diff --git a/arch/cris/kernel/irq.c b/arch/cris/kernel/irq.c
index 30deaf1..b504def 100644
--- a/arch/cris/kernel/irq.c
+++ b/arch/cris/kernel/irq.c
@@ -52,9 +52,8 @@
 
 	if (i == 0) {
 		seq_printf(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
@@ -67,9 +66,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
 		seq_printf(p, " %14s", irq_desc[i].handler->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c
index 27ab4c3..11fa326 100644
--- a/arch/frv/kernel/irq.c
+++ b/arch/frv/kernel/irq.c
@@ -75,9 +75,8 @@
 	switch (i) {
 	case 0:
 		seq_printf(p, "           ");
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 
 		seq_putc(p, '\n');
 		break;
@@ -100,9 +99,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", kstat_cpu(j).irqs[i - 1]);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i - 1]);
 #endif
 
 		level = group->sources[ix]->level - frv_irq_levels;
diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
index e11a092..3d5110b 100644
--- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
@@ -1145,9 +1145,7 @@
 {
 	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 fd1c60c..311b4e7 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -351,8 +351,8 @@
 {
 	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 @@
 	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 @@
 		}
 	}
 	/* 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 @@
 	 */
 	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 @@
 	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 @@
 	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 1db34ef..9074818 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -143,7 +143,7 @@
 	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 @@
 	 * 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;
 
 	/*
diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c
index 0493e8b..1accce5 100644
--- a/arch/i386/oprofile/nmi_int.c
+++ b/arch/i386/oprofile/nmi_int.c
@@ -122,7 +122,7 @@
 static void free_msrs(void)
 {
 	int i;
-	for (i = 0; i < NR_CPUS; ++i) {
+	for_each_cpu(i) {
 		kfree(cpu_msrs[i].counters);
 		cpu_msrs[i].counters = NULL;
 		kfree(cpu_msrs[i].controls);
@@ -138,10 +138,7 @@
 	size_t counters_size = sizeof(struct op_msr) * model->num_counters;
 
 	int i;
-	for (i = 0; i < NR_CPUS; ++i) {
-		if (!cpu_online(i))
-			continue;
-
+	for_each_online_cpu(i) {
 		cpu_msrs[i].counters = kmalloc(counters_size, GFP_KERNEL);
 		if (!cpu_msrs[i].counters) {
 			success = 0;
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index 1ce6392..a4634b0 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -37,9 +37,8 @@
 
 	if (i == 0) {
 		seq_printf(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
@@ -52,9 +51,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
 		seq_printf(p, " %14s", irq_desc[i].handler->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 7d93992..3dd76b3 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -68,9 +68,8 @@
 
 	if (i == 0) {
 		seq_printf(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
@@ -83,9 +82,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
 		seq_printf(p, " %14s", irq_desc[i].handler->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 06ed907..78d171b 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -167,8 +167,8 @@
 	mb();
 
 	/* Send a message to all other CPUs and wait for them to respond */
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_online(i) && i != cpu)
+	for_each_online_cpu(i)
+		if (i != cpu)
 			core_send_ipi(i, SMP_CALL_FUNCTION);
 
 	/* Wait for response */
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 73e5e52..2854ac4 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -88,12 +88,9 @@
 {
 	int cpu, i;
 
-	for (cpu = 0; cpu <= NR_CPUS; cpu++) {
+	for_each_online_cpu(cpu) {
 		struct slice_data *si = cpu_data[cpu].data;
 
-		if (!cpu_online(cpu))
-			continue;
-
 		for (i = BASE_PCI_IRQ; i < LEVELS_PER_SLICE; i++)
 			if (si->level_to_irq[i] == irq) {
 				*cpunum = cpu;
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 25564b7..d6ac1c6 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -298,8 +298,8 @@
 {
 	int i;
 	
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_online(i) && i != smp_processor_id())
+	for_each_online_cpu(i) {
+		if (i != smp_processor_id())
 			send_IPI_single(i, op);
 	}
 }
@@ -643,14 +643,13 @@
 	if ( argc == 1 ){
 	
