When registering irq chip drivers, one common requirement is to
specify the irq_domain irq_base and nr_irq. These fields represent
the system wide logical interrupt range the domain occupies.
For systems with only one interrupt controller, it's trivial to
know these values. But for systems with several irq chip drivers,
it becomes painful to keep track of interrupt ranges in platform
defines. These create needless compile time dependencies, of
which the Device Tree aims to solve.
irq_alloc_desc() can search for a free irq, but is very
inefficient for determining the availability of large ranges.
Additionally, some irq chip drivers allocate irq descriptors
lazily. For example, portions of the Device Tree may not be parsed
until a particular bus is probed. But of_irq_init() is intended to
be run at init time, and this is a natural time to allocate irq
domains. Thus by the time we allocate our irq descriptors, we already
need to know a range of acceptable irqs to use for the domain.
To solve these problems, let's introduce
irq_domain_find_free_range(), which will return to the caller the
first available irq domain range not used already by the system.
This range can then be specified with irq_domain_add().
Change-Id: I8b0f5d25b173c76b8fc5d4f46b3fe9c6bf5c3c8f
Signed-off-by: Michael Bohan <mbohan@codeaurora.org>
It should not be valid to add an irq_domain with a logical irq
range that overlaps with another already registered to the
system. Return an error on such an occurrence.
This change also inherently sorts the irq_domains by logical
irq_base as they are added.
Change-Id: Idef697dbe4584d783703d053fbf09f1b17e62ab0
Signed-off-by: Michael Bohan <mbohan@codeaurora.org>
The current irq_domain_add() design assumes the underlying
irq_descs are valid when irq_domain_add() is called. It also
assumes that every hwirq enlisted in the irq_domain is valid.
Often, these assumptions are not correct.
Typically, irq_domain_add() is called at board_init time, but
sometimes interrupt chip drivers are not initialized until an
underlying bus is probed. When using SPARSE_IRQ, it's quite
natural to hold off allocating irq_descs until the board
topology specifies them as included.
And in such device topologies, there's no guarantee that chip
interrupt numbers will be contiguous. For example, each hwirq may
map to a particular device, but that device may or may not be
present in the actual hardware configuration. In order to support
this, we need the concept of an irq_domain that supports holes
in it.
In order to solve these problems, let's break the irq_domain
creation from the irq registration process. The irq_domain
creation can occur at init time and then have no dependencies. An
interrupt is not 'registered' with the domain until its resources
have already been allocated by the chip driver. For simple cases,
an additional API is provided to register the entire
logical irq_domain range to provide feature parity with what
already exists.
Change-Id: Ie3340d07ba8663196dc87d1185e3bb7fbed4be4d
Signed-off-by: Michael Bohan <mbohan@codeaurora.org>
Interrupt controllers can have non-zero starting value for h/w irq numbers.
Adding support in irq_domain allows the domain hwirq numbering to match
the interrupt controllers' numbering.
As this makes looping over irqs for a domain more complicated, add loop
iterators to iterate over all hwirqs and irqs for a domain.
Change-Id: I64774aea2f3efb883fe11e9f6161970f7e7dc0fc
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Reviewed-by: Jamie Iles <jamie@jamieiles.com>
Tested-by: Thomas Abraham <thomas.abraham@linaro.org>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Trilok Soni <tsoni@codeaurora.org>
irq_domain_generate_simple() is an easy way to generate an irq translation
domain for simple irq controllers. It assumes a flat 1:1 mapping from
hardware irq number to an offset of the first linux irq number assigned
to the controller
Change-Id: I0820754314a0c15b1cc9881bc38b75b0de2509b2
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Sathish Ambley <sambley@codeaurora.org>
This patch adds irq_domain infrastructure for translating from
hardware irq numbers to linux irqs. This is particularly important
for architectures adding device tree support because the current
implementation (excluding PowerPC and SPARC) cannot handle
translation for more than a single interrupt controller. irq_domain
supports device tree translation for any number of interrupt
controllers.
This patch converts x86, Microblaze, ARM and MIPS to use irq_domain
for device tree irq translation. x86 is untested beyond compiling it,
irq_domain is enabled for MIPS and Microblaze, but the old behaviour is
preserved until the core code is modified to actually register an
irq_domain yet. On ARM it works and is required for much of the new
ARM device tree board support.
PowerPC has /not/ been converted to use this new infrastructure. It
is still missing some features before it can replace the virq
infrastructure already in powerpc (see documentation on
irq_domain_map/unmap for details). Followup patches will add the
missing pieces and migrate PowerPC to use irq_domain.
SPARC has its own method of managing interrupts from the device tree
and is unaffected by this change.
Change-Id: Ia5fa674a97c85e2fc8e30275753b1494a97bd1d9
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Sathish Ambley <sambley@codeaurora.org>
