Merge branch 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

Pull percpu consistent-ops changes from Tejun Heo:
 "Way back, before the current percpu allocator was implemented, static
  and dynamic percpu memory areas were allocated and handled separately
  and had their own accessors.  The distinction has been gone for many
  years now; however, the now duplicate two sets of accessors remained
  with the pointer based ones - this_cpu_*() - evolving various other
  operations over time.  During the process, we also accumulated other
  inconsistent operations.

  This pull request contains Christoph's patches to clean up the
  duplicate accessor situation.  __get_cpu_var() uses are replaced with
  with this_cpu_ptr() and __this_cpu_ptr() with raw_cpu_ptr().

  Unfortunately, the former sometimes is tricky thanks to C being a bit
  messy with the distinction between lvalues and pointers, which led to
  a rather ugly solution for cpumask_var_t involving the introduction of
  this_cpu_cpumask_var_ptr().

  This converts most of the uses but not all.  Christoph will follow up
  with the remaining conversions in this merge window and hopefully
  remove the obsolete accessors"

* 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (38 commits)
  irqchip: Properly fetch the per cpu offset
  percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t -fix
  ia64: sn_nodepda cannot be assigned to after this_cpu conversion. Use __this_cpu_write.
  percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t
  Revert "powerpc: Replace __get_cpu_var uses"
  percpu: Remove __this_cpu_ptr
  clocksource: Replace __this_cpu_ptr with raw_cpu_ptr
  sparc: Replace __get_cpu_var uses
  avr32: Replace __get_cpu_var with __this_cpu_write
  blackfin: Replace __get_cpu_var uses
  tile: Use this_cpu_ptr() for hardware counters
  tile: Replace __get_cpu_var uses
  powerpc: Replace __get_cpu_var uses
  alpha: Replace __get_cpu_var
  ia64: Replace __get_cpu_var uses
  s390: cio driver &__get_cpu_var replacements
  s390: Replace __get_cpu_var uses
  mips: Replace __get_cpu_var uses
  MIPS: Replace __get_cpu_var uses in FPU emulator.
  arm: Replace __this_cpu_ptr with raw_cpu_ptr
  ...

96 files changed, 410 insertions, 405 deletions

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index c52e7f0..5c218aa 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -431,7 +431,7 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  */
 static int alpha_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
@@ -483,7 +483,7 @@ static int alpha_pmu_add(struct perf_event *event, int flags)
  */
 static void alpha_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long irq_flags;
 	int j;
@@ -531,7 +531,7 @@ static void alpha_pmu_read(struct perf_event *event)
 static void alpha_pmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		cpuc->idx_mask &= ~(1UL<<hwc->idx);
@@ -551,7 +551,7 @@ static void alpha_pmu_stop(struct perf_event *event, int flags)
 static void alpha_pmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
 		return;
@@ -724,7 +724,7 @@ static int alpha_pmu_event_init(struct perf_event *event)
  */
 static void alpha_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->enabled)
 		return;
@@ -750,7 +750,7 @@ static void alpha_pmu_enable(struct pmu *pmu)
 
 static void alpha_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuc->enabled)
 		return;
@@ -814,8 +814,8 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	struct hw_perf_event *hwc;
 	int idx, j;
 
-	__get_cpu_var(irq_pmi_count)++;
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	__this_cpu_inc(irq_pmi_count);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* Completely counting through the PMC's period to trigger a new PMC
 	 * overflow interrupt while in this interrupt routine is utterly
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index ee39cee..643a9dc 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -56,9 +56,9 @@ unsigned long est_cycle_freq;
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()  __get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()  __this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()      __this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()     __this_cpu_write(irq_work_pending, 0)
 
 void arch_irq_work_raise(void)
 {
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index dfc3213..9309021 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -92,7 +92,7 @@ static int twd_timer_ack(void)
 
 static void twd_timer_stop(void)
 {
-	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 
 	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
 	disable_percpu_irq(clk->irq);
@@ -108,7 +108,7 @@ static void twd_update_frequency(void *new_rate)
 {
 	twd_timer_rate = *((unsigned long *) new_rate);
 
-	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_rate_change(struct notifier_block *nb,
@@ -134,7 +134,7 @@ static struct notifier_block twd_clk_nb = {
 
 static int twd_clk_init(void)
 {
-	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return clk_notifier_register(twd_clk, &twd_clk_nb);
 
 	return 0;
@@ -153,7 +153,7 @@ static void twd_update_frequency(void *data)
 {
 	twd_timer_rate = clk_get_rate(twd_clk);
 
