/*
* Interrupts which are not explicitely requested as threaded
* interrupts rely on the implicit bh/preempt disable of the hard irq
* context. So we need to disable bh here to avoid deadlocks and other
* side effects.
*/
static irqreturn_t
irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
{
irqreturn_t ret;
local_bh_disable();
ret = action->thread_fn(action->irq, action->dev_id);
irq_finalize_oneshot(desc, action);
local_bh_enable();
return ret;
}
/*
* Interrupts explicitly requested as threaded interrupts want to be
* preemtible - many of them need to sleep and wait for slow busses to
* complete.
*/
static irqreturn_t irq_thread_fn(struct irq_desc *desc,
struct irqaction *action)
{
irqreturn_t ret;
ret = action->thread_fn(action->irq, action->dev_id);
irq_finalize_oneshot(desc, action);
return ret;
}
static void wake_threads_waitq(struct irq_desc *desc)
{
if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
static void irq_thread_dtor(struct callback_head *unused)
{
struct task_struct *tsk = current;
struct irq_desc *desc;
struct irqaction *action;
if (WARN_ON_ONCE(!(current->flags & PF_EXITING)))
return;
action = kthread_data(tsk);
pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
tsk->comm, tsk->pid, action->irq);
desc = irq_to_desc(action->irq);
/*
* If IRQTF_RUNTHREAD is set, we need to decrement
* desc->threads_active and wake possible waiters.
*/
if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
wake_threads_waitq(desc);
/* Prevent a stale desc->threads_oneshot */
irq_finalize_oneshot(desc, action);
}
/*
* Interrupt handler thread
*/
static int irq_thread(void *data)
{
struct callback_head on_exit_work;
struct irqaction *action = data;
struct irq_desc *desc = irq_to_desc(action->irq);
irqreturn_t (*handler_fn)(struct irq_desc *desc,
struct irqaction *action);
if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD,
&action->thread_flags))
handler_fn = irq_forced_thread_fn;
else
handler_fn = irq_thread_fn;
init_task_work(&on_exit_work, irq_thread_dtor);
task_work_add(current, &on_exit_work, false);
irq_thread_check_affinity(desc, action);
while (!irq_wait_for_interrupt(action)) {
irqreturn_t action_ret;
irq_thread_check_affinity(desc, action);
action_ret = handler_fn(desc, action);
if (action_ret == IRQ_HANDLED)
atomic_inc(&desc->threads_handled);
wake_threads_waitq(desc);
}
/*
* This is the regular exit path. __free_irq() is stopping the
* thread via kthread_stop() after calling
* synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
* oneshot mask bit can be set. We cannot verify that as we
* cannot touch the oneshot mask at this point anymore as
* __setup_irq() might have given out currents thread_mask
* again.
*/
task_work_cancel(current, irq_thread_dtor);
return 0;
}
/**
* irq_wake_thread - wake the irq thread for the action identified by dev_id
* @irq: Interrupt line
* @dev_id: Device identity for which the thread should be woken
*
*/
void irq_wake_thread(unsigned int irq, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
unsigned long flags;
if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return;
raw_spin_lock_irqsave(&desc->lock, flags);
for (action = desc->action; action; action = action->next) {
if (action->dev_id == dev_id) {
if (action->thread)
__irq_wake_thread(desc, action);
break;
}
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL_GPL(irq_wake_thread);
static void irq_setup_forced_threading(struct irqaction *new)
{
if (!force_irqthreads)
return;
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
return;
new->flags |= IRQF_ONESHOT;
if (!new->thread_fn) {
set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
new->thread_fn = new->handler;
new->handler = irq_default_primary_handler;
}
}
static int irq_request_resources(struct irq_desc *desc)
{
struct irq_data *d = &desc->irq_data;
struct irq_chip *c = d->chip;
return c->irq_request_resources ? c->irq_request_resources(d) : 0;
}
static void irq_release_resources(struct irq_desc *desc)
{
struct irq_data *d = &desc->irq_data;
struct irq_chip *c = d->chip;
if (c->irq_release_resources)
c->irq_release_resources(d);
}
/*
* 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;
unsigned long flags, thread_mask = 0;
int ret, nested, shared = 0;
cpumask_var_t mask;
if (!desc)
return -EINVAL;
if (desc->irq_data.chip == &no_irq_chip)
return -ENOSYS;
if (!try_module_get(desc->owner))
return -ENODEV;
/*
* Check whether the interrupt nests into another interrupt
* thread.
*/
nested = irq_settings_is_nested_thread(desc);
if (nested) {
if (!new->thread_fn) {
ret = -EINVAL;
goto out_mput;
}
/*
* Replace the primary handler which was provided from
* the driver for non nested interrupt handling by the
* dummy function which warns when called.
*/
new->handler = irq_nested_primary_handler;
} else {
if (irq_settings_can_thread(desc))
irq_setup_forced_threading(new);
}
/*
* Create a handler thread when a thread function is supplied
* and the interrupt does not nest into another interrupt
* thread.
*/
if (new->thread_fn && !nested) {
struct task_struct *t;
static const struct sched_param param = {
.sched_priority = MAX_USER_RT_PRIO/2,
};
t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
new->name);
if (IS_ERR(t)) {
ret = PTR_ERR(t);
goto out_mput;
}
sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m);
/*
* 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;
/*
* Tell the thread to set its affinity. This is
* important for shared interrupt handlers as we do
* not invoke setup_affinity() for the secondary
* handlers as everything is already set up. Even for
* interrupts marked with IRQF_NO_BALANCE this is
* correct as we want the thread to move to the cpu(s)
* on which the requesting code placed the interrupt.
*/
set_bit(IRQTF_AFFINITY, &new->thread_flags);
}
if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
ret = -ENOMEM;
goto out_thread;
}
/*
* Drivers are often written to work w/o knowledge about the
* underlying irq chip implementation, so a request for a
* threaded irq without a primary hard irq context handler
* requires the ONESHOT flag to be set. Some irq chips like
* MSI based interrupts are per se one shot safe. Check the
* chip flags, so we can avoid the unmask dance at the end of
* the threaded handler for those.
*/
if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)
new->flags &= ~IRQF_ONESHOT;
/*
* The following block of code has to be executed atomically
*/
raw_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. Also all must
* agree on ONESHOT.
*/
if (!((old->flags & new->flags) & IRQF_SHARED) ||
((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
((old->flags ^ new->flags) & IRQF_ONESHOT))
goto mismatch;
/* All handlers must agree on per-cpuness */
if ((old->flags & IRQF_PERCPU) !=
(new->flags & IRQF_PERCPU))
goto mismatch;
/* add new interrupt at end of irq queue */
do {
/*
* Or all existing action->thread_mask bits,
* so we can find the next zero bit for this
* new action.
*/
thread_mask |= old->thread_mask;
old_ptr = &old->next;
old = *old_ptr;
} while (old);
shared = 1;
}
/*
* Setup the thread mask for this irqaction for ONESHOT. For
* !ONESHOT irqs the thread mask is 0 so we can avoid a
* conditional in irq_wake_thread().
*/
if (new->flags & IRQF_ONESHOT) {
/*
* Unlikely to have 32 resp 64 irqs sharing one line,
* but who knows.
*/
if (thread_mask == ~0UL) {
ret = -EBUSY;
goto out_mask;
}
/*
* The thread_mask for the action is or'ed to
* desc->thread_active to indicate that the
* IRQF_ONESHOT thread handler has been woken, but not
* yet finished. The bit is cleared when a thread
* completes. When all threads of a shared interrupt
* line have completed desc->threads_active becomes
* zero and the interrupt line is unmasked. See
* handle.c:irq_wake_thread() for further information.
*
* If no thread is woken by primary (hard irq context)
* interrupt handlers, then desc->threads_active is
* also checked for zero to unmask the irq line in the
* affected hard irq flow handlers
* (handle_[fasteoi|level]_irq).
*
* The new action gets the first zero bit of
* thread_mask assigned. See the loop above which or's
* all existing action->thread_mask bits.
*/
new->thread_mask = 1 << ffz(thread_mask);
} else if (new->handler == irq_default_primary_handler &&
!(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
/*
* The interrupt was requested with handler = NULL, so
* we use the default primary handler for it. But it
* does not have the oneshot flag set. In combination
* with level interrupts this is deadly, because the
* default primary handler just wakes the thread, then
* the irq lines is reenabled, but the device still
* has the level irq asserted. Rinse and repeat....
*
* While this works for edge type interrupts, we play
* it safe and reject unconditionally because we can't
* say for sure which type this interrupt really
* has. The type flags are unreliable as the
* underlying chip implementation can override them.
*/
pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
irq);
ret = -EINVAL;
goto out_mask;
}
if (!shared) {
ret = irq_request_resources(desc);
if (ret) {
pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
new->name, irq, desc->irq_data.chip->name);
goto out_mask;
}
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_mask;
}
desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
IRQS_ONESHOT | IRQS_WAITING);
irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
if (new->flags & IRQF_PERCPU) {
irqd_set(&desc->irq_data, IRQD_PER_CPU);
irq_settings_set_per_cpu(desc);
}
if (new->flags & IRQF_ONESHOT)
desc->istate |= IRQS_ONESHOT;
if (irq_settings_can_autoenable(desc))
irq_startup(desc, true);
else
/* Undo nested disables: */
desc->depth = 1;
/* Exclude IRQ from balancing if requested */
if (new->flags & IRQF_NOBALANCING) {
irq_settings_set_no_balancing(desc);
irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
}
/* Set default affinity mask once everything is setup */
setup_affinity(irq, desc, mask);
} else if (new->flags & IRQF_TRIGGER_MASK) {
unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
unsigned int omsk = irq_settings_get_trigger_mask(desc);
if (nmsk != omsk)
/* hope the handler works with current trigger mode */
pr_warning("irq %d uses trigger mode %u; requested %u\n",
irq, nmsk, omsk);
}
new->irq = irq;
*old_ptr = new;
irq_pm_install_action(desc, 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->istate & IRQS_SPURIOUS_DISABLED)) {
desc->istate &= ~IRQS_SPURIOUS_DISABLED;
__enable_irq(desc, irq);
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
/*
* Strictly no need to wake it up, but hung_task complains
* when no hard interrupt wakes the thread up.
*/
if (new->thread)
wake_up_process(new->thread);
register_irq_proc(irq, desc);
new->dir = NULL;
register_handler_proc(irq, new);
free_cpumask_var(mask);
return 0;
mismatch:
if (!(new->flags & IRQF_PROBE_SHARED)) {
pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
irq, new->flags, new->name, old->flags, old->name);
#ifdef CONFIG_DEBUG_SHIRQ
dump_stack();
#endif
}
ret = -EBUSY;
out_mask:
raw_spin_unlock_irqrestore(&desc->lock, flags);
free_cpumask_var(mask);
out_thread:
if (new->thread) {
struct task_struct *t = new->thread;
new->thread = NULL;
kthread_stop(t);
put_task_struct(t);
}
out_mput:
module_put(desc->owner);
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)
{
int retval;
struct irq_desc *desc = irq_to_desc(irq);
if (WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return -EINVAL;
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, act);
chip_bus_sync_unlock(desc);
return retval;
}
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;
unsigned long flags;
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
if (!desc)
return NULL;
raw_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);
raw_spin_unlock_irqrestore(&desc->lock, flags);
return NULL;
}
if (action->dev_id == dev_id)
break;
action_ptr = &action->next;
}
/* Found it - now remove it from the list of entries: */
*action_ptr = action->next;
irq_pm_remove_action(desc, action);
/* If this was the last handler, shut down the IRQ line: */
if (!desc->action) {
irq_shutdown(desc);
irq_release_resources(desc);
}
#ifdef CONFIG_SMP
/* make sure affinity_hint is cleaned up */
if (WARN_ON_ONCE(desc->affinity_hint))
desc->affinity_hint = NULL;
#endif
raw_spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
/* Make sure it's not being used on another CPU: */
synchronize_irq(irq);
#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
if (action->thread) {
kthread_stop(action->thread);
put_task_struct(action->thread);
}
module_put(desc->owner);
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)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
__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)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return;
#ifdef CONFIG_SMP
if (WARN_ON(desc->affinity_notify))
desc->affinity_notify = NULL;
#endif
chip_bus_lock(desc);
kfree(__free_irq(irq, dev_id));
chip_bus_sync_unlock(desc);
}
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
* If NULL and thread_fn != NULL the default
* primary handler is installed
* @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 is
* 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_WAKE_THREAD 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_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;
/*
* 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).
*
* Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
* it cannot be set along with IRQF_NO_SUSPEND.
*/
if (((irqflags & IRQF_SHARED) && !dev_id) ||
(!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc)
return -EINVAL;
if (!irq_settings_can_request(desc) ||
WARN_ON(irq_settings_is_per_cpu_devid(desc)))
return -EINVAL;
if (!handler) {
if (!thread_fn)
return -EINVAL;
handler = irq_default_primary_handler;
}
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;
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
chip_bus_sync_unlock(desc);
if (retval)
kfree(action);
#ifdef CONFIG_DEBUG_SHIRQ_FIXME
if (!retval && (irqflags & IRQF_SHARED)) {
/*
* It's a shared IRQ -- the driver ought to be prepared for it
* to happen immediately, so let's make sure....
* We disable the irq to make sure that a 'real' IRQ doesn't
* run in parallel with our fake.
*/
unsigned long flags;
disable_irq(irq);
local_irq_save(flags);
handler(irq, dev_id);
local_irq_restore(flags);
enable_irq(irq);
}
#endif
return retval;
}
EXPORT_SYMBOL(request_threaded_irq);
/**
* request_any_context_irq - allocate an interrupt line
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* Threaded handler for threaded interrupts.
* @flags: Interrupt type flags
* @name: 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. It selects either a
* hardirq or threaded handling method depending on the
* context.
*
* On failure, it returns a negative value. On success,
* it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
*/
int request_any_context_irq(unsigned int irq, irq_handler_t handler,
unsigned long flags, const char *name, void *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
int ret;
if (!desc)
return -EINVAL;
if (irq_settings_is_nested_thread(desc)) {
ret = request_threaded_irq(irq, NULL, handler,
flags, name, dev_id);
return !ret ? IRQC_IS_NESTED : ret;
}
ret = request_irq(irq, handler, flags, name, dev_id);
return !ret ? IRQC_IS_HARDIRQ : ret;
}
EXPORT_SYMBOL_GPL(request_any_context_irq);
void enable_percpu_irq(unsigned int irq, unsigned int type)
{
unsigned int cpu = smp_processor_id();
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return;
type &= IRQ_TYPE_SENSE_MASK;
if (type != IRQ_TYPE_NONE) {
int ret;
ret = __irq_set_trigger(desc, irq, type);
if (ret) {
WARN(1, "failed to set type for IRQ%d\n", irq);
goto out;
}
}
irq_percpu_enable(desc, cpu);
out:
irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(enable_percpu_irq);
void disable_percpu_irq(unsigned int irq)
{
unsigned int cpu = smp_processor_id();
unsigned long flags;
struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
if (!desc)
return;
irq_percpu_disable(desc, cpu);
irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(disable_percpu_irq);
/*
* Internal function to unregister a percpu irqaction.
*/
static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
unsigned long flags;
WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
if (!desc)
return NULL;
raw_spin_lock_irqsave(&desc->lock, flags);
action = desc->action;
if (!action || action->percpu_dev_id != dev_id) {
WARN(1, "Trying to free already-free IRQ %d\n", irq);
goto bad;
}
if (!cpumask_empty(desc->percpu_enabled)) {
WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
irq, cpumask_first(desc->percpu_enabled));
goto bad;
}
/* Found it - now remove it from the list of entries: */
desc->action = NULL;
raw_spin_unlock_irqrestore(&desc->lock, flags);
unregister_handler_proc(irq, action);
module_put(desc->owner);
return action;
bad:
raw_spin_unlock_irqrestore(&desc->lock, flags);
return NULL;
}
/**
* remove_percpu_irq - free a per-cpu interrupt
* @irq: Interrupt line to free
* @act: irqaction for the interrupt
*
* Used to remove interrupts statically setup by the early boot process.
