sparse irq_desc[] array: core kernel and x86 changes

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: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 15 insertions, 0 deletions

diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index cc0f7321b8ce..650ce4102a63 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -40,6 +40,9 @@ unsigned long probe_irq_on(void)
          * flush such a longstanding irq before considering it as spurious.
          */
         for_each_irq_desc_reverse(i, desc) {
+                if (!desc)
+                        continue;
+
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         /*
@@ -68,6 +71,9 @@ unsigned long probe_irq_on(void)
          * happened in the previous stage, it may have masked itself)
          */
         for_each_irq_desc_reverse(i, desc) {
+                if (!desc)
+                        continue;
+
                 spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
@@ -86,6 +92,9 @@ unsigned long probe_irq_on(void)
          * Now filter out any obviously spurious interrupts
          */
         for_each_irq_desc(i, desc) {
+                if (!desc)
+                        continue;
+
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -124,6 +133,9 @@ unsigned int probe_irq_mask(unsigned long val)
         int i;
 
         for_each_irq_desc(i, desc) {
+                if (!desc)
+                        continue;
+
                 spin_lock_irq(&desc->lock);
                 status = desc->status;
 
@@ -166,6 +178,9 @@ int probe_irq_off(unsigned long val)
         unsigned int status;
 
         for_each_irq_desc(i, desc) {
+                if (!desc)
+                        continue;
+
                 spin_lock_irq(&desc->lock);
                 status = desc->status;