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, 11 insertions, 6 deletions

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 81904f07679d..a13431ab7c65 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -27,6 +27,7 @@ static int show_stat(struct seq_file *p, void *v)
         u64 sum = 0;
         struct timespec boottime;
         unsigned int per_irq_sum;
+        struct irq_desc *desc;
 
         user = nice = system = idle = iowait =
                 irq = softirq = steal = cputime64_zero;
@@ -44,10 +45,11 @@ static int show_stat(struct seq_file *p, void *v)
                 softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
                 steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
                 guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
-
-                for_each_irq_nr(j)
+                for_each_irq_desc(j, desc) {
+                        if (!desc)
+                                continue;
                         sum += kstat_irqs_cpu(j, i);
-
+                }
                 sum += arch_irq_stat_cpu(i);
         }
         sum += arch_irq_stat();
@@ -90,11 +92,14 @@ static int show_stat(struct seq_file *p, void *v)
         seq_printf(p, "intr %llu", (unsigned long long)sum);
 
         /* sum again ? it could be updated? */
-        for_each_irq_nr(j) {
+        for (j = 0; j < NR_IRQS; j++) {
+                desc = irq_to_desc(j);
                 per_irq_sum = 0;
 
-                for_each_possible_cpu(i)
-                        per_irq_sum += kstat_irqs_cpu(j, i);
+                if (desc) {
+                        for_each_possible_cpu(i)
+                                per_irq_sum += kstat_irqs_cpu(j, i);
+                }
 
                 seq_printf(p, " %u", per_irq_sum);
         }