On suspend we disable all interrupts in the core code, but this does
not mask the interrupt line in the default implementation as we use a
lazy disable approach. That means we mark the interrupt disabled, but
leave the hardware unmasked. That's an optimization because we avoid
the hardware access for the common case where no interrupt happens
after we marked it disabled. If an interrupt happens, then the
interrupt flow handler masks the line at the hardware level and marks
it pending.

Suspend makes use of this delayed disable as it "disables" all
interrupts when preparing the suspend transition. Right before the
system goes into hardware suspend state it checks whether one of the
interrupts which is marked as a wakeup interrupt came in after
disabling it.

Most interrupt chips have a separate register which selects the
interrupts which can wake up the system from suspend, so we don't have
to mask any on the non wakeup interrupts.

But now we have to deal with brilliant designed hardware which lacks
such a wakeup configuration facility. For such hardware it's necessary
to mask all non wakeup interrupts before going into suspend in order
to avoid the wakeup from random interrupts.

Rather than working around this in the affected interrupt chip
implementations we can solve this elegant in the core code itself.

Add a flag IRQCHIP_MASK_ON_SUSPEND which can be set by the irq chip
implementation to indicate, that the interrupts which are not selected
as wakeup sources must be masked in the suspend path. Mask them in the
loop which checks the wakeup interrupts pending flag.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NAbhijeet Dharmapurikar <adharmap@codeaurora.org>
LKML-Reference: <alpine.LFD.2.00.1103112112310.2787@localhost6.localdomain6>

We have accessors for all fields in irq_data based on irq_desc, but
not for irq_data itself.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Sam Ravnborg <sam@ravnborg.org>

The fasteoi handler must mask the interrupt line in oneshot mode
otherwise we end up with an irq storm.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Add a commandline parameter "threadirqs" which forces all interrupts except
those marked IRQF_NO_THREAD to run threaded. That's mostly a debug option to
allow retrieving better debug data from crashing interrupt handlers. If
"threadirqs" is not enabled on the kernel command line, then there is no
impact in the interrupt hotpath.

Architecture code needs to select CONFIG_IRQ_FORCED_THREADING after
marking the interrupts which cant be threaded IRQF_NO_THREAD. All
interrupts which have IRQF_TIMER set are implict marked
IRQF_NO_THREAD. Also all PER_CPU interrupts are excluded.

Forced threading hard interrupts also forces all soft interrupt
handling into thread context.

When enabled it might slow down things a bit, but for debugging problems in
interrupt code it's a reasonable penalty as it does not immediately
crash and burn the machine when an interrupt handler is buggy.

Some test results on a Core2Duo machine:

Cache cold run of:
 # time git grep irq_desc

      non-threaded       threaded
 real 1m18.741s          1m19.061s
 user 0m1.874s           0m1.757s
 sys  0m5.843s           0m5.427s

 # iperf -c server
non-threaded
[  3]  0.0-10.0 sec  1.09 GBytes   933 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   934 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   933 Mbits/sec
threaded
[  3]  0.0-10.0 sec  1.09 GBytes   939 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   934 Mbits/sec
[  3]  0.0-10.0 sec  1.09 GBytes   937 Mbits/sec
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.772668648@linutronix.de>

When we force thread hard and soft interrupts the startup of ksoftirqd
would hang in kthread_bind() when wait_task_inactive() calls
schedule_timeout_uninterruptible() because there is no softirq yet
which will wake us up.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.677109139@linutronix.de>

Some low level interrupts cannot be threaded even when we force thread
all interrupt handlers. Add a flag to annotate such interrupts. Add
all timer interrupts to this category by default.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.578893460@linutronix.de>

Support ONESHOT on shared interrupts, if all drivers agree on it.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.483640430@linutronix.de>

For level type interrupts we need to track how many threads are on
flight to avoid useless interrupt storms when not all thread handlers
have finished yet. Keep track of the woken threads and only unmask
when there are no more threads in flight.

Yes, I'm lazy and using a bitfield. But not only because I'm lazy, the
main reason is that it's way simpler than using a refcount. A refcount
based solution would need to keep track of various things like
crashing the irq thread, spurious interrupts coming in,
disables/enables, free_irq() and some more. The bitfield keeps the
tracking simple and makes things just work. It's also nicely confined
to the thread code pathes and does not require additional checks all
over the place.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20110223234956.388095876@linutronix.de>

The WARN_ON_ONCE in handle_percpu_event() which emits a warning when
an action handler returns with interrupts enabled is not really
useful. It does not reveal the interrupt number and handler function
which caused it. Make it WARN_ONCE() and add the information.
Reported-by: NTony Luck <tony.luck@intel.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

"def_bool n" without prompt is pointless, these should be just "bool".

[ tglx: Adapted to latest changes ]
Signed-off-by: NJan Beulich <jbeulich@novell.com>
LKML-Reference: <4D5D3309020000780003264A@vpn.id2.novell.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

note_interrupt wants to be called with the combined result of all
handlers called, not with the last one. If it's a shared interrupt
then the last handler might return IRQ_NONE often enough to trigger
the spurious dectector which turns off a perfectly fine working
interrupt line. Bug was introduced in commit 1277a532(genirq: Simplify
handle_irq_event()).

