: */
if (!desc->action) {
desc->status |= IRQ_DISABLED;
if (desc->chip->shutdown)
desc->chip->shutdown(irq);
else
desc->chip->disable(irq);
}
irqthread = action->thread;
action->thread = NULL;
spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
/* Make sure it's not being used on another CPU: */
synchronize_irq(irq);
if (irqthread) {
if (!test_bit(IRQTF_DIED, &action->thread_flags))
kthread_stop(irqthread);
put_task_struct(irqthread);
}
#ifdef CONFIG_DEBUG_SHIRQ
/*
* It's a shared IRQ -- the driver ought to be prepared for an IRQ
* event to happen even now it's being freed, so let's make sure that
* is so by doing an extra call to the handler ....
*
* ( We do this after actually deregistering it, to make sure that a
* 'real' IRQ doesn't run in * parallel with our fake. )
*/
if (action->flags & IRQF_SHARED) {
local_irq_save(flags);
action->handler(irq, dev_id);
local_irq_restore(flags);
}
#endif
return action;
}
/**
* remove_irq - free an interrupt
* @irq: Interrupt line to free
* @act: irqaction for the interrupt
*
* Used to remove interrupts statically setup by the early boot process.
*/
void remove_irq(unsigned int irq, struct irqaction *act)
{
__free_irq(irq, act->dev_id);
}
EXPORT_SYMBOL_GPL(remove_irq);
/**
* free_irq - free an interrupt allocated with request_irq
* @irq: Interrupt line to free
* @dev_id: Device identity to free
*
* Remove an interrupt handler. The handler is removed and if the
* interrupt line is no longer in use by any driver it is disabled.
* On a shared IRQ the caller must ensure the interrupt is disabled
* on the card it drives before calling this function. The function
* does not return until any executing interrupts for this IRQ
* have completed.
*
* This function must not be called from interrupt context.
*/
void free_irq(unsigned int irq, void *dev_id)
{
kfree(__free_irq(irq, dev_id));
}
EXPORT_SYMBOL(free_irq);
/**
* request_threaded_irq - allocate an interrupt line
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* Primary handler for threaded interrupts
* @thread_fn: Function called from the irq handler thread
* If NULL, no irq thread is created
* @irqflags: Interrupt type flags
* @devname: An ascii name for the claiming device
* @dev_id: A cookie passed back to the handler function
*
* This call allocates interrupt resources and enables the
* interrupt line and IRQ handling. From the point this
* call is made your handler function may be invoked. Since
* your handler function must clear any interrupt the board
* raises, you must take care both to initialise your hardware
* and to set up the interrupt handler in the right order.
*
* If you want to set up a threaded irq handler for your device
* then you need to supply @handler and @thread_fn. @handler ist
* still called in hard interrupt context and has to check
* whether the interrupt originates from the device. If yes it
* needs to disable the interrupt on the device and return
* IRQ_THREAD_WAKE which will wake up the handler thread and run
* @thread_fn. This split handler design is necessary to support
* shared interrupts.
*
* Dev_id must be globally unique. Normally the address of the
* device data structure is used as the cookie. Since the handler
* receives this value it makes sense to use it.
*
* If your interrupt is shared you must pass a non NULL dev_id
* as this is required when freeing the interrupt.
*
* Flags:
*
* IRQF_SHARED Interrupt is shared
* IRQF_DISABLED Disable local interrupts while processing
* IRQF_SAMPLE_RANDOM The interrupt can be used for entropy
* IRQF_TRIGGER_* Specify active edge(s) or level
*
*/
int request_threaded_irq(unsigned int irq, irq_handler_t handler,
irq_handler_t thread_fn, unsigned long irqflags,
const char *devname, void *dev_id)
{
struct irqaction *action;
struct irq_desc *desc;
int retval;
/*
* handle_IRQ_event() always ignores IRQF_DISABLED except for
* the _first_ irqaction (sigh). That can cause oopsing, but
* the behavior is classified as "will not fix" so we need to
* start nudging drivers away from using that idiom.
