147 files changed, 520 insertions, 700 deletions
diff --git a/arch/alpha/include/asm/smp.h b/arch/alpha/include/asm/smp.h
index 544c69af8168..547e90951cec 100644
--- a/arch/alpha/include/asm/smp.h
+++ b/arch/alpha/include/asm/smp.h
@@ -45,7 +45,6 @@ extern struct cpuinfo_alpha cpu_data[NR_CPUS];
 #define raw_smp_processor_id()  (current_thread_info()->cpu)
 extern int smp_num_cpus;
-#define cpu_possible_map        cpu_present_map
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi(cpumask_t mask);
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index c626a821cdcb..d0f1620007f7 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -55,7 +55,7 @@ int irq_select_affinity(unsigned int irq)
        last_cpu = cpu;
        irq_desc[irq].affinity = cpumask_of_cpu(cpu);
-        irq_desc[irq].chip->set_affinity(irq, cpumask_of_cpu(cpu));
+        irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu));
        return 0;
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 351407e07e71..f238370c907d 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -94,6 +94,7 @@ common_shutdown_1(void *generic_ptr)
                flags |= 0x00040000UL; /* "remain halted" */
                *pflags = flags;
                cpu_clear(cpuid, cpu_present_map);
+                cpu_clear(cpuid, cpu_possible_map);
                halt();
        }
 #endif
@@ -120,6 +121,7 @@ common_shutdown_1(void *generic_ptr)
 #ifdef CONFIG_SMP
        /* Wait for the secondaries to halt. */
        cpu_clear(boot_cpuid, cpu_present_map);
+        cpu_clear(boot_cpuid, cpu_possible_map);
        while (cpus_weight(cpu_present_map))
                barrier();
 #endif
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index cf7da10097bb..d953e510f68d 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -70,11 +70,6 @@ enum ipi_message_type {
 /* Set to a secondary's cpuid when it comes online.  */
 static int smp_secondary_alive __devinitdata = 0;
-/* Which cpus ids came online.  */
-cpumask_t cpu_online_map;
-EXPORT_SYMBOL(cpu_online_map);
 int smp_num_probed;             /* Internal processor count */
 int smp_num_cpus = 1;           /* Number that came online.  */
 EXPORT_SYMBOL(smp_num_cpus);
@@ -440,6 +435,7 @@ setup_smp(void)
                                ((char *)cpubase + i*hwrpb->processor_size);
                        if ((cpu->flags & 0x1cc) == 0x1cc) {
                                smp_num_probed++;
+                                cpu_set(i, cpu_possible_map);
                                cpu_set(i, cpu_present_map);
                                cpu->pal_revision = boot_cpu_palrev;
                        }
@@ -473,6 +469,7 @@ smp_prepare_cpus(unsigned int max_cpus)
        /* Nothing to do on a UP box, or when told not to.  */
        if (smp_num_probed == 1 || max_cpus == 0) {
+                cpu_possible_map = cpumask_of_cpu(boot_cpuid);
                cpu_present_map = cpumask_of_cpu(boot_cpuid);
                printk(KERN_INFO "SMP mode deactivated.\n");
                return;
diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c
index c71b0fd7a61f..ab44c164d9d4 100644
--- a/arch/alpha/kernel/sys_dp264.c
+++ b/arch/alpha/kernel/sys_dp264.c
@@ -177,19 +177,19 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 }
 static void
-dp264_set_affinity(unsigned int irq, cpumask_t affinity)
+dp264_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
        spin_lock(&dp264_irq_lock);
-        cpu_set_irq_affinity(irq, affinity);
+        cpu_set_irq_affinity(irq, *affinity);
        tsunami_update_irq_hw(cached_irq_mask);
        spin_unlock(&dp264_irq_lock);
 }
 static void
-clipper_set_affinity(unsigned int irq, cpumask_t affinity)
+clipper_set_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
        spin_lock(&dp264_irq_lock);
-        cpu_set_irq_affinity(irq - 16, affinity);
+        cpu_set_irq_affinity(irq - 16, *affinity);
        tsunami_update_irq_hw(cached_irq_mask);
        spin_unlock(&dp264_irq_lock);
 }
diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c
index 52c91ccc1648..27f840a4ad3d 100644
--- a/arch/alpha/kernel/sys_titan.c
+++ b/arch/alpha/kernel/sys_titan.c
@@ -158,10 +158,10 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity)
 }
 static void
-titan_set_irq_affinity(unsigned int irq, cpumask_t affinity)
+titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 { 
        spin_lock(&titan_irq_lock);
-        titan_cpu_set_irq_affinity(irq - 16, affinity);
+        titan_cpu_set_irq_affinity(irq - 16, *affinity);
        titan_update_irq_hw(titan_cached_irq_mask);
        spin_unlock(&titan_irq_lock);
 }
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 7fc9860a97d7..c6884ba1d5ed 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -109,11 +109,11 @@ static void gic_unmask_irq(unsigned int irq)
 }
 #ifdef CONFIG_SMP
-static void gic_set_cpu(unsigned int irq, cpumask_t mask_val)
+static void gic_set_cpu(unsigned int irq, const struct cpumask *mask_val)
 {
        void __iomem *reg = gic_dist_base(irq) + GIC_DIST_TARGET + (gic_irq(irq) & ~3);
        unsigned int shift = (irq % 4) * 8;
-        unsigned int cpu = first_cpu(mask_val);
+        unsigned int cpu = cpumask_first(mask_val);
        u32 val;
        spin_lock(&irq_controller_lock);
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 2f3eb795fa6e..7141cee1fab7 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -174,7 +174,7 @@ static void route_irq(struct irq_desc *desc, unsigned int irq, unsigned int cpu)
        pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", irq, desc->cpu, cpu);
        spin_lock_irq(&desc->lock);
-        desc->chip->set_affinity(irq, cpumask_of_cpu(cpu));
+        desc->chip->set_affinity(irq, cpumask_of(cpu));
        spin_unlock_irq(&desc->lock);
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index e42a749a56dd..bd905c0a7365 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -34,16 +34,6 @@
 #include <asm/ptrace.h>
 /*
- * bitmask of present and online CPUs.
- * The present bitmask indicates that the CPU is physically present.
- * The online bitmask indicates that the CPU is up and running.
- */
-cpumask_t cpu_possible_map;
-EXPORT_SYMBOL(cpu_possible_map);
-cpumask_t cpu_online_map;
-EXPORT_SYMBOL(cpu_online_map);
-/*
 * as from 2.5, kernels no longer have an init_tasks structure
 * so we need some other way of telling a new secondary core
 * where to place its SVC stack
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index a72e798a2a40..72f51d39202c 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -169,7 +169,6 @@ static struct clock_event_device clkevt = {
        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
        .shift          = 32,
        .rating         = 150,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = clkevt32k_next_event,
        .set_mode       = clkevt32k_mode,
 };
@@ -197,7 +196,7 @@ void __init at91rm9200_timer_init(void)
        clkevt.mult = div_sc(AT91_SLOW_CLOCK, NSEC_PER_SEC, clkevt.shift);
        clkevt.max_delta_ns = clockevent_delta2ns(AT91_ST_ALMV, &clkevt);
        clkevt.min_delta_ns = clockevent_delta2ns(2, &clkevt) + 1;
-        clkevt.cpumask = cpumask_of_cpu(0);
+        clkevt.cpumask = cpumask_of(0);
        clockevents_register_device(&clkevt);
        /* register clocksource */
diff --git a/arch/arm/mach-at91/at91sam926x_time.c b/arch/arm/mach-at91/at91sam926x_time.c
index 122fd77ed580..b63e1d5f1bad 100644
--- a/arch/arm/mach-at91/at91sam926x_time.c
+++ b/arch/arm/mach-at91/at91sam926x_time.c
@@ -91,7 +91,6 @@ static struct clock_event_device pit_clkevt = {
        .features       = CLOCK_EVT_FEAT_PERIODIC,
        .shift          = 32,
        .rating         = 100,
-        .cpumask        = CPU_MASK_CPU0,
        .set_mode       = pit_clkevt_mode,
 };
@@ -173,6 +172,7 @@ static void __init at91sam926x_pit_init(void)
        /* Set up and register clockevents */
        pit_clkevt.mult = div_sc(pit_rate, NSEC_PER_SEC, pit_clkevt.shift);
+        pit_clkevt.cpumask = cpumask_of(0);
        clockevents_register_device(&pit_clkevt);
 }
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index 3b9a296b5c4b..f8bcd29d17a6 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -322,7 +322,7 @@ static void __init davinci_timer_init(void)
        clockevent_davinci.min_delta_ns =
                clockevent_delta2ns(1, &clockevent_davinci);
-        clockevent_davinci.cpumask = cpumask_of_cpu(0);
+        clockevent_davinci.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_davinci);
 }
diff --git a/arch/arm/mach-imx/time.c b/arch/arm/mach-imx/time.c
index a11765f5f23b..aff0ebcfa847 100644
--- a/arch/arm/mach-imx/time.c
+++ b/arch/arm/mach-imx/time.c
@@ -184,7 +184,7 @@ static int __init imx_clockevent_init(unsigned long rate)
        clockevent_imx.min_delta_ns =
                clockevent_delta2ns(0xf, &clockevent_imx);
-        clockevent_imx.cpumask = cpumask_of_cpu(0);
+        clockevent_imx.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_imx);
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 7766f469456b..f4656d2ac8a8 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -487,7 +487,7 @@ static int __init ixp4xx_clockevent_init(void)
                clockevent_delta2ns(0xfffffffe, &clockevent_ixp4xx);
        clockevent_ixp4xx.min_delta_ns =
                clockevent_delta2ns(0xf, &clockevent_ixp4xx);
-        clockevent_ixp4xx.cpumask = cpumask_of_cpu(0);
+        clockevent_ixp4xx.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_ixp4xx);
        return 0;
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 345a14cb73c3..444d9c0f5ca6 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -182,7 +182,7 @@ static void __init msm_timer_init(void)
                        clockevent_delta2ns(0xf0000000 >> clock->shift, ce);
                /* 4 gets rounded down to 3 */
                ce->min_delta_ns = clockevent_delta2ns(4, ce);
-                ce->cpumask = cpumask_of_cpu(0);
+                ce->cpumask = cpumask_of(0);
                cs->mult = clocksource_hz2mult(clock->freq, cs->shift);
                res = clocksource_register(cs);
diff --git a/arch/arm/mach-ns9xxx/time-ns9360.c b/arch/arm/mach-ns9xxx/time-ns9360.c
index a63424d083d9..41df69721769 100644
--- a/arch/arm/mach-ns9xxx/time-ns9360.c
+++ b/arch/arm/mach-ns9xxx/time-ns9360.c
@@ -173,7 +173,7 @@ static void __init ns9360_timer_init(void)
        ns9360_clockevent_device.min_delta_ns =
                clockevent_delta2ns(1, &ns9360_clockevent_device);
-        ns9360_clockevent_device.cpumask = cpumask_of_cpu(0);
+        ns9360_clockevent_device.cpumask = cpumask_of(0);
        clockevents_register_device(&ns9360_clockevent_device);
        setup_irq(IRQ_NS9360_TIMER0 + TIMER_CLOCKEVENT,
diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c
index 2cf7e32bd293..495a32c287b4 100644
--- a/arch/arm/mach-omap1/time.c
+++ b/arch/arm/mach-omap1/time.c
@@ -173,7 +173,7 @@ static __init void omap_init_mpu_timer(unsigned long rate)
        clockevent_mpu_timer1.min_delta_ns =
                clockevent_delta2ns(1, &clockevent_mpu_timer1);
-        clockevent_mpu_timer1.cpumask = cpumask_of_cpu(0);
+        clockevent_mpu_timer1.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_mpu_timer1);
 }
diff --git a/arch/arm/mach-omap1/timer32k.c b/arch/arm/mach-omap1/timer32k.c
index 705367ece174..fd3f7396e162 100644
--- a/arch/arm/mach-omap1/timer32k.c
+++ b/arch/arm/mach-omap1/timer32k.c
@@ -187,7 +187,7 @@ static __init void omap_init_32k_timer(void)
        clockevent_32k_timer.min_delta_ns =
                clockevent_delta2ns(1, &clockevent_32k_timer);
-        clockevent_32k_timer.cpumask = cpumask_of_cpu(0);
+        clockevent_32k_timer.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_32k_timer);
 }
diff --git a/arch/arm/mach-omap2/timer-gp.c b/arch/arm/mach-omap2/timer-gp.c
index 589393bedade..ae6036300f60 100644
--- a/arch/arm/mach-omap2/timer-gp.c
+++ b/arch/arm/mach-omap2/timer-gp.c
@@ -120,7 +120,7 @@ static void __init omap2_gp_clockevent_init(void)
        clockevent_gpt.min_delta_ns =
                clockevent_delta2ns(1, &clockevent_gpt);
-        clockevent_gpt.cpumask = cpumask_of_cpu(0);
+        clockevent_gpt.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_gpt);
 }
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index f8a9a62959e5..bf3c9a4aad50 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -122,7 +122,6 @@ static struct clock_event_device ckevt_pxa_osmr0 = {
        .features       = CLOCK_EVT_FEAT_ONESHOT,
        .shift          = 32,
        .rating         = 200,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = pxa_osmr0_set_next_event,
        .set_mode       = pxa_osmr0_set_mode,
 };
@@ -170,6 +169,7 @@ static void __init pxa_timer_init(void)
                clockevent_delta2ns(0x7fffffff, &ckevt_pxa_osmr0);
        ckevt_pxa_osmr0.min_delta_ns =
                clockevent_delta2ns(MIN_OSCR_DELTA * 2, &ckevt_pxa_osmr0) + 1;
+        ckevt_pxa_osmr0.cpumask = cpumask_of(0);
        cksrc_pxa_oscr0.mult =
                clocksource_hz2mult(clock_tick_rate, cksrc_pxa_oscr0.shift);
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 2f04d54711e7..b07cb9b7adb1 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -511,7 +511,7 @@ static struct clock_event_device timer0_clockevent =	 {
        .set_mode       = timer_set_mode,
        .set_next_event = timer_set_next_event,
        .rating         = 300,
-        .cpumask        = CPU_MASK_ALL,
+        .cpumask        = cpu_all_mask,
 };
 static void __init realview_clockevents_init(unsigned int timer_irq)
diff --git a/arch/arm/mach-realview/localtimer.c b/arch/arm/mach-realview/localtimer.c
index 44d178cd5733..504961ef343c 100644
--- a/arch/arm/mach-realview/localtimer.c
+++ b/arch/arm/mach-realview/localtimer.c
@@ -161,7 +161,7 @@ void __cpuinit local_timer_setup(unsigned int cpu)
        clk->set_mode           = local_timer_set_mode;
        clk->set_next_event     = local_timer_set_next_event;
        clk->irq                = IRQ_LOCALTIMER;
-        clk->cpumask            = cpumask_of_cpu(cpu);
+        clk->cpumask            = cpumask_of(cpu);
        clk->shift              = 20;
        clk->mult               = div_sc(mpcore_timer_rate, NSEC_PER_SEC, clk->shift);
        clk->max_delta_ns       = clockevent_delta2ns(0xffffffff, clk);
@@ -199,7 +199,7 @@ void __cpuinit local_timer_setup(unsigned int cpu)
        clk->rating             = 200;
        clk->set_mode           = dummy_timer_set_mode;
        clk->broadcast          = smp_timer_broadcast;
-        clk->cpumask            = cpumask_of_cpu(cpu);
+        clk->cpumask            = cpumask_of(cpu);
        clockevents_register_device(clk);
 }
diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c
index 24c0a4bae850..1cac4ac0b4b8 100644
--- a/arch/arm/mach-sa1100/time.c
+++ b/arch/arm/mach-sa1100/time.c
@@ -73,7 +73,6 @@ static struct clock_event_device ckevt_sa1100_osmr0 = {
        .features       = CLOCK_EVT_FEAT_ONESHOT,
        .shift          = 32,
        .rating         = 200,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = sa1100_osmr0_set_next_event,
        .set_mode       = sa1100_osmr0_set_mode,
 };
@@ -110,6 +109,7 @@ static void __init sa1100_timer_init(void)
                clockevent_delta2ns(0x7fffffff, &ckevt_sa1100_osmr0);
        ckevt_sa1100_osmr0.min_delta_ns =
                clockevent_delta2ns(MIN_OSCR_DELTA * 2, &ckevt_sa1100_osmr0) + 1;
+        ckevt_sa1100_osmr0.cpumask = cpumask_of(0);
        cksrc_sa1100_oscr.mult =
                clocksource_hz2mult(CLOCK_TICK_RATE, cksrc_sa1100_oscr.shift);
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 565e0ba0d67e..a3f1933434e2 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -965,7 +965,7 @@ static void __init versatile_timer_init(void)
        timer0_clockevent.min_delta_ns =
                clockevent_delta2ns(0xf, &timer0_clockevent);
-        timer0_clockevent.cpumask = cpumask_of_cpu(0);
+        timer0_clockevent.cpumask = cpumask_of(0);
        clockevents_register_device(&timer0_clockevent);
 }
diff --git a/arch/arm/oprofile/op_model_mpcore.c b/arch/arm/oprofile/op_model_mpcore.c
index 4de366e8b4c5..6d6bd5899240 100644
--- a/arch/arm/oprofile/op_model_mpcore.c
+++ b/arch/arm/oprofile/op_model_mpcore.c
@@ -260,10 +260,10 @@ static void em_stop(void)
 static void em_route_irq(int irq, unsigned int cpu)
 {
        struct irq_desc *desc = irq_desc + irq;
-        cpumask_t mask = cpumask_of_cpu(cpu);
+        const struct cpumask *mask = cpumask_of(cpu);
        spin_lock_irq(&desc->lock);
-        desc->affinity = mask;
+        desc->affinity = *mask;
        desc->chip->set_affinity(irq, mask);
        spin_unlock_irq(&desc->lock);
 }
diff --git a/arch/arm/plat-mxc/time.c b/arch/arm/plat-mxc/time.c
index fd28f5194f71..758a1293bcfa 100644
--- a/arch/arm/plat-mxc/time.c
+++ b/arch/arm/plat-mxc/time.c
@@ -190,7 +190,7 @@ static int __init mxc_clockevent_init(void)
        clockevent_mxc.min_delta_ns =
                        clockevent_delta2ns(0xff, &clockevent_mxc);
-        clockevent_mxc.cpumask = cpumask_of_cpu(0);
+        clockevent_mxc.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_mxc);
diff --git a/arch/arm/plat-orion/time.c b/arch/arm/plat-orion/time.c
index 544d6b327f3a..6fa2923e6dca 100644
--- a/arch/arm/plat-orion/time.c
+++ b/arch/arm/plat-orion/time.c
@@ -149,7 +149,6 @@ static struct clock_event_device orion_clkevt = {
        .features       = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
        .shift          = 32,
        .rating         = 300,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = orion_clkevt_next_event,
        .set_mode       = orion_clkevt_mode,
 };
@@ -199,5 +198,6 @@ void __init orion_time_init(unsigned int irq, unsigned int tclk)
        orion_clkevt.mult = div_sc(tclk, NSEC_PER_SEC, orion_clkevt.shift);
        orion_clkevt.max_delta_ns = clockevent_delta2ns(0xfffffffe, &orion_clkevt);
        orion_clkevt.min_delta_ns = clockevent_delta2ns(1, &orion_clkevt);
+        orion_clkevt.cpumask = cpumask_of(0);
        clockevents_register_device(&orion_clkevt);
 }
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index 283481d74a5b..0ff46bf873b0 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -106,7 +106,6 @@ static struct clock_event_device comparator = {
        .features       = CLOCK_EVT_FEAT_ONESHOT,
        .shift          = 16,
        .rating         = 50,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = comparator_next_event,
        .set_mode       = comparator_mode,
 };
@@ -134,6 +133,7 @@ void __init time_init(void)
        comparator.mult = div_sc(counter_hz, NSEC_PER_SEC, comparator.shift);
        comparator.max_delta_ns = clockevent_delta2ns((u32)~0, &comparator);
        comparator.min_delta_ns = clockevent_delta2ns(50, &comparator) + 1;
+        comparator.cpumask = cpumask_of(0);
        sysreg_write(COMPARE, 0);
        timer_irqaction.dev_id = &comparator;
diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c
index e887efc86c29..0ed2badfd746 100644
--- a/arch/blackfin/kernel/time-ts.c
+++ b/arch/blackfin/kernel/time-ts.c
@@ -162,7 +162,6 @@ static struct clock_event_device clockevent_bfin = {
        .name           = "bfin_core_timer",
        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
        .shift          = 32,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = bfin_timer_set_next_event,
        .set_mode       = bfin_timer_set_mode,
 };