-	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_cpufreq_transition(struct notifier_block *nb,
@@ -179,7 +179,7 @@ static struct notifier_block twd_cpufreq_nb = {
 
 static int twd_cpufreq_init(void)
 {
-	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return cpufreq_register_notifier(&twd_cpufreq_nb,
 			CPUFREQ_TRANSITION_NOTIFIER);
 
@@ -269,7 +269,7 @@ static void twd_get_clock(struct device_node *np)
  */
 static void twd_timer_setup(void)
 {
-	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 	int cpu = smp_processor_id();
 
 	/*
diff --git a/arch/avr32/kernel/kprobes.c b/arch/avr32/kernel/kprobes.c
index f820e9f..a94ece4 100644
--- a/arch/avr32/kernel/kprobes.c
+++ b/arch/avr32/kernel/kprobes.c
@@ -104,7 +104,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 
 static void __kprobes set_current_kprobe(struct kprobe *p)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static int __kprobes kprobe_handler(struct pt_regs *regs)
diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h
index 17b5e92..fe1160f 100644
--- a/arch/blackfin/include/asm/ipipe.h
+++ b/arch/blackfin/include/asm/ipipe.h
@@ -157,7 +157,7 @@ static inline unsigned long __ipipe_ffnz(unsigned long ul)
 }
 
 #define __ipipe_do_root_xirq(ipd, irq)					\
-	((ipd)->irqs[irq].handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)))
+	((ipd)->irqs[irq].handler(irq, raw_cpu_ptr(&__ipipe_tick_regs)))
 
 #define __ipipe_run_irqtail(irq)  /* Must be a macro */			\
 	do {								\
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index ea20320..1e9c8b0 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -300,7 +300,7 @@ again:
 
 static void bfin_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -318,7 +318,7 @@ static void bfin_pmu_stop(struct perf_event *event, int flags)
 
 static void bfin_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -335,7 +335,7 @@ static void bfin_pmu_start(struct perf_event *event, int flags)
 
 static void bfin_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	bfin_pmu_stop(event, PERF_EF_UPDATE);
 	__clear_bit(event->hw.idx, cpuc->used_mask);
@@ -345,7 +345,7 @@ static void bfin_pmu_del(struct perf_event *event, int flags)
 
 static int bfin_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	int ret = -EAGAIN;
@@ -421,7 +421,7 @@ static int bfin_pmu_event_init(struct perf_event *event)
 
 static void bfin_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	int i;
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 6946193..dd2af74 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -1309,12 +1309,12 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs)
 		bfin_write_TIMER_STATUS(1); /* Latch TIMIL0 */
 #endif
 		/* This is basically what we need from the register frame. */
-		__raw_get_cpu_var(__ipipe_tick_regs).ipend = regs->ipend;
-		__raw_get_cpu_var(__ipipe_tick_regs).pc = regs->pc;
+		__this_cpu_write(__ipipe_tick_regs.ipend, regs->ipend);
+		__this_cpu_write(__ipipe_tick_regs.pc, regs->pc);
 		if (this_domain != ipipe_root_domain)
-			__raw_get_cpu_var(__ipipe_tick_regs).ipend &= ~0x10;
+			__this_cpu_and(__ipipe_tick_regs.ipend, ~0x10);
 		else
-			__raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10;
+			__this_cpu_or(__ipipe_tick_regs.ipend, 0x10);
 	}
 
 	/*
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index ba6c30d..8ad3e90 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -146,7 +146,7 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 	platform_clear_ipi(cpu, IRQ_SUPPLE_1);
 
 	smp_rmb();
-	bfin_ipi_data = &__get_cpu_var(bfin_ipi);
+	bfin_ipi_data = this_cpu_ptr(&bfin_ipi);
 	while ((pending = atomic_xchg(&bfin_ipi_data->bits, 0)) != 0) {
 		msg = 0;
 		do {
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 029bab3..668786e 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -159,7 +159,7 @@ static inline ia64_vector __ia64_irq_to_vector(int irq)
 static inline unsigned int
 __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 
diff --git a/arch/ia64/include/asm/sn/arch.h b/arch/ia64/include/asm/sn/arch.h
index 7caa1f4..31eb784 100644
--- a/arch/ia64/include/asm/sn/arch.h
+++ b/arch/ia64/include/asm/sn/arch.h
@@ -57,7 +57,7 @@ struct sn_hub_info_s {
 	u16 nasid_bitmask;
 };
 DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
-#define sn_hub_info 	(&__get_cpu_var(__sn_hub_info))
+#define sn_hub_info 	this_cpu_ptr(&__sn_hub_info)
 #define is_shub2()	(sn_hub_info->shub2)
 #define is_shub1()	(sn_hub_info->shub2 == 0)
 