 #ifdef DUMP_MORE_STATE
-		for(i=0; i<NR_CPUS; i++) {
+		for_each_online_cpu(i) {
 			int cpus_per_line = 4;
-			if(cpu_online(i)) {
-				if (j++ % cpus_per_line)
-					printk(" %3d",i);
-				else
-					printk("\n %3d",i);
-			}
+
+			if (j++ % cpus_per_line)
+				printk(" %3d",i);
+			else
+				printk("\n %3d",i);
 		}
 		printk("\n"); 
 #else
@@ -659,9 +658,7 @@
 	} else if((argc==2) && !(strcmp(argv[1],"-l"))) {
 		printk("\nCPUSTATE  TASK CPUNUM CPUID HARDCPU(HPA)\n");
 #ifdef DUMP_MORE_STATE
-		for(i=0;i<NR_CPUS;i++) {
-			if (!cpu_online(i))
-				continue;
+		for_each_online_cpu(i) {
 			if (cpu_data[i].cpuid != NO_PROC_ID) {
 				switch(cpu_data[i].state) {
 					case STATE_RENDEZVOUS:
@@ -695,9 +692,7 @@
 	} else if ((argc==2) && !(strcmp(argv[1],"-s"))) { 
 #ifdef DUMP_MORE_STATE
      		printk("\nCPUSTATE   CPUID\n");
-		for (i=0;i<NR_CPUS;i++) {
-			if (!cpu_online(i))
-				continue;
+		for_each_online_cpu(i) {
 			if (cpu_data[i].cpuid != NO_PROC_ID) {
 				switch(cpu_data[i].state) {
 					case STATE_RENDEZVOUS:
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 24dc811..771a59c 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -135,9 +135,8 @@
 #ifdef CONFIG_TAU_INT
 		if (tau_initialized){
 			seq_puts(p, "TAU: ");
-			for (j = 0; j < NR_CPUS; j++)
-				if (cpu_online(j))
-					seq_printf(p, "%10u ", tau_interrupts(j));
+			for_each_online_cpu(j)
+				seq_printf(p, "%10u ", tau_interrupts(j));
 			seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
 		}
 #endif
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index be12041..c1d62bf 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -162,9 +162,8 @@
 #if defined(CONFIG_SMP) && defined(CONFIG_PPC32)
 		unsigned long bogosum = 0;
 		int i;
-		for (i = 0; i < NR_CPUS; ++i)
-			if (cpu_online(i))
-				bogosum += loops_per_jiffy;
+		for_each_online_cpu(i)
+			bogosum += loops_per_jiffy;
 		seq_printf(m, "total bogomips\t: %lu.%02lu\n",
 			   bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
 #endif /* CONFIG_SMP && CONFIG_PPC32 */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index db72a92..dc2770d 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -272,9 +272,8 @@
 	if ( ppc_md.progress ) ppc_md.progress("             ", 0xffff);
 
 	/* register CPU devices */
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_possible(i))
-			register_cpu(&cpu_devices[i], i, NULL);
+	for_each_cpu(i)
+		register_cpu(&cpu_devices[i], i, NULL);
 
 	/* call platform init */
 	if (ppc_md.init != NULL) {
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 6d64a9b..1065d87 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -191,9 +191,7 @@
 	if (num_online_cpus() < 2)
 		return;
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_online(i))
-			continue;
+	for_each_online_cpu(i) {
 		if (target == MSG_ALL
 		    || (target == MSG_ALL_BUT_SELF && i != smp_processor_id())
 		    || target == i) {
diff --git a/arch/ppc/kernel/setup.c b/arch/ppc/kernel/setup.c
index c08ab43..53e9dea 100644
--- a/arch/ppc/kernel/setup.c
+++ b/arch/ppc/kernel/setup.c
@@ -168,9 +168,8 @@
 		/* Show summary information */
 #ifdef CONFIG_SMP
 		unsigned long bogosum = 0;
-		for (i = 0; i < NR_CPUS; ++i)
-			if (cpu_online(i))
-				bogosum += cpu_data[i].loops_per_jiffy;
+		for_each_online_cpu(i)
+			bogosum += cpu_data[i].loops_per_jiffy;
 		seq_printf(m, "total bogomips\t: %lu.%02lu\n",
 			   bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
 #endif /* CONFIG_SMP */
@@ -712,9 +711,8 @@
 	if ( ppc_md.progress ) ppc_md.progress("             ", 0xffff);
 
 	/* register CPU devices */
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_possible(i))
-			register_cpu(&cpu_devices[i], i, NULL);
+	for_each_cpu(i)
+		register_cpu(&cpu_devices[i], i, NULL);
 