@@ -193,6 +192,7 @@ static int __init bfin_clockevent_init(void)
        clockevent_bfin.mult = div_sc(timer_clk, NSEC_PER_SEC, clockevent_bfin.shift);
        clockevent_bfin.max_delta_ns = clockevent_delta2ns(-1, &clockevent_bfin);
        clockevent_bfin.min_delta_ns = clockevent_delta2ns(100, &clockevent_bfin);
+        clockevent_bfin.cpumask = cpumask_of(0);
        clockevents_register_device(&clockevent_bfin);
        return 0;
diff --git a/arch/cris/arch-v32/kernel/irq.c b/arch/cris/arch-v32/kernel/irq.c
index 173c141ac9ba..295131fee710 100644
--- a/arch/cris/arch-v32/kernel/irq.c
+++ b/arch/cris/arch-v32/kernel/irq.c
@@ -325,11 +325,11 @@ static void end_crisv32_irq(unsigned int irq)
 {
 }
-void set_affinity_crisv32_irq(unsigned int irq, cpumask_t dest)
+void set_affinity_crisv32_irq(unsigned int irq, const struct cpumask *dest)
 {
        unsigned long flags;
        spin_lock_irqsave(&irq_lock, flags);
-        irq_allocations[irq - FIRST_IRQ].mask = dest;
+        irq_allocations[irq - FIRST_IRQ].mask = *dest;
        spin_unlock_irqrestore(&irq_lock, flags);
 }
diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c
index 52e16c6436f9..9dac17334640 100644
--- a/arch/cris/arch-v32/kernel/smp.c
+++ b/arch/cris/arch-v32/kernel/smp.c
@@ -29,11 +29,7 @@
 spinlock_t cris_atomic_locks[] = { [0 ... LOCK_COUNT - 1] = SPIN_LOCK_UNLOCKED};
 /* CPU masks */
-cpumask_t cpu_online_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_online_map);
 cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
-cpumask_t cpu_possible_map;
-EXPORT_SYMBOL(cpu_possible_map);
 EXPORT_SYMBOL(phys_cpu_present_map);
 /* Variables used during SMP boot */
diff --git a/arch/cris/include/asm/smp.h b/arch/cris/include/asm/smp.h
index dba33aba3e95..c615a06dd757 100644
--- a/arch/cris/include/asm/smp.h
+++ b/arch/cris/include/asm/smp.h
@@ -4,7 +4,6 @@
 #include <linux/cpumask.h>
 extern cpumask_t phys_cpu_present_map;
-extern cpumask_t cpu_possible_map;
 #define raw_smp_processor_id() (current_thread_info()->cpu)
diff --git a/arch/ia64/hp/sim/hpsim_irq.c b/arch/ia64/hp/sim/hpsim_irq.c
index c2f58ff364e7..cc0a3182db3c 100644
--- a/arch/ia64/hp/sim/hpsim_irq.c
+++ b/arch/ia64/hp/sim/hpsim_irq.c
@@ -22,7 +22,7 @@ hpsim_irq_noop (unsigned int irq)
 }
 static void
-hpsim_set_affinity_noop (unsigned int a, cpumask_t b)
+hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b)
 {
 }
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index 12d96e0cd513..21c402365d0e 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -57,7 +57,6 @@ extern struct smp_boot_data {
 extern char no_int_routing __devinitdata;
-extern cpumask_t cpu_online_map;
 extern cpumask_t cpu_core_map[NR_CPUS];
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern int smp_num_siblings;
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index 5c4674ae8aea..c8adecd5b416 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -330,25 +330,25 @@ unmask_irq (unsigned int irq)
 static void
-iosapic_set_affinity (unsigned int irq, cpumask_t mask)
+iosapic_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
 #ifdef CONFIG_SMP
        u32 high32, low32;
-        int dest, rte_index;
+        int cpu, dest, rte_index;
        int redir = (irq & IA64_IRQ_REDIRECTED) ? 1 : 0;
        struct iosapic_rte_info *rte;
        struct iosapic *iosapic;
        irq &= (~IA64_IRQ_REDIRECTED);
-        cpus_and(mask, mask, cpu_online_map);
+        cpu = cpumask_first_and(cpu_online_mask, mask);
-        if (cpus_empty(mask))
+        if (cpu >= nr_cpu_ids)
                return;
-        if (irq_prepare_move(irq, first_cpu(mask)))
+        if (irq_prepare_move(irq, cpu))
                return;
-        dest = cpu_physical_id(first_cpu(mask));
+        dest = cpu_physical_id(cpu);
        if (!iosapic_intr_info[irq].count)
                return;                 /* not an IOSAPIC interrupt */
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 7fd18f54c056..0b6db53fedcf 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -133,7 +133,6 @@ unsigned int vectors_in_migration[NR_IRQS];
 */
 static void migrate_irqs(void)
 {
-        cpumask_t       mask;
        irq_desc_t *desc;
        int             irq, new_cpu;
@@ -152,15 +151,14 @@ static void migrate_irqs(void)
                if (desc->status == IRQ_PER_CPU)
                        continue;
-                cpus_and(mask, irq_desc[irq].affinity, cpu_online_map);
+                if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask)
-                if (any_online_cpu(mask) == NR_CPUS) {
+                    >= nr_cpu_ids) {
                        /*
                         * Save it for phase 2 processing
                         */
                        vectors_in_migration[irq] = irq;
                        new_cpu = any_online_cpu(cpu_online_map);
-                        mask = cpumask_of_cpu(new_cpu);
                        /*
                         * Al three are essential, currently WARN_ON.. maybe panic?
@@ -168,7 +166,8 @@ static void migrate_irqs(void)
                        if (desc->chip && desc->chip->disable &&
                                desc->chip->enable && desc->chip->set_affinity) {
                                desc->chip->disable(irq);
-                                desc->chip->set_affinity(irq, mask);
+                                desc->chip->set_affinity(irq,
+                                                         cpumask_of(new_cpu));
                                desc->chip->enable(irq);
                        } else {
                                WARN_ON((!(desc->chip) || !(desc->chip->disable) ||
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 702a09c13238..890339339035 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -49,11 +49,12 @@
 static struct irq_chip  ia64_msi_chip;
 #ifdef CONFIG_SMP
-static void ia64_set_msi_irq_affinity(unsigned int irq, cpumask_t cpu_mask)
+static void ia64_set_msi_irq_affinity(unsigned int irq,
+                                      const cpumask_t *cpu_mask)
 {
        struct msi_msg msg;
        u32 addr, data;
-        int cpu = first_cpu(cpu_mask);
+        int cpu = first_cpu(*cpu_mask);
        if (!cpu_online(cpu))
                return;
@@ -166,12 +167,11 @@ void arch_teardown_msi_irq(unsigned int irq)
 #ifdef CONFIG_DMAR
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
+static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
        struct irq_cfg *cfg = irq_cfg + irq;
        struct msi_msg msg;
-        int cpu = first_cpu(mask);
+        int cpu = cpumask_first(mask);
        if (!cpu_online(cpu))
                return;
@@ -187,7 +187,7 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
        msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
        dmar_msi_write(irq, &msg);
-        irq_desc[irq].affinity = mask;
+        irq_desc[irq].affinity = *mask;
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 1dcbb85fc4ee..11463994a7d5 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -131,12 +131,6 @@ struct task_struct *task_for_booting_cpu;
 */
 DEFINE_PER_CPU(int, cpu_state);
-/* Bitmasks of currently online, and possible CPUs */
-cpumask_t cpu_online_map;
-EXPORT_SYMBOL(cpu_online_map);
-cpumask_t cpu_possible_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_possible_map);
 cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned;
 EXPORT_SYMBOL(cpu_core_map);
 DEFINE_PER_CPU_SHARED_ALIGNED(cpumask_t, cpu_sibling_map);
@@ -688,7 +682,7 @@ int migrate_platform_irqs(unsigned int cpu)
 {
        int new_cpei_cpu;
        irq_desc_t *desc = NULL;
-        cpumask_t       mask;
+        const struct cpumask *mask;
        int             retval = 0;
        /*
@@ -701,7 +695,7 @@ int migrate_platform_irqs(unsigned int cpu)
                         * Now re-target the CPEI to a different processor
                         */
                        new_cpei_cpu = any_online_cpu(cpu_online_map);
-                        mask = cpumask_of_cpu(new_cpei_cpu);
+                        mask = cpumask_of(new_cpei_cpu);
                        set_cpei_target_cpu(new_cpei_cpu);
                        desc = irq_desc + ia64_cpe_irq;
                        /*
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index c75b914f2d6b..a8d61a3e9a94 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -219,7 +219,7 @@ static ssize_t show_shared_cpu_map(struct cache_info *this_leaf, char *buf)
        cpumask_t shared_cpu_map;
        cpus_and(shared_cpu_map, this_leaf->shared_cpu_map, cpu_online_map);
-        len = cpumask_scnprintf(buf, NR_CPUS+1, shared_cpu_map);
+        len = cpumask_scnprintf(buf, NR_CPUS+1, &shared_cpu_map);
        len += sprintf(buf+len, "\n");
        return len;
 }
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index 0c66dbdd1d72..66fd705e82c0 100644
--- a/arch/ia64/sn/kernel/irq.c
+++ b/arch/ia64/sn/kernel/irq.c
@@ -227,14 +227,14 @@ finish_up:
        return new_irq_info;
 }
-static void sn_set_affinity_irq(unsigned int irq, cpumask_t mask)
+static void sn_set_affinity_irq(unsigned int irq, const struct cpumask *mask)
 {
        struct sn_irq_info *sn_irq_info, *sn_irq_info_safe;
        nasid_t nasid;
        int slice;
-        nasid = cpuid_to_nasid(first_cpu(mask));
+        nasid = cpuid_to_nasid(cpumask_first(mask));
-        slice = cpuid_to_slice(first_cpu(mask));
+        slice = cpuid_to_slice(cpumask_first(mask));
        list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe,
                                 sn_irq_lh[irq], list)
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 83f190ffe350..ca553b0429ce 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -151,7 +151,8 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry)
 }
 #ifdef CONFIG_SMP
-static void sn_set_msi_irq_affinity(unsigned int irq, cpumask_t cpu_mask)
+static void sn_set_msi_irq_affinity(unsigned int irq,
+                                    const struct cpumask *cpu_mask)
 {
        struct msi_msg msg;
        int slice;
@@ -164,7 +165,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq, cpumask_t cpu_mask)
        struct sn_pcibus_provider *provider;
        unsigned int cpu;
-        cpu = first_cpu(cpu_mask);
+        cpu = cpumask_first(cpu_mask);
        sn_irq_info = sn_msi_info[irq].sn_irq_info;
        if (sn_irq_info == NULL || sn_irq_info->irq_int_bit >= 0)
                return;
@@ -204,7 +205,7 @@ static void sn_set_msi_irq_affinity(unsigned int irq, cpumask_t cpu_mask)
        msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff);
        write_msi_msg(irq, &msg);
-        irq_desc[irq].affinity = cpu_mask;
+        irq_desc[irq].affinity = *cpu_mask;
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 29047d5c259a..cabba332cc48 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -10,6 +10,7 @@ config M32R
        default y
        select HAVE_IDE
        select HAVE_OPROFILE
+        select INIT_ALL_POSSIBLE
 config SBUS
        bool
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index 39cb6da72dcb..0f06b3722e96 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -73,17 +73,11 @@ static unsigned int bsp_phys_id = -1;
 /* Bitmask of physically existing CPUs */
 physid_mask_t phys_cpu_present_map;
-/* Bitmask of currently online CPUs */
-cpumask_t cpu_online_map;
-EXPORT_SYMBOL(cpu_online_map);
 cpumask_t cpu_bootout_map;
 cpumask_t cpu_bootin_map;
 static cpumask_t cpu_callin_map;
 cpumask_t cpu_callout_map;
 EXPORT_SYMBOL(cpu_callout_map);
-cpumask_t cpu_possible_map = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_possible_map);
 /* Per CPU bogomips and other parameters */
 struct cpuinfo_m32r cpu_data[NR_CPUS] __cacheline_aligned;
diff --git a/arch/m68knommu/platform/coldfire/pit.c b/arch/m68knommu/platform/coldfire/pit.c
index c5b916700b22..2a12e7fa9748 100644
--- a/arch/m68knommu/platform/coldfire/pit.c
+++ b/arch/m68knommu/platform/coldfire/pit.c
@@ -156,7 +156,7 @@ void hw_timer_init(void)
 {
        u32 imr;
-        cf_pit_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
+        cf_pit_clockevent.cpumask = cpumask_of(smp_processor_id());
        cf_pit_clockevent.mult = div_sc(FREQ, NSEC_PER_SEC, 32);
        cf_pit_clockevent.max_delta_ns =
                clockevent_delta2ns(0xFFFF, &cf_pit_clockevent);
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index a58f0eecc68f..abc62aa744ac 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -49,7 +49,8 @@ static inline void smtc_im_ack_irq(unsigned int irq)
 #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
 #include <linux/cpumask.h>
-extern void plat_set_irq_affinity(unsigned int irq, cpumask_t affinity);
+extern void plat_set_irq_affinity(unsigned int irq,
+                                  const struct cpumask *affinity);
 extern void smtc_forward_irq(unsigned int irq);
 /*
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 0ff5b523ea77..86557b5d1b3f 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -38,9 +38,6 @@ extern int __cpu_logical_map[NR_CPUS];
 #define SMP_RESCHEDULE_YOURSELF 0x1     /* XXX braindead */
 #define SMP_CALL_FUNCTION       0x2
-extern cpumask_t phys_cpu_present_map;
-#define cpu_possible_map        phys_cpu_present_map
 extern void asmlinkage smp_bootstrap(void);
 /*
diff --git a/arch/mips/jazz/irq.c b/arch/mips/jazz/irq.c
index d7f8a782aae4..03965cb1b252 100644
--- a/arch/mips/jazz/irq.c
+++ b/arch/mips/jazz/irq.c
@@ -146,7 +146,7 @@ void __init plat_time_init(void)
        BUG_ON(HZ != 100);
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        clockevents_register_device(cd);
        action->dev_id = cd;
        setup_irq(JAZZ_TIMER_IRQ, action);
diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c
index 0a57f86945f1..b820661678b0 100644
--- a/arch/mips/kernel/cevt-bcm1480.c
+++ b/arch/mips/kernel/cevt-bcm1480.c
@@ -126,7 +126,7 @@ void __cpuinit sb1480_clockevent_init(void)
        cd->min_delta_ns        = clockevent_delta2ns(2, cd);
        cd->rating              = 200;
        cd->irq                 = irq;
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        cd->set_next_event      = sibyte_next_event;
        cd->set_mode            = sibyte_set_mode;
        clockevents_register_device(cd);
@@ -148,6 +148,6 @@ void __cpuinit sb1480_clockevent_init(void)
        action->name    = name;
        action->dev_id  = cd;
-        irq_set_affinity(irq, cpumask_of_cpu(cpu));
+        irq_set_affinity(irq, cpumask_of(cpu));
        setup_irq(irq, action);
 }
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
index df4acb68bfb5..1ada45ea0700 100644
--- a/arch/mips/kernel/cevt-ds1287.c
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -88,7 +88,6 @@ static void ds1287_event_handler(struct clock_event_device *dev)
 static struct clock_event_device ds1287_clockevent = {
        .name           = "ds1287",
        .features       = CLOCK_EVT_FEAT_PERIODIC,
-        .cpumask        = CPU_MASK_CPU0,
        .set_next_event = ds1287_set_next_event,
        .set_mode       = ds1287_set_mode,
        .event_handler  = ds1287_event_handler,
@@ -122,6 +121,7 @@ int __init ds1287_clockevent_init(int irq)
        clockevent_set_clock(cd, 32768);
        cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
        cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+        cd->cpumask = cpumask_of(0);
        clockevents_register_device(&ds1287_clockevent);
diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c
index 6e2f58520afb..e9b787feedcb 100644
--- a/arch/mips/kernel/cevt-gt641xx.c
+++ b/arch/mips/kernel/cevt-gt641xx.c
@@ -96,7 +96,6 @@ static void gt641xx_timer0_event_handler(struct clock_event_device *dev)
 static struct clock_event_device gt641xx_timer0_clockevent = {
        .name           = "gt641xx-timer0",
        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-        .cpumask        = CPU_MASK_CPU0,
        .irq            = GT641XX_TIMER0_IRQ,
        .set_next_event = gt641xx_timer0_set_next_event,
        .set_mode       = gt641xx_timer0_set_mode,
@@ -132,6 +131,7 @@ static int __init gt641xx_timer0_clockevent_init(void)
        clockevent_set_clock(cd, gt641xx_base_clock);
        cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
        cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+        cd->cpumask = cpumask_of(0);
        clockevents_register_device(&gt641xx_timer0_clockevent);
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 4a4c59f2737a..e1ec83b68031 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -195,7 +195,7 @@ int __cpuinit mips_clockevent_init(void)
        cd->rating              = 300;
        cd->irq                 = irq;
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        cd->set_next_event      = mips_next_event;
        cd->set_mode            = mips_set_clock_mode;
        cd->event_handler       = mips_event_handler;
diff --git a/arch/mips/kernel/cevt-sb1250.c b/arch/mips/kernel/cevt-sb1250.c
index 63ac3ad462bc..a2eebaafda52 100644
--- a/arch/mips/kernel/cevt-sb1250.c
+++ b/arch/mips/kernel/cevt-sb1250.c
@@ -125,7 +125,7 @@ void __cpuinit sb1250_clockevent_init(void)
        cd->min_delta_ns        = clockevent_delta2ns(2, cd);
        cd->rating              = 200;
        cd->irq                 = irq;
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        cd->set_next_event      = sibyte_next_event;
        cd->set_mode            = sibyte_set_mode;
        clockevents_register_device(cd);
@@ -147,6 +147,6 @@ void __cpuinit sb1250_clockevent_init(void)
        action->name    = name;
        action->dev_id  = cd;
-        irq_set_affinity(irq, cpumask_of_cpu(cpu));
+        irq_set_affinity(irq, cpumask_of(cpu));
        setup_irq(irq, action);
 }
diff --git a/arch/mips/kernel/cevt-smtc.c b/arch/mips/kernel/cevt-smtc.c
index 5162fe4b5952..6d45e24db5bf 100644
--- a/arch/mips/kernel/cevt-smtc.c
+++ b/arch/mips/kernel/cevt-smtc.c
@@ -292,7 +292,7 @@ int __cpuinit mips_clockevent_init(void)
        cd->rating              = 300;
        cd->irq                 = irq;
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        cd->set_next_event      = mips_next_event;
        cd->set_mode            = mips_set_clock_mode;
        cd->event_handler       = mips_event_handler;
diff --git a/arch/mips/kernel/cevt-txx9.c b/arch/mips/kernel/cevt-txx9.c
index b5fc4eb412d2..eccf7d6096bd 100644
--- a/arch/mips/kernel/cevt-txx9.c
+++ b/arch/mips/kernel/cevt-txx9.c
@@ -112,7 +112,6 @@ static struct clock_event_device txx9tmr_clock_event_device = {
        .name           = "TXx9",
        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
        .rating         = 200,
-        .cpumask        = CPU_MASK_CPU0,
        .set_mode       = txx9tmr_set_mode,
        .set_next_event = txx9tmr_set_next_event,
 };
@@ -150,6 +149,7 @@ void __init txx9_clockevent_init(unsigned long baseaddr, int irq,
                clockevent_delta2ns(0xffffffff >> (32 - TXX9_TIMER_BITS), cd);
        cd->min_delta_ns = clockevent_delta2ns(0xf, cd);
        cd->irq = irq;
+        cd->cpumask = cpumask_of(0),
        clockevents_register_device(cd);
        setup_irq(irq, &txx9tmr_irq);
        printk(KERN_INFO "TXx9: clockevent device at 0x%lx, irq %d\n",
diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c
index b6ac55162b9a..f4d187825f96 100644
--- a/arch/mips/kernel/i8253.c
+++ b/arch/mips/kernel/i8253.c
@@ -115,7 +115,7 @@ void __init setup_pit_timer(void)
         * Start pit with the boot cpu mask and make it global after the
         * IO_APIC has been initialized.
