[PATCH] more for_each_cpu() conversions

When we stop allocating percpu memory for not-possible CPUs we must not touch
the percpu data for not-possible CPUs at all.  The correct way of doing this
is to test cpu_possible() or to use for_each_cpu().

This patch is a kernel-wide sweep of all instances of NR_CPUS.  I found very
few instances of this bug, if any.  But the patch converts lots of open-coded
test to use the preferred helper macros.

Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Kyle McMartin <kyle@parisc-linux.org>
Cc: Anton Blanchard <anton@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Christian Zankel <chris@zankel.net>
Cc: Philippe Elie <phil.el@wanadoo.fr>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Jens Axboe <axboe@suse.de>
Cc: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 12 insertions, 18 deletions

diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
index e11a09207ec8..3d5110b65cc3 100644
--- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
@@ -1145,9 +1145,7 @@ static int __cpuinit powernowk8_init(void)
 {
         unsigned int i, supported_cpus = 0;
 
-        for (i=0; i<NR_CPUS; i++) {
-                if (!cpu_online(i))
-                        continue;
+        for_each_cpu(i) {
                 if (check_supported_cpu(i))
                         supported_cpus++;
         }
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index fd1c60cfd294..311b4e7266f1 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -351,8 +351,8 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 {
         int i, j;
         Dprintk("Rotating IRQs among CPUs.\n");
-        for (i = 0; i < NR_CPUS; i++) {
-                for (j = 0; cpu_online(i) && (j < NR_IRQS); j++) {
+        for_each_online_cpu(i) {
+                for (j = 0; j < NR_IRQS; j++) {
                         if (!irq_desc[j].action)
                                 continue;
                         /* Is it a significant load ?  */
@@ -381,7 +381,7 @@ static void do_irq_balance(void)
         unsigned long imbalance = 0;
         cpumask_t allowed_mask, target_cpu_mask, tmp;
 
-        for (i = 0; i < NR_CPUS; i++) {
+        for_each_cpu(i) {
                 int package_index;
                 CPU_IRQ(i) = 0;
                 if (!cpu_online(i))
@@ -422,9 +422,7 @@ static void do_irq_balance(void)
                 }
         }
         /* Find the least loaded processor package */
-        for (i = 0; i < NR_CPUS; i++) {
-                if (!cpu_online(i))
-                        continue;
+        for_each_online_cpu(i) {
                 if (i != CPU_TO_PACKAGEINDEX(i))
                         continue;
                 if (min_cpu_irq > CPU_IRQ(i)) {
@@ -441,9 +439,7 @@ tryanothercpu:
          */
         tmp_cpu_irq = 0;
         tmp_loaded = -1;
-        for (i = 0; i < NR_CPUS; i++) {
-                if (!cpu_online(i))
-                        continue;
+        for_each_online_cpu(i) {
                 if (i != CPU_TO_PACKAGEINDEX(i))
                         continue;
                 if (max_cpu_irq <= CPU_IRQ(i)) 
@@ -619,9 +615,7 @@ static int __init balanced_irq_init(void)
         if (smp_num_siblings > 1 && !cpus_empty(tmp))
                 physical_balance = 1;
 
-        for (i = 0; i < NR_CPUS; i++) {
-                if (!cpu_online(i))
-                        continue;
+        for_each_online_cpu(i) {
                 irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
                 irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
                 if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
@@ -638,9 +632,11 @@ static int __init balanced_irq_init(void)
         else 
                 printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq");
 failed:
-        for (i = 0; i < NR_CPUS; i++) {
+        for_each_cpu(i) {
                 kfree(irq_cpu_data[i].irq_delta);
+                irq_cpu_data[i].irq_delta = NULL;
                 kfree(irq_cpu_data[i].last_irq);
+                irq_cpu_data[i].last_irq = NULL;
         }
         return 0;
 }
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 1db34effdd8d..9074818b9473 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -143,7 +143,7 @@ static int __init check_nmi_watchdog(void)
         local_irq_enable();
         mdelay((10*1000)/nmi_hz); // wait 10 ticks
 
-        for (cpu = 0; cpu < NR_CPUS; cpu++) {
+        for_each_cpu(cpu) {
 #ifdef CONFIG_SMP
                 /* Check cpu_callin_map here because that is set
                    after the timer is started. */
@@ -510,7 +510,7 @@ void touch_nmi_watchdog (void)
          * Just reset the alert counters, (other CPUs might be
          * spinning on locks we hold):
          */
-        for (i = 0; i < NR_CPUS; i++)
+        for_each_cpu(i)
                 alert_counter[i] = 0;
 
         /*