*/
if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) ==
(IRQF_SHARED|IRQF_DISABLED)) {
pr_warning(
"IRQ %d/%s: IRQF_DISABLED is not guaranteed on shared IRQs\n",
irq, devname);
}
[PATCH] lockdep: core Do 'make oldconfig' and accept all the defaults for new config options - reboot into the kernel and if everything goes well it should boot up fine and you should have /proc/lockdep and /proc/lockdep_stats files. Typically if the lock validator finds some problem it will print out voluminous debug output that begins with "BUG: ..." and which syslog output can be used by kernel developers to figure out the precise locking scenario. What does the lock validator do? It "observes" and maps all locking rules as they occur dynamically (as triggered by the kernel's natural use of spinlocks, rwlocks, mutexes and rwsems). Whenever the lock validator subsystem detects a new locking scenario, it validates this new rule against the existing set of rules. If this new rule is consistent with the existing set of rules then the new rule is added transparently and the kernel continues as normal. If the new rule could create a deadlock scenario then this condition is printed out. When determining validity of locking, all possible "deadlock scenarios" are considered: assuming arbitrary number of CPUs, arbitrary irq context and task context constellations, running arbitrary combinations of all the existing locking scenarios. In a typical system this means millions of separate scenarios. This is why we call it a "locking correctness" validator - for all rules that are observed the lock validator proves it with mathematical certainty that a deadlock could not occur (assuming that the lock validator implementation itself is correct and its internal data structures are not corrupted by some other kernel subsystem). [see more details and conditionals of this statement in include/linux/lockdep.h and Documentation/lockdep-design.txt] Furthermore, this "all possible scenarios" property of the validator also enables the finding of complex, highly unlikely multi-CPU multi-context races via single single-context rules, increasing the likelyhood of finding bugs drastically. In practical terms: the lock validator already found a bug in the upstream kernel that could only occur on systems with 3 or more CPUs, and which needed 3 very unlikely code sequences to occur at once on the 3 CPUs. That bug was found and reported on a single-CPU system (!). So in essence a race will be found "piecemail-wise", triggering all the necessary components for the race, without having to reproduce the race scenario itself! In its short existence the lock validator found and reported many bugs before they actually caused a real deadlock. To further increase the efficiency of the validator, the mapping is not per "lock instance", but per "lock-class". For example, all struct inode objects in the kernel have inode->inotify_mutex. If there are 10,000 inodes cached, then there are 10,000 lock objects. But ->inotify_mutex is a single "lock type", and all locking activities that occur against ->inotify_mutex are "unified" into this single lock-class. The advantage of the lock-class approach is that all historical ->inotify_mutex uses are mapped into a single (and as narrow as possible) set of locking rules - regardless of how many different tasks or inode structures it took to build this set of rules. The set of rules persist during the lifetime of the kernel. To see the rough magnitude of checking that the lock validator does, here's a portion of /proc/lockdep_stats, fresh after bootup: lock-classes: 694 [max: 2048] direct dependencies: 1598 [max: 8192] indirect dependencies: 17896 all direct dependencies: 16206 dependency chains: 1910 [max: 8192] in-hardirq chains: 17 in-softirq chains: 105 in-process chains: 1065 stack-trace entries: 38761 [max: 131072] combined max dependencies: 2033928 hardirq-safe locks: 24 hardirq-unsafe locks: 176 softirq-safe locks: 53 softirq-unsafe locks: 137 irq-safe locks: 59 irq-unsafe locks: 176 The lock validator has observed 1598 actual single-thread locking patterns, and has validated all possible 2033928 distinct locking scenarios. More details about the design of the lock validator can be found in Documentation/lockdep-design.txt, which can also found at: http://redhat.com/~mingo/lockdep-patches/lockdep-design.txt [bunk@stusta.de: cleanups] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-03 14:24:50 +07:00
#ifdef CONFIG_LOCKDEP
/*
* Lockdep wants atomic interrupt handlers:
*/
irqflags |= IRQF_DISABLED;
[PATCH] lockdep: core Do 'make oldconfig' and accept all the defaults for new config options - reboot into the kernel and if everything goes well it should boot up fine and you should have /proc/lockdep and /proc/lockdep_stats files. Typically if the lock validator finds some problem it will print out voluminous debug output that begins with "BUG: ..." and which syslog output can be used by kernel developers to figure out the precise locking scenario. What does the lock validator do? It "observes" and maps all locking rules as they occur dynamically (as triggered by the kernel's natural use of spinlocks, rwlocks, mutexes and rwsems). Whenever the lock validator subsystem detects a new locking scenario, it validates this new rule against the existing set of rules. If this new rule is consistent with the existing set of rules then the new rule is added transparently and the kernel continues as normal. If the new rule could create a deadlock scenario then this condition is printed out. When determining validity of locking, all possible "deadlock scenarios" are considered: assuming arbitrary number of CPUs, arbitrary irq context and task context constellations, running arbitrary combinations of all the existing locking scenarios. In a typical system this means millions of separate scenarios. This is why we call it a "locking correctness" validator - for all rules that are observed the lock validator proves it with mathematical certainty that a deadlock could not occur (assuming that the lock validator implementation itself is correct and its internal data structures are not corrupted by some other kernel subsystem). [see more details and conditionals of this statement in include/linux/lockdep.h and Documentation/lockdep-design.txt] Furthermore, this "all possible scenarios" property of the validator also enables the finding of complex, highly unlikely multi-CPU multi-context races via single single-context rules, increasing the likelyhood of finding bugs drastically. In practical terms: the lock validator already found a bug in the upstream kernel that could only occur on systems with 3 or more CPUs, and which needed 3 very unlikely code sequences to occur at once on the 3 CPUs. That bug was found and reported on a single-CPU system (!). So in essence a race will be found "piecemail-wise", triggering all the necessary components for the race, without having to reproduce the race scenario itself! In its short existence the lock validator found and reported many bugs before they actually caused a real deadlock. To further increase the efficiency of the validator, the mapping is not per "lock instance", but per "lock-class". For example, all struct inode objects in the kernel have inode->inotify_mutex. If there are 10,000 inodes cached, then there are 10,000 lock objects. But ->inotify_mutex is a single "lock type", and all locking activities that occur against ->inotify_mutex are "unified" into this single lock-class. The advantage of the lock-class approach is that all historical ->inotify_mutex uses are mapped into a single (and as narrow as possible) set of locking rules - regardless of how many different tasks or inode structures it took to build this set of rules. The set of rules persist during the lifetime of the kernel. To see the rough magnitude of checking that the lock validator does, here's a portion of /proc/lockdep_stats, fresh after bootup: lock-classes: 694 [max: 2048] direct dependencies: 1598 [max: 8192] indirect dependencies: 17896 all direct dependencies: 16206 dependency chains: 1910 [max: 8192] in-hardirq chains: 17 in-softirq chains: 105 in-process chains: 1065 stack-trace entries: 38761 [max: 131072] combined max dependencies: 2033928 hardirq-safe locks: 24 hardirq-unsafe locks: 176 softirq-safe locks: 53 softirq-unsafe locks: 137 irq-safe locks: 59 irq-unsafe locks: 176 The lock validator has observed 1598 actual single-thread locking patterns, and has validated all possible 2033928 distinct locking scenarios. More details about the design of the lock validator can be found in Documentation/lockdep-design.txt, which can also found at: http://redhat.com/~mingo/lockdep-patches/lockdep-design.txt [bunk@stusta.de: cleanups] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-03 14:24:50 +07:00
#endif
/*
* Sanity-check: shared interrupts must pass in a real dev-ID,
* otherwise we'll have trouble later trying to figure out
* which interrupt is which (messes up the interrupt freeing
* logic etc).