         */
-        cd->cpumask = cpumask_of_cpu(cpu);
+        cd->cpumask = cpumask_of(cpu);
        clockevent_set_clock(cd, CLOCK_TICK_RATE);
        cd->max_delta_ns = clockevent_delta2ns(0x7FFF, cd);
        cd->min_delta_ns = clockevent_delta2ns(0xF, cd);
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index f0a4bb19e096..494a49a317e9 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -155,7 +155,7 @@ static void gic_unmask_irq(unsigned int irq)
 static DEFINE_SPINLOCK(gic_lock);
-static void gic_set_affinity(unsigned int irq, cpumask_t cpumask)
+static void gic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
        cpumask_t       tmp = CPU_MASK_NONE;
        unsigned long   flags;
@@ -164,7 +164,7 @@ static void gic_set_affinity(unsigned int irq, cpumask_t cpumask)
        pr_debug(KERN_DEBUG "%s called\n", __func__);
        irq -= _irqbase;
-        cpus_and(tmp, cpumask, cpu_online_map);
+        cpumask_and(&tmp, cpumask, cpu_online_mask);
        if (cpus_empty(tmp))
                return;
@@ -187,7 +187,7 @@ static void gic_set_affinity(unsigned int irq, cpumask_t cpumask)
                set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
        }
-        irq_desc[irq].affinity = cpumask;
+        irq_desc[irq].affinity = *cpumask;
        spin_unlock_irqrestore(&gic_lock, flags);
 }
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index ca476c4f62a5..f27beca4b26d 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -51,10 +51,10 @@ static int __init allowcpus(char *str)
        int len;
        cpus_clear(cpu_allow_map);
-        if (cpulist_parse(str, cpu_allow_map) == 0) {
+        if (cpulist_parse(str, &cpu_allow_map) == 0) {
                cpu_set(0, cpu_allow_map);
                cpus_and(cpu_possible_map, cpu_possible_map, cpu_allow_map);
-                len = cpulist_scnprintf(buf, sizeof(buf)-1, cpu_possible_map);
+                len = cpulist_scnprintf(buf, sizeof(buf)-1, &cpu_possible_map);
                buf[len] = '\0';
                pr_debug("Allowable CPUs: %s\n", buf);
                return 1;
@@ -226,7 +226,7 @@ void __init cmp_smp_setup(void)
        for (i = 1; i < NR_CPUS; i++) {
                if (amon_cpu_avail(i)) {
-                        cpu_set(i, phys_cpu_present_map);
+                        cpu_set(i, cpu_possible_map);
                        __cpu_number_map[i]     = ++ncpu;
                        __cpu_logical_map[ncpu] = i;
                }
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 87a1816c1f45..6f7ee5ac46ee 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -70,7 +70,7 @@ static unsigned int __init smvp_vpe_init(unsigned int tc, unsigned int mvpconf0,
                write_vpe_c0_vpeconf0(tmp);
                /* Record this as available CPU */
-                cpu_set(tc, phys_cpu_present_map);
+                cpu_set(tc, cpu_possible_map);
                __cpu_number_map[tc]    = ++ncpu;
                __cpu_logical_map[ncpu] = tc;
        }
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 8bf88faf5afd..3da94704f816 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -44,15 +44,10 @@
 #include <asm/mipsmtregs.h>
 #endif /* CONFIG_MIPS_MT_SMTC */
-cpumask_t phys_cpu_present_map;         /* Bitmask of available CPUs */
 volatile cpumask_t cpu_callin_map;      /* Bitmask of started secondaries */
-cpumask_t cpu_online_map;               /* Bitmask of currently online CPUs */
 int __cpu_number_map[NR_CPUS];          /* Map physical to logical */
 int __cpu_logical_map[NR_CPUS];         /* Map logical to physical */
-EXPORT_SYMBOL(phys_cpu_present_map);
-EXPORT_SYMBOL(cpu_online_map);
 extern void cpu_idle(void);
 /* Number of TCs (or siblings in Intel speak) per CPU core */
@@ -195,7 +190,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 /* preload SMP state for boot cpu */
 void __devinit smp_prepare_boot_cpu(void)
 {
-        cpu_set(0, phys_cpu_present_map);
+        cpu_set(0, cpu_possible_map);
        cpu_set(0, cpu_online_map);
        cpu_set(0, cpu_callin_map);
 }
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 897fb2b4751c..b6cca01ff82b 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -290,7 +290,7 @@ static void smtc_configure_tlb(void)
 * possibly leave some TCs/VPEs as "slave" processors.
 *
 * Use c0_MVPConf0 to find out how many TCs are available, setting up
- * phys_cpu_present_map and the logical/physical mappings.
+ * cpu_possible_map and the logical/physical mappings.
 */
 int __init smtc_build_cpu_map(int start_cpu_slot)
@@ -304,7 +304,7 @@ int __init smtc_build_cpu_map(int start_cpu_slot)
         */
        ntcs = ((read_c0_mvpconf0() & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
        for (i=start_cpu_slot; i<NR_CPUS && i<ntcs; i++) {
-                cpu_set(i, phys_cpu_present_map);
+                cpu_set(i, cpu_possible_map);
                __cpu_number_map[i] = i;
                __cpu_logical_map[i] = i;
        }
@@ -521,7 +521,7 @@ void smtc_prepare_cpus(int cpus)
         * Pull any physically present but unused TCs out of circulation.
         */
        while (tc < (((val & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1)) {
-                cpu_clear(tc, phys_cpu_present_map);
+                cpu_clear(tc, cpu_possible_map);
                cpu_clear(tc, cpu_present_map);
                tc++;
        }
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
index f84a46a8ae6e..aabd7274507b 100644
--- a/arch/mips/mti-malta/malta-smtc.c
+++ b/arch/mips/mti-malta/malta-smtc.c
@@ -114,9 +114,9 @@ struct plat_smp_ops msmtc_smp_ops = {
 */
-void plat_set_irq_affinity(unsigned int irq, cpumask_t affinity)
+void plat_set_irq_affinity(unsigned int irq, const struct cpumask *affinity)
 {
-        cpumask_t tmask = affinity;
+        cpumask_t tmask = *affinity;
        int cpu = 0;
        void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff);
@@ -139,7 +139,7 @@ void plat_set_irq_affinity(unsigned int irq, cpumask_t affinity)
         * be made to forward to an offline "CPU".
         */
-        for_each_cpu_mask(cpu, affinity) {
+        for_each_cpu(cpu, affinity) {
                if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu))
                        cpu_clear(cpu, tmask);
        }
diff --git a/arch/mips/nxp/pnx8550/common/time.c b/arch/mips/nxp/pnx8550/common/time.c
index 62f495b57f93..cf293b279098 100644
--- a/arch/mips/nxp/pnx8550/common/time.c
+++ b/arch/mips/nxp/pnx8550/common/time.c
@@ -102,6 +102,7 @@ __init void plat_time_init(void)
        unsigned int p;
        unsigned int pow2p;
+        pnx8xxx_clockevent.cpumask = cpu_none_mask;
        clockevents_register_device(&pnx8xxx_clockevent);
        clocksource_register(&pnx_clocksource);
diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c
index 3a7df647ca77..f78c29b68d77 100644
--- a/arch/mips/pmc-sierra/yosemite/smp.c
+++ b/arch/mips/pmc-sierra/yosemite/smp.c
@@ -141,7 +141,7 @@ static void __cpuinit yos_boot_secondary(int cpu, struct task_struct *idle)
 }
 /*
- * Detect available CPUs, populate phys_cpu_present_map before smp_init
+ * Detect available CPUs, populate cpu_possible_map before smp_init
 *
 * We don't want to start the secondary CPU yet nor do we have a nice probing
 * feature in PMON so we just assume presence of the secondary core.
@@ -150,10 +150,10 @@ static void __init yos_smp_setup(void)
 {
        int i;
-        cpus_clear(phys_cpu_present_map);
+        cpus_clear(cpu_possible_map);
        for (i = 0; i < 2; i++) {
-                cpu_set(i, phys_cpu_present_map);
+                cpu_set(i, cpu_possible_map);
                __cpu_number_map[i]     = i;
                __cpu_logical_map[i]    = i;
        }
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index ba5cdebeaf0d..5b47d6b65275 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -76,7 +76,7 @@ static int do_cpumask(cnodeid_t cnode, nasid_t nasid, int highest)
                        /* Only let it join in if it's marked enabled */
                        if ((acpu->cpu_info.flags & KLINFO_ENABLE) &&
                            (tot_cpus_found != NR_CPUS)) {
-                                cpu_set(cpuid, phys_cpu_present_map);
+                                cpu_set(cpuid, cpu_possible_map);
                                alloc_cpupda(cpuid, tot_cpus_found);
                                cpus_found++;
                                tot_cpus_found++;
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index 1327c2746fb7..f024057a35f8 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -134,7 +134,7 @@ void __cpuinit hub_rt_clock_event_init(void)
        cd->min_delta_ns        = clockevent_delta2ns(0x300, cd);
        cd->rating              = 200;
        cd->irq                 = irq;
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        cd->set_next_event      = rt_next_event;
        cd->set_mode            = rt_set_mode;
        clockevents_register_device(cd);
diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c
index a35818ed4263..12b465d404df 100644
--- a/arch/mips/sibyte/bcm1480/irq.c
+++ b/arch/mips/sibyte/bcm1480/irq.c
@@ -50,7 +50,7 @@ static void enable_bcm1480_irq(unsigned int irq);
 static void disable_bcm1480_irq(unsigned int irq);
 static void ack_bcm1480_irq(unsigned int irq);
 #ifdef CONFIG_SMP
-static void bcm1480_set_affinity(unsigned int irq, cpumask_t mask);
+static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask);
 #endif
 #ifdef CONFIG_PCI
@@ -109,7 +109,7 @@ void bcm1480_unmask_irq(int cpu, int irq)
 }
 #ifdef CONFIG_SMP
-static void bcm1480_set_affinity(unsigned int irq, cpumask_t mask)
+static void bcm1480_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
        int i = 0, old_cpu, cpu, int_on, k;
        u64 cur_ints;
@@ -117,11 +117,11 @@ static void bcm1480_set_affinity(unsigned int irq, cpumask_t mask)
        unsigned long flags;
        unsigned int irq_dirty;
-        if (cpus_weight(mask) != 1) {
+        if (cpumask_weight(mask) != 1) {
                printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
                return;
        }
-        i = first_cpu(mask);
+        i = cpumask_first(mask);
        /* Convert logical CPU to physical CPU */
        cpu = cpu_logical_map(i);
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index bd9eeb43ed0e..dddfda8e8294 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -136,7 +136,7 @@ static void __cpuinit bcm1480_boot_secondary(int cpu, struct task_struct *idle)
 /*
 * Use CFE to find out how many CPUs are available, setting up
- * phys_cpu_present_map and the logical/physical mappings.
+ * cpu_possible_map and the logical/physical mappings.
 * XXXKW will the boot CPU ever not be physical 0?
 *
 * Common setup before any secondaries are started
@@ -145,14 +145,14 @@ static void __init bcm1480_smp_setup(void)
 {
        int i, num;
-        cpus_clear(phys_cpu_present_map);
+        cpus_clear(cpu_possible_map);
-        cpu_set(0, phys_cpu_present_map);
+        cpu_set(0, cpu_possible_map);
        __cpu_number_map[0] = 0;
        __cpu_logical_map[0] = 0;
        for (i = 1, num = 0; i < NR_CPUS; i++) {
                if (cfe_cpu_stop(i) == 0) {
-                        cpu_set(i, phys_cpu_present_map);
+                        cpu_set(i, cpu_possible_map);
                        __cpu_number_map[i] = ++num;
                        __cpu_logical_map[num] = i;
                }
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index a5158483986e..808ac2959b8c 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -50,7 +50,7 @@ static void enable_sb1250_irq(unsigned int irq);
 static void disable_sb1250_irq(unsigned int irq);
 static void ack_sb1250_irq(unsigned int irq);
 #ifdef CONFIG_SMP
-static void sb1250_set_affinity(unsigned int irq, cpumask_t mask);
+static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask);
 #endif
 #ifdef CONFIG_SIBYTE_HAS_LDT
@@ -103,16 +103,16 @@ void sb1250_unmask_irq(int cpu, int irq)
 }
 #ifdef CONFIG_SMP
-static void sb1250_set_affinity(unsigned int irq, cpumask_t mask)
+static void sb1250_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
        int i = 0, old_cpu, cpu, int_on;
        u64 cur_ints;
        struct irq_desc *desc = irq_desc + irq;
        unsigned long flags;
-        i = first_cpu(mask);
+        i = cpumask_first(mask);
-        if (cpus_weight(mask) > 1) {
+        if (cpumask_weight(mask) > 1) {
                printk("attempted to set irq affinity for irq %d to multiple CPUs\n", irq);
                return;
        }
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index 0734b933e969..5950a288a7da 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -124,7 +124,7 @@ static void __cpuinit sb1250_boot_secondary(int cpu, struct task_struct *idle)
 /*
 * Use CFE to find out how many CPUs are available, setting up
- * phys_cpu_present_map and the logical/physical mappings.
+ * cpu_possible_map and the logical/physical mappings.
 * XXXKW will the boot CPU ever not be physical 0?
 *
 * Common setup before any secondaries are started
@@ -133,14 +133,14 @@ static void __init sb1250_smp_setup(void)
 {
        int i, num;
-        cpus_clear(phys_cpu_present_map);
+        cpus_clear(cpu_possible_map);
-        cpu_set(0, phys_cpu_present_map);
+        cpu_set(0, cpu_possible_map);
        __cpu_number_map[0] = 0;
        __cpu_logical_map[0] = 0;
        for (i = 1, num = 0; i < NR_CPUS; i++) {
                if (cfe_cpu_stop(i) == 0) {
-                        cpu_set(i, phys_cpu_present_map);
+                        cpu_set(i, cpu_possible_map);
                        __cpu_number_map[i] = ++num;
                        __cpu_logical_map[num] = i;
                }
diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c
index 796e3ce28720..69f5f88711cc 100644
--- a/arch/mips/sni/time.c
+++ b/arch/mips/sni/time.c
@@ -80,7 +80,7 @@ static void __init sni_a20r_timer_setup(void)
        struct irqaction *action = &a20r_irqaction;
        unsigned int cpu = smp_processor_id();
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        clockevents_register_device(cd);
        action->dev_id = cd;
        setup_irq(SNI_A20R_IRQ_TIMER, &a20r_irqaction);
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 644a70b1b04e..aacf11d33723 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -11,6 +11,7 @@ config PARISC
        select HAVE_OPROFILE
        select RTC_CLASS
        select RTC_DRV_PARISC
+        select INIT_ALL_POSSIBLE
        help
          The PA-RISC microprocessor is designed by Hewlett-Packard and used
          in many of their workstations & servers (HP9000 700 and 800 series,
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 23ef950df008..4cea935e2f99 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -131,12 +131,12 @@ int cpu_check_affinity(unsigned int irq, cpumask_t *dest)
        return 0;
 }
-static void cpu_set_affinity_irq(unsigned int irq, cpumask_t dest)
+static void cpu_set_affinity_irq(unsigned int irq, const struct cpumask *dest)
 {
-        if (cpu_check_affinity(irq, &dest))
+        if (cpu_check_affinity(irq, dest))
                return;
-        irq_desc[irq].affinity = dest;
+        irq_desc[irq].affinity = *dest;
 }
 #endif
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index d47f3975c9c6..80bc000523fa 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -67,21 +67,6 @@ static volatile int cpu_now_booting __read_mostly = 0;	/* track which CPU is boo
 static int parisc_max_cpus __read_mostly = 1;
-/* online cpus are ones that we've managed to bring up completely
- * possible cpus are all valid cpu 
- * present cpus are all detected cpu
- *
- * On startup we bring up the "possible" cpus. Since we discover
- * CPUs later, we add them as hotplug, so the possible cpu mask is
- * empty in the beginning.
