Impact: save RAM with large NR_CPUS, get smaller nr_irqs
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NMike Travis <travis@sgi.com>

Ingo Molnar wrote:

> All non-x86 architectures fail to build:
>
> In file included from /home/mingo/tip/include/linux/random.h:11,
>                  from /home/mingo/tip/include/linux/stackprotector.h:6,
>                  from /home/mingo/tip/init/main.c:17:
> /home/mingo/tip/include/linux/irqnr.h:26:63: error: asm/irq_vectors.h: No such file or directory

Do not include asm/irq_vectors.h in generic code - it's not available
on all architectures.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: reduce memory usage.

Allocate kstat_irqs_legacy based on nr_cpu_ids to deal with this
memory usage bump when NR_CPUS bumped from 128 to 4096:

     8192   +253952    262144 +3100%  kstat_irqs_legacy(.bss)

This is only when CONFIG_SPARSE_IRQS=y.
Signed-off-by: NMike Travis <travis@sgi.com>

Impact: Reduce memory usage.

This is the second half of the changes to make the irq_desc_ptrs be
variable sized based on nr_cpu_ids.  This is done by adding a new
"max_nr_irqs" macro to irq_vectors.h (and a dummy in irqnr.h) to
return a max NR_IRQS value based on NR_CPUS or nr_cpu_ids.

This necessitated moving the define of MAX_IO_APICS to a separate
file (asm/apicnum.h) so it could be included without the baggage
of the other asm/apicdef.h declarations.
Signed-off-by: NMike Travis <travis@sgi.com>

Impact: allocate irq_desc_ptrs in preparation for making it variable-sized.

This addresses this memory usage bump when NR_CPUS bumped from 128 to 4096:

    34816   +229376    264192  +658%  irq_desc_ptrs(.data.read_mostly)

The patch is split into two parts, the first simply allocates the
irq_desc_ptrs array.  Then next will deal with making it variable.
This is only when CONFIG_SPARSE_IRQS=y.
Signed-off-by: NMike Travis <travis@sgi.com>

Impact: cleanup WARN msg.

Ingo requested:
> While at it, could you please also convert this to a WARN() construct
> instead? (in a separate commit)

... and it shall be done.  ;-)
Signed-off-by: NMike Travis <travis@sgi.com>

Impact: preparation, cleanup, add KERN_INFO printk

Modify references from NR_IRQS to nr_irqs as the later will become
variable-sized based on nr_cpu_ids when CONFIG_SPARSE_IRQS=y.
Signed-off-by: NMike Travis <travis@sgi.com>

Impact: fix bug where new irq_desc uses old cpumask pointers which are freed.

As Yinghai pointed out, init_copy_one_irq_desc() copies the old desc to
the new desc overwriting the cpumask pointers.  Since the old_desc and
the cpumask pointers are freed, then memory corruption will occur if
these old pointers are used.

Move the allocation of these pointers to after the copy.
Signed-off-by: NMike Travis <travis@sgi.com>
Cc: Yinghai Lu <yinghai@kernel.org>

Impact: reduce memory usage, use new cpumask API.

Replace the affinity and pending_masks with cpumask_var_t's.  This adds
to the significant size reduction done with the SPARSE_IRQS changes.

The added functions (init_alloc_desc_masks & init_copy_desc_masks) are
in the include file so they can be inlined (and optimized out for the
!CONFIG_CPUMASKS_OFFSTACK case.)  [Naming chosen to be consistent with
the other init*irq functions, as well as the backwards arg declaration
of "from, to" instead of the more common "to, from" standard.]

Includes a slight change to the declaration of struct irq_desc to embed
the pending_mask within ifdef(CONFIG_SMP) to be consistent with other
references, and some small changes to Xen.

Tested: sparse/non-sparse/cpumask_offstack/non-cpumask_offstack/nonuma/nosmp on x86_64
Signed-off-by: NMike Travis <travis@sgi.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: virtualization@lists.osdl.org
Cc: xen-devel@lists.xensource.com
Cc: Yinghai Lu <yhlu.kernel@gmail.com>

Impact: fix boot crash if the kernel is built with certain GCC versions

GCC has a bug with __weak alias functions: if the functions are in
the same compilation unit as their call site, GCC can decide to
inline them - and thus rob the linker of the opportunity to override
the weak alias with the real thing.

This can lead to the boot crash reported by Kamalesh Babulal:

 ACPI: Core revision 20080926
 Setting APIC routing to flat
 BUG: unable to handle kernel NULL pointer dereference at
 0000000000000000
 IP: [<ffffffff8021f9a8>] add_pin_to_irq_cpu+0x14/0x74
 PGD 0
 Oops: 0000 [#1] SMP
 [...]