*/
if ((irqflags & IRQF_SHARED) && !dev_id)
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc)
return -EINVAL;
if (desc->status & IRQ_NOREQUEST)
return -EINVAL;
if (!handler)
return -EINVAL;
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!action)
return -ENOMEM;
action->handler = handler;
action->thread_fn = thread_fn;
action->flags = irqflags;
action->name = devname;
action->dev_id = dev_id;
retval = __setup_irq(irq, desc, action);
genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 <ME,IR,DR> CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-22 01:58:28 +07:00
if (retval)
kfree(action);
#ifdef CONFIG_DEBUG_SHIRQ
if (irqflags & IRQF_SHARED) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
* to happen immediately, so let's make sure....
genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 <ME,IR,DR> CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-22 01:58:28 +07:00
* We disable the irq to make sure that a 'real' IRQ doesn't
* run in parallel with our fake.
*/
request_irq: fix DEBUG_SHIRQ handling Mariusz Kozlowski reported lockdep's warning: > ================================= > [ INFO: inconsistent lock state ] > 2.6.23-rc2-mm1 #7 > --------------------------------- > inconsistent {in-hardirq-W} -> {hardirq-on-W} usage. > ifconfig/5492 [HC0[0]:SC0[0]:HE1:SE1] takes: > (&tp->lock){+...}, at: [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > {in-hardirq-W} state was registered at: > [<c0138eeb>] __lock_acquire+0x949/0x11ac > [<c01397e7>] lock_acquire+0x99/0xb2 > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c0147a5d>] handle_IRQ_event+0x28/0x59 > [<c01493ca>] handle_level_irq+0xad/0x10b > [<c0105a13>] do_IRQ+0x93/0xd0 > [<c010441e>] common_interrupt+0x2e/0x34 ... > other info that might help us debug this: > 1 lock held by ifconfig/5492: > #0: (rtnl_mutex){--..}, at: [<c0451778>] mutex_lock+0x1c/0x1f > > stack backtrace: ... > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c01480fd>] free_irq+0x11b/0x146 > [<de871d59>] rtl8139_close+0x8a/0x14a [8139too] > [<c03bde63>] dev_close+0x57/0x74 ... This shows that a driver's irq handler was running both in hard interrupt and process contexts with irqs enabled. The latter was done during free_irq() call and was possible only with CONFIG_DEBUG_SHIRQ enabled. This was fixed by another patch. But similar problem is possible with request_irq(): any locks taken from irq handler could be vulnerable - especially with soft interrupts. This patch fixes it by disabling local interrupts during handler's run. (It seems, disabling softirqs should be enough, but it needs more checking on possible races or other special cases). Reported-by: Mariusz Kozlowski <m.kozlowski@tuxland.pl> Signed-off-by: Jarek Poplawski <jarkao2@o2.pl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-08-31 13:56:34 +07:00
unsigned long flags;
genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 <ME,IR,DR> CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-22 01:58:28 +07:00
disable_irq(irq);
request_irq: fix DEBUG_SHIRQ handling Mariusz Kozlowski reported lockdep's warning: > ================================= > [ INFO: inconsistent lock state ] > 2.6.23-rc2-mm1 #7 > --------------------------------- > inconsistent {in-hardirq-W} -> {hardirq-on-W} usage. > ifconfig/5492 [HC0[0]:SC0[0]:HE1:SE1] takes: > (&tp->lock){+...}, at: [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > {in-hardirq-W} state was registered at: > [<c0138eeb>] __lock_acquire+0x949/0x11ac > [<c01397e7>] lock_acquire+0x99/0xb2 > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c0147a5d>] handle_IRQ_event+0x28/0x59 > [<c01493ca>] handle_level_irq+0xad/0x10b > [<c0105a13>] do_IRQ+0x93/0xd0 > [<c010441e>] common_interrupt+0x2e/0x34 ... > other info that might help us debug this: > 1 lock held by ifconfig/5492: > #0: (rtnl_mutex){--..