*/
void remove_percpu_irq(unsigned int irq, struct irqaction *act)
{
struct irq_desc *desc = irq_to_desc(irq);
if (desc && irq_settings_is_per_cpu_devid(desc))
__free_percpu_irq(irq, act->percpu_dev_id);
}
/**
* free_percpu_irq - free an interrupt allocated with request_percpu_irq
* @irq: Interrupt line to free
* @dev_id: Device identity to free
*
* Remove a percpu interrupt handler. The handler is removed, but
* the interrupt line is not disabled. This must be done on each
* CPU 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_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
struct irq_desc *desc = irq_to_desc(irq);
if (!desc || !irq_settings_is_per_cpu_devid(desc))
return;
chip_bus_lock(desc);
kfree(__free_percpu_irq(irq, dev_id));
chip_bus_sync_unlock(desc);
}
/**
* setup_percpu_irq - setup a per-cpu interrupt
* @irq: Interrupt line to setup
* @act: irqaction for the interrupt
*
* Used to statically setup per-cpu interrupts in the early boot process.
*/
int setup_percpu_irq(unsigned int irq, struct irqaction *act)
{
struct irq_desc *desc = irq_to_desc(irq);
int retval;
if (!desc || !irq_settings_is_per_cpu_devid(desc))
return -EINVAL;
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, act);
chip_bus_sync_unlock(desc);
return retval;
}
/**
* request_percpu_irq - allocate a percpu interrupt line
* @irq: Interrupt line to allocate
* @handler: Function to be called when the IRQ occurs.
* @devname: An ascii name for the claiming device
* @dev_id: A percpu cookie passed back to the handler function
*
* This call allocates interrupt resources, but doesn't
* automatically enable the interrupt. It has to be done on each
* CPU using enable_percpu_irq().
*
* Dev_id must be globally unique. It is a per-cpu variable, and
* the handler gets called with the interrupted CPU's instance of
* that variable.
*/
int request_percpu_irq(unsigned int irq, irq_handler_t handler,
const char *devname, void __percpu *dev_id)
{
struct irqaction *action;
struct irq_desc *desc;
int retval;
if (!dev_id)
return -EINVAL;
desc = irq_to_desc(irq);
if (!desc || !irq_settings_can_request(desc) ||
!irq_settings_is_per_cpu_devid(desc))
return -EINVAL;
action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!action)
return -ENOMEM;
action->handler = handler;
action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
action->name = devname;
action->percpu_dev_id = dev_id;
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
chip_bus_sync_unlock(desc);
if (retval)
kfree(action);
return retval;
}
/**
* irq_get_irqchip_state - returns the irqchip state of a interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: One of IRQCHIP_STATE_* the caller wants to know about
* @state: a pointer to a boolean where the state is to be storeed
*
* This call snapshots the internal irqchip state of an
* interrupt, returning into @state the bit corresponding to
* stage @which
*
* This function should be called with preemption disabled if the
* interrupt controller has per-cpu registers.
*/
int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
bool *state)
{
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
unsigned long flags;
int err = -EINVAL;
desc = irq_get_desc_buslock(irq, &flags, 0);
if (!desc)
return err;
data = irq_desc_get_irq_data(desc);
do {
chip = irq_data_get_irq_chip(data);
if (chip->irq_get_irqchip_state)
break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
data = data->parent_data;
#else
data = NULL;
#endif
} while (data);
if (data)
err = chip->irq_get_irqchip_state(data, which, state);
irq_put_desc_busunlock(desc, flags);
return err;
}
/**
* irq_set_irqchip_state - set the state of a forwarded interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: State to be restored (one of IRQCHIP_STATE_*)
* @val: Value corresponding to @which
*
* This call sets the internal irqchip state of an interrupt,
* depending on the value of @which.
*
* This function should be called with preemption disabled if the
* interrupt controller has per-cpu registers.
*/
int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
bool val)
{
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
unsigned long flags;
int err = -EINVAL;
desc = irq_get_desc_buslock(irq, &flags, 0);
if (!desc)
return err;
data = irq_desc_get_irq_data(desc);
do {
chip = irq_data_get_irq_chip(data);
if (chip->irq_set_irqchip_state)
break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
data = data->parent_data;
#else
data = NULL;
#endif
} while (data);
if (data)
err = chip->irq_set_irqchip_state(data, which, val);
irq_put_desc_busunlock(desc, flags);
return err;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/migration.c
#include <linux/irq.h>
#include <linux/interrupt.h>
#include "internals.h"
void irq_move_masked_irq(struct irq_data *idata)
{
struct irq_desc *desc = irq_data_to_desc(idata);
struct irq_chip *chip = desc->irq_data.chip;
if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
return;
irqd_clr_move_pending(&desc->irq_data);
/*
* Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
*/
if (irqd_is_per_cpu(&desc->irq_data)) {
WARN_ON(1);
return;
}
if (unlikely(cpumask_empty(desc->pending_mask)))
return;
if (!chip->irq_set_affinity)
return;
assert_raw_spin_locked(&desc->lock);
/*
* If there was a valid mask to work with, please
* do the disable, re-program, enable sequence.
* This is *not* particularly important for level triggered
* but in a edge trigger case, we might be setting rte
* when an active trigger is coming in. This could
* cause some ioapics to mal-function.
* Being paranoid i guess!
*
* For correct operation this depends on the caller
* masking the irqs.
*/
if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
cpumask_clear(desc->pending_mask);
}
void irq_move_irq(struct irq_data *idata)
{
bool masked;
/*
* Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled,
* and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is
* disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here.
*/
idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
if (likely(!irqd_is_setaffinity_pending(idata)))
return;
if (unlikely(irqd_irq_disabled(idata)))
return;
/*
* Be careful vs. already masked interrupts. If this is a
* threaded interrupt with ONESHOT set, we can end up with an
* interrupt storm.
*/
masked = irqd_irq_masked(idata);
if (!masked)
idata->chip->irq_mask(idata);
irq_move_masked_irq(idata);
if (!masked)
idata->chip->irq_unmask(idata);
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/msi.c
/*
* linux/kernel/irq/msi.c
*
* Copyright (C) 2014 Intel Corp.
* Author: Jiang Liu <jiang.liu@linux.intel.com>
*
* This file is licensed under GPLv2.
*
* This file contains common code to support Message Signalled Interrupt for
* PCI compatible and non PCI compatible devices.
*/
#include <linux/types.h>
#include <linux/device.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/msi.h>
/* Temparory solution for building, will be removed later */
#include <linux/pci.h>
void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
*msg = entry->msg;
}
void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__get_cached_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(get_cached_msi_msg);
#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
static inline void irq_chip_write_msi_msg(struct irq_data *data,
struct msi_msg *msg)
{
data->chip->irq_write_msi_msg(data, msg);
}
/**
* msi_domain_set_affinity - Generic affinity setter function for MSI domains
* @irq_data: The irq data associated to the interrupt
* @mask: The affinity mask to set
* @force: Flag to enforce setting (disable online checks)
*
* Intended to be used by MSI interrupt controllers which are
* implemented with hierarchical domains.
*/
int msi_domain_set_affinity(struct irq_data *irq_data,
const struct cpumask *mask, bool force)
{
struct irq_data *parent = irq_data->parent_data;
struct msi_msg msg;
int ret;
ret = parent->chip->irq_set_affinity(parent, mask, force);
if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
irq_chip_write_msi_msg(irq_data, &msg);
}
return ret;
}
static void msi_domain_activate(struct irq_domain *domain,
struct irq_data *irq_data)
{
struct msi_msg msg;
BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
irq_chip_write_msi_msg(irq_data, &msg);
}
static void msi_domain_deactivate(struct irq_domain *domain,
struct irq_data *irq_data)
{
struct msi_msg msg;
memset(&msg, 0, sizeof(msg));
irq_chip_write_msi_msg(irq_data, &msg);
}
static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
irq_hw_number_t hwirq = ops->get_hwirq(info, arg);
int i, ret;
if (irq_find_mapping(domain, hwirq) > 0)
return -EEXIST;
ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
if (ret < 0)
return ret;
for (i = 0; i < nr_irqs; i++) {
ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg);
if (ret < 0) {
if (ops->msi_free) {
for (i--; i > 0; i--)
ops->msi_free(domain, info, virq + i);
}
irq_domain_free_irqs_top(domain, virq, nr_irqs);
return ret;
}
}
return 0;
}
static void msi_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs)
{
struct msi_domain_info *info = domain->host_data;
int i;
if (info->ops->msi_free) {
for (i = 0; i < nr_irqs; i++)
info->ops->msi_free(domain, info, virq + i);
}
irq_domain_free_irqs_top(domain, virq, nr_irqs);
}
static const struct irq_domain_ops msi_domain_ops = {
.alloc = msi_domain_alloc,
.free = msi_domain_free,
.activate = msi_domain_activate,
.deactivate = msi_domain_deactivate,
};
#ifdef GENERIC_MSI_DOMAIN_OPS
static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
msi_alloc_info_t *arg)
{
return arg->hwirq;
}
static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev,
int nvec, msi_alloc_info_t *arg)
{
memset(arg, 0, sizeof(*arg));
return 0;
}
static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
struct msi_desc *desc)
{
arg->desc = desc;
}
#else
#define msi_domain_ops_get_hwirq NULL
#define msi_domain_ops_prepare NULL
#define msi_domain_ops_set_desc NULL
#endif /* !GENERIC_MSI_DOMAIN_OPS */
static int msi_domain_ops_init(struct irq_domain *domain,
struct msi_domain_info *info,
unsigned int virq, irq_hw_number_t hwirq,
msi_alloc_info_t *arg)
{
irq_domain_set_hwirq_and_chip(domain, virq, hwirq, info->chip,
info->chip_data);
if (info->handler && info->handler_name) {
__irq_set_handler(virq, info->handler, 0, info->handler_name);
if (info->handler_data)
irq_set_handler_data(virq, info->handler_data);
}
return 0;
}
static int msi_domain_ops_check(struct irq_domain *domain,
struct msi_domain_info *info,
struct device *dev)
{
return 0;
}
static struct msi_domain_ops msi_domain_ops_default = {
.get_hwirq = msi_domain_ops_get_hwirq,
.msi_init = msi_domain_ops_init,
.msi_check = msi_domain_ops_check,
.msi_prepare = msi_domain_ops_prepare,
.set_desc = msi_domain_ops_set_desc,
};
static void msi_domain_update_dom_ops(struct msi_domain_info *info)
{
struct msi_domain_ops *ops = info->ops;
if (ops == NULL) {
info->ops = &msi_domain_ops_default;
return;
}
if (ops->get_hwirq == NULL)
ops->get_hwirq = msi_domain_ops_default.get_hwirq;
if (ops->msi_init == NULL)
ops->msi_init = msi_domain_ops_default.msi_init;
if (ops->msi_check == NULL)
ops->msi_check = msi_domain_ops_default.msi_check;
if (ops->msi_prepare == NULL)
ops->msi_prepare = msi_domain_ops_default.msi_prepare;
if (ops->set_desc == NULL)
ops->set_desc = msi_domain_ops_default.set_desc;
}
static void msi_domain_update_chip_ops(struct msi_domain_info *info)
{
struct irq_chip *chip = info->chip;
BUG_ON(!chip);
if (!chip->irq_mask)
chip->irq_mask = pci_msi_mask_irq;
if (!chip->irq_unmask)
chip->irq_unmask = pci_msi_unmask_irq;
if (!chip->irq_set_affinity)
chip->irq_set_affinity = msi_domain_set_affinity;
}
/**
* msi_create_irq_domain - Create a MSI interrupt domain
* @of_node: Optional device-tree node of the interrupt controller
* @info: MSI domain info
* @parent: Parent irq domain
*/
struct irq_domain *msi_create_irq_domain(struct device_node *node,
struct msi_domain_info *info,
struct irq_domain *parent)
{
if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
msi_domain_update_dom_ops(info);
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
msi_domain_update_chip_ops(info);
return irq_domain_add_hierarchy(parent, 0, 0, node, &msi_domain_ops,
info);
}
/**
* msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
* @domain: The domain to allocate from
* @dev: Pointer to device struct of the device for which the interrupts
* are allocated
* @nvec: The number of interrupts to allocate
*
* Returns 0 on success or an error code.
*/
int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
int nvec)
{
struct msi_domain_info *info = domain->host_data;
struct msi_domain_ops *ops = info->ops;
msi_alloc_info_t arg;
struct msi_desc *desc;
int i, ret, virq = -1;
ret = ops->msi_check(domain, info, dev);
if (ret == 0)
ret = ops->msi_prepare(domain, dev, nvec, &arg);
if (ret)
return ret;
for_each_msi_entry(desc, dev) {
ops->set_desc(&arg, desc);
if (info->flags & MSI_FLAG_IDENTITY_MAP)
virq = (int)ops->get_hwirq(info, &arg);
else
virq = -1;
virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
dev_to_node(dev), &arg, false);
if (virq < 0) {
ret = -ENOSPC;
if (ops->handle_error)
ret = ops->handle_error(domain, desc, ret);
if (ops->msi_finish)
ops->msi_finish(&arg, ret);
return ret;
}
for (i = 0; i < desc->nvec_used; i++)
irq_set_msi_desc_off(virq, i, desc);
}
if (ops->msi_finish)
ops->msi_finish(&arg, 0);
for_each_msi_entry(desc, dev) {
if (desc->nvec_used == 1)
dev_dbg(dev, "irq %d for MSI\n", virq);
else
dev_dbg(dev, "irq [%d-%d] for MSI\n",
virq, virq + desc->nvec_used - 1);
}
return 0;
}
/**
* msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
* @domain: The domain to managing the interrupts
* @dev: Pointer to device struct of the device for which the interrupts
* are free
*/
void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
struct msi_desc *desc;
for_each_msi_entry(desc, dev) {
/*
* We might have failed to allocate an MSI early
* enough that there is no IRQ associated to this
* entry. If that's the case, don't do anything.
*/
if (desc->irq) {
irq_domain_free_irqs(desc->irq, desc->nvec_used);
desc->irq = 0;
}
}
}
/**
* msi_get_domain_info - Get the MSI interrupt domain info for @domain
* @domain: The interrupt domain to retrieve data from
*
* Returns the pointer to the msi_domain_info stored in
* @domain->host_data.
*/
struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain)
{
return (struct msi_domain_info *)domain->host_data;
}
#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/pm.c
/*
* linux/kernel/irq/pm.c
*
* Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
*
* This file contains power management functions related to interrupts.
*/
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include "internals.h"
bool irq_pm_check_wakeup(struct irq_desc *desc)
{
if (irqd_is_wakeup_armed(&desc->irq_data)) {
irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
desc->istate |= IRQS_SUSPENDED | IRQS_PENDING;
desc->depth++;
irq_disable(desc);
pm_system_wakeup();
return true;
}
return false;
}
/*
* Called from __setup_irq() with desc->lock held after @action has
* been installed in the action chain.
*/
void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action)
{
desc->nr_actions++;
if (action->flags & IRQF_FORCE_RESUME)
desc->force_resume_depth++;
WARN_ON_ONCE(desc->force_resume_depth &&
desc->force_resume_depth != desc->nr_actions);
if (action->flags & IRQF_NO_SUSPEND)
desc->no_suspend_depth++;
else if (action->flags & IRQF_COND_SUSPEND)
desc->cond_suspend_depth++;
WARN_ON_ONCE(desc->no_suspend_depth &&
(desc->no_suspend_depth +
desc->cond_suspend_depth) != desc->nr_actions);
}
/*
* Called from __free_irq() with desc->lock held after @action has
* been removed from the action chain.