So move the arch_init_chip_data() function from handle.c to manage.c.
Reported-by: NKamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix hang

Suresh report his two sockets system only works with SPARSE_IRQ enable
it turns out we miss the setting desc->irq

so provide early_irq_init() even !SPARSE_IRQ to set desc->irq
Reported-by: N"Siddha, Suresh B" <suresh.b.siddha@intel.com>
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: add lockdep annotation to legacy IRQ descs

Warnings resulting out of this were not seen in practice, but it's prudent
to initialize the legacy descriptors to the lock class as well, symmetric
to how we do it with other descriptors.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix panic on null pointer with sparseirq

Some GCC versions seem to inline the weak global function,
when that function is empty.

Work it around, by making the functions return a (dummy) integer.
Signed-off-by: NYinghai <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

init_one_irq_desc() does not initialize the desc->lock properly -
you cannot init a lock by memcpying some other lock on it.

This happens to work right now (because irq_desc_init is never in use),
but it's a dangerous construct nevertheless, so fix it.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: clean up

We already have a weak copy of this function in init/main.c
Signed-off-by: NYinghai <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

all for_each_irq_desc() usage point have !desc check.
then its check can move into for_each_irq_desc() macro.
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

irq_desc can be NULL when CONFIG_SPARSE_IRQ=y only.
therefore, NULL checking can move into kstat_irqs_cpu() of SPARSE_IRQ version.
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: N"Yinghai Lu" <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

before CONFIG_SPARSE_IRQ age, for_each_irq_desc() sat in irqnr.h and
could be called from generic code.

CONFIG_SPARSE_IRQ breaks this assumption, but SPARSE_IRQ version
for_each_irq_desc() also can move into irqnr.h easily.

Also, this patch unifies CONFIG_SPARSE_IRQ and !CONFIG_SPARSE_IRQ
for_each_irq_desc().
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: simplify code

commit "08678b08: generic: sparse irqs: use irq_desc() [...]" introduced
the irq_desc_lock_class variable.

But it is used only if CONFIG_SPARSE_IRQ=Y or CONFIG_TRACE_IRQFLAGS=Y.
Otherwise, following warnings happen:

	CC      kernel/irq/handle.o
	kernel/irq/handle.c:26: warning: 'irq_desc_lock_class' defined but not used

Actually, current early_init_irq_lock_class has a bit strange and messy ifdef.
In addition, it is not valueable.

1. this function is protected by !CONFIG_SPARSE_IRQ, but that is not necessary.
   if CONFIG_SPARSE_IRQ=Y, desc of all irq number are initialized by NULL
   at first - then this function calling is safe.

2. this function protected by CONFIG_TRACE_IRQFLAGS too. but it is not
   necessary either, because lockdep_set_class() doesn't have bad side
   effect even if CONFIG_TRACE_IRQFLAGS=n.

This patch bloat kernel size a bit on CONFIG_TRACE_IRQFLAGS=n and
CONFIG_SPARSE_IRQ=Y - but that's ok. early_init_irq_lock_class() is not
a fastpatch at all.

To avoid messy ifdefs is more important than a few bytes diet.
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: improve NUMA handling by migrating irq_desc on smp_affinity changes

if CONFIG_NUMA_MIGRATE_IRQ_DESC is set:

-  make irq_desc to go with affinity aka irq_desc moving etc
-  call move_irq_desc in irq_complete_move()
-  legacy irq_desc is not moved, because they are allocated via static array

for logical apic mode, need to add move_desc_in_progress_in_same_domain,
otherwise it will not be moved ==> also could need two phases to get
irq_desc moved.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

Introduce NR_IRQS_LEGACY instead of hard coded number.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: new feature

Problem on distro kernels: irq_desc[NR_IRQS] takes megabytes of RAM with
NR_CPUS set to large values. The goal is to be able to scale up to much
larger NR_IRQS value without impacting the (important) common case.

To solve this, we generalize irq_desc[NR_IRQS] to an (optional) array of
irq_desc pointers.

When CONFIG_SPARSE_IRQ=y is used, we use kzalloc_node to get irq_desc,
this also makes the IRQ descriptors NUMA-local (to the site that calls
request_irq()).

This gets rid of the irq_cfg[] static array on x86 as well: irq_cfg now
uses desc->chip_data for x86 to store irq_cfg.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Use for_each_irq_desc[_reverse] for all the iteration loops.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

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

Revert the dynarray changes. They need more thought and polishing.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

This code is not ready, but we need to rip it out instead of rebasing
as we would lose the APIC/IO_APIC unification otherwise.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

For the non sparse irq case an inline function is perfectly fine.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

when SPARSE_IRQ is not used, should still use irq_desc->lock
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

caused by

commit a532e19680ada3b8579b81e67e76d3ebd19c340f
Author: Yinghai Lu <yhlu.kernel@gmail.com>
Date:   Wed Aug 20 20:46:25 2008 -0700

    x86: sparse_irq needs spin_lock in allocations
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

fix non-sparseirq architectures.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Suresh Siddha noticed that we should have a spinlock around it.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