@@ -72,7 +72,7 @@ DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
  * cpu.
  */
 DECLARE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
-#define sn_cnodeid_to_nasid	(&__get_cpu_var(__sn_cnodeid_to_nasid[0]))
+#define sn_cnodeid_to_nasid	this_cpu_ptr(&__sn_cnodeid_to_nasid[0])
 
 
 extern u8 sn_partition_id;
diff --git a/arch/ia64/include/asm/sn/nodepda.h b/arch/ia64/include/asm/sn/nodepda.h
index ee118b9..7c8b471 100644
--- a/arch/ia64/include/asm/sn/nodepda.h
+++ b/arch/ia64/include/asm/sn/nodepda.h
@@ -70,7 +70,7 @@ typedef struct nodepda_s nodepda_t;
  */
 
 DECLARE_PER_CPU(struct nodepda_s *, __sn_nodepda);
-#define sn_nodepda		(__get_cpu_var(__sn_nodepda))
+#define sn_nodepda		__this_cpu_read(__sn_nodepda)
 #define	NODEPDA(cnodeid)	(sn_nodepda->pernode_pdaindr[cnodeid])
 
 /*
diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h
index d38c7ea..e8f3585 100644
--- a/arch/ia64/include/asm/switch_to.h
+++ b/arch/ia64/include/asm/switch_to.h
@@ -32,7 +32,7 @@ extern void ia64_load_extra (struct task_struct *task);
 
 #ifdef CONFIG_PERFMON
   DECLARE_PER_CPU(unsigned long, pfm_syst_info);
-# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
+# define PERFMON_IS_SYSWIDE() (__this_cpu_read(pfm_syst_info) & 0x1)
 #else
 # define PERFMON_IS_SYSWIDE() (0)
 #endif
diff --git a/arch/ia64/include/asm/uv/uv_hub.h b/arch/ia64/include/asm/uv/uv_hub.h
index 53e9dfa..2a88c720 100644
--- a/arch/ia64/include/asm/uv/uv_hub.h
+++ b/arch/ia64/include/asm/uv/uv_hub.h
@@ -108,7 +108,7 @@ struct uv_hub_info_s {
 	unsigned char	n_val;
 };
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info 		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index f2c41828..812a1e6 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -42,7 +42,7 @@ ia64_vector __ia64_irq_to_vector(int irq)
 
 unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 03ea78e..698d8fe 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -330,7 +330,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 		int irq;
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
-		irq = __get_cpu_var(vector_irq)[vector];
+		irq = __this_cpu_read(vector_irq[vector]);
 		if (irq < 0)
 			continue;
 
@@ -344,7 +344,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 			goto unlock;
 
 		spin_lock_irqsave(&vector_lock, flags);
-		__get_cpu_var(vector_irq)[vector] = -1;
+		__this_cpu_write(vector_irq[vector], -1);
 		cpu_clear(me, vector_table[vector]);
 		spin_unlock_irqrestore(&vector_lock, flags);
 		cfg->move_cleanup_count--;
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 074fde4..c7c5144 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -396,7 +396,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	unsigned int i;
 	i = atomic_read(&kcb->prev_kprobe_index);
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe[i-1].kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe[i-1].kp);
 	kcb->kprobe_status = kcb->prev_kprobe[i-1].status;
 	atomic_sub(1, &kcb->prev_kprobe_index);
 }
@@ -404,7 +404,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p,
 			struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static void kretprobe_trampoline(void)
@@ -823,7 +823,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			/*
 			 * jprobe instrumented function just completed
 			 */
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs)) {
 				goto ss_probe;
 			}
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index db7b36b..8bfd36a 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1341,7 +1341,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		ia64_mlogbuf_finish(1);
 	}
 
-	if (__get_cpu_var(ia64_mca_tr_reload)) {
+	if (__this_cpu_read(ia64_mca_tr_reload)) {
 		mca_insert_tr(0x1); /*Reload dynamic itrs*/
 		mca_insert_tr(0x2); /*Reload dynamic itrs*/
 	}
@@ -1868,14 +1868,14 @@ ia64_mca_cpu_init(void *cpu_data)
 		"MCA", cpu);
 	format_mca_init_stack(data, offsetof(struct ia64_mca_cpu, init_stack),
 		"INIT", cpu);
-	__get_cpu_var(ia64_mca_data) = __per_cpu_mca[cpu] = __pa(data);
+	__this_cpu_write(ia64_mca_data, (__per_cpu_mca[cpu] = __pa(data)));
 