*/
void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
{
desc->nr_actions--;
if (action->flags & IRQF_FORCE_RESUME)
desc->force_resume_depth--;
if (action->flags & IRQF_NO_SUSPEND)
desc->no_suspend_depth--;
else if (action->flags & IRQF_COND_SUSPEND)
desc->cond_suspend_depth--;
}
static bool suspend_device_irq(struct irq_desc *desc, int irq)
{
if (!desc->action || desc->no_suspend_depth)
return false;
if (irqd_is_wakeup_set(&desc->irq_data)) {
irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
/*
* We return true here to force the caller to issue
* synchronize_irq(). We need to make sure that the
* IRQD_WAKEUP_ARMED is visible before we return from
* suspend_device_irqs().
*/
return true;
}
desc->istate |= IRQS_SUSPENDED;
__disable_irq(desc, irq);
/*
* Hardware which has no wakeup source configuration facility
* requires that the non wakeup interrupts are masked at the
* chip level. The chip implementation indicates that with
* IRQCHIP_MASK_ON_SUSPEND.
*/
if (irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
mask_irq(desc);
return true;
}
/**
* suspend_device_irqs - disable all currently enabled interrupt lines
*
* During system-wide suspend or hibernation device drivers need to be
* prevented from receiving interrupts and this function is provided
* for this purpose.
*
* So we disable all interrupts and mark them IRQS_SUSPENDED except
* for those which are unused, those which are marked as not
* suspendable via an interrupt request with the flag IRQF_NO_SUSPEND
* set and those which are marked as active wakeup sources.
*
* The active wakeup sources are handled by the flow handler entry
* code which checks for the IRQD_WAKEUP_ARMED flag, suspends the
* interrupt and notifies the pm core about the wakeup.
*/
void suspend_device_irqs(void)
{
struct irq_desc *desc;
int irq;
for_each_irq_desc(irq, desc) {
unsigned long flags;
bool sync;
if (irq_settings_is_nested_thread(desc))
continue;
raw_spin_lock_irqsave(&desc->lock, flags);
sync = suspend_device_irq(desc, irq);
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (sync)
synchronize_irq(irq);
}
}
EXPORT_SYMBOL_GPL(suspend_device_irqs);
static void resume_irq(struct irq_desc *desc, int irq)
{
irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
if (desc->istate & IRQS_SUSPENDED)
goto resume;
/* Force resume the interrupt? */
if (!desc->force_resume_depth)
return;
/* Pretend that it got disabled ! */
desc->depth++;
resume:
desc->istate &= ~IRQS_SUSPENDED;
__enable_irq(desc, irq);
}
static void resume_irqs(bool want_early)
{
struct irq_desc *desc;
int irq;
for_each_irq_desc(irq, desc) {
unsigned long flags;
bool is_early = desc->action &&
desc->action->flags & IRQF_EARLY_RESUME;
if (!is_early && want_early)
continue;
if (irq_settings_is_nested_thread(desc))
continue;
raw_spin_lock_irqsave(&desc->lock, flags);
resume_irq(desc, irq);
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
}
/**
* irq_pm_syscore_ops - enable interrupt lines early
*
* Enable all interrupt lines with %IRQF_EARLY_RESUME set.
*/
static void irq_pm_syscore_resume(void)
{
resume_irqs(true);
}
static struct syscore_ops irq_pm_syscore_ops = {
.resume = irq_pm_syscore_resume,
};
static int __init irq_pm_init_ops(void)
{
register_syscore_ops(&irq_pm_syscore_ops);
return 0;
}
device_initcall(irq_pm_init_ops);
/**
* resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs()
*
* Enable all non-%IRQF_EARLY_RESUME interrupt lines previously
* disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag
* set as well as those with %IRQF_FORCE_RESUME.
*/
void resume_device_irqs(void)
{
resume_irqs(false);
}
EXPORT_SYMBOL_GPL(resume_device_irqs);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/proc.c
/*
* linux/kernel/irq/proc.c
*
* Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
*
* This file contains the /proc/irq/ handling code.
*/
#include <linux/irq.h>
#include <linux/gfp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/mutex.h>
#include "internals.h"
/*
* Access rules:
*
* procfs protects read/write of /proc/irq/N/ files against a
* concurrent free of the interrupt descriptor. remove_proc_entry()
* immediately prevents new read/writes to happen and waits for
* already running read/write functions to complete.
*
* We remove the proc entries first and then delete the interrupt
* descriptor from the radix tree and free it. So it is guaranteed
* that irq_to_desc(N) is valid as long as the read/writes are
* permitted by procfs.
*
* The read from /proc/interrupts is a different problem because there
* is no protection. So the lookup and the access to irqdesc
* information must be protected by sparse_irq_lock.
*/
static struct proc_dir_entry *root_irq_dir;
#ifdef CONFIG_SMP
static int show_irq_affinity(int type, struct seq_file *m, void *v)
{
struct irq_desc *desc = irq_to_desc((long)m->private);
const struct cpumask *mask = desc->irq_data.affinity;
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (irqd_is_setaffinity_pending(&desc->irq_data))
mask = desc->pending_mask;
#endif
if (type)
seq_printf(m, "%*pbl\n", cpumask_pr_args(mask));
else
seq_printf(m, "%*pb\n", cpumask_pr_args(mask));
return 0;
}
static int irq_affinity_hint_proc_show(struct seq_file *m, void *v)
{
struct irq_desc *desc = irq_to_desc((long)m->private);
unsigned long flags;
cpumask_var_t mask;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
raw_spin_lock_irqsave(&desc->lock, flags);
if (desc->affinity_hint)
cpumask_copy(mask, desc->affinity_hint);
raw_spin_unlock_irqrestore(&desc->lock, flags);
seq_printf(m, "%*pb\n", cpumask_pr_args(mask));
free_cpumask_var(mask);
return 0;
}
#ifndef is_affinity_mask_valid
#define is_affinity_mask_valid(val) 1
#endif
int no_irq_affinity;
static int irq_affinity_proc_show(struct seq_file *m, void *v)
{
return show_irq_affinity(0, m, v);
}
static int irq_affinity_list_proc_show(struct seq_file *m, void *v)
{
return show_irq_affinity(1, m, v);
}
static ssize_t write_irq_affinity(int type, struct file *file,
const char __user *buffer, size_t count, loff_t *pos)
{
unsigned int irq = (int)(long)PDE_DATA(file_inode(file));
cpumask_var_t new_value;
int err;
if (!irq_can_set_affinity(irq) || no_irq_affinity)
return -EIO;
if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
if (type)
err = cpumask_parselist_user(buffer, count, new_value);
else
err = cpumask_parse_user(buffer, count, new_value);
if (err)
goto free_cpumask;
if (!is_affinity_mask_valid(new_value)) {
err = -EINVAL;
goto free_cpumask;
}
/*
* Do not allow disabling IRQs completely - it's a too easy
* way to make the system unusable accidentally :-) At least
* one online CPU still has to be targeted.
*/
if (!cpumask_intersects(new_value, cpu_online_mask)) {
/* Special case for empty set - allow the architecture
code to set default SMP affinity. */
err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count;
} else {
irq_set_affinity(irq, new_value);
err = count;
}
free_cpumask:
free_cpumask_var(new_value);
return err;
}
static ssize_t irq_affinity_proc_write(struct file *file,
const char __user *buffer, size_t count, loff_t *pos)
{
return write_irq_affinity(0, file, buffer, count, pos);
}
static ssize_t irq_affinity_list_proc_write(struct file *file,
const char __user *buffer, size_t count, loff_t *pos)
{
return write_irq_affinity(1, file, buffer, count, pos);
}
static int irq_affinity_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, irq_affinity_proc_show, PDE_DATA(inode));
}
static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode));
}
static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode));
}
static const struct file_operations irq_affinity_proc_fops = {
.open = irq_affinity_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
.write = irq_affinity_proc_write,
};
static const struct file_operations irq_affinity_hint_proc_fops = {
.open = irq_affinity_hint_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static const struct file_operations irq_affinity_list_proc_fops = {
.open = irq_affinity_list_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
.write = irq_affinity_list_proc_write,
};
static int default_affinity_show(struct seq_file *m, void *v)
{
seq_printf(m, "%*pb\n", cpumask_pr_args(irq_default_affinity));
return 0;
}
static ssize_t default_affinity_write(struct file *file,
const char __user *buffer, size_t count, loff_t *ppos)
{
cpumask_var_t new_value;
int err;
if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
if (err)
goto out;
if (!is_affinity_mask_valid(new_value)) {
err = -EINVAL;
goto out;
}
/*
* Do not allow disabling IRQs completely - it's a too easy
* way to make the system unusable accidentally :-) At least
* one online CPU still has to be targeted.
*/
if (!cpumask_intersects(new_value, cpu_online_mask)) {
err = -EINVAL;
goto out;
}
cpumask_copy(irq_default_affinity, new_value);
err = count;
out:
free_cpumask_var(new_value);
return err;
}
static int default_affinity_open(struct inode *inode, struct file *file)
{
return single_open(file, default_affinity_show, PDE_DATA(inode));
}
static const struct file_operations default_affinity_proc_fops = {
.open = default_affinity_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
.write = default_affinity_write,
};
static int irq_node_proc_show(struct seq_file *m, void *v)
{
struct irq_desc *desc = irq_to_desc((long) m->private);
seq_printf(m, "%d\n", irq_desc_get_node(desc));
return 0;
}
static int irq_node_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, irq_node_proc_show, PDE_DATA(inode));
}
static const struct file_operations irq_node_proc_fops = {
.open = irq_node_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
#endif
static int irq_spurious_proc_show(struct seq_file *m, void *v)
{
struct irq_desc *desc = irq_to_desc((long) m->private);
seq_printf(m, "count %u\n" "unhandled %u\n" "last_unhandled %u ms\n",
desc->irq_count, desc->irqs_unhandled,
jiffies_to_msecs(desc->last_unhandled));
return 0;
}
static int irq_spurious_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, irq_spurious_proc_show, PDE_DATA(inode));
}
static const struct file_operations irq_spurious_proc_fops = {
.open = irq_spurious_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
#define MAX_NAMELEN 128
static int name_unique(unsigned int irq, struct irqaction *new_action)
{
struct irq_desc *desc = irq_to_desc(irq);
struct irqaction *action;
unsigned long flags;
int ret = 1;
raw_spin_lock_irqsave(&desc->lock, flags);
for (action = desc->action ; action; action = action->next) {
if ((action != new_action) && action->name &&
!strcmp(new_action->name, action->name)) {
ret = 0;
break;
}
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
void register_handler_proc(unsigned int irq, struct irqaction *action)
{
char name [MAX_NAMELEN];
struct irq_desc *desc = irq_to_desc(irq);
if (!desc->dir || action->dir || !action->name ||
!name_unique(irq, action))
return;
memset(name, 0, MAX_NAMELEN);
snprintf(name, MAX_NAMELEN, "%s", action->name);
/* create /proc/irq/1234/handler/ */
action->dir = proc_mkdir(name, desc->dir);
}
#undef MAX_NAMELEN
#define MAX_NAMELEN 10
void register_irq_proc(unsigned int irq, struct irq_desc *desc)
{
static DEFINE_MUTEX(register_lock);
char name [MAX_NAMELEN];
if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
return;
/*
* irq directories are registered only when a handler is
* added, not when the descriptor is created, so multiple
* tasks might try to register at the same time.
*/
mutex_lock(®ister_lock);
if (desc->dir)
goto out_unlock;
memset(name, 0, MAX_NAMELEN);
sprintf(name, "%d", irq);
/* create /proc/irq/1234 */
desc->dir = proc_mkdir(name, root_irq_dir);
if (!desc->dir)
goto out_unlock;
#ifdef CONFIG_SMP
/* create /proc/irq/<irq>/smp_affinity */
proc_create_data("smp_affinity", 0644, desc->dir,
&irq_affinity_proc_fops, (void *)(long)irq);
/* create /proc/irq/<irq>/affinity_hint */
proc_create_data("affinity_hint", 0444, desc->dir,
&irq_affinity_hint_proc_fops, (void *)(long)irq);
/* create /proc/irq/<irq>/smp_affinity_list */
proc_create_data("smp_affinity_list", 0644, desc->dir,
&irq_affinity_list_proc_fops, (void *)(long)irq);
proc_create_data("node", 0444, desc->dir,
&irq_node_proc_fops, (void *)(long)irq);
#endif
proc_create_data("spurious", 0444, desc->dir,
&irq_spurious_proc_fops, (void *)(long)irq);
out_unlock:
mutex_unlock(®ister_lock);
}
void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
{
char name [MAX_NAMELEN];
if (!root_irq_dir || !desc->dir)
return;
#ifdef CONFIG_SMP
remove_proc_entry("smp_affinity", desc->dir);
remove_proc_entry("affinity_hint", desc->dir);
remove_proc_entry("smp_affinity_list", desc->dir);
remove_proc_entry("node", desc->dir);
#endif
remove_proc_entry("spurious", desc->dir);
memset(name, 0, MAX_NAMELEN);
sprintf(name, "%u", irq);
remove_proc_entry(name, root_irq_dir);
}
#undef MAX_NAMELEN
void unregister_handler_proc(unsigned int irq, struct irqaction *action)
{
proc_remove(action->dir);
}
static void register_default_affinity_proc(void)
{
#ifdef CONFIG_SMP
proc_create("irq/default_smp_affinity", 0644, NULL,
&default_affinity_proc_fops);
#endif
}
void init_irq_proc(void)
{
unsigned int irq;
struct irq_desc *desc;
/* create /proc/irq */
root_irq_dir = proc_mkdir("irq", NULL);
if (!root_irq_dir)
return;
register_default_affinity_proc();
/*
* Create entries for all existing IRQs.
*/
for_each_irq_desc(irq, desc) {
if (!desc)
continue;
register_irq_proc(irq, desc);
}
}
#ifdef CONFIG_GENERIC_IRQ_SHOW
int __weak arch_show_interrupts(struct seq_file *p, int prec)
{
return 0;
}
#ifndef ACTUAL_NR_IRQS
# define ACTUAL_NR_IRQS nr_irqs
#endif
int show_interrupts(struct seq_file *p, void *v)
{
static int prec;
unsigned long flags, any_count = 0;
int i = *(loff_t *) v, j;
struct irqaction *action;
struct irq_desc *desc;
if (i > ACTUAL_NR_IRQS)
return 0;
if (i == ACTUAL_NR_IRQS)
return arch_show_interrupts(p, prec);
/* print header and calculate the width of the first column */
if (i == 0) {
for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
j *= 10;
seq_printf(p, "%*s", prec + 8, "");
for_each_online_cpu(j)
seq_printf(p, "CPU%-8d", j);
seq_putc(p, '\n');
}
irq_lock_sparse();
desc = irq_to_desc(i);
if (!desc)
goto outsparse;
raw_spin_lock_irqsave(&desc->lock, flags);
for_each_online_cpu(j)
any_count |= kstat_irqs_cpu(i, j);
action = desc->action;
if (!action && !any_count)
goto out;
seq_printf(p, "%*d: ", prec, i);
for_each_online_cpu(j)
seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
if (desc->irq_data.chip) {
if (desc->irq_data.chip->irq_print_chip)
desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
else if (desc->irq_data.chip->name)
seq_printf(p, " %8s", desc->irq_data.chip->name);
else
seq_printf(p, " %8s", "-");
} else {
seq_printf(p, " %8s", "None");
}
if (desc->irq_data.domain)
seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq);
#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
#endif
if (desc->name)
seq_printf(p, "-%-8s", desc->name);
if (action) {
seq_printf(p, " %s", action->name);
while ((action = action->next) != NULL)
seq_printf(p, ", %s", action->name);
}
seq_putc(p, '\n');
out:
raw_spin_unlock_irqrestore(&desc->lock, flags);
outsparse:
irq_unlock_sparse();
return 0;
}
#endif
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/resend.c
/*
* linux/kernel/irq/resend.c
*
* Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
* Copyright (C) 2005-2006, Thomas Gleixner
*
* This file contains the IRQ-resend code
*
* If the interrupt is waiting to be processed, we try to re-run it.