- */
-cpumask_t cpu_online_map   __read_mostly = CPU_MASK_NONE;       /* Bitmap of online CPUs */
-cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;        /* Bitmap of Present CPUs */
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL(cpu_possible_map);
 DEFINE_PER_CPU(spinlock_t, ipi_lock) = SPIN_LOCK_UNLOCKED;
 enum ipi_message_type {
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index ac222d0ab12e..23b8b5e36f98 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -237,7 +237,7 @@ void fixup_irqs(cpumask_t map)
                        mask = map;
                }
                if (irq_desc[irq].chip->set_affinity)
-                        irq_desc[irq].chip->set_affinity(irq, mask);
+                        irq_desc[irq].chip->set_affinity(irq, &mask);
                else if (irq_desc[irq].action && !(warned++))
                        printk("Cannot set affinity for irq %i\n", irq);
        }
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ff9f7010097d..d1165566f064 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -60,13 +60,9 @@
 int smp_hw_index[NR_CPUS];
 struct thread_info *secondary_ti;
-cpumask_t cpu_possible_map = CPU_MASK_NONE;
-cpumask_t cpu_online_map = CPU_MASK_NONE;
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 DEFINE_PER_CPU(cpumask_t, cpu_core_map) = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL(cpu_possible_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e2ee66b5831d..6f39d35d6f55 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -869,7 +869,7 @@ static void register_decrementer_clockevent(int cpu)
        struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;
        *dec = decrementer_clockevent;
-        dec->cpumask = cpumask_of_cpu(cpu);
+        dec->cpumask = cpumask_of(cpu);
        printk(KERN_DEBUG "clockevent: %s mult[%lx] shift[%d] cpu[%d]\n",
               dec->name, dec->mult, dec->shift, cpu);
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index e1904774a70f..424b335a71c8 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -332,7 +332,7 @@ static void xics_eoi_lpar(unsigned int virq)
        lpar_xirr_info_set((0xff << 24) | irq);
 }
-static void xics_set_affinity(unsigned int virq, cpumask_t cpumask)
+static void xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 {
        unsigned int irq;
        int status;
@@ -845,7 +845,7 @@ void xics_migrate_irqs_away(void)
                /* Reset affinity to all cpus */
                irq_desc[virq].affinity = CPU_MASK_ALL;
-                desc->chip->set_affinity(virq, CPU_MASK_ALL);
+                desc->chip->set_affinity(virq, cpu_all_mask);
 unlock:
                spin_unlock_irqrestore(&desc->lock, flags);
        }
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 1890fb085cde..5d7f9f0c93c3 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -817,7 +817,7 @@ static void mpic_end_ipi(unsigned int irq)
 #endif /* CONFIG_SMP */
-void mpic_set_affinity(unsigned int irq, cpumask_t cpumask)
+void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
        struct mpic *mpic = mpic_from_irq(irq);
        unsigned int src = mpic_irq_to_hw(irq);
@@ -829,7 +829,7 @@ void mpic_set_affinity(unsigned int irq, cpumask_t cpumask)
        } else {
                cpumask_t tmp;
-                cpus_and(tmp, cpumask, cpu_online_map);
+                cpumask_and(&tmp, cpumask, cpu_online_mask);
                mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION),
                               mpic_physmask(cpus_addr(tmp)[0]));
diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
index 6209c62a426d..3cef2af10f42 100644
--- a/arch/powerpc/sysdev/mpic.h
+++ b/arch/powerpc/sysdev/mpic.h
@@ -36,6 +36,6 @@ static inline int mpic_pasemi_msi_init(struct mpic *mpic)
 extern int mpic_set_irq_type(unsigned int virq, unsigned int flow_type);
 extern void mpic_set_vector(unsigned int virq, unsigned int vector);
-extern void mpic_set_affinity(unsigned int irq, cpumask_t cpumask);
+extern void mpic_set_affinity(unsigned int irq, const struct cpumask *cpumask);
 #endif /* _POWERPC_SYSDEV_MPIC_H */
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8116a3328a19..b4aa5869c7f9 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -75,6 +75,7 @@ config S390
        select HAVE_KRETPROBES
        select HAVE_KVM if 64BIT
        select HAVE_ARCH_TRACEHOOK
+        select INIT_ALL_POSSIBLE
 source "init/Kconfig"
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index b5595688a477..f03914b8ed2f 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -52,12 +52,6 @@
 struct _lowcore *lowcore_ptr[NR_CPUS];
 EXPORT_SYMBOL(lowcore_ptr);
-cpumask_t cpu_online_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_online_map);
-cpumask_t cpu_possible_map = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_possible_map);
 static struct task_struct *current_set[NR_CPUS];
 static u8 smp_cpu_type;
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index eccefbbff887..f5bd141c8443 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -154,7 +154,7 @@ void init_cpu_timer(void)
        cd->min_delta_ns        = 1;
        cd->max_delta_ns        = LONG_MAX;
        cd->rating              = 400;
-        cd->cpumask             = cpumask_of_cpu(cpu);
+        cd->cpumask             = cpumask_of(cpu);
        cd->set_next_event      = s390_next_event;
        cd->set_mode            = s390_set_mode;
diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h
index 85b660c17eb0..c24e9c6a1736 100644
--- a/arch/sh/include/asm/smp.h
+++ b/arch/sh/include/asm/smp.h
@@ -31,7 +31,7 @@ enum {
 };
 void smp_message_recv(unsigned int msg);
-void smp_timer_broadcast(cpumask_t mask);
+void smp_timer_broadcast(const struct cpumask *mask);
 void local_timer_interrupt(void);
 void local_timer_setup(unsigned int cpu);
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index 3c5ad1660bbc..8f4027412614 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -31,12 +31,6 @@
 int __cpu_number_map[NR_CPUS];          /* Map physical to logical */
 int __cpu_logical_map[NR_CPUS];         /* Map logical to physical */
-cpumask_t cpu_possible_map;
-EXPORT_SYMBOL(cpu_possible_map);
-cpumask_t cpu_online_map;
-EXPORT_SYMBOL(cpu_online_map);
 static inline void __init smp_store_cpu_info(unsigned int cpu)
 {
        struct sh_cpuinfo *c = cpu_data + cpu;
@@ -190,11 +184,11 @@ void arch_send_call_function_single_ipi(int cpu)
        plat_send_ipi(cpu, SMP_MSG_FUNCTION_SINGLE);
 }
-void smp_timer_broadcast(cpumask_t mask)
+void smp_timer_broadcast(const struct cpumask *mask)
 {
        int cpu;
-        for_each_cpu_mask(cpu, mask)
+        for_each_cpu(cpu, mask)
                plat_send_ipi(cpu, SMP_MSG_TIMER);
 }
diff --git a/arch/sh/kernel/timers/timer-broadcast.c b/arch/sh/kernel/timers/timer-broadcast.c
index c2317635230f..96e8eaea1e62 100644
--- a/arch/sh/kernel/timers/timer-broadcast.c
+++ b/arch/sh/kernel/timers/timer-broadcast.c
@@ -51,7 +51,7 @@ void __cpuinit local_timer_setup(unsigned int cpu)
        clk->mult               = 1;
        clk->set_mode           = dummy_timer_set_mode;
        clk->broadcast          = smp_timer_broadcast;
-        clk->cpumask            = cpumask_of_cpu(cpu);
+        clk->cpumask            = cpumask_of(cpu);
        clockevents_register_device(clk);
 }
diff --git a/arch/sh/kernel/timers/timer-tmu.c b/arch/sh/kernel/timers/timer-tmu.c
index 3c61ddd4d43e..0db3f9510336 100644
--- a/arch/sh/kernel/timers/timer-tmu.c
+++ b/arch/sh/kernel/timers/timer-tmu.c
@@ -263,7 +263,7 @@ static int tmu_timer_init(void)
        tmu0_clockevent.min_delta_ns =
                        clockevent_delta2ns(1, &tmu0_clockevent);
-        tmu0_clockevent.cpumask = cpumask_of_cpu(0);
+        tmu0_clockevent.cpumask = cpumask_of(0);
        clockevents_register_device(&tmu0_clockevent);
diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h
index a8180e546a48..8408d9d2a662 100644
--- a/arch/sparc/include/asm/smp_32.h
+++ b/arch/sparc/include/asm/smp_32.h
@@ -29,8 +29,6 @@
 */
 extern unsigned char boot_cpu_id;
-extern cpumask_t phys_cpu_present_map;
-#define cpu_possible_map phys_cpu_present_map
 typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long,
                       unsigned long, unsigned long);
diff --git a/arch/sparc/kernel/smp.c b/arch/sparc/kernel/smp.c
index e396c1f17a92..1e5ac4e282e1 100644
--- a/arch/sparc/kernel/smp.c
+++ b/arch/sparc/kernel/smp.c
@@ -39,8 +39,6 @@ volatile unsigned long cpu_callin_map[NR_CPUS] __cpuinitdata = {0,};
 unsigned char boot_cpu_id = 0;
 unsigned char boot_cpu_id4 = 0; /* boot_cpu_id << 2 */
-cpumask_t cpu_online_map = CPU_MASK_NONE;
-cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
 cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 /* The only guaranteed locking primitive available on all Sparc
@@ -334,7 +332,7 @@ void __init smp_setup_cpu_possible_map(void)
        instance = 0;
        while (!cpu_find_by_instance(instance, NULL, &mid)) {
                if (mid < NR_CPUS) {
-                        cpu_set(mid, phys_cpu_present_map);
+                        cpu_set(mid, cpu_possible_map);
                        cpu_set(mid, cpu_present_map);
                }
                instance++;
@@ -354,7 +352,7 @@ void __init smp_prepare_boot_cpu(void)
        current_thread_info()->cpu = cpuid;
        cpu_set(cpuid, cpu_online_map);
-        cpu_set(cpuid, phys_cpu_present_map);
+        cpu_set(cpuid, cpu_possible_map);
 }
 int __cpuinit __cpu_up(unsigned int cpu)
diff --git a/arch/sparc/kernel/sparc_ksyms.c b/arch/sparc/kernel/sparc_ksyms.c
index b0dfff848653..32d11a5fe3a8 100644
--- a/arch/sparc/kernel/sparc_ksyms.c
+++ b/arch/sparc/kernel/sparc_ksyms.c
@@ -113,10 +113,6 @@ EXPORT_PER_CPU_SYMBOL(__cpu_data);
 #ifdef CONFIG_SMP
 /* IRQ implementation. */
 EXPORT_SYMBOL(synchronize_irq);
-/* CPU online map and active count. */
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL(phys_cpu_present_map);
 #endif
 EXPORT_SYMBOL(__udelay);
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index 52fc836f464d..4aaf18e83c8c 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -312,7 +312,8 @@ static void sun4u_irq_enable(unsigned int virt_irq)
        }
 }
-static void sun4u_set_affinity(unsigned int virt_irq, cpumask_t mask)
+static void sun4u_set_affinity(unsigned int virt_irq,
+                               const struct cpumask *mask)
 {
        sun4u_irq_enable(virt_irq);
 }
@@ -362,7 +363,8 @@ static void sun4v_irq_enable(unsigned int virt_irq)
                       ino, err);
 }
-static void sun4v_set_affinity(unsigned int virt_irq, cpumask_t mask)
+static void sun4v_set_affinity(unsigned int virt_irq,
+                               const struct cpumask *mask)
 {
        unsigned int ino = virt_irq_table[virt_irq].dev_ino;
        unsigned long cpuid = irq_choose_cpu(virt_irq);
@@ -429,7 +431,8 @@ static void sun4v_virq_enable(unsigned int virt_irq)
                       dev_handle, dev_ino, err);
 }
-static void sun4v_virt_set_affinity(unsigned int virt_irq, cpumask_t mask)
+static void sun4v_virt_set_affinity(unsigned int virt_irq,
+                                    const struct cpumask *mask)
 {
        unsigned long cpuid, dev_handle, dev_ino;
        int err;
@@ -788,7 +791,7 @@ void fixup_irqs(void)
                    !(irq_desc[irq].status & IRQ_PER_CPU)) {
                        if (irq_desc[irq].chip->set_affinity)
                                irq_desc[irq].chip->set_affinity(irq,
-                                        irq_desc[irq].affinity);
+                                        &irq_desc[irq].affinity);
                }
                spin_unlock_irqrestore(&irq_desc[irq].lock, flags);
        }
diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc64/kernel/of_device.c
index 0f616ae3246c..df2efb7fc14c 100644
--- a/arch/sparc64/kernel/of_device.c
+++ b/arch/sparc64/kernel/of_device.c
@@ -780,7 +780,7 @@ out:
        if (nid != -1) {
                cpumask_t numa_mask = node_to_cpumask(nid);
-                irq_set_affinity(irq, numa_mask);
+                irq_set_affinity(irq, &numa_mask);
        }
        return irq;
diff --git a/arch/sparc64/kernel/pci_msi.c b/arch/sparc64/kernel/pci_msi.c
index 2e680f34f727..0d0cd815e83e 100644
--- a/arch/sparc64/kernel/pci_msi.c
+++ b/arch/sparc64/kernel/pci_msi.c
@@ -288,7 +288,7 @@ static int bringup_one_msi_queue(struct pci_pbm_info *pbm,
        if (nid != -1) {
                cpumask_t numa_mask = node_to_cpumask(nid);
-                irq_set_affinity(irq, numa_mask);
+                irq_set_affinity(irq, &numa_mask);
        }
        err = request_irq(irq, sparc64_msiq_interrupt, 0,
                          "MSIQ",
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index f500b0618bb0..a97b8822c22c 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -49,14 +49,10 @@
 int sparc64_multi_core __read_mostly;
-cpumask_t cpu_possible_map __read_mostly = CPU_MASK_NONE;
-cpumask_t cpu_online_map __read_mostly = CPU_MASK_NONE;
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
        { [0 ... NR_CPUS-1] = CPU_MASK_NONE };
-EXPORT_SYMBOL(cpu_possible_map);
-EXPORT_SYMBOL(cpu_online_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_SYMBOL(cpu_core_map);
diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c
index 141da3759091..9df8f095a8b1 100644
--- a/arch/sparc64/kernel/time.c
+++ b/arch/sparc64/kernel/time.c
@@ -763,7 +763,7 @@ void __devinit setup_sparc64_timer(void)
        sevt = &__get_cpu_var(sparc64_events);
        memcpy(sevt, &sparc64_clockevent, sizeof(*sevt));
-        sevt->cpumask = cpumask_of_cpu(smp_processor_id());
+        sevt->cpumask = cpumask_of(smp_processor_id());
        clockevents_register_device(sevt);
 }
diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index 045772142844..98351c78bc81 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -25,13 +25,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 #include "irq_user.h"
 #include "os.h"
-/* CPU online map, set by smp_boot_cpus */
-cpumask_t cpu_online_map = CPU_MASK_NONE;
-cpumask_t cpu_possible_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_online_map);
-EXPORT_SYMBOL(cpu_possible_map);
 /* Per CPU bogomips and other parameters
 * The only piece used here is the ipi pipe, which is set before SMP is
 * started and never changed.
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 47f04f4a3464..b13a87a3ec95 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -50,7 +50,7 @@ static int itimer_next_event(unsigned long delta,
 static struct clock_event_device itimer_clockevent = {
        .name           = "itimer",
        .rating         = 250,
-        .cpumask        = CPU_MASK_ALL,
+        .cpumask        = cpu_all_mask,
        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
        .set_mode       = itimer_set_mode,
        .set_next_event = itimer_next_event,
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 16f94879b525..b2cef49f3085 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -141,7 +141,7 @@ static int lapic_next_event(unsigned long delta,
                            struct clock_event_device *evt);
 static void lapic_timer_setup(enum clock_event_mode mode,
                              struct clock_event_device *evt);
-static void lapic_timer_broadcast(cpumask_t mask);
+static void lapic_timer_broadcast(const struct cpumask *mask);
 static void apic_pm_activate(void);
 /*
@@ -453,10 +453,10 @@ static void lapic_timer_setup(enum clock_event_mode mode,
 /*
 * Local APIC timer broadcast function
 */
-static void lapic_timer_broadcast(cpumask_t mask)
+static void lapic_timer_broadcast(const struct cpumask *mask)
 {
 #ifdef CONFIG_SMP
-        send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+        send_IPI_mask(*mask, LOCAL_TIMER_VECTOR);
 #endif
 }
@@ -469,7 +469,7 @@ static void __cpuinit setup_APIC_timer(void)
        struct clock_event_device *levt = &__get_cpu_var(lapic_events);
        memcpy(levt, &lapic_clockevent, sizeof(*levt));
-        levt->cpumask = cpumask_of_cpu(smp_processor_id());
+        levt->cpumask = cpumask_of(smp_processor_id());
        clockevents_register_device(levt);
 }
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 3f46afbb1cf1..43ea612d3e9d 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -626,8 +626,8 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
                cpumask_t *mask = &this_leaf->shared_cpu_map;
                n = type?
-                        cpulist_scnprintf(buf, len-2, *mask):
+                        cpulist_scnprintf(buf, len-2, mask) :
-                        cpumask_scnprintf(buf, len-2, *mask);
+                        cpumask_scnprintf(buf, len-2, mask);
                buf[n++] = '\n';
                buf[n] = '\0';
        }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 067d8de913f6..e76d7e272974 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -246,7 +246,7 @@ static void hpet_legacy_clockevent_register(void)
         * Start hpet with the boot cpu mask and make it
         * global after the IO_APIC has been initialized.
         */
-        hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
+        hpet_clockevent.cpumask = cpumask_of(smp_processor_id());
        clockevents_register_device(&hpet_clockevent);
        global_clock_event = &hpet_clockevent;
        printk(KERN_DEBUG "hpet clockevent registered\n");
@@ -301,7 +301,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
                        struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
                        hpet_setup_msi_irq(hdev->irq);
                        disable_irq(hdev->irq);
-                        irq_set_affinity(hdev->irq, cpumask_of_cpu(hdev->cpu));
+                        irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
                        enable_irq(hdev->irq);
                }
                break;
@@ -449,7 +449,7 @@ static int hpet_setup_irq(struct hpet_dev *dev)
                return -1;
        disable_irq(dev->irq);
-        irq_set_affinity(dev->irq, cpumask_of_cpu(dev->cpu));
+        irq_set_affinity(dev->irq, cpumask_of(dev->cpu));
        enable_irq(dev->irq);
        printk(KERN_DEBUG "hpet: %s irq %d for MSI\n",
@@ -500,7 +500,7 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
        /* 5 usec minimum reprogramming delta. */
        evt->min_delta_ns = 5000;
-        evt->cpumask = cpumask_of_cpu(hdev->cpu);
+        evt->cpumask = cpumask_of(hdev->cpu);
        clockevents_register_device(evt);
 }
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index c1b5e3ece1f2..10f92fb532f3 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -114,7 +114,7 @@ void __init setup_pit_timer(void)
         * Start pit with the boot cpu mask and make it global after the
         * IO_APIC has been initialized.
         */
-        pit_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
+        pit_clockevent.cpumask = cpumask_of(smp_processor_id());
        pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC,
                                     pit_clockevent.shift);
        pit_clockevent.max_delta_ns =
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index a1a2e070f31a..d7f0993b8056 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -398,7 +398,8 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 static int assign_irq_vector(int irq, struct irq_cfg *cfg, cpumask_t mask);
-static void set_ioapic_affinity_irq_desc(struct irq_desc *desc, cpumask_t mask)
+static void set_ioapic_affinity_irq_desc(struct irq_desc *desc,
+                                         const struct cpumask *mask)
 {
        struct irq_cfg *cfg;
        unsigned long flags;
@@ -406,18 +407,17 @@ static void set_ioapic_affinity_irq_desc(struct irq_desc *desc, cpumask_t mask)
        cpumask_t tmp;
        unsigned int irq;
-        cpus_and(tmp, mask, cpu_online_map);
+        if (!cpumask_intersects(mask, cpu_online_mask))
-        if (cpus_empty(tmp))
                return;
        irq = desc->irq;
        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(irq, cfg, *mask))
                return;
-        set_extra_move_desc(desc, mask);
+        set_extra_move_desc(desc, *mask);
-        cpus_and(tmp, cfg->domain, mask);
+        cpumask_and(&tmp, &cfg->domain, mask);
        dest = cpu_mask_to_apicid(tmp);
        /*
         * Only the high 8 bits are valid.