}, at: [<c0451778>] mutex_lock+0x1c/0x1f > > stack backtrace: ... > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c01480fd>] free_irq+0x11b/0x146 > [<de871d59>] rtl8139_close+0x8a/0x14a [8139too] > [<c03bde63>] dev_close+0x57/0x74 ... This shows that a driver's irq handler was running both in hard interrupt and process contexts with irqs enabled. The latter was done during free_irq() call and was possible only with CONFIG_DEBUG_SHIRQ enabled. This was fixed by another patch. But similar problem is possible with request_irq(): any locks taken from irq handler could be vulnerable - especially with soft interrupts. This patch fixes it by disabling local interrupts during handler's run. (It seems, disabling softirqs should be enough, but it needs more checking on possible races or other special cases). Reported-by: Mariusz Kozlowski <m.kozlowski@tuxland.pl> Signed-off-by: Jarek Poplawski <jarkao2@o2.pl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-08-31 13:56:34 +07:00
local_irq_save(flags);
genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 <ME,IR,DR> CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-22 01:58:28 +07:00
request_irq: fix DEBUG_SHIRQ handling Mariusz Kozlowski reported lockdep's warning: > ================================= > [ INFO: inconsistent lock state ] > 2.6.23-rc2-mm1 #7 > --------------------------------- > inconsistent {in-hardirq-W} -> {hardirq-on-W} usage. > ifconfig/5492 [HC0[0]:SC0[0]:HE1:SE1] takes: > (&tp->lock){+...}, at: [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > {in-hardirq-W} state was registered at: > [<c0138eeb>] __lock_acquire+0x949/0x11ac > [<c01397e7>] lock_acquire+0x99/0xb2 > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c0147a5d>] handle_IRQ_event+0x28/0x59 > [<c01493ca>] handle_level_irq+0xad/0x10b > [<c0105a13>] do_IRQ+0x93/0xd0 > [<c010441e>] common_interrupt+0x2e/0x34 ... > other info that might help us debug this: > 1 lock held by ifconfig/5492: > #0: (rtnl_mutex){--..}, at: [<c0451778>] mutex_lock+0x1c/0x1f > > stack backtrace: ... > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c01480fd>] free_irq+0x11b/0x146 > [<de871d59>] rtl8139_close+0x8a/0x14a [8139too] > [<c03bde63>] dev_close+0x57/0x74 ... This shows that a driver's irq handler was running both in hard interrupt and process contexts with irqs enabled. The latter was done during free_irq() call and was possible only with CONFIG_DEBUG_SHIRQ enabled. This was fixed by another patch. But similar problem is possible with request_irq(): any locks taken from irq handler could be vulnerable - especially with soft interrupts. This patch fixes it by disabling local interrupts during handler's run. (It seems, disabling softirqs should be enough, but it needs more checking on possible races or other special cases). Reported-by: Mariusz Kozlowski <m.kozlowski@tuxland.pl> Signed-off-by: Jarek Poplawski <jarkao2@o2.pl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-08-31 13:56:34 +07:00
handler(irq, dev_id);
genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 <ME,IR,DR> CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-22 01:58:28 +07:00