* We can't directly run it from here since the caller might be in an
* interrupt-protected region. Not all irq controller chips can
* retrigger interrupts at the hardware level, so in those cases
* we allow the resending of IRQs via a tasklet.
*/
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include "internals.h"
#ifdef CONFIG_HARDIRQS_SW_RESEND
/* Bitmap to handle software resend of interrupts: */
static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
/*
* Run software resends of IRQ's
*/
static void resend_irqs(unsigned long arg)
{
struct irq_desc *desc;
int irq;
while (!bitmap_empty(irqs_resend, nr_irqs)) {
irq = find_first_bit(irqs_resend, nr_irqs);
clear_bit(irq, irqs_resend);
desc = irq_to_desc(irq);
local_irq_disable();
desc->handle_irq(irq, desc);
local_irq_enable();
}
}
/* Tasklet to handle resend: */
static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0);
#endif
/*
* IRQ resend
*
* Is called with interrupts disabled and desc->lock held.
*/
void check_irq_resend(struct irq_desc *desc, unsigned int irq)
{
/*
* We do not resend level type interrupts. Level type
* interrupts are resent by hardware when they are still
* active. Clear the pending bit so suspend/resume does not
* get confused.
*/
if (irq_settings_is_level(desc)) {
desc->istate &= ~IRQS_PENDING;
return;
}
if (desc->istate & IRQS_REPLAY)
return;
if (desc->istate & IRQS_PENDING) {
desc->istate &= ~IRQS_PENDING;
desc->istate |= IRQS_REPLAY;
if (!desc->irq_data.chip->irq_retrigger ||
!desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
#ifdef CONFIG_HARDIRQS_SW_RESEND
/*
* If the interrupt is running in the thread
* context of the parent irq we need to be
* careful, because we cannot trigger it
* directly.
*/
if (irq_settings_is_nested_thread(desc)) {
/*
* If the parent_irq is valid, we
* retrigger the parent, otherwise we
* do nothing.
*/
if (!desc->parent_irq)
return;
irq = desc->parent_irq;
}
/* Set it pending and activate the softirq: */
set_bit(irq, irqs_resend);
tasklet_schedule(&resend_tasklet);
#endif
}
}
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/settings.h
/*
* Internal header to deal with irq_desc->status which will be renamed
* to irq_desc->settings.
*/
enum {
_IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS,
_IRQ_PER_CPU = IRQ_PER_CPU,
_IRQ_LEVEL = IRQ_LEVEL,
_IRQ_NOPROBE = IRQ_NOPROBE,
_IRQ_NOREQUEST = IRQ_NOREQUEST,
_IRQ_NOTHREAD = IRQ_NOTHREAD,
_IRQ_NOAUTOEN = IRQ_NOAUTOEN,
_IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT,
_IRQ_NO_BALANCING = IRQ_NO_BALANCING,
_IRQ_NESTED_THREAD = IRQ_NESTED_THREAD,
_IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID,
_IRQ_IS_POLLED = IRQ_IS_POLLED,
_IRQF_MODIFY_MASK = IRQF_MODIFY_MASK,
};
#define IRQ_PER_CPU GOT_YOU_MORON
#define IRQ_NO_BALANCING GOT_YOU_MORON
#define IRQ_LEVEL GOT_YOU_MORON
#define IRQ_NOPROBE GOT_YOU_MORON
#define IRQ_NOREQUEST GOT_YOU_MORON
#define IRQ_NOTHREAD GOT_YOU_MORON
#define IRQ_NOAUTOEN GOT_YOU_MORON
#define IRQ_NESTED_THREAD GOT_YOU_MORON
#define IRQ_PER_CPU_DEVID GOT_YOU_MORON
#define IRQ_IS_POLLED GOT_YOU_MORON
#undef IRQF_MODIFY_MASK
#define IRQF_MODIFY_MASK GOT_YOU_MORON
static inline void
irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set)
{
desc->status_use_accessors &= ~(clr & _IRQF_MODIFY_MASK);
desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK);
}
static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_PER_CPU;
}
static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_PER_CPU_DEVID;
}
static inline void irq_settings_set_per_cpu(struct irq_desc *desc)
{
desc->status_use_accessors |= _IRQ_PER_CPU;
}
static inline void irq_settings_set_no_balancing(struct irq_desc *desc)
{
desc->status_use_accessors |= _IRQ_NO_BALANCING;
}
static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_NO_BALANCING;
}
static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc)
{
return desc->status_use_accessors & IRQ_TYPE_SENSE_MASK;
}
static inline void
irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask)
{
desc->status_use_accessors &= ~IRQ_TYPE_SENSE_MASK;
desc->status_use_accessors |= mask & IRQ_TYPE_SENSE_MASK;
}
static inline bool irq_settings_is_level(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_LEVEL;
}
static inline void irq_settings_clr_level(struct irq_desc *desc)
{
desc->status_use_accessors &= ~_IRQ_LEVEL;
}
static inline void irq_settings_set_level(struct irq_desc *desc)
{
desc->status_use_accessors |= _IRQ_LEVEL;
}
static inline bool irq_settings_can_request(struct irq_desc *desc)
{
return !(desc->status_use_accessors & _IRQ_NOREQUEST);
}
static inline void irq_settings_clr_norequest(struct irq_desc *desc)
{
desc->status_use_accessors &= ~_IRQ_NOREQUEST;
}
static inline void irq_settings_set_norequest(struct irq_desc *desc)
{
desc->status_use_accessors |= _IRQ_NOREQUEST;
}
static inline bool irq_settings_can_thread(struct irq_desc *desc)
{
return !(desc->status_use_accessors & _IRQ_NOTHREAD);
}
static inline void irq_settings_clr_nothread(struct irq_desc *desc)
{
desc->status_use_accessors &= ~_IRQ_NOTHREAD;
}
static inline void irq_settings_set_nothread(struct irq_desc *desc)
{
desc->status_use_accessors |= _IRQ_NOTHREAD;
}
static inline bool irq_settings_can_probe(struct irq_desc *desc)
{
return !(desc->status_use_accessors & _IRQ_NOPROBE);
}
static inline void irq_settings_clr_noprobe(struct irq_desc *desc)
{
desc->status_use_accessors &= ~_IRQ_NOPROBE;
}
static inline void irq_settings_set_noprobe(struct irq_desc *desc)
{
desc->status_use_accessors |= _IRQ_NOPROBE;
}
static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_MOVE_PCNTXT;
}
static inline bool irq_settings_can_autoenable(struct irq_desc *desc)
{
return !(desc->status_use_accessors & _IRQ_NOAUTOEN);
}
static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_NESTED_THREAD;
}
static inline bool irq_settings_is_polled(struct irq_desc *desc)
{
return desc->status_use_accessors & _IRQ_IS_POLLED;
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq/spurious.c
/*
* linux/kernel/irq/spurious.c
*
* Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
*
* This file contains spurious interrupt handling.
*/
#include <linux/jiffies.h>
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
#include <linux/moduleparam.h>
#include <linux/timer.h>
#include "internals.h"
static int irqfixup __read_mostly;
#define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
static void poll_spurious_irqs(unsigned long dummy);
static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0);
static int irq_poll_cpu;
static atomic_t irq_poll_active;
/*
* We wait here for a poller to finish.
*
* If the poll runs on this CPU, then we yell loudly and return
* false. That will leave the interrupt line disabled in the worst
* case, but it should never happen.
*
* We wait until the poller is done and then recheck disabled and
* action (about to be disabled). Only if it's still active, we return
* true and let the handler run.
*/
bool irq_wait_for_poll(struct irq_desc *desc)
{
if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
"irq poll in progress on cpu %d for irq %d\n",
smp_processor_id(), desc->irq_data.irq))
return false;
#ifdef CONFIG_SMP
do {
raw_spin_unlock(&desc->lock);
while (irqd_irq_inprogress(&desc->irq_data))
cpu_relax();
raw_spin_lock(&desc->lock);
} while (irqd_irq_inprogress(&desc->irq_data));
/* Might have been disabled in meantime */
return !irqd_irq_disabled(&desc->irq_data) && desc->action;
#else
return false;
#endif
}
/*
* Recovery handler for misrouted interrupts.
*/
static int try_one_irq(int irq, struct irq_desc *desc, bool force)
{
irqreturn_t ret = IRQ_NONE;
struct irqaction *action;
raw_spin_lock(&desc->lock);
/*
* PER_CPU, nested thread interrupts and interrupts explicitely
* marked polled are excluded from polling.
*/
if (irq_settings_is_per_cpu(desc) ||
irq_settings_is_nested_thread(desc) ||
irq_settings_is_polled(desc))
goto out;
/*
* Do not poll disabled interrupts unless the spurious
* disabled poller asks explicitely.
*/
if (irqd_irq_disabled(&desc->irq_data) && !force)
goto out;
/*
* All handlers must agree on IRQF_SHARED, so we test just the
* first.
*/
action = desc->action;
if (!action || !(action->flags & IRQF_SHARED) ||
(action->flags & __IRQF_TIMER))
goto out;
/* Already running on another processor */
if (irqd_irq_inprogress(&desc->irq_data)) {
/*
* Already running: If it is shared get the other
* CPU to go looking for our mystery interrupt too
*/
desc->istate |= IRQS_PENDING;
goto out;
}
/* Mark it poll in progress */
desc->istate |= IRQS_POLL_INPROGRESS;
do {
if (handle_irq_event(desc) == IRQ_HANDLED)
ret = IRQ_HANDLED;
/* Make sure that there is still a valid action */
action = desc->action;
} while ((desc->istate & IRQS_PENDING) && action);
desc->istate &= ~IRQS_POLL_INPROGRESS;
out:
raw_spin_unlock(&desc->lock);
return ret == IRQ_HANDLED;
}
static int misrouted_irq(int irq)
{
struct irq_desc *desc;
int i, ok = 0;
if (atomic_inc_return(&irq_poll_active) != 1)
goto out;
irq_poll_cpu = smp_processor_id();
for_each_irq_desc(i, desc) {
if (!i)
continue;
if (i == irq) /* Already tried */
continue;
if (try_one_irq(i, desc, false))
ok = 1;
}
out:
atomic_dec(&irq_poll_active);
/* So the caller can adjust the irq error counts */
return ok;
}
static void poll_spurious_irqs(unsigned long dummy)
{
struct irq_desc *desc;
int i;
if (atomic_inc_return(&irq_poll_active) != 1)
goto out;
irq_poll_cpu = smp_processor_id();
for_each_irq_desc(i, desc) {
unsigned int state;
if (!i)
continue;
/* Racy but it doesn't matter */
state = desc->istate;
barrier();
if (!(state & IRQS_SPURIOUS_DISABLED))
continue;
local_irq_disable();
try_one_irq(i, desc, true);
local_irq_enable();
}
out:
atomic_dec(&irq_poll_active);
mod_timer(&poll_spurious_irq_timer,
jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
}
static inline int bad_action_ret(irqreturn_t action_ret)
{
if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
return 0;
return 1;
}
/*
* If 99,900 of the previous 100,000 interrupts have not been handled
* then assume that the IRQ is stuck in some manner. Drop a diagnostic
* and try to turn the IRQ off.
*
* (The other 100-of-100,000 interrupts may have been a correctly
* functioning device sharing an IRQ with the failing one)
*/
static void
__report_bad_irq(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
struct irqaction *action;
unsigned long flags;
if (bad_action_ret(action_ret)) {
printk(KERN_ERR "irq event %d: bogus return value %x\n",
irq, action_ret);
} else {
printk(KERN_ERR "irq %d: nobody cared (try booting with "
"the \"irqpoll\" option)\n", irq);
}
dump_stack();
printk(KERN_ERR "handlers:\n");
/*
* We need to take desc->lock here. note_interrupt() is called
* w/o desc->lock held, but IRQ_PROGRESS set. We might race
* with something else removing an action. It's ok to take
* desc->lock here. See synchronize_irq().
*/
raw_spin_lock_irqsave(&desc->lock, flags);
action = desc->action;
while (action) {
printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler);
if (action->thread_fn)
printk(KERN_CONT " threaded [<%p>] %pf",
action->thread_fn, action->thread_fn);
printk(KERN_CONT "\n");
action = action->next;
}
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
static void
report_bad_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret)
{
static int count = 100;
if (count > 0) {
count--;
__report_bad_irq(irq, desc, action_ret);
}
}
static inline int
try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
struct irqaction *action;
if (!irqfixup)
return 0;
/* We didn't actually handle the IRQ - see if it was misrouted? */
if (action_ret == IRQ_NONE)
return 1;
/*
* But for 'irqfixup == 2' we also do it for handled interrupts if
* they are marked as IRQF_IRQPOLL (or for irq zero, which is the
* traditional PC timer interrupt.. Legacy)
*/
if (irqfixup < 2)
return 0;
if (!irq)
return 1;
/*
* Since we don't get the descriptor lock, "action" can
* change under us. We don't really care, but we don't
* want to follow a NULL pointer. So tell the compiler to
* just load it once by using a barrier.
*/
action = desc->action;
barrier();
return action && (action->flags & IRQF_IRQPOLL);
}
#define SPURIOUS_DEFERRED 0x80000000
void note_interrupt(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
if (desc->istate & IRQS_POLL_INPROGRESS ||
irq_settings_is_polled(desc))
return;
if (bad_action_ret(action_ret)) {
report_bad_irq(irq, desc, action_ret);
return;
}
/*
* We cannot call note_interrupt from the threaded handler
* because we need to look at the compound of all handlers
* (primary and threaded). Aside of that in the threaded
* shared case we have no serialization against an incoming
* hardware interrupt while we are dealing with a threaded
* result.
*
* So in case a thread is woken, we just note the fact and
* defer the analysis to the next hardware interrupt.
*
* The threaded handlers store whether they sucessfully
* handled an interrupt and we check whether that number
* changed versus the last invocation.
*
* We could handle all interrupts with the delayed by one
* mechanism, but for the non forced threaded case we'd just
* add pointless overhead to the straight hardirq interrupts
* for the sake of a few lines less code.
*/
if (action_ret & IRQ_WAKE_THREAD) {
/*
* There is a thread woken. Check whether one of the
* shared primary handlers returned IRQ_HANDLED. If
* not we defer the spurious detection to the next
* interrupt.
*/
if (action_ret == IRQ_WAKE_THREAD) {
int handled;
/*
* We use bit 31 of thread_handled_last to
* denote the deferred spurious detection
* active. No locking necessary as
* thread_handled_last is only accessed here
* and we have the guarantee that hard
* interrupts are not reentrant.
*/
if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) {
desc->threads_handled_last |= SPURIOUS_DEFERRED;
return;
}
/*
* Check whether one of the threaded handlers
* returned IRQ_HANDLED since the last
* interrupt happened.
*
* For simplicity we just set bit 31, as it is
* set in threads_handled_last as well. So we
* avoid extra masking. And we really do not
* care about the high bits of the handled
* count. We just care about the count being
* different than the one we saw before.