@@ -426,11 +426,12 @@ static void set_ioapic_affinity_irq_desc(struct irq_desc *desc, cpumask_t mask)
        spin_lock_irqsave(&ioapic_lock, flags);
        __target_IO_APIC_irq(irq, dest, cfg);
-        desc->affinity = mask;
+        cpumask_copy(&desc->affinity, mask);
        spin_unlock_irqrestore(&ioapic_lock, flags);
 }
-static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+static void set_ioapic_affinity_irq(unsigned int irq,
+                                    const struct cpumask *mask)
 {
        struct irq_desc *desc;
@@ -2272,7 +2273,7 @@ static void ir_irq_migration(struct work_struct *work)
                                continue;
                        }
-                        desc->chip->set_affinity(irq, desc->pending_mask);
+                        desc->chip->set_affinity(irq, &desc->pending_mask);
                        spin_unlock_irqrestore(&desc->lock, flags);
                }
        }
@@ -2281,18 +2282,20 @@ static void ir_irq_migration(struct work_struct *work)
 /*
 * Migrates the IRQ destination in the process context.
 */
-static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, cpumask_t mask)
+static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
+                                            const struct cpumask *mask)
 {
        if (desc->status & IRQ_LEVEL) {
                desc->status |= IRQ_MOVE_PENDING;
-                desc->pending_mask = mask;
+                cpumask_copy(&desc->pending_mask, mask);
                migrate_irq_remapped_level_desc(desc);
                return;
        }
        migrate_ioapic_irq_desc(desc, mask);
 }
-static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+static void set_ir_ioapic_affinity_irq(unsigned int irq,
+                                       const struct cpumask *mask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
@@ -3146,7 +3149,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 }
 #ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+static void set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
        struct irq_cfg *cfg;
@@ -3154,17 +3157,16 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
        unsigned int dest;
        cpumask_t tmp;
-        cpus_and(tmp, mask, cpu_online_map);
+        if (!cpumask_intersects(mask, cpu_online_mask))
-        if (cpus_empty(tmp))
                return;
        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(irq, cfg, *mask))
                return;
-        set_extra_move_desc(desc, mask);
+        set_extra_move_desc(desc, *mask);
-        cpus_and(tmp, cfg->domain, mask);
+        cpumask_and(&tmp, &cfg->domain, mask);
        dest = cpu_mask_to_apicid(tmp);
        read_msi_msg_desc(desc, &msg);
@@ -3175,14 +3177,15 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
        msg.address_lo |= MSI_ADDR_DEST_ID(dest);
        write_msi_msg_desc(desc, &msg);
-        desc->affinity = mask;
+        cpumask_copy(&desc->affinity, mask);
 }
 #ifdef CONFIG_INTR_REMAP
 /*
 * Migrate the MSI irq to another cpumask. This migration is
 * done in the process context using interrupt-remapping hardware.
 */
-static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+static void ir_set_msi_irq_affinity(unsigned int irq,
+                                    const struct cpumask *mask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
        struct irq_cfg *cfg;
@@ -3190,20 +3193,19 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
        cpumask_t tmp, cleanup_mask;
        struct irte irte;
-        cpus_and(tmp, mask, cpu_online_map);
+        if (!cpumask_intersects(mask, cpu_online_mask))
-        if (cpus_empty(tmp))
                return;
        if (get_irte(irq, &irte))
                return;
        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(irq, cfg, *mask))
                return;
        set_extra_move_desc(desc, mask);
-        cpus_and(tmp, cfg->domain, mask);
+        cpumask_and(&tmp, &cfg->domain, mask);
        dest = cpu_mask_to_apicid(tmp);
        irte.vector = cfg->vector;
@@ -3226,7 +3228,7 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
                cfg->move_in_progress = 0;
        }
-        desc->affinity = mask;
+        cpumask_copy(&desc->affinity, mask);
 }
 #endif
@@ -3417,7 +3419,7 @@ void arch_teardown_msi_irq(unsigned int irq)
 #ifdef CONFIG_DMAR
 #ifdef CONFIG_SMP
-static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
+static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
        struct irq_cfg *cfg;
@@ -3425,17 +3427,16 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
        unsigned int dest;
        cpumask_t tmp;
-        cpus_and(tmp, mask, cpu_online_map);
+        if (!cpumask_intersects(mask, cpu_online_mask))
-        if (cpus_empty(tmp))
                return;
        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(irq, cfg, *mask))
                return;
-        set_extra_move_desc(desc, mask);
+        set_extra_move_desc(desc, *mask);
-        cpus_and(tmp, cfg->domain, mask);
+        cpumask_and(&tmp, &cfg->domain, mask);
        dest = cpu_mask_to_apicid(tmp);
        dmar_msi_read(irq, &msg);
@@ -3446,7 +3447,7 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
        msg.address_lo |= MSI_ADDR_DEST_ID(dest);
        dmar_msi_write(irq, &msg);
-        desc->affinity = mask;
+        cpumask_copy(&desc->affinity, mask);
 }
 #endif /* CONFIG_SMP */
@@ -3480,7 +3481,7 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 #ifdef CONFIG_SMP
-static void hpet_msi_set_affinity(unsigned int irq, cpumask_t mask)
+static void hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
        struct irq_cfg *cfg;
@@ -3488,17 +3489,16 @@ static void hpet_msi_set_affinity(unsigned int irq, cpumask_t mask)
        unsigned int dest;
        cpumask_t tmp;
-        cpus_and(tmp, mask, cpu_online_map);
+        if (!cpumask_intersects(mask, cpu_online_mask))
-        if (cpus_empty(tmp))
                return;
        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(irq, cfg, *mask))
                return;
-        set_extra_move_desc(desc, mask);
+        set_extra_move_desc(desc, *mask);
-        cpus_and(tmp, cfg->domain, mask);
+        cpumask_and(&tmp, &cfg->domain, mask);
        dest = cpu_mask_to_apicid(tmp);
        hpet_msi_read(irq, &msg);
@@ -3509,7 +3509,7 @@ static void hpet_msi_set_affinity(unsigned int irq, cpumask_t mask)
        msg.address_lo |= MSI_ADDR_DEST_ID(dest);
        hpet_msi_write(irq, &msg);
-        desc->affinity = mask;
+        cpumask_copy(&desc->affinity, mask);
 }
 #endif /* CONFIG_SMP */
@@ -3564,28 +3564,27 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
        write_ht_irq_msg(irq, &msg);
 }
-static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
+static void set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
        struct irq_cfg *cfg;
        unsigned int dest;
        cpumask_t tmp;
-        cpus_and(tmp, mask, cpu_online_map);
+        if (!cpumask_intersects(mask, cpu_online_mask))
-        if (cpus_empty(tmp))
                return;
        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(irq, cfg, *mask))
                return;
-        set_extra_move_desc(desc, mask);
+        set_extra_move_desc(desc, *mask);
-        cpus_and(tmp, cfg->domain, mask);
+        cpumask_and(&tmp, &cfg->domain, mask);
        dest = cpu_mask_to_apicid(tmp);
        target_ht_irq(irq, dest, cfg->vector);
-        desc->affinity = mask;
+        cpumask_copy(&desc->affinity, mask);
 }
 #endif
@@ -3928,10 +3927,10 @@ void __init setup_ioapic_dest(void)
 #ifdef CONFIG_INTR_REMAP
                        if (intr_remapping_enabled)
-                                set_ir_ioapic_affinity_irq_desc(desc, mask);
+                                set_ir_ioapic_affinity_irq_desc(desc, &mask);
                        else
 #endif
-                                set_ioapic_affinity_irq_desc(desc, mask);
+                                set_ioapic_affinity_irq_desc(desc, &mask);
                }
        }
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 119fc9c8ff7f..9cf9cbbf7a02 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -253,7 +253,7 @@ void fixup_irqs(cpumask_t map)
                        mask = map;
                }
                if (desc->chip->set_affinity)
-                        desc->chip->set_affinity(irq, mask);
+                        desc->chip->set_affinity(irq, &mask);
                else if (desc->action && !(warned++))
                        printk("Cannot set affinity for irq %i\n", irq);
        }
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 900009c70591..27f2307b0a34 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -118,7 +118,7 @@ void fixup_irqs(cpumask_t map)
                        desc->chip->mask(irq);
                if (desc->chip->set_affinity)
-                        desc->chip->set_affinity(irq, mask);
+                        desc->chip->set_affinity(irq, &mask);
                else if (!(warned++))
                        set_affinity = 0;
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 3b599518c322..c12314c9e86f 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -287,7 +287,7 @@ static struct clock_event_device mfgpt_clockevent = {
        .set_mode = mfgpt_set_mode,
        .set_next_event = mfgpt_next_event,
        .rating = 250,
-        .cpumask = CPU_MASK_ALL,
+        .cpumask = cpu_all_mask,
        .shift = 32
 };
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index ae0c0d3bb770..1c2084291f97 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -282,7 +282,7 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
        else
                cpu_clear(cpu, *mask);
-        cpulist_scnprintf(buf, sizeof(buf), *mask);
+        cpulist_scnprintf(buf, sizeof(buf), mask);
        printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
                enable? "numa_add_cpu":"numa_remove_cpu", cpu, node, buf);
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0e9f446269f4..9d58134e0231 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -102,14 +102,8 @@ EXPORT_SYMBOL(smp_num_siblings);
 /* Last level cache ID of each logical CPU */
 DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
-/* bitmap of online cpus */
-cpumask_t cpu_online_map __read_mostly;
-EXPORT_SYMBOL(cpu_online_map);
 cpumask_t cpu_callin_map;
 cpumask_t cpu_callout_map;
-cpumask_t cpu_possible_map;
-EXPORT_SYMBOL(cpu_possible_map);
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index 254ee07f8635..c4c1f9e09402 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -226,7 +226,7 @@ static void __devinit vmi_time_init_clockevent(void)
        /* Upper bound is clockevent's use of ulong for cycle deltas. */
        evt->max_delta_ns = clockevent_delta2ns(ULONG_MAX, evt);
        evt->min_delta_ns = clockevent_delta2ns(1, evt);
-        evt->cpumask = cpumask_of_cpu(cpu);
+        evt->cpumask = cpumask_of(cpu);
        printk(KERN_WARNING "vmi: registering clock event %s. mult=%lu shift=%u\n",
               evt->name, evt->mult, evt->shift);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index a5d8e1ace1cf..104c8220a383 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -737,7 +737,7 @@ static void lguest_time_init(void)
        /* We can't set cpumask in the initializer: damn C limitations!  Set it
         * here and register our timer device. */
-        lguest_clockevent.cpumask = cpumask_of_cpu(0);
+        lguest_clockevent.cpumask = cpumask_of(0);
        clockevents_register_device(&lguest_clockevent);
        /* Finally, we unblock the timer interrupt. */
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 52145007bd7e..9c990185e9f2 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -63,11 +63,6 @@ static int voyager_extended_cpus = 1;
 /* Used for the invalidate map that's also checked in the spinlock */
 static volatile unsigned long smp_invalidate_needed;
-/* Bitmask of currently online CPUs - used by setup.c for
-   /proc/cpuinfo, visible externally but still physical */
-cpumask_t cpu_online_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_online_map);
 /* Bitmask of CPUs present in the system - exported by i386_syms.c, used
 * by scheduler but indexed physically */
 cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
@@ -218,8 +213,6 @@ static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 /* This is for the new dynamic CPU boot code */
 cpumask_t cpu_callin_map = CPU_MASK_NONE;
 cpumask_t cpu_callout_map = CPU_MASK_NONE;
-cpumask_t cpu_possible_map = CPU_MASK_NONE;
-EXPORT_SYMBOL(cpu_possible_map);
 /* The per processor IRQ masks (these are usually kept in sync) */
 static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c9f7cda48ed7..65d75a6be0ba 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -437,7 +437,7 @@ void xen_setup_timer(int cpu)
        evt = &per_cpu(xen_clock_events, cpu);
        memcpy(evt, xen_clockevent, sizeof(*evt));
-        evt->cpumask = cpumask_of_cpu(cpu);
+        evt->cpumask = cpumask_of(cpu);
        evt->irq = irq;
        setup_runstate_info(cpu);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 64f5d54f7edc..4259072f5bd0 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -109,7 +109,7 @@ static SYSDEV_ATTR(crash_notes, 0400, show_crash_notes, NULL);
 */
 static ssize_t print_cpus_map(char *buf, cpumask_t *map)
 {
-        int n = cpulist_scnprintf(buf, PAGE_SIZE-2, *map);
+        int n = cpulist_scnprintf(buf, PAGE_SIZE-2, map);
        buf[n++] = '\n';
        buf[n] = '\0';
diff --git a/drivers/base/node.c b/drivers/base/node.c
index f5207090885a..91636cd8b6c9 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -30,8 +30,8 @@ static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf)
        BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1));
        len = type?
-                cpulist_scnprintf(buf, PAGE_SIZE-2, *mask):
+                cpulist_scnprintf(buf, PAGE_SIZE-2, mask) :
-                cpumask_scnprintf(buf, PAGE_SIZE-2, *mask);
+                cpumask_scnprintf(buf, PAGE_SIZE-2, mask);
        buf[len++] = '\n';
        buf[len] = '\0';
        return len;
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 199cd97e32e6..a8bc1cbcfa7c 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -49,8 +49,8 @@ static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
        if (len > 1) {
                n = type?
-                        cpulist_scnprintf(buf, len-2, *mask):
+                        cpulist_scnprintf(buf, len-2, mask) :
-                        cpumask_scnprintf(buf, len-2, *mask);
+                        cpumask_scnprintf(buf, len-2, mask);
                buf[n++] = '\n';
                buf[n] = '\0';
        }
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index f450588e5858..254f1064d973 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -154,7 +154,6 @@ static struct tc_clkevt_device clkevt = {
                .shift          = 32,
                /* Should be lower than at91rm9200's system timer */
                .rating         = 125,
-                .cpumask        = CPU_MASK_CPU0,
                .set_next_event = tc_next_event,
                .set_mode       = tc_mode,
        },
@@ -195,6 +194,7 @@ static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
        clkevt.clkevt.max_delta_ns
                = clockevent_delta2ns(0xffff, &clkevt.clkevt);
        clkevt.clkevt.min_delta_ns = clockevent_delta2ns(1, &clkevt.clkevt) + 1;
+        clkevt.clkevt.cpumask = cpumask_of(0);
        setup_irq(irq, &tc_irqaction);
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 7beffcab2745..9dedbbd218c3 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -704,16 +704,17 @@ static unsigned int iosapic_startup_irq(unsigned int irq)
 }
 #ifdef CONFIG_SMP
-static void iosapic_set_affinity_irq(unsigned int irq, cpumask_t dest)
+static void iosapic_set_affinity_irq(unsigned int irq,
+                                     const struct cpumask *dest)
 {
        struct vector_info *vi = iosapic_get_vector(irq);
        u32 d0, d1, dummy_d0;
        unsigned long flags;
-        if (cpu_check_affinity(irq, &dest))
+        if (cpu_check_affinity(irq, dest))
                return;
-        vi->txn_addr = txn_affinity_addr(irq, first_cpu(dest));
+        vi->txn_addr = txn_affinity_addr(irq, cpumask_first(dest));
        spin_lock_irqsave(&iosapic_lock, flags);
        /* d1 contains the destination CPU, so only want to set that
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 5d72866897a8..c88485860a0a 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -74,7 +74,7 @@ static ssize_t local_cpus_show(struct device *dev,
        int len;
        mask = pcibus_to_cpumask(to_pci_dev(dev)->bus);
-        len = cpumask_scnprintf(buf, PAGE_SIZE-2, mask);
+        len = cpumask_scnprintf(buf, PAGE_SIZE-2, &mask);
        buf[len++] = '\n';
        buf[len] = '\0';
        return len;
@@ -88,7 +88,7 @@ static ssize_t local_cpulist_show(struct device *dev,
        int len;
        mask = pcibus_to_cpumask(to_pci_dev(dev)->bus);
-        len = cpulist_scnprintf(buf, PAGE_SIZE-2, mask);
+        len = cpulist_scnprintf(buf, PAGE_SIZE-2, &mask);
        buf[len++] = '\n';
        buf[len] = '\0';
        return len;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 003a9b3c293f..5b3f5937ecf5 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -55,8 +55,8 @@ static ssize_t pci_bus_show_cpuaffinity(struct device *dev,
        cpumask = pcibus_to_cpumask(to_pci_bus(dev));
        ret = type?
-                cpulist_scnprintf(buf, PAGE_SIZE-2, cpumask):
+                cpulist_scnprintf(buf, PAGE_SIZE-2, &cpumask) :
-                cpumask_scnprintf(buf, PAGE_SIZE-2, cpumask);
+                cpumask_scnprintf(buf, PAGE_SIZE-2, &cpumask);
        buf[ret++] = '\n';
        buf[ret] = '\0';
        return ret;
diff --git a/drivers/video/aty/radeon_accel.c b/drivers/video/aty/radeon_accel.c
index 8da5e5ab8547..a469a3d6edcb 100644
--- a/drivers/video/aty/radeon_accel.c
+++ b/drivers/video/aty/radeon_accel.c
@@ -5,61 +5,61 @@
 * --dte
 */
-#define FLUSH_CACHE_WORKAROUND  1
+static void radeon_fixup_offset(struct radeonfb_info *rinfo)
-void radeon_fifo_update_and_wait(struct radeonfb_info *rinfo, int entries)
 {
-        int i;
+        u32 local_base;
+        /* *** Ugly workaround *** */
+        /*
+         * On some platforms, the video memory is mapped at 0 in radeon chip space
+         * (like PPCs) by the firmware. X will always move it up so that it's seen
+         * by the chip to be at the same address as the PCI BAR.
+         * That means that when switching back from X, there is a mismatch between
+         * the offsets programmed into the engine. This means that potentially,
+         * accel operations done before radeonfb has a chance to re-init the engine
+         * will have incorrect offsets, and potentially trash system memory !
+         *
+         * The correct fix is for fbcon to never call any accel op before the engine
+         * has properly been re-initialized (by a call to set_var), but this is a
+         * complex fix. This workaround in the meantime, called before every accel
+         * operation, makes sure the offsets are in sync.