request_irq: fix DEBUG_SHIRQ handling Mariusz Kozlowski reported lockdep's warning: > ================================= > [ INFO: inconsistent lock state ] > 2.6.23-rc2-mm1 #7 > --------------------------------- > inconsistent {in-hardirq-W} -> {hardirq-on-W} usage. > ifconfig/5492 [HC0[0]:SC0[0]:HE1:SE1] takes: > (&tp->lock){+...}, at: [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > {in-hardirq-W} state was registered at: > [<c0138eeb>] __lock_acquire+0x949/0x11ac > [<c01397e7>] lock_acquire+0x99/0xb2 > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c0147a5d>] handle_IRQ_event+0x28/0x59 > [<c01493ca>] handle_level_irq+0xad/0x10b > [<c0105a13>] do_IRQ+0x93/0xd0 > [<c010441e>] common_interrupt+0x2e/0x34 ... > other info that might help us debug this: > 1 lock held by ifconfig/5492: > #0: (rtnl_mutex){--..}, at: [<c0451778>] mutex_lock+0x1c/0x1f > > stack backtrace: ... > [<c0452ff3>] _spin_lock+0x35/0x42 > [<de8706e0>] rtl8139_interrupt+0x27/0x46b [8139too] > [<c01480fd>] free_irq+0x11b/0x146 > [<de871d59>] rtl8139_close+0x8a/0x14a [8139too] > [<c03bde63>] dev_close+0x57/0x74 ... This shows that a driver's irq handler was running both in hard interrupt and process contexts with irqs enabled. The latter was done during free_irq() call and was possible only with CONFIG_DEBUG_SHIRQ enabled. This was fixed by another patch. But similar problem is possible with request_irq(): any locks taken from irq handler could be vulnerable - especially with soft interrupts. This patch fixes it by disabling local interrupts during handler's run. (It seems, disabling softirqs should be enough, but it needs more checking on possible races or other special cases). Reported-by: Mariusz Kozlowski <m.kozlowski@tuxland.pl> Signed-off-by: Jarek Poplawski <jarkao2@o2.pl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-08-31 13:56:34 +07:00
local_irq_restore(flags);
genirq: fix irq_desc->depth handling with DEBUG_SHIRQ When DEBUG_SHIRQ is selected, a spurious IRQ is issued before the setup_irq() initializes the desc->depth. An IRQ handler may call disable_irq_nosync(), but then setup_irq() will overwrite desc->depth, and upon enable_irq() we'll catch this WARN: ------------[ cut here ]------------ Badness at kernel/irq/manage.c:180 NIP: c0061ab8 LR: c0061f10 CTR: 00000000 REGS: cf83be50 TRAP: 0700 Not tainted (2.6.27-rc3-23450-g74919b0) MSR: 00021032 <ME,IR,DR> CR: 22042022 XER: 20000000 TASK = cf829100[5] 'events/0' THREAD: cf83a000 GPR00: c0061f10 cf83bf00 cf829100 c038e674 00000016 00000000 cf83bef8 00000038 GPR08: c0298910 00000000 c0310d28 cf83a000 00000c9c 1001a1a8 0fffe000 00800000 GPR16: ffffffff 00000000 007fff00 00000000 007ffeb0 c03320a0 c031095c c0310924 GPR24: cf8292ec cf807190 cf83a000 00009032 c038e6a4 c038e674 cf99b1cc c038e674 NIP [c0061ab8] __enable_irq+0x20/0x80 LR [c0061f10] enable_irq+0x50/0x70 Call Trace: [cf83bf00] [c038e674] irq_desc+0x630/0x9000 (unreliable) [cf83bf10] [c0061f10] enable_irq+0x50/0x70 [cf83bf30] [c01abe94] phy_change+0x68/0x108 [cf83bf50] [c0046394] run_workqueue+0xc4/0x16c [cf83bf90] [c0046834] worker_thread+0x74/0xd4 [cf83bfd0] [c004ab7c] kthread+0x48/0x84 [cf83bff0] [c00135e0] kernel_thread+0x44/0x60 Instruction dump: 4e800020 3d20c031 38a94214 4bffffcc 9421fff0 7c0802a6 93e1000c 7c7f1b78 90010014 8123001c 2f890000 409e001c <0fe00000> 80010014 83e1000c 38210010 That trace corresponds to this line: WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); The patch fixes the problem by moving the SHIRQ code below the setup_irq(). Unfortunately we can't easily move the SHIRQ code inside the setup_irq(), since it grabs a spinlock, so to prvent a 'real' IRQ from interfere us we should disable that IRQ. p.s. The driver in question is drivers/net/phy/phy.c. Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-22 01:58:28 +07:00
enable_irq(irq);
}
#endif
return retval;
}
EXPORT_SYMBOL(request_threaded_irq);