*/
handled = atomic_read(&desc->threads_handled);
handled |= SPURIOUS_DEFERRED;
if (handled != desc->threads_handled_last) {
action_ret = IRQ_HANDLED;
/*
* Note: We keep the SPURIOUS_DEFERRED
* bit set. We are handling the
* previous invocation right now.
* Keep it for the current one, so the
* next hardware interrupt will
* account for it.
*/
desc->threads_handled_last = handled;
} else {
/*
* None of the threaded handlers felt
* responsible for the last interrupt
*
* We keep the SPURIOUS_DEFERRED bit
* set in threads_handled_last as we
* need to account for the current
* interrupt as well.
*/
action_ret = IRQ_NONE;
}
} else {
/*
* One of the primary handlers returned
* IRQ_HANDLED. So we don't care about the
* threaded handlers on the same line. Clear
* the deferred detection bit.
*
* In theory we could/should check whether the
* deferred bit is set and take the result of
* the previous run into account here as
* well. But it's really not worth the
* trouble. If every other interrupt is
* handled we never trigger the spurious
* detector. And if this is just the one out
* of 100k unhandled ones which is handled
* then we merily delay the spurious detection
* by one hard interrupt. Not a real problem.
*/
desc->threads_handled_last &= ~SPURIOUS_DEFERRED;
}
}
if (unlikely(action_ret == IRQ_NONE)) {
/*
* If we are seeing only the odd spurious IRQ caused by
* bus asynchronicity then don't eventually trigger an error,
* otherwise the counter becomes a doomsday timer for otherwise
* working systems
*/
if (time_after(jiffies, desc->last_unhandled + HZ/10))
desc->irqs_unhandled = 1;
else
desc->irqs_unhandled++;
desc->last_unhandled = jiffies;
}
if (unlikely(try_misrouted_irq(irq, desc, action_ret))) {
int ok = misrouted_irq(irq);
if (action_ret == IRQ_NONE)
desc->irqs_unhandled -= ok;
}
desc->irq_count++;
if (likely(desc->irq_count < 100000))
return;
desc->irq_count = 0;
if (unlikely(desc->irqs_unhandled > 99900)) {
/*
* The interrupt is stuck
*/
__report_bad_irq(irq, desc, action_ret);
/*
* Now kill the IRQ
*/
printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
desc->istate |= IRQS_SPURIOUS_DISABLED;
desc->depth++;
irq_disable(desc);
mod_timer(&poll_spurious_irq_timer,
jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
}
desc->irqs_unhandled = 0;
}
bool noirqdebug __read_mostly;
int noirqdebug_setup(char *str)
{
noirqdebug = 1;
printk(KERN_INFO "IRQ lockup detection disabled\n");
return 1;
}
__setup("noirqdebug", noirqdebug_setup);
module_param(noirqdebug, bool, 0644);
MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true");
static int __init irqfixup_setup(char *str)
{
irqfixup = 1;
printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
printk(KERN_WARNING "This may impact system performance.\n");
return 1;
}
__setup("irqfixup", irqfixup_setup);
module_param(irqfixup, int, 0644);
static int __init irqpoll_setup(char *str)
{
irqfixup = 2;
printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
"enabled\n");
printk(KERN_WARNING "This may significantly impact system "
"performance\n");
return 1;
}
__setup("irqpoll", irqpoll_setup);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/irq_work.c
/*
* Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
* Provides a framework for enqueueing and running callbacks from hardirq
* context. The enqueueing is NMI-safe.
*/
#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/irq_work.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/tick.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <asm/processor.h>
static DEFINE_PER_CPU(struct llist_head, raised_list);
static DEFINE_PER_CPU(struct llist_head, lazy_list);
/*
* Claim the entry so that no one else will poke at it.
*/
static bool irq_work_claim(struct irq_work *work)
{
unsigned long flags, oflags, nflags;
/*
* Start with our best wish as a premise but only trust any
* flag value after cmpxchg() result.
*/
flags = work->flags & ~IRQ_WORK_PENDING;
for (;;) {
nflags = flags | IRQ_WORK_FLAGS;
oflags = cmpxchg(&work->flags, flags, nflags);
if (oflags == flags)
break;
if (oflags & IRQ_WORK_PENDING)
return false;
flags = oflags;
cpu_relax();
}
return true;
}
void __weak arch_irq_work_raise(void)
{
/*
* Lame architectures will get the timer tick callback
*/
}
#ifdef CONFIG_SMP
/*
* Enqueue the irq_work @work on @cpu unless it's already pending
* somewhere.
*
* Can be re-enqueued while the callback is still in progress.
*/
bool irq_work_queue_on(struct irq_work *work, int cpu)
{
/* All work should have been flushed before going offline */
WARN_ON_ONCE(cpu_is_offline(cpu));
/* Arch remote IPI send/receive backend aren't NMI safe */
WARN_ON_ONCE(in_nmi());
/* Only queue if not already pending */
if (!irq_work_claim(work))
return false;
if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
arch_send_call_function_single_ipi(cpu);
return true;
}
EXPORT_SYMBOL_GPL(irq_work_queue_on);
#endif
/* Enqueue the irq work @work on the current CPU */
bool irq_work_queue(struct irq_work *work)
{
/* Only queue if not already pending */
if (!irq_work_claim(work))
return false;
/* Queue the entry and raise the IPI if needed. */
preempt_disable();
/* If the work is "lazy", handle it from next tick if any */
if (work->flags & IRQ_WORK_LAZY) {
if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
tick_nohz_tick_stopped())
arch_irq_work_raise();
} else {
if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
arch_irq_work_raise();
}
preempt_enable();
return true;
}
EXPORT_SYMBOL_GPL(irq_work_queue);
bool irq_work_needs_cpu(void)
{
struct llist_head *raised, *lazy;
raised = this_cpu_ptr(&raised_list);
lazy = this_cpu_ptr(&lazy_list);
if (llist_empty(raised) || arch_irq_work_has_interrupt())
if (llist_empty(lazy))
return false;
/* All work should have been flushed before going offline */
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
return true;
}
static void irq_work_run_list(struct llist_head *list)
{
unsigned long flags;
struct irq_work *work;
struct llist_node *llnode;
BUG_ON(!irqs_disabled());
if (llist_empty(list))
return;
llnode = llist_del_all(list);
while (llnode != NULL) {
work = llist_entry(llnode, struct irq_work, llnode);
llnode = llist_next(llnode);
/*
* Clear the PENDING bit, after this point the @work
* can be re-used.
* Make it immediately visible so that other CPUs trying
* to claim that work don't rely on us to handle their data
* while we are in the middle of the func.
*/
flags = work->flags & ~IRQ_WORK_PENDING;
xchg(&work->flags, flags);
work->func(work);
/*
* Clear the BUSY bit and return to the free state if
* no-one else claimed it meanwhile.
*/
(void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
}
}
/*
* hotplug calls this through:
* hotplug_cfd() -> flush_smp_call_function_queue()
*/
void irq_work_run(void)
{
irq_work_run_list(this_cpu_ptr(&raised_list));
irq_work_run_list(this_cpu_ptr(&lazy_list));
}
EXPORT_SYMBOL_GPL(irq_work_run);
void irq_work_tick(void)
{
struct llist_head *raised = this_cpu_ptr(&raised_list);
if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
irq_work_run_list(raised);
irq_work_run_list(this_cpu_ptr(&lazy_list));
}
/*
* Synchronize against the irq_work @entry, ensures the entry is not
* currently in use.
*/
void irq_work_sync(struct irq_work *work)
{
WARN_ON_ONCE(irqs_disabled());
while (work->flags & IRQ_WORK_BUSY)
cpu_relax();
}
EXPORT_SYMBOL_GPL(irq_work_sync);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/jump_label.c
/*
* jump label support
*
* Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
* Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com>
*
*/
#include <linux/memory.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/err.h>
#include <linux/static_key.h>
#include <linux/jump_label_ratelimit.h>
#ifdef HAVE_JUMP_LABEL
/* mutex to protect coming/going of the the jump_label table */
static DEFINE_MUTEX(jump_label_mutex);
void jump_label_lock(void)
{
mutex_lock(&jump_label_mutex);
}
void jump_label_unlock(void)
{
mutex_unlock(&jump_label_mutex);
}
static int jump_label_cmp(const void *a, const void *b)
{
const struct jump_entry *jea = a;
const struct jump_entry *jeb = b;
if (jea->key < jeb->key)
return -1;
if (jea->key > jeb->key)
return 1;
return 0;
}
static void
jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
{
unsigned long size;
size = (((unsigned long)stop - (unsigned long)start)
/ sizeof(struct jump_entry));
sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
}
static void jump_label_update(struct static_key *key, int enable);
void static_key_slow_inc(struct static_key *key)
{
STATIC_KEY_CHECK_USE();
if (atomic_inc_not_zero(&key->enabled))
return;
jump_label_lock();
if (atomic_read(&key->enabled) == 0) {
if (!jump_label_get_branch_default(key))
jump_label_update(key, JUMP_LABEL_ENABLE);
else
jump_label_update(key, JUMP_LABEL_DISABLE);
}
atomic_inc(&key->enabled);
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_slow_inc);
static void __static_key_slow_dec(struct static_key *key,
unsigned long rate_limit, struct delayed_work *work)
{
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
WARN(atomic_read(&key->enabled) < 0,
"jump label: negative count!\n");
return;
}
if (rate_limit) {
atomic_inc(&key->enabled);
schedule_delayed_work(work, rate_limit);
} else {
if (!jump_label_get_branch_default(key))
jump_label_update(key, JUMP_LABEL_DISABLE);
else
jump_label_update(key, JUMP_LABEL_ENABLE);
}
jump_label_unlock();
}
static void jump_label_update_timeout(struct work_struct *work)
{
struct static_key_deferred *key =
container_of(work, struct static_key_deferred, work.work);
__static_key_slow_dec(&key->key, 0, NULL);
}
void static_key_slow_dec(struct static_key *key)
{
STATIC_KEY_CHECK_USE();
__static_key_slow_dec(key, 0, NULL);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec);
void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
STATIC_KEY_CHECK_USE();
__static_key_slow_dec(&key->key, key->timeout, &key->work);
}
EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
STATIC_KEY_CHECK_USE();
key->timeout = rl;
INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
}
EXPORT_SYMBOL_GPL(jump_label_rate_limit);
static int addr_conflict(struct jump_entry *entry, void *start, void *end)
{
if (entry->code <= (unsigned long)end &&
entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start)
return 1;
return 0;
}
static int __jump_label_text_reserved(struct jump_entry *iter_start,
struct jump_entry *iter_stop, void *start, void *end)
{
struct jump_entry *iter;
iter = iter_start;
while (iter < iter_stop) {
if (addr_conflict(iter, start, end))
return 1;
iter++;
}
return 0;
}
/*
* Update code which is definitely not currently executing.
* Architectures which need heavyweight synchronization to modify
* running code can override this to make the non-live update case
* cheaper.
*/
void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type)
{
arch_jump_label_transform(entry, type);
}
static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
struct jump_entry *stop, int enable)
{
for (; (entry < stop) &&
(entry->key == (jump_label_t)(unsigned long)key);
entry++) {
/*
* entry->code set to 0 invalidates module init text sections
* kernel_text_address() verifies we are not in core kernel
* init code, see jump_label_invalidate_module_init().
*/
if (entry->code && kernel_text_address(entry->code))
arch_jump_label_transform(entry, enable);
}
}
static enum jump_label_type jump_label_type(struct static_key *key)
{
bool true_branch = jump_label_get_branch_default(key);
bool state = static_key_enabled(key);
if ((!true_branch && state) || (true_branch && !state))
return JUMP_LABEL_ENABLE;
return JUMP_LABEL_DISABLE;
}
void __init jump_label_init(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
struct static_key *key = NULL;
struct jump_entry *iter;
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
struct static_key *iterk;
iterk = (struct static_key *)(unsigned long)iter->key;
arch_jump_label_transform_static(iter, jump_label_type(iterk));
if (iterk == key)
continue;
key = iterk;
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
#ifdef CONFIG_MODULES
key->next = NULL;
#endif
}
static_key_initialized = true;
jump_label_unlock();
}
#ifdef CONFIG_MODULES
struct static_key_mod {
struct static_key_mod *next;
struct jump_entry *entries;
struct module *mod;
};
static int __jump_label_mod_text_reserved(void *start, void *end)
{
struct module *mod;
mod = __module_text_address((unsigned long)start);
if (!mod)
return 0;
WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
return __jump_label_text_reserved(mod->jump_entries,
mod->jump_entries + mod->num_jump_entries,
start, end);
}
static void __jump_label_mod_update(struct static_key *key, int enable)
{
struct static_key_mod *mod = key->next;
while (mod) {
struct module *m = mod->mod;
__jump_label_update(key, mod->entries,
m->jump_entries + m->num_jump_entries,
enable);
mod = mod->next;
}
}
/***
* apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
* @mod: module to patch
*
* Allow for run-time selection of the optimal nops. Before the module
* loads patch these with arch_get_jump_label_nop(), which is specified by
* the arch specific jump label code.
*/
void jump_label_apply_nops(struct module *mod)
{
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
return;
for (iter = iter_start; iter < iter_stop; iter++) {
arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE);
}
}
static int jump_label_add_module(struct module *mod)
{
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct static_key *key = NULL;
struct static_key_mod *jlm;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
return 0;
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
struct static_key *iterk;
iterk = (struct static_key *)(unsigned long)iter->key;
if (iterk == key)
continue;
key = iterk;
if (within_module(iter->key, mod)) {
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
key->next = NULL;
continue;
}
jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
if (!jlm)
return -ENOMEM;
jlm->mod = mod;
jlm->entries = iter;
jlm->next = key->next;
key->next = jlm;
if (jump_label_type(key) == JUMP_LABEL_ENABLE)
__jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE);
}
return 0;
}
static void jump_label_del_module(struct module *mod)
{
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct static_key *key = NULL;
struct static_key_mod *jlm, **prev;
for (iter = iter_start; iter < iter_stop; iter++) {
if (iter->key == (jump_label_t)(unsigned long)key)
continue;
key = (struct static_key *)(unsigned long)iter->key;
if (within_module(iter->key, mod))
continue;
prev = &key->next;
jlm = key->next;
while (jlm && jlm->mod != mod) {
prev = &jlm->next;
jlm = jlm->next;
}
if (jlm) {
*prev = jlm->next;
kfree(jlm);
}
}
}
static void jump_label_invalidate_module_init(struct module *mod)
{
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
for (iter = iter_start; iter < iter_stop; iter++) {
if (within_module_init(iter->code, mod))
iter->code = 0;
}
}
static int
jump_label_module_notify(struct notifier_block *self, unsigned long val,
void *data)
{
struct module *mod = data;
int ret = 0;
switch (val) {
case MODULE_STATE_COMING:
jump_label_lock();
ret = jump_label_add_module(mod);
if (ret)
jump_label_del_module(mod);
jump_label_unlock();
break;
case MODULE_STATE_GOING:
jump_label_lock();
jump_label_del_module(mod);
jump_label_unlock();
break;
case MODULE_STATE_LIVE:
jump_label_lock();
jump_label_invalidate_module_init(mod);
jump_label_unlock();
break;
}
return notifier_from_errno(ret);
}
struct notifier_block jump_label_module_nb = {
.notifier_call = jump_label_module_notify,
.priority = 1, /* higher than tracepoints */
};
static __init int jump_label_init_module(void)
{
return register_module_notifier(&jump_label_module_nb);
}
early_initcall(jump_label_init_module);
#endif /* CONFIG_MODULES */
/***
* jump_label_text_reserved - check if addr range is reserved
* @start: start text addr
* @end: end text addr
*
* checks if the text addr located between @start and @end
* overlaps with any of the jump label patch addresses. Code
* that wants to modify kernel text should first verify that
* it does not overlap with any of the jump label addresses.