Yes, I really messed up there. First the variable ret should not have
been named differently to avoid similarity with retval. Second it
should have been declared in the do {} loop.

Rename it to res and move it into the do {} loop and vanish under a
huge brown paperbag.
Reported-bisected-tested-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

The switch case in __irq_set_trigger() lacks a break, which emits a
pr_err unconditionally on success.
Reported-by: NLars-Peter Clausen <lars@metafoo.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

The runtime expansion of nr_irqs does not take into account that
bitmap_find_next_zero_area() returns "start" + size in case the search
for an matching zero area fails. That results in a start value which
can be completely off and is not covered by the following
expand_nr_irqs() and possibly outside of the absolute limit. But we
use it without further checking.

Use IRQ_BITMAP_BITS as the limit for the bitmap search and expand
nr_irqs when the start bit is beyond nr_irqs. So start is always
pointing to the correct area in the bitmap. nr_irqs is just the limit
for irq enumerations, not the real limit for the irq space.

[ tglx: Let irq_expand_nr_irqs() take the new upper end so we do not
  	expand nr_irqs more than necessary. Made changelog readable ]
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
LKML-Reference: <4D6014F9.8040605@kernel.org>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

We lazy disable interrupt lines, so only mark the line masked, when
the chip provides an irq_disable callback.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

No need to lookup the irq descriptor when calling from a chip callback
function which has irq_data already handy.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Some chips want irq_eoi() only called when an interrupt is actually
handled. So they have checks for INPROGRESS and DISABLED in their
irq_eoi callbacks. Add a chip flag, which allows to handle that in the
generic code. No impact on the fastpath.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

sparc64 needs to call a preflow handler on certain interrupts befor
calling the action chain. Integrate it into handle_fasteoi_irq. Must
be enabled via CONFIG_IRQ_FASTEOI_PREFLOW. No impact when disabled.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: David S. Miller <davem@davemloft.net>

No need to have separate functions if we have one plus inline wrappers.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Convert the management functions to use the common irq_get/put
function.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Most of the managing functions get the irq descriptor and lock it -
either with or without buslock. Instead of open coding this over and
over provide a common function to do that.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

These transition helpers are stale for years now. Remove them.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

If everything uses the right accessors, then enabling
GENERIC_HARDIRQS_NO_COMPAT should just work. If not it will tell you.

Don't be lazy and use the trick which I use in the core code!

git grep status_use_accessors

will unearth it in a split second. Offenders are tracked down and not
slapped with stinking trouts. This time we use frozen shark for a
better educational value.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Required by x86.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Some irq_chips need to know the state of wakeup mode for
setting the trigger type etc. Reflect it in irq_data state.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

irq_chips, which require to mask the chip before changing the trigger
type should set this flag. So the core takes care of it and the
requirement for looking into desc->status in the chip goes away.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Linus Walleij <linus.walleij@stericsson.com>
Cc: Lars-Peter Clausen <lars@metafoo.de>

Looking through irq_chip implementations I noticed that some of them
have special requirements, like setting the type masked and therefor
fiddle in irq_desc->status. Add a flag field, so the core code can
handle it.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Put the constants into an enum and document them.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Force the usage of wrappers by another nasty CPP substitution.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Use wrappers to keep them away from the core code.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

That's the data structure chip functions get provided. Also allow them
to signal the core code that they updated the flags in irq_data.state
by returning IRQ_SET_MASK_OK_NOCOPY. The default is unchanged.

The type bits should be accessed via:

val = irqd_get_trigger_type(irqdata);
and
irqd_set_trigger_type(irqdata, val);

Coders who access them directly will be tracked down and slapped with
stinking trouts.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Keep status in sync until last abuser is gone.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Add a !desc check while at it.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

That's the right data structure to look at for arch code.

Accessor functions are provided.

	 irqd_is_per_cpu(irqdata);
	 irqd_can_balance(irqdata);

Coders who access them directly will be tracked down and slapped with
stinking trouts.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

It'll break when I'm going to undefine the constants.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Its' too ugly and needs to go. The only users are core code and
parisc. Core code does not need it and parisc gets a new check once
IRQ_PER_CPU is reflected in irq_data.state.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

The saving of this switch is minimal versus the ifdef mess it
creates. Simple enable PER_CPU unconditionally and remove the config
switch.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

chip implementations need to know about it. Keep status in sync until
all users are fixed. 

Accessor function: irqd_is_setaffinity_pending(irqdata)

Coders who access them directly will be tracked down and slapped with
stinking trouts.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Some chip implementations need to access certain status flags. With
sparse irqs that requires a lookup of the irq descriptor. Add a state
field which contains such flags.

Name it in a way which will make coders happy to access it with the
proper accessor functions. And it's easy to grep for.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>