 	/* call platform init */
 	if (ppc_md.init != NULL) {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 7dbe00c..d52d6d2 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -799,9 +799,7 @@
          */
 	print_cpu_info(&S390_lowcore.cpu_data);
 
-        for(i = 0; i < NR_CPUS; i++) {
-		if (!cpu_possible(i))
-			continue;
+        for_each_cpu(i) {
 		lowcore_ptr[i] = (struct _lowcore *)
 			__get_free_pages(GFP_KERNEL|GFP_DMA, 
 					sizeof(void*) == 8 ? 1 : 0);
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 6883c00..b56e796 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -35,9 +35,8 @@
 
 	if (i == 0) {
 		seq_puts(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index a067a34..c0e79843 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -404,9 +404,8 @@
 {
 	int cpu_id;
 
-	for (cpu_id = 0; cpu_id < NR_CPUS; cpu_id++)
-		if (cpu_possible(cpu_id))
-			register_cpu(&cpu[cpu_id], cpu_id, NULL);
+	for_each_cpu(cpu_id)
+		register_cpu(&cpu[cpu_id], cpu_id, NULL);
 
 	return 0;
 }
diff --git a/arch/sh64/kernel/irq.c b/arch/sh64/kernel/irq.c
index 9fc2b71..d69879c 100644
--- a/arch/sh64/kernel/irq.c
+++ b/arch/sh64/kernel/irq.c
@@ -53,9 +53,8 @@
 
 	if (i == 0) {
 		seq_puts(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
diff --git a/arch/sparc/kernel/irq.c b/arch/sparc/kernel/irq.c
index 410b9a7..4c60a6e 100644
--- a/arch/sparc/kernel/irq.c
+++ b/arch/sparc/kernel/irq.c
@@ -184,9 +184,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++) {
-			if (cpu_online(j))
-				seq_printf(p, "%10u ",
+		for_each_online_cpu(j) {
+			seq_printf(p, "%10u ",
 				    kstat_cpu(cpu_logical_map(j)).irqs[i]);
 		}
 #endif
diff --git a/arch/sparc/kernel/smp.c b/arch/sparc/kernel/smp.c
index c6e721d..ea5682c 100644
--- a/arch/sparc/kernel/smp.c
+++ b/arch/sparc/kernel/smp.c
@@ -243,9 +243,8 @@
 		return -EINVAL;
 
 	spin_lock_irqsave(&prof_setup_lock, flags);
-	for(i = 0; i < NR_CPUS; i++) {
-		if (cpu_possible(i))
-			load_profile_irq(i, lvl14_resolution / multiplier);
+	for_each_cpu(i) {
+		load_profile_irq(i, lvl14_resolution / multiplier);
 		prof_multiplier(i) = multiplier;
 	}
 	spin_unlock_irqrestore(&prof_setup_lock, flags);
@@ -273,13 +272,12 @@
 {
 	int i;
 	
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_online(i))
-			seq_printf(m,
-				   "Cpu%dBogo\t: %lu.%02lu\n", 
-				   i,
-				   cpu_data(i).udelay_val/(500000/HZ),
-				   (cpu_data(i).udelay_val/(5000/HZ))%100);
+	for_each_online_cpu(i) {
+		seq_printf(m,
+			   "Cpu%dBogo\t: %lu.%02lu\n",
+			   i,
+			   cpu_data(i).udelay_val/(500000/HZ),
+			   (cpu_data(i).udelay_val/(5000/HZ))%100);
 	}
 }
 
@@ -288,8 +286,6 @@
 	int i;
 
 	seq_printf(m, "State:\n");
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_online(i))
-			seq_printf(m, "CPU%d\t\t: online\n", i);
-	}
+	for_each_online_cpu(i)
+		seq_printf(m, "CPU%d\t\t: online\n", i);
 }
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index 5262134..cea7fc6 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -103,11 +103,9 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (x = 0; x < NR_CPUS; x++) {
-			if (cpu_online(x))
-				seq_printf(p, "%10u ",
-				       kstat_cpu(cpu_logical_map(x)).irqs[i]);
-		}
+		for_each_online_cpu(x)
+			seq_printf(p, "%10u ",
+			       kstat_cpu(cpu_logical_map(x)).irqs[i]);
 #endif
 		seq_printf(p, "%c %s",
 			(action->flags & SA_INTERRUPT) ? '+' : ' ',
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index 4219dd2..41bb959 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -249,11 +249,9 @@
 	} else {
 		unsigned long bogosum = 0;
 		