* Caller must hold jump_label_mutex.
*
* returns 1 if there is an overlap, 0 otherwise
*/
int jump_label_text_reserved(void *start, void *end)
{
int ret = __jump_label_text_reserved(__start___jump_table,
__stop___jump_table, start, end);
if (ret)
return ret;
#ifdef CONFIG_MODULES
ret = __jump_label_mod_text_reserved(start, end);
#endif
return ret;
}
static void jump_label_update(struct static_key *key, int enable)
{
struct jump_entry *stop = __stop___jump_table;
struct jump_entry *entry = jump_label_get_entries(key);
#ifdef CONFIG_MODULES
struct module *mod;
__jump_label_mod_update(key, enable);
preempt_disable();
mod = __module_address((unsigned long)key);
if (mod)
stop = mod->jump_entries + mod->num_jump_entries;
preempt_enable();
#endif
/* if there are no users, entry can be NULL */
if (entry)
__jump_label_update(key, entry, stop, enable);
}
#endif
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/kallsyms.c
/*
* kallsyms.c: in-kernel printing of symbolic oopses and stack traces.
*
* Rewritten and vastly simplified by Rusty Russell for in-kernel
* module loader:
* Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
*
* ChangeLog:
*
* (25/Aug/2004) Paulo Marques <pmarques@grupopie.com>
* Changed the compression method from stem compression to "table lookup"
* compression (see scripts/kallsyms.c for a more complete description)
*/
#include <linux/kallsyms.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/kdb.h>
#include <linux/err.h>
#include <linux/proc_fs.h>
#include <linux/sched.h> /* for cond_resched */
#include <linux/mm.h>
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/compiler.h>
#include <asm/sections.h>
#ifdef CONFIG_KALLSYMS_ALL
#define all_var 1
#else
#define all_var 0
#endif
/*
* These will be re-linked against their real values
* during the second link stage.
*/
extern const unsigned long kallsyms_addresses[] __weak;
extern const u8 kallsyms_names[] __weak;
/*
* Tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV).
*/
extern const unsigned long kallsyms_num_syms
__attribute__((weak, section(".rodata")));
extern const u8 kallsyms_token_table[] __weak;
extern const u16 kallsyms_token_index[] __weak;
extern const unsigned long kallsyms_markers[] __weak;
static inline int is_kernel_inittext(unsigned long addr)
{
if (addr >= (unsigned long)_sinittext
&& addr <= (unsigned long)_einittext)
return 1;
return 0;
}
static inline int is_kernel_text(unsigned long addr)
{
if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) ||
arch_is_kernel_text(addr))
return 1;
return in_gate_area_no_mm(addr);
}
static inline int is_kernel(unsigned long addr)
{
if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end)
return 1;
return in_gate_area_no_mm(addr);
}
static int is_ksym_addr(unsigned long addr)
{
if (all_var)
return is_kernel(addr);
return is_kernel_text(addr) || is_kernel_inittext(addr);
}
/*
* Expand a compressed symbol data into the resulting uncompressed string,
* if uncompressed string is too long (>= maxlen), it will be truncated,
* given the offset to where the symbol is in the compressed stream.
*/
static unsigned int kallsyms_expand_symbol(unsigned int off,
char *result, size_t maxlen)
{
int len, skipped_first = 0;
const u8 *tptr, *data;
/* Get the compressed symbol length from the first symbol byte. */
data = &kallsyms_names[off];
len = *data;
data++;
/*
* Update the offset to return the offset for the next symbol on
* the compressed stream.
*/
off += len + 1;
/*
* For every byte on the compressed symbol data, copy the table
* entry for that byte.
*/
while (len) {
tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
data++;
len--;
while (*tptr) {
if (skipped_first) {
if (maxlen <= 1)
goto tail;
*result = *tptr;
result++;
maxlen--;
} else
skipped_first = 1;
tptr++;
}
}
tail:
if (maxlen)
*result = '\0';
/* Return to offset to the next symbol. */
return off;
}
/*
* Get symbol type information. This is encoded as a single char at the
* beginning of the symbol name.
*/
static char kallsyms_get_symbol_type(unsigned int off)
{
/*
* Get just the first code, look it up in the token table,
* and return the first char from this token.
*/
return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
}
/*
* Find the offset on the compressed stream given and index in the
* kallsyms array.
*/
static unsigned int get_symbol_offset(unsigned long pos)
{
const u8 *name;
int i;
/*
* Use the closest marker we have. We have markers every 256 positions,
* so that should be close enough.
*/
name = &kallsyms_names[kallsyms_markers[pos >> 8]];
/*
* Sequentially scan all the symbols up to the point we're searching
* for. Every symbol is stored in a [<len>][<len> bytes of data] format,
* so we just need to add the len to the current pointer for every
* symbol we wish to skip.
*/
for (i = 0; i < (pos & 0xFF); i++)
name = name + (*name) + 1;
return name - kallsyms_names;
}
/* Lookup the address for this symbol. Returns 0 if not found. */
unsigned long kallsyms_lookup_name(const char *name)
{
char namebuf[KSYM_NAME_LEN];
unsigned long i;
unsigned int off;
for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
if (strcmp(namebuf, name) == 0)
return kallsyms_addresses[i];
}
return module_kallsyms_lookup_name(name);
}
EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long),
void *data)
{
char namebuf[KSYM_NAME_LEN];
unsigned long i;
unsigned int off;
int ret;
for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
ret = fn(data, namebuf, NULL, kallsyms_addresses[i]);
if (ret != 0)
return ret;
}
return module_kallsyms_on_each_symbol(fn, data);
}
EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol);
static unsigned long get_symbol_pos(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset)
{
unsigned long symbol_start = 0, symbol_end = 0;
unsigned long i, low, high, mid;
/* This kernel should never had been booted. */
BUG_ON(!kallsyms_addresses);
/* Do a binary search on the sorted kallsyms_addresses array. */
low = 0;
high = kallsyms_num_syms;
while (high - low > 1) {
mid = low + (high - low) / 2;
if (kallsyms_addresses[mid] <= addr)
low = mid;
else
high = mid;
}
/*
* Search for the first aliased symbol. Aliased
* symbols are symbols with the same address.
*/
while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low])
--low;
symbol_start = kallsyms_addresses[low];
/* Search for next non-aliased symbol. */
for (i = low + 1; i < kallsyms_num_syms; i++) {
if (kallsyms_addresses[i] > symbol_start) {
symbol_end = kallsyms_addresses[i];
break;
}
}
/* If we found no next symbol, we use the end of the section. */
if (!symbol_end) {
if (is_kernel_inittext(addr))
symbol_end = (unsigned long)_einittext;
else if (all_var)
symbol_end = (unsigned long)_end;
else
symbol_end = (unsigned long)_etext;
}
if (symbolsize)
*symbolsize = symbol_end - symbol_start;
if (offset)
*offset = addr - symbol_start;
return low;
}
/*
* Lookup an address but don't bother to find any names.
*/
int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
unsigned long *offset)
{
char namebuf[KSYM_NAME_LEN];
if (is_ksym_addr(addr))
return !!get_symbol_pos(addr, symbolsize, offset);
return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf);
}
/*
* Lookup an address
* - modname is set to NULL if it's in the kernel.
* - We guarantee that the returned name is valid until we reschedule even if.
* It resides in a module.
* - We also guarantee that modname will be valid until rescheduled.
*/
const char *kallsyms_lookup(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset,
char **modname, char *namebuf)
{
namebuf[KSYM_NAME_LEN - 1] = 0;
namebuf[0] = 0;
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, symbolsize, offset);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
namebuf, KSYM_NAME_LEN);
if (modname)
*modname = NULL;
return namebuf;
}
/* See if it's in a module. */
return module_address_lookup(addr, symbolsize, offset, modname,
namebuf);
}
int lookup_symbol_name(unsigned long addr, char *symname)
{
symname[0] = '\0';
symname[KSYM_NAME_LEN - 1] = '\0';
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, NULL, NULL);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
symname, KSYM_NAME_LEN);
return 0;
}
/* See if it's in a module. */
return lookup_module_symbol_name(addr, symname);
}
int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
unsigned long *offset, char *modname, char *name)
{
name[0] = '\0';
name[KSYM_NAME_LEN - 1] = '\0';
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, size, offset);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
name, KSYM_NAME_LEN);
modname[0] = '\0';
return 0;
}
/* See if it's in a module. */
return lookup_module_symbol_attrs(addr, size, offset, modname, name);
}
/* Look up a kernel symbol and return it in a text buffer. */
static int __sprint_symbol(char *buffer, unsigned long address,
int symbol_offset, int add_offset)
{
char *modname;
const char *name;
unsigned long offset, size;
int len;
address += symbol_offset;
name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
if (!name)
return sprintf(buffer, "0x%lx", address - symbol_offset);
if (name != buffer)
strcpy(buffer, name);
len = strlen(buffer);
offset -= symbol_offset;
if (add_offset)
len += sprintf(buffer + len, "+%#lx/%#lx", offset, size);
if (modname)
len += sprintf(buffer + len, " [%s]", modname);
return len;
}
/**
* sprint_symbol - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name,
* offset, size and module name to @buffer if possible. If no symbol was found,
* just saves its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, 0, 1);
}
EXPORT_SYMBOL_GPL(sprint_symbol);
/**
* sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name
* and module name to @buffer if possible. If no symbol was found, just saves
* its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol_no_offset(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, 0, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
/**
* sprint_backtrace - Look up a backtrace symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function is for stack backtrace and does the same thing as
* sprint_symbol() but with modified/decreased @address. If there is a
* tail-call to the function marked "noreturn", gcc optimized out code after
* the call so that the stack-saved return address could point outside of the
* caller. This function ensures that kallsyms will find the original caller
* by decreasing @address.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_backtrace(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, -1, 1);
}
/* Look up a kernel symbol and print it to the kernel messages. */
void __print_symbol(const char *fmt, unsigned long address)
{
char buffer[KSYM_SYMBOL_LEN];
sprint_symbol(buffer, address);
printk(fmt, buffer);
}
EXPORT_SYMBOL(__print_symbol);
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
struct kallsym_iter {
loff_t pos;
unsigned long value;
unsigned int nameoff; /* If iterating in core kernel symbols. */
char type;
char name[KSYM_NAME_LEN];
char module_name[MODULE_NAME_LEN];
int exported;
};
static int get_ksymbol_mod(struct kallsym_iter *iter)
{
if (module_get_kallsym(iter->pos - kallsyms_num_syms, &iter->value,
&iter->type, iter->name, iter->module_name,
&iter->exported) < 0)
return 0;
return 1;
}
/* Returns space to next name. */
static unsigned long get_ksymbol_core(struct kallsym_iter *iter)
{
unsigned off = iter->nameoff;
iter->module_name[0] = '\0';
iter->value = kallsyms_addresses[iter->pos];
iter->type = kallsyms_get_symbol_type(off);
off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name));
return off - iter->nameoff;
}
static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
{
iter->name[0] = '\0';
iter->nameoff = get_symbol_offset(new_pos);
iter->pos = new_pos;
}
/* Returns false if pos at or past end of file. */
static int update_iter(struct kallsym_iter *iter, loff_t pos)
{
/* Module symbols can be accessed randomly. */
if (pos >= kallsyms_num_syms) {
iter->pos = pos;
return get_ksymbol_mod(iter);
}
/* If we're not on the desired position, reset to new position. */
if (pos != iter->pos)
reset_iter(iter, pos);
iter->nameoff += get_ksymbol_core(iter);
iter->pos++;
return 1;
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
(*pos)++;
if (!update_iter(m->private, *pos))
return NULL;
return p;
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
if (!update_iter(m->private, *pos))
return NULL;
return m->private;
}
static void s_stop(struct seq_file *m, void *p)
{
}
static int s_show(struct seq_file *m, void *p)
{
struct kallsym_iter *iter = m->private;
/* Some debugging symbols have no name. Ignore them. */
if (!iter->name[0])
return 0;
if (iter->module_name[0]) {
char type;
/*
* Label it "global" if it is exported,
* "local" if not exported.
*/
type = iter->exported ? toupper(iter->type) :
tolower(iter->type);
seq_printf(m, "%pK %c %s\t[%s]\n", (void *)iter->value,
type, iter->name, iter->module_name);
} else
seq_printf(m, "%pK %c %s\n", (void *)iter->value,
iter->type, iter->name);
return 0;
}
static const struct seq_operations kallsyms_op = {
.start = s_start,
.next = s_next,
.stop = s_stop,
.show = s_show
};
static int kallsyms_open(struct inode *inode, struct file *file)
{
/*
* We keep iterator in m->private, since normal case is to
* s_start from where we left off, so we avoid doing
* using get_symbol_offset for every symbol.
*/
struct kallsym_iter *iter;
iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter));
if (!iter)
return -ENOMEM;
reset_iter(iter, 0);
return 0;
}
#ifdef CONFIG_KGDB_KDB
const char *kdb_walk_kallsyms(loff_t *pos)
{
static struct kallsym_iter kdb_walk_kallsyms_iter;
if (*pos == 0) {
memset(&kdb_walk_kallsyms_iter, 0,
sizeof(kdb_walk_kallsyms_iter));
reset_iter(&kdb_walk_kallsyms_iter, 0);
}
while (1) {
if (!update_iter(&kdb_walk_kallsyms_iter, *pos))
return NULL;
++*pos;
/* Some debugging symbols have no name. Ignore them. */
if (kdb_walk_kallsyms_iter.name[0])
return kdb_walk_kallsyms_iter.name;
}
}
#endif /* CONFIG_KGDB_KDB */
static const struct file_operations kallsyms_operations = {
.open = kallsyms_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
};
static int __init kallsyms_init(void)
{
proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
return 0;
}
device_initcall(kallsyms_init);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/kcmp.c
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/fdtable.h>
#include <linux/string.h>
#include <linux/random.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/cache.h>
#include <linux/bug.h>
#include <linux/err.h>
#include <linux/kcmp.h>
#include <asm/unistd.h>
/*
* We don't expose the real in-memory order of objects for security reasons.
* But still the comparison results should be suitable for sorting. So we
* obfuscate kernel pointers values and compare the production instead.
*
* The obfuscation is done in two steps. First we xor the kernel pointer with
* a random value, which puts pointer into a new position in a reordered space.
* Secondly we multiply the xor production with a large odd random number to
* permute its bits even more (the odd multiplier guarantees that the product
* is unique ever after the high bits are truncated, since any odd number is
* relative prime to 2^n).
*
* Note also that the obfuscation itself is invisible to userspace and if needed
* it can be changed to an alternate scheme.
*/
static unsigned long cookies[KCMP_TYPES][2] __read_mostly;
static long kptr_obfuscate(long v, int type)
{
return (v ^ cookies[type][0]) * cookies[type][1];
}
/*
* 0 - equal, i.e. v1 = v2
* 1 - less than, i.e. v1 < v2
* 2 - greater than, i.e. v1 > v2
* 3 - not equal but ordering unavailable (reserved for future)
*/
static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
{
long t1, t2;
t1 = kptr_obfuscate((long)v1, type);
t2 = kptr_obfuscate((long)v2, type);
return (t1 < t2) | ((t1 > t2) << 1);
}
/* The caller must have pinned the task */
static struct file *
get_file_raw_ptr(struct task_struct *task, unsigned int idx)
{
struct file *file = NULL;
task_lock(task);
rcu_read_lock();
if (task->files)
file = fcheck_files(task->files, idx);
rcu_read_unlock();
task_unlock(task);
return file;
}
static void kcmp_unlock(struct mutex *m1, struct mutex *m2)
{
if (likely(m2 != m1))
mutex_unlock(m2);
mutex_unlock(m1);
}
static int kcmp_lock(struct mutex *m1, struct mutex *m2)
{
int err;
if (m2 > m1)
swap(m1, m2);
err = mutex_lock_killable(m1);
if (!err && likely(m1 != m2)) {
err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING);
if (err)
mutex_unlock(m1);
}
return err;
}
SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
unsigned long, idx1, unsigned long, idx2)
{
struct task_struct *task1, *task2;
int ret;
rcu_read_lock();
/*
* Tasks are looked up in caller's PID namespace only.