+         */
-        for (i=0; i<2000000; i++) {
+        radeon_fifo_wait (1);
-                rinfo->fifo_free = INREG(RBBM_STATUS) & 0x7f;
+        local_base = INREG(MC_FB_LOCATION) << 16;
-                if (rinfo->fifo_free >= entries)
+        if (local_base == rinfo->fb_local_base)
-                        return;
+                return;
-                udelay(10);
-        }
-        printk(KERN_ERR "radeonfb: FIFO Timeout !\n");
-        /* XXX Todo: attempt to reset the engine */
-}
-static inline void radeon_fifo_wait(struct radeonfb_info *rinfo, int entries)
+        rinfo->fb_local_base = local_base;
-{
-        if (entries <= rinfo->fifo_free)
-                rinfo->fifo_free -= entries;
-        else
-                radeon_fifo_update_and_wait(rinfo, entries);
-}
-static inline void radeonfb_set_creg(struct radeonfb_info *rinfo, u32 reg,
+        radeon_fifo_wait (3);
-                                     u32 *cache, u32 new_val)
+        OUTREG(DEFAULT_PITCH_OFFSET, (rinfo->pitch << 0x16) |
-{
+                                     (rinfo->fb_local_base >> 10));
-        if (new_val == *cache)
+        OUTREG(DST_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10));
-                return;
+        OUTREG(SRC_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10));
-        *cache = new_val;
-        radeon_fifo_wait(rinfo, 1);
-        OUTREG(reg, new_val);
 }
 static void radeonfb_prim_fillrect(struct radeonfb_info *rinfo, 
                                   const struct fb_fillrect *region)
 {
-        radeonfb_set_creg(rinfo, DP_GUI_MASTER_CNTL, &rinfo->dp_gui_mc_cache,
+        radeon_fifo_wait(4);  
-                          rinfo->dp_gui_mc_base | GMC_BRUSH_SOLID_COLOR | ROP3_P);
+  
-        radeonfb_set_creg(rinfo, DP_CNTL, &rinfo->dp_cntl_cache,
+        OUTREG(DP_GUI_MASTER_CNTL,  
-                          DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM);
+                rinfo->dp_gui_master_cntl  /* contains, like GMC_DST_32BPP */
-        radeonfb_set_creg(rinfo, DP_BRUSH_FRGD_CLR, &rinfo->dp_brush_fg_cache,
+                | GMC_BRUSH_SOLID_COLOR
-                          region->color);
+                | ROP3_P);
+        if (radeon_get_dstbpp(rinfo->depth) != DST_8BPP)
-        /* Ensure the dst cache is flushed and the engine idle before
+                OUTREG(DP_BRUSH_FRGD_CLR, rinfo->pseudo_palette[region->color]);
-         * issuing the operation.
+        else
-         *
+                OUTREG(DP_BRUSH_FRGD_CLR, region->color);
-         * This works around engine lockups on some cards
+        OUTREG(DP_WRITE_MSK, 0xffffffff);
-         */
+        OUTREG(DP_CNTL, (DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM));
-#if FLUSH_CACHE_WORKAROUND
-        radeon_fifo_wait(rinfo, 2);
+        radeon_fifo_wait(2);
        OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL);
        OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE));
-#endif
-        radeon_fifo_wait(rinfo, 2);
+        radeon_fifo_wait(2);  
        OUTREG(DST_Y_X, (region->dy << 16) | region->dx);
        OUTREG(DST_WIDTH_HEIGHT, (region->width << 16) | region->height);
 }
@@ -70,14 +70,15 @@ void radeonfb_fillrect(struct fb_info *info, const struct fb_fillrect *region)
        struct fb_fillrect modded;
        int vxres, vyres;
  
-        WARN_ON(rinfo->gfx_mode);
+        if (info->state != FBINFO_STATE_RUNNING)
-        if (info->state != FBINFO_STATE_RUNNING || rinfo->gfx_mode)
                return;
        if (info->flags & FBINFO_HWACCEL_DISABLED) {
                cfb_fillrect(info, region);
                return;
        }
+        radeon_fixup_offset(rinfo);
        vxres = info->var.xres_virtual;
        vyres = info->var.yres_virtual;
@@ -90,10 +91,6 @@ void radeonfb_fillrect(struct fb_info *info, const struct fb_fillrect *region)
        if(modded.dx + modded.width  > vxres) modded.width  = vxres - modded.dx;
        if(modded.dy + modded.height > vyres) modded.height = vyres - modded.dy;
-        if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
-            info->fix.visual == FB_VISUAL_DIRECTCOLOR )
-                modded.color = ((u32 *) (info->pseudo_palette))[region->color];
        radeonfb_prim_fillrect(rinfo, &modded);
 }
@@ -112,22 +109,22 @@ static void radeonfb_prim_copyarea(struct radeonfb_info *rinfo,
        if ( xdir < 0 ) { sx += w-1; dx += w-1; }
        if ( ydir < 0 ) { sy += h-1; dy += h-1; }
-        radeonfb_set_creg(rinfo, DP_GUI_MASTER_CNTL, &rinfo->dp_gui_mc_cache,
+        radeon_fifo_wait(3);
-                          rinfo->dp_gui_mc_base |
+        OUTREG(DP_GUI_MASTER_CNTL,
-                          GMC_BRUSH_NONE |
+                rinfo->dp_gui_master_cntl /* i.e. GMC_DST_32BPP */
-                          GMC_SRC_DATATYPE_COLOR |
+                | GMC_BRUSH_NONE
-                          ROP3_S |
+                | GMC_SRC_DSTCOLOR
-                          DP_SRC_SOURCE_MEMORY);
+                | ROP3_S 
-        radeonfb_set_creg(rinfo, DP_CNTL, &rinfo->dp_cntl_cache,
+                | DP_SRC_SOURCE_MEMORY );
-                          (xdir>=0 ? DST_X_LEFT_TO_RIGHT : 0) |
+        OUTREG(DP_WRITE_MSK, 0xffffffff);
-                          (ydir>=0 ? DST_Y_TOP_TO_BOTTOM : 0));
+        OUTREG(DP_CNTL, (xdir>=0 ? DST_X_LEFT_TO_RIGHT : 0)
+                        | (ydir>=0 ? DST_Y_TOP_TO_BOTTOM : 0));
-#if FLUSH_CACHE_WORKAROUND
-        radeon_fifo_wait(rinfo, 2);
+        radeon_fifo_wait(2);
        OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL);
        OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE));
-#endif
-        radeon_fifo_wait(rinfo, 3);
+        radeon_fifo_wait(3);
        OUTREG(SRC_Y_X, (sy << 16) | sx);
        OUTREG(DST_Y_X, (dy << 16) | dx);
        OUTREG(DST_HEIGHT_WIDTH, (h << 16) | w);
@@ -146,14 +143,15 @@ void radeonfb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
        modded.width  = area->width;
        modded.height = area->height;
  
-        WARN_ON(rinfo->gfx_mode);
+        if (info->state != FBINFO_STATE_RUNNING)
-        if (info->state != FBINFO_STATE_RUNNING || rinfo->gfx_mode)
                return;
        if (info->flags & FBINFO_HWACCEL_DISABLED) {
                cfb_copyarea(info, area);
                return;
        }
+        radeon_fixup_offset(rinfo);
        vxres = info->var.xres_virtual;
        vyres = info->var.yres_virtual;
@@ -170,116 +168,13 @@ void radeonfb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
        radeonfb_prim_copyarea(rinfo, &modded);
 }
-static void radeonfb_prim_imageblit(struct radeonfb_info *rinfo,
-                                    const struct fb_image *image,
-                                    u32 fg, u32 bg)
-{
-        unsigned int dwords;
-        u32 *bits;
-        radeonfb_set_creg(rinfo, DP_GUI_MASTER_CNTL, &rinfo->dp_gui_mc_cache,
-                          rinfo->dp_gui_mc_base |
-                          GMC_BRUSH_NONE | GMC_DST_CLIP_LEAVE |
-                          GMC_SRC_DATATYPE_MONO_FG_BG |
-                          ROP3_S |
-                          GMC_BYTE_ORDER_MSB_TO_LSB |
-                          DP_SRC_SOURCE_HOST_DATA);
-        radeonfb_set_creg(rinfo, DP_CNTL, &rinfo->dp_cntl_cache,
-                          DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM);
-        radeonfb_set_creg(rinfo, DP_SRC_FRGD_CLR, &rinfo->dp_src_fg_cache, fg);
-        radeonfb_set_creg(rinfo, DP_SRC_BKGD_CLR, &rinfo->dp_src_bg_cache, bg);
-        /* Ensure the dst cache is flushed and the engine idle before
-         * issuing the operation.
-         *
-         * This works around engine lockups on some cards
-         */
-#if FLUSH_CACHE_WORKAROUND
-        radeon_fifo_wait(rinfo, 2);
-        OUTREG(DSTCACHE_CTLSTAT, RB2D_DC_FLUSH_ALL);
-        OUTREG(WAIT_UNTIL, (WAIT_2D_IDLECLEAN | WAIT_DMA_GUI_IDLE));
-#endif
-        /* X here pads width to a multiple of 32 and uses the clipper to
-         * adjust the result. Is that really necessary ? Things seem to
-         * work ok for me without that and the doco doesn't seem to imply]
-         * there is such a restriction.
-         */
-        radeon_fifo_wait(rinfo, 4);
-        OUTREG(SC_TOP_LEFT, (image->dy << 16) | image->dx);
-        OUTREG(SC_BOTTOM_RIGHT, ((image->dy + image->height) << 16) |
-               (image->dx + image->width));
-        OUTREG(DST_Y_X, (image->dy << 16) | image->dx);
-        OUTREG(DST_HEIGHT_WIDTH, (image->height << 16) | ((image->width + 31) & ~31));
-        dwords = (image->width + 31) >> 5;
-        dwords *= image->height;
-        bits = (u32*)(image->data);
-        while(dwords >= 8) {
-                radeon_fifo_wait(rinfo, 8);
-#if BITS_PER_LONG == 64
-                __raw_writeq(*((u64 *)(bits)), rinfo->mmio_base + HOST_DATA0);
-                __raw_writeq(*((u64 *)(bits+2)), rinfo->mmio_base + HOST_DATA2);
-                __raw_writeq(*((u64 *)(bits+4)), rinfo->mmio_base + HOST_DATA4);
-                __raw_writeq(*((u64 *)(bits+6)), rinfo->mmio_base + HOST_DATA6);
-                bits += 8;
-#else
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA0);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA1);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA2);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA3);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA4);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA5);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA6);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA7);
-#endif
-                dwords -= 8;
-        }
-        while(dwords--) {
-                radeon_fifo_wait(rinfo, 1);
-                __raw_writel(*(bits++), rinfo->mmio_base + HOST_DATA0);
-        }
-}
 void radeonfb_imageblit(struct fb_info *info, const struct fb_image *image)
 {
        struct radeonfb_info *rinfo = info->par;
-        u32 fg, bg;
-        WARN_ON(rinfo->gfx_mode);
+        if (info->state != FBINFO_STATE_RUNNING)
-        if (info->state != FBINFO_STATE_RUNNING || rinfo->gfx_mode)
-                return;
-        if (!image->width || !image->height)
                return;
+        radeon_engine_idle();
-        /* We only do 1 bpp color expansion for now */
-        if (!accel_cexp ||
-            (info->flags & FBINFO_HWACCEL_DISABLED) || image->depth != 1)
-                goto fallback;
-        /* Fallback if running out of the screen. We may do clipping
-         * in the future */
-        if ((image->dx + image->width) > info->var.xres_virtual ||
-            (image->dy + image->height) > info->var.yres_virtual)
-                goto fallback;
-        if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
-            info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
-                fg = ((u32*)(info->pseudo_palette))[image->fg_color];
-                bg = ((u32*)(info->pseudo_palette))[image->bg_color];
-        } else {
-                fg = image->fg_color;
-                bg = image->bg_color;
-        }
-        radeonfb_prim_imageblit(rinfo, image, fg, bg);
-        return;
- fallback:
-        radeon_engine_idle(rinfo);
        cfb_imageblit(info, image);
 }
@@ -290,8 +185,7 @@ int radeonfb_sync(struct fb_info *info)
        if (info->state != FBINFO_STATE_RUNNING)
                return 0;
+        radeon_engine_idle();
-        radeon_engine_idle(rinfo);
        return 0;
 }
@@ -367,10 +261,9 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo)
        /* disable 3D engine */
        OUTREG(RB3D_CNTL, 0);
-        rinfo->fifo_free = 0;
        radeonfb_engine_reset(rinfo);
-        radeon_fifo_wait(rinfo, 1);
+        radeon_fifo_wait (1);
        if (IS_R300_VARIANT(rinfo)) {
                OUTREG(RB2D_DSTCACHE_MODE, INREG(RB2D_DSTCACHE_MODE) |
                       RB2D_DC_AUTOFLUSH_ENABLE |
@@ -384,7 +277,7 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo)
                OUTREG(RB2D_DSTCACHE_MODE, 0);
        }
-        radeon_fifo_wait(rinfo, 3);
+        radeon_fifo_wait (3);
        /* We re-read MC_FB_LOCATION from card as it can have been
         * modified by XFree drivers (ouch !)
         */
@@ -395,57 +288,41 @@ void radeonfb_engine_init (struct radeonfb_info *rinfo)
        OUTREG(DST_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10));
        OUTREG(SRC_PITCH_OFFSET, (rinfo->pitch << 0x16) | (rinfo->fb_local_base >> 10));
-        radeon_fifo_wait(rinfo, 1);
+        radeon_fifo_wait (1);
-#ifdef __BIG_ENDIAN
+#if defined(__BIG_ENDIAN)
        OUTREGP(DP_DATATYPE, HOST_BIG_ENDIAN_EN, ~HOST_BIG_ENDIAN_EN);
 #else
        OUTREGP(DP_DATATYPE, 0, ~HOST_BIG_ENDIAN_EN);
 #endif
-        radeon_fifo_wait(rinfo, 2);
+        radeon_fifo_wait (2);
        OUTREG(DEFAULT_SC_TOP_LEFT, 0);
        OUTREG(DEFAULT_SC_BOTTOM_RIGHT, (DEFAULT_SC_RIGHT_MAX |
                                         DEFAULT_SC_BOTTOM_MAX));
-        /* set default DP_GUI_MASTER_CNTL */
        temp = radeon_get_dstbpp(rinfo->depth);
-        rinfo->dp_gui_mc_base = ((temp << 8) | GMC_CLR_CMP_CNTL_DIS);
+        rinfo->dp_gui_master_cntl = ((temp << 8) | GMC_CLR_CMP_CNTL_DIS);
-        rinfo->dp_gui_mc_cache = rinfo->dp_gui_mc_base |
+        radeon_fifo_wait (1);
-                GMC_BRUSH_SOLID_COLOR |
+        OUTREG(DP_GUI_MASTER_CNTL, (rinfo->dp_gui_master_cntl |
-                GMC_SRC_DATATYPE_COLOR;
+                                    GMC_BRUSH_SOLID_COLOR |
-        radeon_fifo_wait(rinfo, 1);
+                                    GMC_SRC_DATATYPE_COLOR));
-        OUTREG(DP_GUI_MASTER_CNTL, rinfo->dp_gui_mc_cache);
+        radeon_fifo_wait (7);
        /* clear line drawing regs */
-        radeon_fifo_wait(rinfo, 2);
        OUTREG(DST_LINE_START, 0);
        OUTREG(DST_LINE_END, 0);
-        /* set brush and source color regs */
+        /* set brush color regs */
-        rinfo->dp_brush_fg_cache = 0xffffffff;
+        OUTREG(DP_BRUSH_FRGD_CLR, 0xffffffff);
-        rinfo->dp_brush_bg_cache = 0x00000000;
+        OUTREG(DP_BRUSH_BKGD_CLR, 0x00000000);
-        rinfo->dp_src_fg_cache = 0xffffffff;
-        rinfo->dp_src_bg_cache = 0x00000000;
+        /* set source color regs */
-        radeon_fifo_wait(rinfo, 4);
+        OUTREG(DP_SRC_FRGD_CLR, 0xffffffff);
-        OUTREG(DP_BRUSH_FRGD_CLR, rinfo->dp_brush_fg_cache);
+        OUTREG(DP_SRC_BKGD_CLR, 0x00000000);
-        OUTREG(DP_BRUSH_BKGD_CLR, rinfo->dp_brush_bg_cache);
-        OUTREG(DP_SRC_FRGD_CLR, rinfo->dp_src_fg_cache);
-        OUTREG(DP_SRC_BKGD_CLR, rinfo->dp_src_bg_cache);
-        /* Default direction */
-        rinfo->dp_cntl_cache = DST_X_LEFT_TO_RIGHT | DST_Y_TOP_TO_BOTTOM;
-        radeon_fifo_wait(rinfo, 1);
-        OUTREG(DP_CNTL, rinfo->dp_cntl_cache);
        /* default write mask */
-        radeon_fifo_wait(rinfo, 1);
        OUTREG(DP_WRITE_MSK, 0xffffffff);
-        /* Default to no swapping of host data */
+        radeon_engine_idle ();
-        radeon_fifo_wait(rinfo, 1);
-        OUTREG(RBBM_GUICNTL, RBBM_GUICNTL_HOST_DATA_SWAP_NONE);
-        /* Make sure it's settled */
-        radeon_engine_idle(rinfo);
 }
diff --git a/drivers/video/aty/radeon_backlight.c b/drivers/video/aty/radeon_backlight.c
index f343ba83f0ae..1a056adb61c8 100644
--- a/drivers/video/aty/radeon_backlight.c
+++ b/drivers/video/aty/radeon_backlight.c
@@ -66,7 +66,7 @@ static int radeon_bl_update_status(struct backlight_device *bd)
                level = bd->props.brightness;
        del_timer_sync(&rinfo->lvds_timer);
-        radeon_engine_idle(rinfo);
+        radeon_engine_idle();
        lvds_gen_cntl = INREG(LVDS_GEN_CNTL);
        if (level > 0) {
diff --git a/drivers/video/aty/radeon_base.c b/drivers/video/aty/radeon_base.c
index d5b27f9d374d..d0f1a7fc2c9d 100644
--- a/drivers/video/aty/radeon_base.c
+++ b/drivers/video/aty/radeon_base.c
@@ -282,8 +282,6 @@ static int backlight = 1;
 static int backlight = 0;
 #endif
-int accel_cexp = 0;
 /*
 * prototypes
 */
@@ -854,6 +852,7 @@ static int radeonfb_pan_display (struct fb_var_screeninfo *var,
        if (rinfo->asleep)
                return 0;
+        radeon_fifo_wait(2);
        OUTREG(CRTC_OFFSET, ((var->yoffset * var->xres_virtual + var->xoffset)
                             * var->bits_per_pixel / 8) & ~7);
        return 0;
@@ -883,6 +882,7 @@ static int radeonfb_ioctl (struct fb_info *info, unsigned int cmd,
                        if (rc)
                                return rc;
+                        radeon_fifo_wait(2);
                        if (value & 0x01) {
                                tmp = INREG(LVDS_GEN_CNTL);
@@ -940,7 +940,7 @@ int radeon_screen_blank(struct radeonfb_info *rinfo, int blank, int mode_switch)
        if (rinfo->lock_blank)
                return 0;
-        radeon_engine_idle(rinfo);
+        radeon_engine_idle();
        val = INREG(CRTC_EXT_CNTL);
        val &= ~(CRTC_DISPLAY_DIS | CRTC_HSYNC_DIS |
@@ -1048,7 +1048,7 @@ static int radeonfb_blank (int blank, struct fb_info *info)
        if (rinfo->asleep)
                return 0;
+                
        return radeon_screen_blank(rinfo, blank, 0);
 }
@@ -1074,6 +1074,8 @@ static int radeon_setcolreg (unsigned regno, unsigned red, unsigned green,
        pindex = regno;
        if (!rinfo->asleep) {