-		for(i = 0; i < NR_CPUS; i++) {
-			if (cpu_isset(i, cpu_present_map)) {
-				bogosum += cpu_data(i).udelay_val;
-				smp_highest_cpu = i;
-			}
+		for_each_present_cpu(i) {
+			bogosum += cpu_data(i).udelay_val;
+			smp_highest_cpu = i;
 		}
 		SMP_PRINTK(("Total of %d Processors activated (%lu.%02lu BogoMIPS).\n", cpucount + 1, bogosum/(500000/HZ), (bogosum/(5000/HZ))%100));
 		printk("Total of %d Processors activated (%lu.%02lu BogoMIPS).\n",
diff --git a/arch/sparc/kernel/sun4m_smp.c b/arch/sparc/kernel/sun4m_smp.c
index fbbd8a4..1dde312 100644
--- a/arch/sparc/kernel/sun4m_smp.c
+++ b/arch/sparc/kernel/sun4m_smp.c
@@ -218,10 +218,8 @@
 		cpu_present_map = cpumask_of_cpu(smp_processor_id());
 	} else {
 		unsigned long bogosum = 0;
-		for(i = 0; i < NR_CPUS; i++) {
-			if (cpu_isset(i, cpu_present_map))
-				bogosum += cpu_data(i).udelay_val;
-		}
+		for_each_present_cpu(i)
+			bogosum += cpu_data(i).udelay_val;
 		printk("Total of %d Processors activated (%lu.%02lu BogoMIPS).\n",
 		       cpucount + 1,
 		       bogosum/(500000/HZ),
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index 8c93ba6..e505a41 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -117,9 +117,7 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++) {
-			if (!cpu_online(j))
-				continue;
+		for_each_online_cpu(j) {
 			seq_printf(p, "%10u ",
 				   kstat_cpu(j).irqs[i]);
 		}
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index 373a701..1b6e2ad 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -57,25 +57,21 @@
 	int i;
 	
 	seq_printf(m, "State:\n");
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_online(i))
-			seq_printf(m,
-				   "CPU%d:\t\tonline\n", i);
-	}
+	for_each_online_cpu(i)
+		seq_printf(m, "CPU%d:\t\tonline\n", i);
 }
 
 void smp_bogo(struct seq_file *m)
 {
 	int i;
 	
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_online(i))
-			seq_printf(m,
-				   "Cpu%dBogo\t: %lu.%02lu\n"
-				   "Cpu%dClkTck\t: %016lx\n",
-				   i, cpu_data(i).udelay_val / (500000/HZ),
-				   (cpu_data(i).udelay_val / (5000/HZ)) % 100,
-				   i, cpu_data(i).clock_tick);
+	for_each_online_cpu(i)
+		seq_printf(m,
+			   "Cpu%dBogo\t: %lu.%02lu\n"
+			   "Cpu%dClkTck\t: %016lx\n",
+			   i, cpu_data(i).udelay_val / (500000/HZ),
+			   (cpu_data(i).udelay_val / (5000/HZ)) % 100,
+			   i, cpu_data(i).clock_tick);
 }
 
 void __init smp_store_cpu_info(int id)
@@ -1282,7 +1278,7 @@
 		return -EINVAL;
 
 	spin_lock_irqsave(&prof_setup_lock, flags);
-	for (i = 0; i < NR_CPUS; i++)
+	for_each_cpu(i)
 		prof_multiplier(i) = multiplier;
 	current_tick_offset = (timer_tick_offset / multiplier);
 	spin_unlock_irqrestore(&prof_setup_lock, flags);
@@ -1384,10 +1380,8 @@
 	unsigned long bogosum = 0;
 	int i;
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_online(i))
-			bogosum += cpu_data(i).udelay_val;
-	}
+	for_each_online_cpu(i)
+		bogosum += cpu_data(i).udelay_val;
 	printk("Total of %ld processors activated "
 	       "(%lu.%02lu BogoMIPS).\n",
 	       (long) num_online_cpus(),
diff --git a/arch/x86_64/kernel/irq.c b/arch/x86_64/kernel/irq.c
index 30d2a1e..d8bd0b3 100644
--- a/arch/x86_64/kernel/irq.c
+++ b/arch/x86_64/kernel/irq.c
@@ -38,9 +38,8 @@
 
 	if (i == 0) {
 		seq_printf(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
@@ -53,10 +52,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-			seq_printf(p, "%10u ",
-				kstat_cpu(j).irqs[i]);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
 		seq_printf(p, " %14s", irq_desc[i].handler->typename);
 