 	/*
 	 * Stash away a copy of the PTE needed to map the per-CPU page.
 	 * We may need it during MCA recovery.
 	 */
-	__get_cpu_var(ia64_mca_per_cpu_pte) =
-		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_per_cpu_pte,
+		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL)));
 
 	/*
 	 * Also, stash away a copy of the PAL address and the PTE
@@ -1884,10 +1884,10 @@ ia64_mca_cpu_init(void *cpu_data)
 	pal_vaddr = efi_get_pal_addr();
 	if (!pal_vaddr)
 		return;
-	__get_cpu_var(ia64_mca_pal_base) =
-		GRANULEROUNDDOWN((unsigned long) pal_vaddr);
-	__get_cpu_var(ia64_mca_pal_pte) = pte_val(mk_pte_phys(__pa(pal_vaddr),
-							      PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_pal_base,
+		GRANULEROUNDDOWN((unsigned long) pal_vaddr));
+	__this_cpu_write(ia64_mca_pal_pte, pte_val(mk_pte_phys(__pa(pal_vaddr),
+							      PAGE_KERNEL)));
 }
 
 static void ia64_mca_cmc_vector_adjust(void *dummy)
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index deed6fa..b515149 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -215,7 +215,7 @@ static inline void play_dead(void)
 	unsigned int this_cpu = smp_processor_id();
 
 	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 
 	max_xtp();
 	local_irq_disable();
@@ -273,7 +273,7 @@ ia64_save_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_save_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE)
 		pfm_syst_wide_update_task(task, info, 0);
 #endif
@@ -293,7 +293,7 @@ ia64_load_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_load_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE) 
 		pfm_syst_wide_update_task(task, info, 1);
 #endif
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index d3636e6..6f7d4a4 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -299,7 +299,7 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 
 	if (!(current->thread.flags & IA64_THREAD_FPEMU_NOPRINT))  {
 		unsigned long count, current_jiffies = jiffies;
-		struct fpu_swa_msg *cp = &__get_cpu_var(cpulast);
+		struct fpu_swa_msg *cp = this_cpu_ptr(&cpulast);
 
 		if (unlikely(current_jiffies > cp->time))
 			cp->count = 0;
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 36182c8..5f6b6b4 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -629,7 +629,7 @@ void sn_cpu_init(void)
 
 	cnode = nasid_to_cnodeid(nasid);
 
-	sn_nodepda = nodepdaindr[cnode];
+	__this_cpu_write(__sn_nodepda, nodepdaindr[cnode]);
 
 	pda->led_address =
 	    (typeof(pda->led_address)) (LED0 + (slice << LED_CPU_SHIFT));
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 68c8454..f9c8d9f 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -134,8 +134,8 @@ sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 	itc = ia64_get_itc();
 	smp_flush_tlb_cpumask(*mm_cpumask(mm));
 	itc = ia64_get_itc() - itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes_itc_clocks += itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes++;
+	__this_cpu_add(ptcstats.shub_ipi_flushes_itc_clocks, itc);
+	__this_cpu_inc(ptcstats.shub_ipi_flushes);
 }
 
 /**
@@ -199,14 +199,14 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 			start += (1UL << nbits);
 		} while (start < end);
 		ia64_srlz_i();
-		__get_cpu_var(ptcstats).ptc_l++;
+		__this_cpu_inc(ptcstats.ptc_l);
 		preempt_enable();
 		return;
 	}
 
 	if (atomic_read(&mm->mm_users) == 1 && mymm) {
 		flush_tlb_mm(mm);
-		__get_cpu_var(ptcstats).change_rid++;
+		__this_cpu_inc(ptcstats.change_rid);
 		preempt_enable();
 		return;
 	}
@@ -250,11 +250,11 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	spin_lock_irqsave(PTC_LOCK(shub1), flags);
 	itc2 = ia64_get_itc();
 