+                radeon_fifo_wait(9);
                if (rinfo->bpp == 16) {
                        pindex = regno * 8;
@@ -1242,6 +1244,8 @@ static void radeon_write_pll_regs(struct radeonfb_info *rinfo, struct radeon_reg
 {
        int i;
+        radeon_fifo_wait(20);
        /* Workaround from XFree */
        if (rinfo->is_mobility) {
                /* A temporal workaround for the occational blanking on certain laptop
@@ -1337,7 +1341,7 @@ static void radeon_lvds_timer_func(unsigned long data)
 {
        struct radeonfb_info *rinfo = (struct radeonfb_info *)data;
-        radeon_engine_idle(rinfo);
+        radeon_engine_idle();
        OUTREG(LVDS_GEN_CNTL, rinfo->pending_lvds_gen_cntl);
 }
@@ -1355,11 +1359,10 @@ void radeon_write_mode (struct radeonfb_info *rinfo, struct radeon_regs *mode,
        if (nomodeset)
                return;
-        radeon_engine_idle(rinfo);
        if (!regs_only)
                radeon_screen_blank(rinfo, FB_BLANK_NORMAL, 0);
+        radeon_fifo_wait(31);
        for (i=0; i<10; i++)
                OUTREG(common_regs[i].reg, common_regs[i].val);
@@ -1387,6 +1390,7 @@ void radeon_write_mode (struct radeonfb_info *rinfo, struct radeon_regs *mode,
        radeon_write_pll_regs(rinfo, mode);
        if ((primary_mon == MT_DFP) || (primary_mon == MT_LCD)) {
+                radeon_fifo_wait(10);
                OUTREG(FP_CRTC_H_TOTAL_DISP, mode->fp_crtc_h_total_disp);
                OUTREG(FP_CRTC_V_TOTAL_DISP, mode->fp_crtc_v_total_disp);
                OUTREG(FP_H_SYNC_STRT_WID, mode->fp_h_sync_strt_wid);
@@ -1401,6 +1405,7 @@ void radeon_write_mode (struct radeonfb_info *rinfo, struct radeon_regs *mode,
        if (!regs_only)
                radeon_screen_blank(rinfo, FB_BLANK_UNBLANK, 0);
+        radeon_fifo_wait(2);
        OUTPLL(VCLK_ECP_CNTL, mode->vclk_ecp_cntl);
        
        return;
@@ -1551,7 +1556,7 @@ static int radeonfb_set_par(struct fb_info *info)
        /* We always want engine to be idle on a mode switch, even
         * if we won't actually change the mode
         */
-        radeon_engine_idle(rinfo);
+        radeon_engine_idle();
        hSyncStart = mode->xres + mode->right_margin;
        hSyncEnd = hSyncStart + mode->hsync_len;
@@ -1846,6 +1851,7 @@ static int radeonfb_set_par(struct fb_info *info)
        return 0;
 }
 static struct fb_ops radeonfb_ops = {
        .owner                  = THIS_MODULE,
        .fb_check_var           = radeonfb_check_var,
@@ -1869,7 +1875,6 @@ static int __devinit radeon_set_fbinfo (struct radeonfb_info *rinfo)
        info->par = rinfo;
        info->pseudo_palette = rinfo->pseudo_palette;
        info->flags = FBINFO_DEFAULT
-                    | FBINFO_HWACCEL_IMAGEBLIT
                    | FBINFO_HWACCEL_COPYAREA
                    | FBINFO_HWACCEL_FILLRECT
                    | FBINFO_HWACCEL_XPAN
@@ -1877,7 +1882,6 @@ static int __devinit radeon_set_fbinfo (struct radeonfb_info *rinfo)
        info->fbops = &radeonfb_ops;
        info->screen_base = rinfo->fb_base;
        info->screen_size = rinfo->mapped_vram;
        /* Fill fix common fields */
        strlcpy(info->fix.id, rinfo->name, sizeof(info->fix.id));
        info->fix.smem_start = rinfo->fb_base_phys;
@@ -1892,25 +1896,8 @@ static int __devinit radeon_set_fbinfo (struct radeonfb_info *rinfo)
        info->fix.mmio_len = RADEON_REGSIZE;
        info->fix.accel = FB_ACCEL_ATI_RADEON;
-        /* Allocate colormap */
        fb_alloc_cmap(&info->cmap, 256, 0);
-        /* Setup pixmap used for acceleration */
-#define PIXMAP_SIZE     (2048 * 4)
-        info->pixmap.addr = kmalloc(PIXMAP_SIZE, GFP_KERNEL);
-        if (!info->pixmap.addr) {
-                printk(KERN_ERR "radeonfb: Failed to allocate pixmap !\n");
-                noaccel = 1;
-                goto bail;
-        }
-        info->pixmap.size = PIXMAP_SIZE;
-        info->pixmap.flags = FB_PIXMAP_SYSTEM;
-        info->pixmap.scan_align = 4;
-        info->pixmap.buf_align = 4;
-        info->pixmap.access_align = 32;
-bail:
        if (noaccel)
                info->flags |= FBINFO_HWACCEL_DISABLED;
@@ -2019,6 +2006,7 @@ static void radeon_identify_vram(struct radeonfb_info *rinfo)
          u32 tom = INREG(NB_TOM);
          tmp = ((((tom >> 16) - (tom & 0xffff) + 1) << 6) * 1024);
+                radeon_fifo_wait(6);
          OUTREG(MC_FB_LOCATION, tom);
          OUTREG(DISPLAY_BASE_ADDR, (tom & 0xffff) << 16);
          OUTREG(CRTC2_DISPLAY_BASE_ADDR, (tom & 0xffff) << 16);
@@ -2522,8 +2510,6 @@ static int __init radeonfb_setup (char *options)
                } else if (!strncmp(this_opt, "ignore_devlist", 14)) {
                        ignore_devlist = 1;
 #endif
-                } else if (!strncmp(this_opt, "accel_cexp", 12)) {
-                        accel_cexp = 1;
                } else
                        mode_option = this_opt;
        }
@@ -2571,8 +2557,6 @@ module_param(monitor_layout, charp, 0);
 MODULE_PARM_DESC(monitor_layout, "Specify monitor mapping (like XFree86)");
 module_param(force_measure_pll, bool, 0);
 MODULE_PARM_DESC(force_measure_pll, "Force measurement of PLL (debug)");
-module_param(accel_cexp, bool, 0);
-MODULE_PARM_DESC(accel_cexp, "Use acceleration engine for color expansion");
 #ifdef CONFIG_MTRR
 module_param(nomtrr, bool, 0);
 MODULE_PARM_DESC(nomtrr, "bool: disable use of MTRR registers");
diff --git a/drivers/video/aty/radeon_pm.c b/drivers/video/aty/radeon_pm.c
index 3df5015f1d13..675abdafc2d8 100644
--- a/drivers/video/aty/radeon_pm.c
+++ b/drivers/video/aty/radeon_pm.c
@@ -2653,9 +2653,9 @@ int radeonfb_pci_suspend(struct pci_dev *pdev, pm_message_t mesg)
        if (!(info->flags & FBINFO_HWACCEL_DISABLED)) {
                /* Make sure engine is reset */
-                radeon_engine_idle(rinfo);
+                radeon_engine_idle();
                radeonfb_engine_reset(rinfo);
-                radeon_engine_idle(rinfo);
+                radeon_engine_idle();
        }
        /* Blank display and LCD */
@@ -2767,7 +2767,7 @@ int radeonfb_pci_resume(struct pci_dev *pdev)
                rinfo->asleep = 0;
        } else
-                radeon_engine_idle(rinfo);
+                radeon_engine_idle();
        /* Restore display & engine */
        radeon_write_mode (rinfo, &rinfo->state, 1);
diff --git a/drivers/video/aty/radeonfb.h b/drivers/video/aty/radeonfb.h
index 974ca6d86540..3ea1b00fdd22 100644
--- a/drivers/video/aty/radeonfb.h
+++ b/drivers/video/aty/radeonfb.h
@@ -336,15 +336,7 @@ struct radeonfb_info {
        int                     mon2_type;
        u8                      *mon2_EDID;
-        /* accel bits */
+        u32                     dp_gui_master_cntl;
-        u32                     dp_gui_mc_base;
-        u32                     dp_gui_mc_cache;
-        u32                     dp_cntl_cache;
-        u32                     dp_brush_fg_cache;
-        u32                     dp_brush_bg_cache;
-        u32                     dp_src_fg_cache;
-        u32                     dp_src_bg_cache;
-        u32                     fifo_free;
        struct pll_info         pll;
@@ -356,7 +348,6 @@ struct radeonfb_info {
        int                     lock_blank;
        int                     dynclk;
        int                     no_schedule;
-        int                     gfx_mode;
        enum radeon_pm_mode     pm_mode;
        reinit_function_ptr     reinit_func;
@@ -401,14 +392,8 @@ static inline void _radeon_msleep(struct radeonfb_info *rinfo, unsigned long ms)
 #define OUTREG8(addr,val)       writeb(val, (rinfo->mmio_base)+addr)
 #define INREG16(addr)           readw((rinfo->mmio_base)+addr)
 #define OUTREG16(addr,val)      writew(val, (rinfo->mmio_base)+addr)
-#ifdef CONFIG_PPC
-#define INREG(addr)             ({ eieio(); ld_le32(rinfo->mmio_base+(addr)); })
-#define OUTREG(addr,val)        do { eieio(); st_le32(rinfo->mmio_base+(addr),(val)); } while(0)
-#else
 #define INREG(addr)             readl((rinfo->mmio_base)+addr)
 #define OUTREG(addr,val)        writel(val, (rinfo->mmio_base)+addr)
-#endif
 static inline void _OUTREGP(struct radeonfb_info *rinfo, u32 addr,
                       u32 val, u32 mask)
@@ -550,7 +535,17 @@ static inline u32 radeon_get_dstbpp(u16 depth)
 * 2D Engine helper routines
 */
-extern void radeon_fifo_update_and_wait(struct radeonfb_info *rinfo, int entries);
+static inline void _radeon_fifo_wait(struct radeonfb_info *rinfo, int entries)
+{
+        int i;
+        for (i=0; i<2000000; i++) {
+                if ((INREG(RBBM_STATUS) & 0x7f) >= entries)
+                        return;
+                udelay(1);
+        }
+        printk(KERN_ERR "radeonfb: FIFO Timeout !\n");
+}
 static inline void radeon_engine_flush (struct radeonfb_info *rinfo)
 {
@@ -563,7 +558,7 @@ static inline void radeon_engine_flush (struct radeonfb_info *rinfo)
        /* Ensure FIFO is empty, ie, make sure the flush commands
         * has reached the cache
         */
-        radeon_fifo_update_and_wait(rinfo, 64);
+        _radeon_fifo_wait (rinfo, 64);
        /* Wait for the flush to complete */
        for (i=0; i < 2000000; i++) {
@@ -575,12 +570,12 @@ static inline void radeon_engine_flush (struct radeonfb_info *rinfo)
 }
-static inline void radeon_engine_idle(struct radeonfb_info *rinfo)
+static inline void _radeon_engine_idle(struct radeonfb_info *rinfo)
 {
        int i;
        /* ensure FIFO is empty before waiting for idle */
-        radeon_fifo_update_and_wait (rinfo, 64);
+        _radeon_fifo_wait (rinfo, 64);
        for (i=0; i<2000000; i++) {
                if (((INREG(RBBM_STATUS) & GUI_ACTIVE)) == 0) {
@@ -593,6 +588,8 @@ static inline void radeon_engine_idle(struct radeonfb_info *rinfo)
 }
+#define radeon_engine_idle()            _radeon_engine_idle(rinfo)
+#define radeon_fifo_wait(entries)       _radeon_fifo_wait(rinfo,entries)
 #define radeon_msleep(ms)               _radeon_msleep(rinfo,ms)
@@ -622,7 +619,6 @@ extern void radeonfb_imageblit(struct fb_info *p, const struct fb_image *image);
 extern int radeonfb_sync(struct fb_info *info);
 extern void radeonfb_engine_init (struct radeonfb_info *rinfo);
 extern void radeonfb_engine_reset(struct radeonfb_info *rinfo);
-extern void radeon_fixup_mem_offset(struct radeonfb_info *rinfo);
 /* Other functions */
 extern int radeon_screen_blank(struct radeonfb_info *rinfo, int blank, int mode_switch);
@@ -638,6 +634,4 @@ static inline void radeonfb_bl_init(struct radeonfb_info *rinfo) {}
 static inline void radeonfb_bl_exit(struct radeonfb_info *rinfo) {}
 #endif
-extern int accel_cexp;
 #endif /* __RADEONFB_H__ */
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 2924faa7f6c4..6c8193046e0d 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -583,7 +583,7 @@ void rebind_evtchn_irq(int evtchn, int irq)
        spin_unlock(&irq_mapping_update_lock);
        /* new event channels are always bound to cpu 0 */
-        irq_set_affinity(irq, cpumask_of_cpu(0));
+        irq_set_affinity(irq, cpumask_of(0));
        /* Unmask the event channel. */
        enable_irq(irq);
@@ -612,9 +612,9 @@ static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 }
-static void set_affinity_irq(unsigned irq, cpumask_t dest)
+static void set_affinity_irq(unsigned irq, const struct cpumask *dest)
 {
-        unsigned tcpu = first_cpu(dest);
+        unsigned tcpu = cpumask_first(dest);
        rebind_irq_to_cpu(irq, tcpu);
 }
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 54bbf6e04ee8..0e9e2bc0ee96 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -40,6 +40,9 @@
 #ifndef node_to_cpumask
 #define node_to_cpumask(node)   ((void)node, cpu_online_map)
 #endif
+#ifndef cpumask_of_node
+#define cpumask_of_node(node)   ((void)node, cpu_online_mask)
+#endif
 #ifndef node_to_first_cpu
 #define node_to_first_cpu(node) ((void)(node),0)
 #endif
@@ -54,9 +57,18 @@
                                )
 #endif
+#ifndef cpumask_of_pcibus
+#define cpumask_of_pcibus(bus)  (pcibus_to_node(bus) == -1 ?            \
+                                 cpu_all_mask :                         \
+                                 cpumask_of_node(pcibus_to_node(bus)))
+#endif
 #endif  /* CONFIG_NUMA */
-/* returns pointer to cpumask for specified node */
+/*
+ * returns pointer to cpumask for specified node
+ * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
+ */
 #ifndef node_to_cpumask_ptr
 #define node_to_cpumask_ptr(v, node)                                    \
diff --git a/include/asm-m32r/smp.h b/include/asm-m32r/smp.h
index c5dd66916692..b96a6d2ffbc3 100644
--- a/include/asm-m32r/smp.h
+++ b/include/asm-m32r/smp.h
@@ -63,8 +63,6 @@ extern volatile int cpu_2_physid[NR_CPUS];
 #define raw_smp_processor_id()  (current_thread_info()->cpu)
 extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_possible_map;
-extern cpumask_t cpu_present_map;
 static __inline__ int hard_smp_processor_id(void)
 {
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index ed3a5d473e52..cea153697ec7 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -82,13 +82,13 @@ struct clock_event_device {
        int                     shift;
        int                     rating;
        int                     irq;
-        cpumask_t               cpumask;
+        const struct cpumask    *cpumask;
        int                     (*set_next_event)(unsigned long evt,
                                                  struct clock_event_device *);
        void                    (*set_mode)(enum clock_event_mode mode,
                                            struct clock_event_device *);
        void                    (*event_handler)(struct clock_event_device *);
-        void                    (*broadcast)(cpumask_t mask);
+        void                    (*broadcast)(const struct cpumask *mask);
        struct list_head        list;
        enum clock_event_mode   mode;
        ktime_t                 next_event;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 21e1dd43e52a..d4bf52603e6b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -339,36 +339,6 @@ extern cpumask_t cpu_mask_all;
 #endif
 #define CPUMASK_PTR(v, m)       cpumask_t *v = &(m->v)
-#define cpumask_scnprintf(buf, len, src) \
-                        __cpumask_scnprintf((buf), (len), &(src), NR_CPUS)
-static inline int __cpumask_scnprintf(char *buf, int len,
-                                        const cpumask_t *srcp, int nbits)
-{
-        return bitmap_scnprintf(buf, len, srcp->bits, nbits);
-}
-#define cpumask_parse_user(ubuf, ulen, dst) \
-                        __cpumask_parse_user((ubuf), (ulen), &(dst), NR_CPUS)
-static inline int __cpumask_parse_user(const char __user *buf, int len,
-                                        cpumask_t *dstp, int nbits)
-{
-        return bitmap_parse_user(buf, len, dstp->bits, nbits);
-}
-#define cpulist_scnprintf(buf, len, src) \
-                        __cpulist_scnprintf((buf), (len), &(src), NR_CPUS)
-static inline int __cpulist_scnprintf(char *buf, int len,
-                                        const cpumask_t *srcp, int nbits)
-{
-        return bitmap_scnlistprintf(buf, len, srcp->bits, nbits);
-}
-#define cpulist_parse(buf, dst) __cpulist_parse((buf), &(dst), NR_CPUS)
-static inline int __cpulist_parse(const char *buf, cpumask_t *dstp, int nbits)
-{
-        return bitmap_parselist(buf, dstp->bits, nbits);
-}
 #define cpu_remap(oldbit, old, new) \
                __cpu_remap((oldbit), &(old), &(new), NR_CPUS)
 static inline int __cpu_remap(int oldbit,
@@ -540,9 +510,6 @@ extern cpumask_t cpu_active_map;
        [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD \
 }
-/* This produces more efficient code. */
-#define nr_cpumask_bits NR_CPUS
 #else /* NR_CPUS > BITS_PER_LONG */
 #define CPU_BITS_ALL                                            \
@@ -550,9 +517,15 @@ extern cpumask_t cpu_active_map;
        [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,                \
        [BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD         \
 }
+#endif /* NR_CPUS > BITS_PER_LONG */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* Assuming NR_CPUS is huge, a runtime limit is more efficient.  Also,
+ * not all bits may be allocated. */
 #define nr_cpumask_bits nr_cpu_ids
-#endif /* NR_CPUS > BITS_PER_LONG */
+#else
+#define nr_cpumask_bits NR_CPUS
+#endif
 /* verify cpu argument to cpumask_* operators */
 static inline unsigned int cpumask_check(unsigned int cpu)
@@ -946,6 +919,63 @@ static inline void cpumask_copy(struct cpumask *dstp,
 #define cpumask_of(cpu) (get_cpu_mask(cpu))
 /**
+ * cpumask_scnprintf - print a cpumask into a string as comma-separated hex
+ * @buf: the buffer to sprintf into
+ * @len: the length of the buffer
+ * @srcp: the cpumask to print
+ *
+ * If len is zero, returns zero.  Otherwise returns the length of the
+ * (nul-terminated) @buf string.
+ */
+static inline int cpumask_scnprintf(char *buf, int len,
+                                    const struct cpumask *srcp)
+{
+        return bitmap_scnprintf(buf, len, srcp->bits, nr_cpumask_bits);
+}
+/**
+ * cpumask_parse_user - extract a cpumask from a user string
+ * @buf: the buffer to extract from
+ * @len: the length of the buffer
+ * @dstp: the cpumask to set.
+ *
+ * Returns -errno, or 0 for success.