@@ -68,15 +65,13 @@
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
 	} else if (i == NR_IRQS) {
 		seq_printf(p, "NMI: ");
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
 		seq_putc(p, '\n');
 #ifdef CONFIG_X86_LOCAL_APIC
 		seq_printf(p, "LOC: ");
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs);
 		seq_putc(p, '\n');
 #endif
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 5bf17e4..66c009e 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -162,9 +162,7 @@
 	local_irq_enable();
 	mdelay((10*1000)/nmi_hz); // wait 10 ticks
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
-		if (!cpu_online(cpu))
-			continue;
+	for_each_online_cpu(cpu) {
 		if (cpu_pda(cpu)->__nmi_count - counts[cpu] <= 5) {
 			endflag = 1;
 			printk("CPU#%d: NMI appears to be stuck (%d->%d)!\n",
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 4cbf6d9..51f9bed 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -83,9 +83,8 @@
 
 	if (i == 0) {
 		seq_printf(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
@@ -98,9 +97,8 @@
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
 		seq_printf(p, " %14s", irq_desc[i].handler->typename);
 		seq_printf(p, "  %s", action->name);
@@ -113,9 +111,8 @@
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
 	} else if (i == NR_IRQS) {
 		seq_printf(p, "NMI: ");
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", nmi_count(j));
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", nmi_count(j));
 		seq_putc(p, '\n');
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 	}
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 690a1aa..0c13795 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -172,11 +172,9 @@
 
 	memset(stats, 0, sizeof(struct net_device_stats));
 
-	for (i=0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		struct net_device_stats *lb_stats;
 
-		if (!cpu_possible(i)) 
-			continue;
 		lb_stats = &per_cpu(loopback_stats, i);
 		stats->rx_bytes   += lb_stats->rx_bytes;
 		stats->tx_bytes   += lb_stats->tx_bytes;
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 78193e4..330d386 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -38,9 +38,8 @@
 {
 	int i;
  
-	for_each_online_cpu(i) {
+	for_each_online_cpu(i)
 		vfree(cpu_buffer[i].buffer);
-	}
 }
 
 int alloc_cpu_buffers(void)
diff --git a/fs/xfs/linux-2.6/xfs_stats.c b/fs/xfs/linux-2.6/xfs_stats.c
index 8955720..713e6a7 100644
--- a/fs/xfs/linux-2.6/xfs_stats.c
+++ b/fs/xfs/linux-2.6/xfs_stats.c
@@ -62,18 +62,15 @@
 		while (j < xstats[i].endpoint) {
 			val = 0;
 			/* sum over all cpus */
-			for (c = 0; c < NR_CPUS; c++) {
-				if (!cpu_possible(c)) continue;
+			for_each_cpu(c)
 				val += *(((__u32*)&per_cpu(xfsstats, c) + j));
-			}
 			len += sprintf(buffer + len, " %u", val);
 			j++;
 		}
 		buffer[len++] = '\n';
 	}
 	/* extra precision counters */
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_possible(i)) continue;
+	for_each_cpu(i) {
 		xs_xstrat_bytes += per_cpu(xfsstats, i).xs_xstrat_bytes;
 		xs_write_bytes += per_cpu(xfsstats, i).xs_write_bytes;
 		xs_read_bytes += per_cpu(xfsstats, i).xs_read_bytes;
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index a025649..7079cc8 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -38,8 +38,7 @@
 
 	if (!ret && write && *valp) {
 		printk("XFS Clearing xfsstats\n");
-		for (c = 0; c < NR_CPUS; c++) {
-			if (!cpu_possible(c)) continue;
+		for_each_cpu(c) {
 			preempt_disable();
 			/* save vn_active, it's a universal truth! */
 			vn_active = per_cpu(xfsstats, c).vn_active;
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