-tip testing found this lockdep splat:

[    0.000000] Initializing CPU#0
[    0.000000] found new irq_desc for irq 0
[    0.000000] INFO: trying to register non-static key.
[    0.000000] the code is fine but needs lockdep annotation.
[    0.000000] turning off the locking correctness validator.
[    0.000000] Pid: 0, comm: swapper Not tainted 2.6.27-rc3-tip-00191-g98ccb89-dirty #1
[    0.000000]  [<c0153c22>] register_lock_class+0x3d2/0x400
[    0.000000]  [<c0104d87>] ? mcount_call+0x5/0xa
[    0.000000]  [<c0154f3a>] __lock_acquire+0x22a/0x5d0
[    0.000000]  [<c0104d87>] ? mcount_call+0x5/0xa
[    0.000000]  [<c0155351>] lock_acquire+0x71/0xa0
[    0.000000]  [<c016d61f>] ? set_irq_chip+0x3f/0x90
[    0.000000]  [<c070f148>] _spin_lock_irqsave+0x58/0x90
[    0.000000]  [<c016d61f>] ? set_irq_chip+0x3f/0x90
[    0.000000]  [<c016d61f>] set_irq_chip+0x3f/0x90
[    0.000000]  [<c016d7e0>] ? handle_level_irq+0x0/0xe0
[    0.000000]  [<c016da1a>] set_irq_chip_and_handler_name+0x1a/0x40
[    0.000000]  [<c0a396c1>] init_ISA_irqs+0x51/0xa0
[    0.000000]  [<c0a4a365>] pre_intr_init_hook+0x25/0x30
[    0.000000]  [<c0a39723>] native_init_IRQ+0x13/0x370
[    0.000000]  [<c015569c>] ? lock_release+0xcc/0x1d0
[    0.000000]  [<c0104d87>] ? mcount_call+0x5/0xa
[    0.000000]  [<c070dc22>] ? __mutex_unlock_slowpath+0x92/0x110
[    0.000000]  [<c070dcad>] ? mutex_unlock+0xd/0x10
[    0.000000]  [<c0135f62>] ? cpu_maps_update_done+0x12/0x20
[    0.000000]  [<c06c6743>] ? register_cpu_notifier+0x23/0x30
[    0.000000]  [<c011e8ae>] init_IRQ+0xe/0x10
[    0.000000]  [<c0a357a5>] start_kernel+0x1c5/0x340
[    0.000000]  [<c0a35280>] ? unknown_bootoption+0x0/0x210
[    0.000000]  [<c0a3506b>] i386_start_kernel+0x6b/0x80
[    0.000000]  =======================
[    0.000000] found new irq_desc for irq 1
[    0.000000] found new irq_desc for irq 2
[    0.000000] found new irq_desc for irq 3

this:

 static void init_one_irq_desc(struct irq_desc *desc)
 {
         memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
 #ifdef CONFIG_TRACE_IRQFLAGS
         lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 #endif
 }

should be unconditional.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

so later don't need compare with -1U
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

change names:

          irq_desc() ==> irq_desc_alloc
	__irq_desc() ==> irq_desc

Also split a few of the uses in lowlevel x86 code.

v2: need to check if desc is null in smp_irq_move_cleanup
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

So we could remove some duplicated calling to irq_desc

v2: make sure irq_desc in  init/main.c is not used without generic_hardirqs
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

add an irq_desc accessor that will not allocate any sparse entry
but returns failure if there's no entry present.
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

based on Eric's patch ...

together mold it with dyn_array for irq_desc, will allcate kstat_irqs for
nr_irq_desc alltogether if needed. -- at that point nr_cpus is known already.

v2: make sure system without generic_hardirqs works they don't have irq_desc
v3: fix merging
v4: [mingo@elte.hu] fix typo

[ mingo@elte.hu ] irq: build fix

fix:

 arch/x86/xen/spinlock.c: In function 'xen_spin_lock_slow':
 arch/x86/xen/spinlock.c:90: error: 'struct kernel_stat' has no member named 'irqs'
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

add CONFIG_HAVE_SPARSE_IRQ to for use condensed array.
Get rid of irq_desc[] array assumptions.

Preallocate 32 irq_desc, and irq_desc() will try to get more.

( No change in functionality is expected anywhere, except the odd build
  failure where we missed a code site or where a crossing commit itroduces
  new irq_desc[] usage. )

v2: according to Eric, change get_irq_desc() to irq_desc()
Signed-off-by: NYinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

fix:

  Building modules, stage 2.
  MODPOST 458 modules
  ERROR: "nr_irqs" [drivers/serial/8250.ko] undefined!
Signed-off-by: NIngo Molnar <mingo@elte.hu>