[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>
diff --git a/include/asm-alpha/mmu_context.h b/include/asm-alpha/mmu_context.h
index 6f92482..0c017fc 100644
--- a/include/asm-alpha/mmu_context.h
+++ b/include/asm-alpha/mmu_context.h
@@ -231,9 +231,8 @@
 {
 	int i;
 
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_online(i))
-			mm->context[i] = 0;
+	for_each_online_cpu(i)
+		mm->context[i] = 0;
 	if (tsk != current)
 		task_thread_info(tsk)->pcb.ptbr
 		  = ((unsigned long)mm->pgd - IDENT_ADDR) >> PAGE_SHIFT;
diff --git a/include/asm-alpha/topology.h b/include/asm-alpha/topology.h
index eb740e2..420ccde 100644
--- a/include/asm-alpha/topology.h
+++ b/include/asm-alpha/topology.h
@@ -27,8 +27,8 @@
 	cpumask_t node_cpu_mask = CPU_MASK_NONE;
 	int cpu;
 
-	for(cpu = 0; cpu < NR_CPUS; cpu++) {
-		if (cpu_online(cpu) && (cpu_to_node(cpu) == node))
+	for_each_online_cpu(cpu) {
+		if (cpu_to_node(cpu) == node)
 			cpu_set(cpu, node_cpu_mask);
 	}
 
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 9044aeb..78cf455 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -19,10 +19,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset[__i],	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset[__i],		\
+		       (src), (size));				\
 } while (0)
 #else /* ! SMP */
 
diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h
index e31922c..464301c 100644
--- a/include/asm-powerpc/percpu.h
+++ b/include/asm-powerpc/percpu.h
@@ -27,10 +27,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 
 extern void setup_per_cpu_areas(void);
diff --git a/include/asm-s390/percpu.h b/include/asm-s390/percpu.h
index 123fcac..e10ed87 100644
--- a/include/asm-s390/percpu.h
+++ b/include/asm-s390/percpu.h
@@ -46,10 +46,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset[__i],	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset[__i],		\
+		       (src), (size));				\
 } while (0)
 
 #else /* ! SMP */
diff --git a/include/asm-sparc64/percpu.h b/include/asm-sparc64/percpu.h
index aea4e51..82032e1 100644
--- a/include/asm-sparc64/percpu.h
+++ b/include/asm-sparc64/percpu.h
@@ -26,10 +26,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 #else /* ! SMP */
 
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 29a6b04..4405b4a 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -26,10 +26,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 
 extern void setup_per_cpu_areas(void);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index eef5ccd..fd647fd 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -149,22 +149,16 @@
 ({									\
 	typeof(gendiskp->dkstats->field) res = 0;			\
 	int i;								\
-	for (i=0; i < NR_CPUS; i++) {					\
-		if (!cpu_possible(i))					\
-			continue;					\
+	for_each_cpu(i)							\
 		res += per_cpu_ptr(gendiskp->dkstats, i)->field;	\
-	}								\
 	res;								\
 })
 
 static inline void disk_stat_set_all(struct gendisk *gendiskp, int value)	{
 	int i;
-	for (i=0; i < NR_CPUS; i++) {
-		if (cpu_possible(i)) {
-			memset(per_cpu_ptr(gendiskp->dkstats, i), value,	
-					sizeof (struct disk_stats));
-		}
-	}
+	for_each_cpu(i)
+		memset(per_cpu_ptr(gendiskp->dkstats, i), value,
+				sizeof (struct disk_stats));
 }		
 				
 #else