*/
task1 = find_task_by_vpid(pid1);
task2 = find_task_by_vpid(pid2);
if (!task1 || !task2)
goto err_no_task;
get_task_struct(task1);
get_task_struct(task2);
rcu_read_unlock();
/*
* One should have enough rights to inspect task details.
*/
ret = kcmp_lock(&task1->signal->cred_guard_mutex,
&task2->signal->cred_guard_mutex);
if (ret)
goto err;
if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
!ptrace_may_access(task2, PTRACE_MODE_READ)) {
ret = -EPERM;
goto err_unlock;
}
switch (type) {
case KCMP_FILE: {
struct file *filp1, *filp2;
filp1 = get_file_raw_ptr(task1, idx1);
filp2 = get_file_raw_ptr(task2, idx2);
if (filp1 && filp2)
ret = kcmp_ptr(filp1, filp2, KCMP_FILE);
else
ret = -EBADF;
break;
}
case KCMP_VM:
ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM);
break;
case KCMP_FILES:
ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
break;
case KCMP_FS:
ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
break;
case KCMP_SIGHAND:
ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
break;
case KCMP_IO:
ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO);
break;
case KCMP_SYSVSEM:
#ifdef CONFIG_SYSVIPC
ret = kcmp_ptr(task1->sysvsem.undo_list,
task2->sysvsem.undo_list,
KCMP_SYSVSEM);
#else
ret = -EOPNOTSUPP;
#endif
break;
default:
ret = -EINVAL;
break;
}
err_unlock:
kcmp_unlock(&task1->signal->cred_guard_mutex,
&task2->signal->cred_guard_mutex);
err:
put_task_struct(task1);
put_task_struct(task2);
return ret;
err_no_task:
rcu_read_unlock();
return -ESRCH;
}
static __init int kcmp_cookies_init(void)
{
int i;
get_random_bytes(cookies, sizeof(cookies));
for (i = 0; i < KCMP_TYPES; i++)
cookies[i][1] |= (~(~0UL >> 1) | 1);
return 0;
}
arch_initcall(kcmp_cookies_init);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/Kconfig.freezer
config FREEZER
def_bool PM_SLEEP || CGROUP_FREEZER
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/Kconfig.hz
#
# Timer Interrupt Frequency Configuration
#
choice
prompt "Timer frequency"
default HZ_250
help
Allows the configuration of the timer frequency. It is customary
to have the timer interrupt run at 1000 Hz but 100 Hz may be more
beneficial for servers and NUMA systems that do not need to have
a fast response for user interaction and that may experience bus
contention and cacheline bounces as a result of timer interrupts.
Note that the timer interrupt occurs on each processor in an SMP
environment leading to NR_CPUS * HZ number of timer interrupts
per second.
config HZ_100
bool "100 HZ"
help
100 Hz is a typical choice for servers, SMP and NUMA systems
with lots of processors that may show reduced performance if
too many timer interrupts are occurring.
config HZ_250
bool "250 HZ"
help
250 Hz is a good compromise choice allowing server performance
while also showing good interactive responsiveness even
on SMP and NUMA systems. If you are going to be using NTSC video
or multimedia, selected 300Hz instead.
config HZ_300
bool "300 HZ"
help
300 Hz is a good compromise choice allowing server performance
while also showing good interactive responsiveness even
on SMP and NUMA systems and exactly dividing by both PAL and
NTSC frame rates for video and multimedia work.
config HZ_1000
bool "1000 HZ"
help
1000 Hz is the preferred choice for desktop systems and other
systems requiring fast interactive responses to events.
endchoice
config HZ
int
default 100 if HZ_100
default 250 if HZ_250
default 300 if HZ_300
default 1000 if HZ_1000
config SCHED_HRTICK
def_bool HIGH_RES_TIMERS
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/Kconfig.locks
#
# The ARCH_INLINE foo is necessary because select ignores "depends on"
#
config ARCH_INLINE_SPIN_TRYLOCK
bool
config ARCH_INLINE_SPIN_TRYLOCK_BH
bool
config ARCH_INLINE_SPIN_LOCK
bool
config ARCH_INLINE_SPIN_LOCK_BH
bool
config ARCH_INLINE_SPIN_LOCK_IRQ
bool
config ARCH_INLINE_SPIN_LOCK_IRQSAVE
bool
config ARCH_INLINE_SPIN_UNLOCK
bool
config ARCH_INLINE_SPIN_UNLOCK_BH
bool
config ARCH_INLINE_SPIN_UNLOCK_IRQ
bool
config ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
bool
config ARCH_INLINE_READ_TRYLOCK
bool
config ARCH_INLINE_READ_LOCK
bool
config ARCH_INLINE_READ_LOCK_BH
bool
config ARCH_INLINE_READ_LOCK_IRQ
bool
config ARCH_INLINE_READ_LOCK_IRQSAVE
bool
config ARCH_INLINE_READ_UNLOCK
bool
config ARCH_INLINE_READ_UNLOCK_BH
bool
config ARCH_INLINE_READ_UNLOCK_IRQ
bool
config ARCH_INLINE_READ_UNLOCK_IRQRESTORE
bool
config ARCH_INLINE_WRITE_TRYLOCK
bool
config ARCH_INLINE_WRITE_LOCK
bool
config ARCH_INLINE_WRITE_LOCK_BH
bool
config ARCH_INLINE_WRITE_LOCK_IRQ
bool
config ARCH_INLINE_WRITE_LOCK_IRQSAVE
bool
config ARCH_INLINE_WRITE_UNLOCK
bool
config ARCH_INLINE_WRITE_UNLOCK_BH
bool
config ARCH_INLINE_WRITE_UNLOCK_IRQ
bool
config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
bool
config UNINLINE_SPIN_UNLOCK
bool
#
# lock_* functions are inlined when:
# - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y
#
# trylock_* functions are inlined when:
# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
#
# unlock and unlock_irq functions are inlined when:
# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
# or
# - DEBUG_SPINLOCK=n and PREEMPT=n
#
# unlock_bh and unlock_irqrestore functions are inlined when:
# - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
#
if !DEBUG_SPINLOCK
config INLINE_SPIN_TRYLOCK
def_bool y
depends on ARCH_INLINE_SPIN_TRYLOCK
config INLINE_SPIN_TRYLOCK_BH
def_bool y
depends on ARCH_INLINE_SPIN_TRYLOCK_BH
config INLINE_SPIN_LOCK
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK
config INLINE_SPIN_LOCK_BH
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_BH
config INLINE_SPIN_LOCK_IRQ
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQ
config INLINE_SPIN_LOCK_IRQSAVE
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQSAVE
config INLINE_SPIN_UNLOCK_BH
def_bool y
depends on ARCH_INLINE_SPIN_UNLOCK_BH
config INLINE_SPIN_UNLOCK_IRQ
def_bool y
depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ
config INLINE_SPIN_UNLOCK_IRQRESTORE
def_bool y
depends on ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE
config INLINE_READ_TRYLOCK
def_bool y
depends on ARCH_INLINE_READ_TRYLOCK
config INLINE_READ_LOCK
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK
config INLINE_READ_LOCK_BH
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_BH
config INLINE_READ_LOCK_IRQ
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQ
config INLINE_READ_LOCK_IRQSAVE
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQSAVE
config INLINE_READ_UNLOCK
def_bool y
depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK
config INLINE_READ_UNLOCK_BH
def_bool y
depends on ARCH_INLINE_READ_UNLOCK_BH
config INLINE_READ_UNLOCK_IRQ
def_bool y
depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ
config INLINE_READ_UNLOCK_IRQRESTORE
def_bool y
depends on ARCH_INLINE_READ_UNLOCK_IRQRESTORE
config INLINE_WRITE_TRYLOCK
def_bool y
depends on ARCH_INLINE_WRITE_TRYLOCK
config INLINE_WRITE_LOCK
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK
config INLINE_WRITE_LOCK_BH
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_BH
config INLINE_WRITE_LOCK_IRQ
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQ
config INLINE_WRITE_LOCK_IRQSAVE
def_bool y
depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQSAVE
config INLINE_WRITE_UNLOCK
def_bool y
depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK
config INLINE_WRITE_UNLOCK_BH
def_bool y
depends on ARCH_INLINE_WRITE_UNLOCK_BH
config INLINE_WRITE_UNLOCK_IRQ
def_bool y
depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ
config INLINE_WRITE_UNLOCK_IRQRESTORE
def_bool y
depends on ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
endif
config ARCH_SUPPORTS_ATOMIC_RMW
bool
config MUTEX_SPIN_ON_OWNER
def_bool y
depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
config RWSEM_SPIN_ON_OWNER
def_bool y
depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
config LOCK_SPIN_ON_OWNER
def_bool y
depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER
config ARCH_USE_QUEUED_SPINLOCKS
bool
config QUEUED_SPINLOCKS
def_bool y if ARCH_USE_QUEUED_SPINLOCKS
depends on SMP
config ARCH_USE_QUEUED_RWLOCKS
bool
config QUEUED_RWLOCKS
def_bool y if ARCH_USE_QUEUED_RWLOCKS
depends on SMP
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/Kconfig.preempt
choice
prompt "Preemption Model"
default PREEMPT_NONE
config PREEMPT_NONE
bool "No Forced Preemption (Server)"
help
This is the traditional Linux preemption model, geared towards
throughput. It will still provide good latencies most of the
time, but there are no guarantees and occasional longer delays
are possible.
Select this option if you are building a kernel for a server or
scientific/computation system, or if you want to maximize the
raw processing power of the kernel, irrespective of scheduling
latencies.
config PREEMPT_VOLUNTARY
bool "Voluntary Kernel Preemption (Desktop)"
help
This option reduces the latency of the kernel by adding more
"explicit preemption points" to the kernel code. These new
preemption points have been selected to reduce the maximum
latency of rescheduling, providing faster application reactions,
at the cost of slightly lower throughput.
This allows reaction to interactive events by allowing a
low priority process to voluntarily preempt itself even if it
is in kernel mode executing a system call. This allows
applications to run more 'smoothly' even when the system is
under load.
Select this if you are building a kernel for a desktop system.
config PREEMPT
bool "Preemptible Kernel (Low-Latency Desktop)"
select PREEMPT_COUNT
select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
help
This option reduces the latency of the kernel by making
all kernel code (that is not executing in a critical section)
preemptible. This allows reaction to interactive events by
permitting a low priority process to be preempted involuntarily
even if it is in kernel mode executing a system call and would
otherwise not be about to reach a natural preemption point.
This allows applications to run more 'smoothly' even when the
system is under load, at the cost of slightly lower throughput
and a slight runtime overhead to kernel code.
Select this if you are building a kernel for a desktop or
embedded system with latency requirements in the milliseconds
range.
endchoice
config PREEMPT_COUNT
bool
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/kexec.c
/*
* kexec.c - kexec system call
* Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com>
*
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
*/
#define pr_fmt(fmt) "kexec: " fmt
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/kexec.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/reboot.h>
#include <linux/ioport.h>
#include <linux/hardirq.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/utsname.h>
#include <linux/numa.h>
#include <linux/suspend.h>
#include <linux/device.h>
#include <linux/freezer.h>
#include <linux/pm.h>
#include <linux/cpu.h>
#include <linux/console.h>
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/syscore_ops.h>
#include <linux/compiler.h>
#include <linux/hugetlb.h>
#include <asm/page.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/sections.h>
#include <crypto/hash.h>
#include <crypto/sha.h>
/* Per cpu memory for storing cpu states in case of system crash. */
note_buf_t __percpu *crash_notes;
/* vmcoreinfo stuff */
static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
/* Flag to indicate we are going to kexec a new kernel */
bool kexec_in_progress = false;
/*
* Declare these symbols weak so that if architecture provides a purgatory,
* these will be overridden.
*/
char __weak kexec_purgatory[0];
size_t __weak kexec_purgatory_size = 0;
#ifdef CONFIG_KEXEC_FILE
static int kexec_calculate_store_digests(struct kimage *image);
#endif
/* Location of the reserved area for the crash kernel */
struct resource crashk_res = {
.name = "Crash kernel",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
struct resource crashk_low_res = {
.name = "Crash kernel",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
};
int kexec_should_crash(struct task_struct *p)
{
/*
* If crash_kexec_post_notifiers is enabled, don't run
* crash_kexec() here yet, which must be run after panic
* notifiers in panic().
*/
if (crash_kexec_post_notifiers)
return 0;
/*
* There are 4 panic() calls in do_exit() path, each of which
* corresponds to each of these 4 conditions.
*/
if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
return 1;
return 0;
}
/*
* When kexec transitions to the new kernel there is a one-to-one
* mapping between physical and virtual addresses. On processors
* where you can disable the MMU this is trivial, and easy. For
* others it is still a simple predictable page table to setup.
*
* In that environment kexec copies the new kernel to its final
* resting place. This means I can only support memory whose
* physical address can fit in an unsigned long. In particular
* addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
* If the assembly stub has more restrictive requirements
* KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
* defined more restrictively in <asm/kexec.h>.
*
* The code for the transition from the current kernel to the
* the new kernel is placed in the control_code_buffer, whose size
* is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single
* page of memory is necessary, but some architectures require more.
* Because this memory must be identity mapped in the transition from
* virtual to physical addresses it must live in the range
* 0 - TASK_SIZE, as only the user space mappings are arbitrarily
* modifiable.
*
* The assembly stub in the control code buffer is passed a linked list
* of descriptor pages detailing the source pages of the new kernel,
* and the destination addresses of those source pages. As this data
* structure is not used in the context of the current OS, it must
* be self-contained.
*
* The code has been made to work with highmem pages and will use a
* destination page in its final resting place (if it happens
* to allocate it). The end product of this is that most of the
* physical address space, and most of RAM can be used.
*
* Future directions include:
* - allocating a page table with the control code buffer identity
* mapped, to simplify machine_kexec and make kexec_on_panic more
* reliable.
*/
/*
* KIMAGE_NO_DEST is an impossible destination address..., for
* allocating pages whose destination address we do not care about.
*/
#define KIMAGE_NO_DEST (-1UL)
static int kimage_is_destination_range(struct kimage *image,
unsigned long start, unsigned long end);
static struct page *kimage_alloc_page(struct kimage *image,
gfp_t gfp_mask,
unsigned long dest);
static int copy_user_segment_list(struct kimage *image,
unsigned long nr_segments,
struct kexec_segment __user *segments)
{
int ret;
size_t segment_bytes;
/* Read in the segments */
image->nr_segments = nr_segments;
segment_bytes = nr_segments * sizeof(*segments);
ret = copy_from_user(image->segment, segments, segment_bytes);
if (ret)
ret = -EFAULT;
return ret;
}
static int sanity_check_segment_list(struct kimage *image)
{
int result, i;
unsigned long nr_segments = image->nr_segments;
/*
* Verify we have good destination addresses. The caller is
* responsible for making certain we don't attempt to load
* the new image into invalid or reserved areas of RAM. This
* just verifies it is an address we can use.
*
* Since the kernel does everything in page size chunks ensure
* the destination addresses are page aligned. Too many
* special cases crop of when we don't do this. The most
* insidious is getting overlapping destination addresses
* simply because addresses are changed to page size
* granularity.