+ */
+static inline int cpumask_parse_user(const char __user *buf, int len,
+                                     struct cpumask *dstp)
+{
+        return bitmap_parse_user(buf, len, dstp->bits, nr_cpumask_bits);
+}
+/**
+ * cpulist_scnprintf - print a cpumask into a string as comma-separated list
+ * @buf: the buffer to sprintf into
+ * @len: the length of the buffer
+ * @srcp: the cpumask to print
+ *
+ * If len is zero, returns zero.  Otherwise returns the length of the
+ * (nul-terminated) @buf string.
+ */
+static inline int cpulist_scnprintf(char *buf, int len,
+                                    const struct cpumask *srcp)
+{
+        return bitmap_scnlistprintf(buf, len, srcp->bits, nr_cpumask_bits);
+}
+/**
+ * cpulist_parse_user - extract a cpumask from a user string of ranges
+ * @buf: the buffer to extract from
+ * @len: the length of the buffer
+ * @dstp: the cpumask to set.
+ *
+ * Returns -errno, or 0 for success.
+ */
+static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
+{
+        return bitmap_parselist(buf, dstp->bits, nr_cpumask_bits);
+}
+/**
 * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
 * @bitmap: the bitmap
 *
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 777f89e00b4a..7e85a6e89e41 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -111,13 +111,13 @@ extern void enable_irq(unsigned int irq);
 extern cpumask_t irq_default_affinity;
-extern int irq_set_affinity(unsigned int irq, cpumask_t cpumask);
+extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 #else /* CONFIG_SMP */
-static inline int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
+static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
 {
        return -EINVAL;
 }
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b5749db3e5a1..59525b74979f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -113,7 +113,8 @@ struct irq_chip {
        void            (*eoi)(unsigned int irq);
        void            (*end)(unsigned int irq);
-        void            (*set_affinity)(unsigned int irq, cpumask_t dest);
+        void            (*set_affinity)(unsigned int irq,
+                                        const struct cpumask *dest);
        int             (*retrigger)(unsigned int irq);
        int             (*set_type)(unsigned int irq, unsigned int flow_type);
        int             (*set_wake)(unsigned int irq, unsigned int on);
diff --git a/include/video/radeon.h b/include/video/radeon.h
index d5dcaf154ba4..1cd09cc5b169 100644
--- a/include/video/radeon.h
+++ b/include/video/radeon.h
@@ -525,9 +525,6 @@
 #define CRTC_DISPLAY_DIS                           (1 << 10)
 #define CRTC_CRT_ON                                (1 << 15)
-/* DSTCACHE_MODE bits constants */
-#define RB2D_DC_AUTOFLUSH_ENABLE                   (1 << 8)
-#define RB2D_DC_DC_DISABLE_IGNORE_PE               (1 << 17)
 /* DSTCACHE_CTLSTAT bit constants */
 #define RB2D_DC_FLUSH_2D                           (1 << 0)
@@ -869,10 +866,15 @@
 #define GMC_DST_16BPP_YVYU422                      0x00000c00
 #define GMC_DST_32BPP_AYUV444                      0x00000e00
 #define GMC_DST_16BPP_ARGB4444                     0x00000f00
+#define GMC_SRC_MONO                               0x00000000
+#define GMC_SRC_MONO_LBKGD                         0x00001000
+#define GMC_SRC_DSTCOLOR                           0x00003000
 #define GMC_BYTE_ORDER_MSB_TO_LSB                  0x00000000
 #define GMC_BYTE_ORDER_LSB_TO_MSB                  0x00004000
 #define GMC_DP_CONVERSION_TEMP_9300                0x00008000
 #define GMC_DP_CONVERSION_TEMP_6500                0x00000000
+#define GMC_DP_SRC_RECT                            0x02000000
+#define GMC_DP_SRC_HOST                            0x03000000
 #define GMC_DP_SRC_HOST_BYTEALIGN                  0x04000000
 #define GMC_3D_FCN_EN_CLR                          0x00000000
 #define GMC_3D_FCN_EN_SET                          0x08000000
@@ -883,9 +885,6 @@
 #define GMC_WRITE_MASK_LEAVE                       0x00000000
 #define GMC_WRITE_MASK_SET                         0x40000000
 #define GMC_CLR_CMP_CNTL_DIS                       (1 << 28)
-#define GMC_SRC_DATATYPE_MASK                      (3 << 12)
-#define GMC_SRC_DATATYPE_MONO_FG_BG                (0 << 12)
-#define GMC_SRC_DATATYPE_MONO_FG_LA                (1 << 12)
 #define GMC_SRC_DATATYPE_COLOR                     (3 << 12)
 #define ROP3_S                                     0x00cc0000
 #define ROP3_SRCCOPY                               0x00cc0000
@@ -894,7 +893,6 @@
 #define DP_SRC_SOURCE_MASK                         (7    << 24)
 #define GMC_BRUSH_NONE                             (15   <<  4)
 #define DP_SRC_SOURCE_MEMORY                       (2    << 24)
-#define DP_SRC_SOURCE_HOST_DATA                    (3    << 24)
 #define GMC_BRUSH_SOLIDCOLOR                       0x000000d0
 /* DP_MIX bit constants */
@@ -980,12 +978,6 @@
 #define DISP_PWR_MAN_TV_ENABLE_RST                 (1 << 25)
 #define DISP_PWR_MAN_AUTO_PWRUP_EN                 (1 << 26)
-/* RBBM_GUICNTL constants */
-#define RBBM_GUICNTL_HOST_DATA_SWAP_NONE           (0 << 0)
-#define RBBM_GUICNTL_HOST_DATA_SWAP_16BIT          (1 << 0)
-#define RBBM_GUICNTL_HOST_DATA_SWAP_32BIT          (2 << 0)
-#define RBBM_GUICNTL_HOST_DATA_SWAP_HDW            (3 << 0)
 /* masks */
 #define CONFIG_MEMSIZE_MASK             0x1f000000
diff --git a/init/Kconfig b/init/Kconfig
index f291f086caa1..b3782c6d5ede 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -917,6 +917,15 @@ config KMOD
 endif # MODULES
+config INIT_ALL_POSSIBLE
+        bool
+        help
+          Back when each arch used to define their own cpu_online_map and
+          cpu_possible_map, some of them chose to initialize cpu_possible_map
+          with all 1s, and others with all 0s.  When they were centralised,
+          it was better to provide this option than to break all the archs
+          and have several arch maintainers persuing me down dark alleys.
 config STOP_MACHINE
        bool
        default y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8ea32e8d68b0..bae131a1211b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -24,19 +24,20 @@
 cpumask_t cpu_present_map __read_mostly;
 EXPORT_SYMBOL(cpu_present_map);
-#ifndef CONFIG_SMP
 /*
 * Represents all cpu's that are currently online.
 */
-cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+cpumask_t cpu_online_map __read_mostly;
 EXPORT_SYMBOL(cpu_online_map);
+#ifdef CONFIG_INIT_ALL_POSSIBLE
 cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+#else
+cpumask_t cpu_possible_map __read_mostly;
+#endif
 EXPORT_SYMBOL(cpu_possible_map);
-#else /* CONFIG_SMP */
+#ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_map, cpu_present_map */
 static DEFINE_MUTEX(cpu_add_remove_lock);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 96c0ba13b8cd..39c1a4c1c5a9 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -896,7 +896,7 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
        if (!*buf) {
                cpus_clear(trialcs.cpus_allowed);
        } else {
-                retval = cpulist_parse(buf, trialcs.cpus_allowed);
+                retval = cpulist_parse(buf, &trialcs.cpus_allowed);
                if (retval < 0)
                        return retval;
@@ -1482,7 +1482,7 @@ static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
        mask = cs->cpus_allowed;
        mutex_unlock(&callback_mutex);
-        return cpulist_scnprintf(page, PAGE_SIZE, mask);
+        return cpulist_scnprintf(page, PAGE_SIZE, &mask);
 }
 static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 8e4fce4a1b1f..0af16aeee8b6 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -46,7 +46,7 @@ void dynamic_irq_init(unsigned int irq)
        desc->irq_count = 0;
        desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-        cpus_setall(desc->affinity);
+        cpumask_setall(&desc->affinity);
 #endif
        spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 801addda3c43..10ad2f87ed9a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -79,7 +79,7 @@ int irq_can_set_affinity(unsigned int irq)
 *      @cpumask:       cpumask
 *
 */
-int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
+int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
        struct irq_desc *desc = irq_to_desc(irq);
        unsigned long flags;
@@ -91,14 +91,14 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 #ifdef CONFIG_GENERIC_PENDING_IRQ
        if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-                desc->affinity = cpumask;
+                cpumask_copy(&desc->affinity, cpumask);
                desc->chip->set_affinity(irq, cpumask);
        } else {
                desc->status |= IRQ_MOVE_PENDING;
-                desc->pending_mask = cpumask;
+                cpumask_copy(&desc->pending_mask, cpumask);
        }
 #else
-        desc->affinity = cpumask;
+        cpumask_copy(&desc->affinity, cpumask);
        desc->chip->set_affinity(irq, cpumask);
 #endif
        desc->status |= IRQ_AFFINITY_SET;
@@ -112,26 +112,24 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 */
 int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
 {
-        cpumask_t mask;
        if (!irq_can_set_affinity(irq))
                return 0;
-        cpus_and(mask, cpu_online_map, irq_default_affinity);
        /*
         * Preserve an userspace affinity setup, but make sure that
         * one of the targets is online.
         */
        if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-                if (cpus_intersects(desc->affinity, cpu_online_map))
+                if (cpumask_any_and(&desc->affinity, cpu_online_mask)
-                        mask = desc->affinity;
+                    < nr_cpu_ids)
+                        goto set_affinity;
                else
                        desc->status &= ~IRQ_AFFINITY_SET;
        }
-        desc->affinity = mask;
+        cpumask_and(&desc->affinity, cpu_online_mask, &irq_default_affinity);
-        desc->chip->set_affinity(irq, mask);
+set_affinity:
+        desc->chip->set_affinity(irq, &desc->affinity);
        return 0;
 }
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 9db681d95814..bd72329e630c 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -4,7 +4,6 @@
 void move_masked_irq(int irq)
 {
        struct irq_desc *desc = irq_to_desc(irq);
-        cpumask_t tmp;
        if (likely(!(desc->status & IRQ_MOVE_PENDING)))
                return;
@@ -19,7 +18,7 @@ void move_masked_irq(int irq)
        desc->status &= ~IRQ_MOVE_PENDING;
-        if (unlikely(cpus_empty(desc->pending_mask)))
+        if (unlikely(cpumask_empty(&desc->pending_mask)))
                return;
        if (!desc->chip->set_affinity)
@@ -27,8 +26,6 @@ void move_masked_irq(int irq)
        assert_spin_locked(&desc->lock);
-        cpus_and(tmp, desc->pending_mask, cpu_online_map);
        /*
         * If there was a valid mask to work with, please
         * do the disable, re-program, enable sequence.
@@ -41,10 +38,13 @@ void move_masked_irq(int irq)
         * For correct operation this depends on the caller
         * masking the irqs.
         */
-        if (likely(!cpus_empty(tmp))) {
+        if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
-                desc->chip->set_affinity(irq,tmp);
+                   < nr_cpu_ids)) {
+                cpumask_and(&desc->affinity,
+                            &desc->pending_mask, cpu_online_mask);
+                desc->chip->set_affinity(irq, &desc->affinity);
        }
-        cpus_clear(desc->pending_mask);
+        cpumask_clear(&desc->pending_mask);
 }
 void move_native_irq(int irq)
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index f6b3440f05bc..d2c0e5ee53c5 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -40,33 +40,42 @@ static ssize_t irq_affinity_proc_write(struct file *file,
                const char __user *buffer, size_t count, loff_t *pos)
 {
        unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data;
-        cpumask_t new_value;
+        cpumask_var_t new_value;
        int err;
        if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
            irq_balancing_disabled(irq))
                return -EIO;
+        if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+                return -ENOMEM;
        err = cpumask_parse_user(buffer, count, new_value);
        if (err)
-                return err;
+                goto free_cpumask;
-        if (!is_affinity_mask_valid(new_value))
+        if (!is_affinity_mask_valid(*new_value)) {
-                return -EINVAL;
+                err = -EINVAL;
+                goto free_cpumask;
+        }
        /*
         * Do not allow disabling IRQs completely - it's a too easy
         * way to make the system unusable accidentally :-) At least
         * one online CPU still has to be targeted.
         */
-        if (!cpus_intersects(new_value, cpu_online_map))
+        if (!cpumask_intersects(new_value, cpu_online_mask)) {
                /* Special case for empty set - allow the architecture
                   code to set default SMP affinity. */
-                return irq_select_affinity_usr(irq) ? -EINVAL : count;
+                err = irq_select_affinity_usr(irq) ? -EINVAL : count;
+        } else {
-        irq_set_affinity(irq, new_value);
+                irq_set_affinity(irq, new_value);
+                err = count;
+        }
-        return count;
+free_cpumask:
+        free_cpumask_var(new_value);
+        return err;
 }
 static int irq_affinity_proc_open(struct inode *inode, struct file *file)
@@ -95,7 +104,7 @@ static ssize_t default_affinity_write(struct file *file,
        cpumask_t new_value;
        int err;
-        err = cpumask_parse_user(buffer, count, new_value);
+        err = cpumask_parse_user(buffer, count, &new_value);
        if (err)
                return err;
diff --git a/kernel/profile.c b/kernel/profile.c
index 60adefb59b5e..4cb7d68fed82 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -442,7 +442,7 @@ void profile_tick(int type)
 static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
                        int count, int *eof, void *data)
 {
-        int len = cpumask_scnprintf(page, count, *(cpumask_t *)data);
+        int len = cpumask_scnprintf(page, count, (cpumask_t *)data);
        if (count - len < 2)
                return -EINVAL;
        len += sprintf(page + len, "\n");
@@ -456,7 +456,7 @@ static int prof_cpu_mask_write_proc(struct file *file,
        unsigned long full_count = count, err;
        cpumask_t new_value;
-        err = cpumask_parse_user(buffer, count, new_value);
+        err = cpumask_parse_user(buffer, count, &new_value);
        if (err)
                return err;
diff --git a/kernel/sched.c b/kernel/sched.c
index e00c92d22655..b309027bf9e8 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6643,7 +6643,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
        struct sched_group *group = sd->groups;
        char str[256];
-        cpulist_scnprintf(str, sizeof(str), *sched_domain_span(sd));
+        cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
        cpumask_clear(groupmask);
        printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
@@ -6696,7 +6696,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                cpumask_or(groupmask, groupmask, sched_group_cpus(group));
-                cpulist_scnprintf(str, sizeof(str), *sched_group_cpus(group));
+                cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
                printk(KERN_CONT " %s", str);
                group = group->next;
@@ -6938,7 +6938,7 @@ static cpumask_var_t cpu_isolated_map;
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
-        cpulist_parse(str, *cpu_isolated_map);
+        cpulist_parse(str, cpu_isolated_map);
        return 1;
 }
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index ce340835d055..5fcf0e184586 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -43,7 +43,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
                        enum cpu_idle_type itype;
                        cpumask_scnprintf(mask_str, mask_len,
-                                          *sched_domain_span(sd));
+                                          sched_domain_span(sd));
                        seq_printf(seq, "domain%d %s", dcount++, mask_str);
                        for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
                                        itype++) {
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index bd6be76303cf..6d7dc4ec4aa5 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -352,7 +352,7 @@ static int parse(struct nlattr *na, cpumask_t *mask)
        if (!data)
                return -ENOMEM;
        nla_strlcpy(data, na, len);
-        ret = cpulist_parse(data, *mask);
+        ret = cpulist_parse(data, mask);
        kfree(data);
        return ret;
 }
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index f8d968063cea..ea2f48af83cf 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -166,6 +166,8 @@ static void clockevents_notify_released(void)
 void clockevents_register_device(struct clock_event_device *dev)
 {
        BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+        BUG_ON(!dev->cpumask);
        /*
         * A nsec2cyc multiplicator of 0 is invalid and we'd crash
         * on it, so fix it up and emit a warning:
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f98a1b7b16e9..9590af2327be 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -150,7 +150,7 @@ static void tick_do_broadcast(cpumask_t mask)
                 */
                cpu = first_cpu(mask);
                td = &per_cpu(tick_cpu_device, cpu);
-                td->evtdev->broadcast(mask);
+                td->evtdev->broadcast(&mask);
        }
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index df12434b43ca..f8372be74122 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -136,7 +136,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 */
 static void tick_setup_device(struct tick_device *td,
                              struct clock_event_device *newdev, int cpu,
-                              const cpumask_t *cpumask)
+                              const struct cpumask *cpumask)
 {
        ktime_t next_event;
        void (*handler)(struct clock_event_device *) = NULL;
@@ -171,8 +171,8 @@ static void tick_setup_device(struct tick_device *td,
         * When the device is not per cpu, pin the interrupt to the
         * current cpu:
         */
-        if (!cpus_equal(newdev->cpumask, *cpumask))
+        if (!cpumask_equal(newdev->cpumask, cpumask))
-                irq_set_affinity(newdev->irq, *cpumask);
+                irq_set_affinity(newdev->irq, cpumask);
        /*
         * When global broadcasting is active, check if the current
@@ -202,14 +202,14 @@ static int tick_check_new_device(struct clock_event_device *newdev)
        spin_lock_irqsave(&tick_device_lock, flags);
        cpu = smp_processor_id();
-        if (!cpu_isset(cpu, newdev->cpumask))
+        if (!cpumask_test_cpu(cpu, newdev->cpumask))
                goto out_bc;
        td = &per_cpu(tick_cpu_device, cpu);
        curdev = td->evtdev;
        /* cpu local device ? */
-        if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) {
+        if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
                /*
                 * If the cpu affinity of the device interrupt can not
@@ -222,7 +222,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
                 * If we have a cpu local device already, do not replace it
                 * by a non cpu local device
                 */
-                if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu)))
+                if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
                        goto out_bc;
        }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8ebe0070c47a..6adf660fc816 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2646,7 +2646,7 @@ tracing_cpumask_read(struct file *filp, char __user *ubuf,
        mutex_lock(&tracing_cpumask_update_lock);
-        len = cpumask_scnprintf(mask_str, count, tracing_cpumask);
+        len = cpumask_scnprintf(mask_str, count, &tracing_cpumask);
        if (count - len < 2) {
                count = -EINVAL;
                goto out_err;
@@ -2667,7 +2667,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
        int err, cpu;
        mutex_lock(&tracing_cpumask_update_lock);
-        err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
+        err = cpumask_parse_user(ubuf, count, &tracing_cpumask_new);
        if (err)
                goto err_unlock;
diff --git a/lib/Kconfig b/lib/Kconfig
index 85cf7ea978aa..7823f8342abf 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -157,4 +157,11 @@ config CHECK_SIGNATURE
 config HAVE_LMB
        boolean
+config CPUMASK_OFFSTACK
+        bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+        help
+          Use dynamic allocation for cpumask_var_t, instead of putting
+          them on the stack.  This is a bit more expensive, but avoids
+          stack overflow.
 endmenu
diff --git a/mm/slub.c b/mm/slub.c
index a2cd47d89e0a..8e516e29f989 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3626,7 +3626,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
                                len < PAGE_SIZE - 60) {
                        len += sprintf(buf + len, " cpus=");
                        len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50,
-                                        l->cpus);
+                                        &l->cpus);
                }
                if (num_online_nodes() > 1 && !nodes_empty(l->nodes) &&