[PATCH] percpu data: only iterate over possible CPUs

percpu_data blindly allocates bootmem memory to store NR_CPUS instances of
cpudata, instead of allocating memory only for possible cpus.

As a preparation for changing that, we need to convert various 0 -> NR_CPUS
loops to use for_each_cpu().

(The above only applies to users of asm-generic/percpu.h.  powerpc has gone it
alone and is presently only allocating memory for present CPUs, so it's
currently corrupting memory).

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <axboe@suse.de>
Cc: Anton Blanchard <anton@samba.org>
Acked-by: William Irwin <wli@holomorphy.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/nmi.c

@@ -138,7 +138,7 @@ static int __init check_nmi_watchdog(void)
 	if (nmi_watchdog == NMI_LOCAL_APIC)
 		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
+	for_each_cpu(cpu)
 		prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count;
 	local_irq_enable();
 	mdelay((10*1000)/nmi_hz); // wait 10 ticks

block/ll_rw_blk.c

@@ -3453,7 +3453,7 @@ int __init blk_dev_init(void)
 	iocontext_cachep = kmem_cache_create("blkdev_ioc",
 			sizeof(struct io_context), 0, SLAB_PANIC, NULL, NULL);
 
-	for (i = 0; i < NR_CPUS; i++)
+	for_each_cpu(i)
 		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
 
 	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL);

drivers/scsi/scsi.c

@@ -1245,7 +1245,7 @@ static int __init init_scsi(void)
 	if (error)
 		goto cleanup_sysctl;
 
-	for (i = 0; i < NR_CPUS; i++)
+	for_each_cpu(i)
 		INIT_LIST_HEAD(&per_cpu(scsi_done_q, i));
 
 	devfs_mk_dir("scsi");

fs/file.c

@@ -379,7 +379,6 @@ static void __devinit fdtable_defer_list_init(int cpu)
 void __init files_defer_init(void)
 {
 	int i;
-	/* Really early - can't use for_each_cpu */
-	for (i = 0; i < NR_CPUS; i++)
+	for_each_cpu(i)
 		fdtable_defer_list_init(i);
 }

kernel/sched.c

@@ -6109,7 +6109,7 @@ void __init sched_init(void)
 	runqueue_t *rq;
 	int i, j, k;
 
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		prio_array_t *array;
 
 		rq = cpu_rq(i);

mm/page_alloc.c

@@ -1213,18 +1213,21 @@ static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
 {
 	int cpu = 0;
 
-	memset(ret, 0, sizeof(*ret));
+	memset(ret, 0, nr * sizeof(unsigned long));
 	cpus_and(*cpumask, *cpumask, cpu_online_map);
 
 	cpu = first_cpu(*cpumask);
 	while (cpu < NR_CPUS) {
 		unsigned long *in, *out, off;
 
+		if (!cpu_isset(cpu, *cpumask))
+			continue;
+
 		in = (unsigned long *)&per_cpu(page_states, cpu);
 
 		cpu = next_cpu(cpu, *cpumask);
 
-		if (cpu < NR_CPUS)
+		if (likely(cpu < NR_CPUS))
 			prefetch(&per_cpu(page_states, cpu));
 
 		out = (unsigned long *)ret;
@@ -1886,8 +1889,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
  * not check if the processor is online before following the pageset pointer.
  * Other parts of the kernel may not check if the zone is available.
  */
-static struct per_cpu_pageset
-	boot_pageset[NR_CPUS];
+static struct per_cpu_pageset boot_pageset[NR_CPUS];
 
 /*
  * Dynamically allocate memory for the

net/core/dev.c

@@ -3237,7 +3237,7 @@ static int __init net_dev_init(void)
 	 *	Initialise the packet receive queues.
 	 */
 
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		struct softnet_data *queue;
 
 		queue = &per_cpu(softnet_data, i);

net/core/utils.c

@@ -121,7 +121,7 @@ void __init net_random_init(void)
 {
 	int i;
 
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		struct nrnd_state *state = &per_cpu(net_rand_state,i);
 		__net_srandom(state, i+jiffies);
 	}
@@ -133,7 +133,7 @@ static int net_random_reseed(void)
 	unsigned long seed[NR_CPUS];
 
 	get_random_bytes(seed, sizeof(seed));
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		struct nrnd_state *state = &per_cpu(net_rand_state,i);
 		__net_srandom(state, seed[i]);
 	}

net/ipv4/proc.c

@@ -49,7 +49,7 @@ static int fold_prot_inuse(struct proto *proto)
 	int res = 0;
 	int cpu;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
+	for_each_cpu(cpu)
 		res += proto->stats[cpu].inuse;
 
 	return res;

net/ipv6/proc.c

@@ -38,7 +38,7 @@ static int fold_prot_inuse(struct proto *proto)
 	int res = 0;
 	int cpu;
 
-	for (cpu=0; cpu<NR_CPUS; cpu++)
+	for_each_cpu(cpu)
 		res += proto->stats[cpu].inuse;
 
 	return res;

net/socket.c

@@ -2078,7 +2078,7 @@ void socket_seq_show(struct seq_file *seq)
 	int cpu;
 	int counter = 0;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
+	for_each_cpu(cpu)
 		counter += per_cpu(sockets_in_use, cpu);
 
 	/* It can be negative, by the way. 8) */