*/
result = -EADDRNOTAVAIL;
for (i = 0; i < nr_segments; i++) {
unsigned long mstart, mend;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz;
if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
return result;
if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
return result;
}
/* Verify our destination addresses do not overlap.
* If we alloed overlapping destination addresses
* through very weird things can happen with no
* easy explanation as one segment stops on another.
*/
result = -EINVAL;
for (i = 0; i < nr_segments; i++) {
unsigned long mstart, mend;
unsigned long j;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz;
for (j = 0; j < i; j++) {
unsigned long pstart, pend;
pstart = image->segment[j].mem;
pend = pstart + image->segment[j].memsz;
/* Do the segments overlap ? */
if ((mend > pstart) && (mstart < pend))
return result;
}
}
/* Ensure our buffer sizes are strictly less than
* our memory sizes. This should always be the case,
* and it is easier to check up front than to be surprised
* later on.
*/
result = -EINVAL;
for (i = 0; i < nr_segments; i++) {
if (image->segment[i].bufsz > image->segment[i].memsz)
return result;
}
/*
* Verify we have good destination addresses. Normally
* the caller is responsible for making certain we don't
* attempt to load the new image into invalid or reserved
* areas of RAM. But crash kernels are preloaded into a
* reserved area of ram. We must ensure the addresses
* are in the reserved area otherwise preloading the
* kernel could corrupt things.
*/
if (image->type == KEXEC_TYPE_CRASH) {
result = -EADDRNOTAVAIL;
for (i = 0; i < nr_segments; i++) {
unsigned long mstart, mend;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz - 1;
/* Ensure we are within the crash kernel limits */
if ((mstart < crashk_res.start) ||
(mend > crashk_res.end))
return result;
}
}
return 0;
}
static struct kimage *do_kimage_alloc_init(void)
{
struct kimage *image;
/* Allocate a controlling structure */
image = kzalloc(sizeof(*image), GFP_KERNEL);
if (!image)
return NULL;
image->head = 0;
image->entry = &image->head;
image->last_entry = &image->head;
image->control_page = ~0; /* By default this does not apply */
image->type = KEXEC_TYPE_DEFAULT;
/* Initialize the list of control pages */
INIT_LIST_HEAD(&image->control_pages);
/* Initialize the list of destination pages */
INIT_LIST_HEAD(&image->dest_pages);
/* Initialize the list of unusable pages */
INIT_LIST_HEAD(&image->unusable_pages);
return image;
}
static void kimage_free_page_list(struct list_head *list);
static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
unsigned long nr_segments,
struct kexec_segment __user *segments,
unsigned long flags)
{
int ret;
struct kimage *image;
bool kexec_on_panic = flags & KEXEC_ON_CRASH;
if (kexec_on_panic) {
/* Verify we have a valid entry point */
if ((entry < crashk_res.start) || (entry > crashk_res.end))
return -EADDRNOTAVAIL;
}
/* Allocate and initialize a controlling structure */
image = do_kimage_alloc_init();
if (!image)
return -ENOMEM;
image->start = entry;
ret = copy_user_segment_list(image, nr_segments, segments);
if (ret)
goto out_free_image;
ret = sanity_check_segment_list(image);
if (ret)
goto out_free_image;
/* Enable the special crash kernel control page allocation policy. */
if (kexec_on_panic) {
image->control_page = crashk_res.start;
image->type = KEXEC_TYPE_CRASH;
}
/*
* Find a location for the control code buffer, and add it
* the vector of segments so that it's pages will also be
* counted as destination pages.
*/
ret = -ENOMEM;
image->control_code_page = kimage_alloc_control_pages(image,
get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
pr_err("Could not allocate control_code_buffer\n");
goto out_free_image;
}
if (!kexec_on_panic) {
image->swap_page = kimage_alloc_control_pages(image, 0);
if (!image->swap_page) {
pr_err("Could not allocate swap buffer\n");
goto out_free_control_pages;
}
}
*rimage = image;
return 0;
out_free_control_pages:
kimage_free_page_list(&image->control_pages);
out_free_image:
kfree(image);
return ret;
}
#ifdef CONFIG_KEXEC_FILE
static int copy_file_from_fd(int fd, void **buf, unsigned long *buf_len)
{
struct fd f = fdget(fd);
int ret;
struct kstat stat;
loff_t pos;
ssize_t bytes = 0;
if (!f.file)
return -EBADF;
ret = vfs_getattr(&f.file->f_path, &stat);
if (ret)
goto out;
if (stat.size > INT_MAX) {
ret = -EFBIG;
goto out;
}
/* Don't hand 0 to vmalloc, it whines. */
if (stat.size == 0) {
ret = -EINVAL;
goto out;
}
*buf = vmalloc(stat.size);
if (!*buf) {
ret = -ENOMEM;
goto out;
}
pos = 0;
while (pos < stat.size) {
bytes = kernel_read(f.file, pos, (char *)(*buf) + pos,
stat.size - pos);
if (bytes < 0) {
vfree(*buf);
ret = bytes;
goto out;
}
if (bytes == 0)
break;
pos += bytes;
}
if (pos != stat.size) {
ret = -EBADF;
vfree(*buf);
goto out;
}
*buf_len = pos;
out:
fdput(f);
return ret;
}
/* Architectures can provide this probe function */
int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
unsigned long buf_len)
{
return -ENOEXEC;
}
void * __weak arch_kexec_kernel_image_load(struct kimage *image)
{
return ERR_PTR(-ENOEXEC);
}
void __weak arch_kimage_file_post_load_cleanup(struct kimage *image)
{
}
int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
unsigned long buf_len)
{
return -EKEYREJECTED;
}
/* Apply relocations of type RELA */
int __weak
arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
unsigned int relsec)
{
pr_err("RELA relocation unsupported.\n");
return -ENOEXEC;
}
/* Apply relocations of type REL */
int __weak
arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
unsigned int relsec)
{
pr_err("REL relocation unsupported.\n");
return -ENOEXEC;
}
/*
* Free up memory used by kernel, initrd, and command line. This is temporary
* memory allocation which is not needed any more after these buffers have
* been loaded into separate segments and have been copied elsewhere.
*/
static void kimage_file_post_load_cleanup(struct kimage *image)
{
struct purgatory_info *pi = &image->purgatory_info;
vfree(image->kernel_buf);
image->kernel_buf = NULL;
vfree(image->initrd_buf);
image->initrd_buf = NULL;
kfree(image->cmdline_buf);
image->cmdline_buf = NULL;
vfree(pi->purgatory_buf);
pi->purgatory_buf = NULL;
vfree(pi->sechdrs);
pi->sechdrs = NULL;
/* See if architecture has anything to cleanup post load */
arch_kimage_file_post_load_cleanup(image);
/*
* Above call should have called into bootloader to free up
* any data stored in kimage->image_loader_data. It should
* be ok now to free it up.
*/
kfree(image->image_loader_data);
image->image_loader_data = NULL;
}
/*
* In file mode list of segments is prepared by kernel. Copy relevant
* data from user space, do error checking, prepare segment list
*/
static int
kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
const char __user *cmdline_ptr,
unsigned long cmdline_len, unsigned flags)
{
int ret = 0;
void *ldata;
ret = copy_file_from_fd(kernel_fd, &image->kernel_buf,
&image->kernel_buf_len);
if (ret)
return ret;
/* Call arch image probe handlers */
ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
image->kernel_buf_len);
if (ret)
goto out;
#ifdef CONFIG_KEXEC_VERIFY_SIG
ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
image->kernel_buf_len);
if (ret) {
pr_debug("kernel signature verification failed.\n");
goto out;
}
pr_debug("kernel signature verification successful.\n");
#endif
/* It is possible that there no initramfs is being loaded */
if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
ret = copy_file_from_fd(initrd_fd, &image->initrd_buf,
&image->initrd_buf_len);
if (ret)
goto out;
}
if (cmdline_len) {
image->cmdline_buf = kzalloc(cmdline_len, GFP_KERNEL);
if (!image->cmdline_buf) {
ret = -ENOMEM;
goto out;
}
ret = copy_from_user(image->cmdline_buf, cmdline_ptr,
cmdline_len);
if (ret) {
ret = -EFAULT;
goto out;
}
image->cmdline_buf_len = cmdline_len;
/* command line should be a string with last byte null */
if (image->cmdline_buf[cmdline_len - 1] != '\0') {
ret = -EINVAL;
goto out;
}
}
/* Call arch image load handlers */
ldata = arch_kexec_kernel_image_load(image);
if (IS_ERR(ldata)) {
ret = PTR_ERR(ldata);
goto out;
}
image->image_loader_data = ldata;
out:
/* In case of error, free up all allocated memory in this function */
if (ret)
kimage_file_post_load_cleanup(image);
return ret;
}
static int
kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
int initrd_fd, const char __user *cmdline_ptr,
unsigned long cmdline_len, unsigned long flags)
{
int ret;
struct kimage *image;
bool kexec_on_panic = flags & KEXEC_FILE_ON_CRASH;
image = do_kimage_alloc_init();
if (!image)
return -ENOMEM;
image->file_mode = 1;
if (kexec_on_panic) {
/* Enable special crash kernel control page alloc policy. */
image->control_page = crashk_res.start;
image->type = KEXEC_TYPE_CRASH;
}
ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd,
cmdline_ptr, cmdline_len, flags);
if (ret)
goto out_free_image;
ret = sanity_check_segment_list(image);
if (ret)
goto out_free_post_load_bufs;
ret = -ENOMEM;
image->control_code_page = kimage_alloc_control_pages(image,
get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
pr_err("Could not allocate control_code_buffer\n");
goto out_free_post_load_bufs;
}
if (!kexec_on_panic) {
image->swap_page = kimage_alloc_control_pages(image, 0);
if (!image->swap_page) {
pr_err("Could not allocate swap buffer\n");
goto out_free_control_pages;
}
}
*rimage = image;
return 0;
out_free_control_pages:
kimage_free_page_list(&image->control_pages);
out_free_post_load_bufs:
kimage_file_post_load_cleanup(image);
out_free_image:
kfree(image);
return ret;
}
#else /* CONFIG_KEXEC_FILE */
static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
#endif /* CONFIG_KEXEC_FILE */
static int kimage_is_destination_range(struct kimage *image,
unsigned long start,
unsigned long end)
{
unsigned long i;
for (i = 0; i < image->nr_segments; i++) {
unsigned long mstart, mend;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz;
if ((end > mstart) && (start < mend))
return 1;
}
return 0;
}
static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
{
struct page *pages;
pages = alloc_pages(gfp_mask, order);
if (pages) {
unsigned int count, i;
pages->mapping = NULL;
set_page_private(pages, order);
count = 1 << order;
for (i = 0; i < count; i++)
SetPageReserved(pages + i);
}
return pages;
}
static void kimage_free_pages(struct page *page)
{
unsigned int order, count, i;
order = page_private(page);
count = 1 << order;
for (i = 0; i < count; i++)
ClearPageReserved(page + i);
__free_pages(page, order);
}
static void kimage_free_page_list(struct list_head *list)
{
struct list_head *pos, *next;
list_for_each_safe(pos, next, list) {
struct page *page;
page = list_entry(pos, struct page, lru);
list_del(&page->lru);
kimage_free_pages(page);
}
}
static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
unsigned int order)
{
/* Control pages are special, they are the intermediaries
* that are needed while we copy the rest of the pages
* to their final resting place. As such they must
* not conflict with either the destination addresses
* or memory the kernel is already using.
*
* The only case where we really need more than one of
* these are for architectures where we cannot disable
* the MMU and must instead generate an identity mapped
* page table for all of the memory.
*
* At worst this runs in O(N) of the image size.
*/
struct list_head extra_pages;
struct page *pages;
unsigned int count;
count = 1 << order;
INIT_LIST_HEAD(&extra_pages);
/* Loop while I can allocate a page and the page allocated
* is a destination page.
*/
do {
unsigned long pfn, epfn, addr, eaddr;
pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
if (!pages)
break;
pfn = page_to_pfn(pages);
epfn = pfn + count;
addr = pfn << PAGE_SHIFT;
eaddr = epfn << PAGE_SHIFT;
if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
kimage_is_destination_range(image, addr, eaddr)) {
list_add(&pages->lru, &extra_pages);
pages = NULL;
}
} while (!pages);
if (pages) {
/* Remember the allocated page... */
list_add(&pages->lru, &image->control_pages);
/* Because the page is already in it's destination
* location we will never allocate another page at
* that address. Therefore kimage_alloc_pages
* will not return it (again) and we don't need
* to give it an entry in image->segment[].
*/
}
/* Deal with the destination pages I have inadvertently allocated.
*
* Ideally I would convert multi-page allocations into single
* page allocations, and add everything to image->dest_pages.
*
* For now it is simpler to just free the pages.
*/
kimage_free_page_list(&extra_pages);
return pages;
}
static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
unsigned int order)
{
/* Control pages are special, they are the intermediaries
* that are needed while we copy the rest of the pages
* to their final resting place. As such they must
* not conflict with either the destination addresses
* or memory the kernel is already using.
*
* Control pages are also the only pags we must allocate
* when loading a crash kernel. All of the other pages
* are specified by the segments and we just memcpy
* into them directly.
*
* The only case where we really need more than one of
* these are for architectures where we cannot disable
* the MMU and must instead generate an identity mapped
* page table for all of the memory.
*
* Given the low demand this implements a very simple
* allocator that finds the first hole of the appropriate
* size in the reserved memory region, and allocates all
* of the memory up to and including the hole.
*/
unsigned long hole_start, hole_end, size;
struct page *pages;
pages = NULL;
size = (1 << order) << PAGE_SHIFT;
hole_start = (image->control_page + (size - 1)) & ~(size - 1);
hole_end = hole_start + size - 1;
while (hole_end <= crashk_res.end) {
unsigned long i;
if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
break;
/* See if I overlap any of the segments */
for (i = 0; i < image->nr_segments; i++) {
unsigned long mstart, mend;
mstart = image->segment[i].mem;
mend = mstart + image->segment[i].memsz - 1;
if ((hole_end >= mstart) && (hole_start <= mend)) {
/* Advance the hole to the end of the segment */
hole_start = (mend + (size - 1)) & ~(size - 1);
hole_end = hole_start + size - 1;
break;
}
}
/* If I don't overlap any segments I have found my hole! */
if (i == image->nr_segments) {
pages = pfn_to_page(hole_start >> PAGE_SHIFT);
break;
}
}
if (pages)
image->control_page = hole_end;
return pages;
}
struct page *kimage_alloc_control_pages(struct kimage *image,
unsigned int order)
{
struct page *pages = NULL;
switch (image->type) {
case KEXEC_TYPE_DEFAULT:
pages = kimage_alloc_normal_control_pages(image, order);
break;
case KEXEC_TYPE_CRASH:
pages = kimage_alloc_crash_control_pages(image, order);
break;
}
return pages;
}
static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
{
if (*image->entry != 0)
image->entry++;
if (image->entry == image->last_entry) {
kimage_entry_t *ind_page;
struct page *page;
page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
if (!page)
return -ENOMEM;
ind_page = page_address(page);
*image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
image->entry = ind_page;
image->last_entry = ind_page +
((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
}
*image->entry = entry;
image->entry++;
*image->entry = 0;
return 0;
}
static int kimage_set_destination(struct kimage *image,
unsigned long destination)
{
int result;
destination &= PAGE_MASK;
result = kimage_add_entry(image, destination | IND_DESTINATION);
return result;
}
static int kimage_add_page(struct kimage *image, unsigned long page)
{
int result;
page &= PAGE_MASK;
result = kimage_add_entry(image, page | IND_SOURCE);
return result;
}
扫一扫
05-22
1159
1159
10-07
46
46
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