-	__get_cpu_var(ptcstats).lock_itc_clocks += itc2 - itc;
-	__get_cpu_var(ptcstats).shub_ptc_flushes++;
-	__get_cpu_var(ptcstats).nodes_flushed += nix;
+	__this_cpu_add(ptcstats.lock_itc_clocks, itc2 - itc);
+	__this_cpu_inc(ptcstats.shub_ptc_flushes);
+	__this_cpu_add(ptcstats.nodes_flushed, nix);
 	if (!mymm)
-		 __get_cpu_var(ptcstats).shub_ptc_flushes_not_my_mm++;
+		 __this_cpu_inc(ptcstats.shub_ptc_flushes_not_my_mm);
 
 	if (use_cpu_ptcga && !mymm) {
 		old_rr = ia64_get_rr(start);
@@ -299,9 +299,9 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 
 done:
 	itc2 = ia64_get_itc() - itc2;
-	__get_cpu_var(ptcstats).shub_itc_clocks += itc2;
-	if (itc2 > __get_cpu_var(ptcstats).shub_itc_clocks_max)
-		__get_cpu_var(ptcstats).shub_itc_clocks_max = itc2;
+	__this_cpu_add(ptcstats.shub_itc_clocks, itc2);
+	if (itc2 > __this_cpu_read(ptcstats.shub_itc_clocks_max))
+		__this_cpu_write(ptcstats.shub_itc_clocks_max, itc2);
 
 	if (old_rr) {
 		ia64_set_rr(start, old_rr);
@@ -311,7 +311,7 @@ done:
 	spin_unlock_irqrestore(PTC_LOCK(shub1), flags);
 
 	if (flush_opt == 1 && deadlock) {
-		__get_cpu_var(ptcstats).deadlocks++;
+		__this_cpu_inc(ptcstats.deadlocks);
 		sn2_ipi_flush_all_tlb(mm);
 	}
 
@@ -334,7 +334,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 	short nasid, i;
 	unsigned long *piows, zeroval, n;
 
-	__get_cpu_var(ptcstats).deadlocks++;
+	__this_cpu_inc(ptcstats.deadlocks);
 
 	piows = (unsigned long *) pda->pio_write_status_addr;
 	zeroval = pda->pio_write_status_val;
@@ -349,7 +349,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 			ptc1 = CHANGE_NASID(nasid, ptc1);
 
 		n = sn2_ptc_deadlock_recovery_core(ptc0, data0, ptc1, data1, piows, zeroval);
-		__get_cpu_var(ptcstats).deadlocks2 += n;
+		__this_cpu_add(ptcstats.deadlocks2, n);
 	}
 
 }
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 02c0873..2478ec6 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -258,7 +258,7 @@ int metag_pmu_event_set_period(struct perf_event *event,
 
 static void metag_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -306,7 +306,7 @@ static void metag_pmu_stop(struct perf_event *event, int flags)
 
 static int metag_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = 0, ret = 0;
 
@@ -348,7 +348,7 @@ out:
 
 static void metag_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -597,7 +597,7 @@ static int _hw_perf_event_init(struct perf_event *event)
 
 static void metag_pmu_enable_counter(struct hw_perf_event *event, int idx)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	unsigned int config = event->config;
 	unsigned int tmp = config & 0xf0;
 	unsigned long flags;
@@ -670,7 +670,7 @@ unlock:
 
 static void metag_pmu_disable_counter(struct hw_perf_event *event, int idx)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	unsigned int tmp = 0;
 	unsigned long flags;
 
@@ -718,7 +718,7 @@ out:
 
 static void metag_pmu_write_counter(int idx, u32 val)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	u32 tmp = 0;
 	unsigned long flags;
 
@@ -751,7 +751,7 @@ static int metag_pmu_event_map(int idx)
 static irqreturn_t metag_pmu_counter_overflow(int irq, void *dev)
 {
 	int idx = (int)dev;
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event = cpuhw->events[idx];
 	struct hw_perf_event *hwc = &event->hw;
 	struct pt_regs *regs = get_irq_regs();
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 1b82ac6..7417340 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -264,13 +264,13 @@ static void octeon_irq_ciu_enable_local(struct irq_data *data)
 	unsigned long *pen;
 	unsigned long flags;
 	union octeon_ciu_chip_data cd;
-	raw_spinlock_t *lock = &__get_cpu_var(octeon_irq_ciu_spinlock);
+	raw_spinlock_t *lock = this_cpu_ptr(&octeon_irq_ciu_spinlock);
 
 	cd.p = irq_data_get_irq_chip_data(data);
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (cd.s.line == 0) {
-		pen = &__get_cpu_var(octeon_irq_ciu0_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu0_en_mirror);
 		__set_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -279,7 +279,7 @@ static void octeon_irq_ciu_enable_local(struct irq_data *data)
 		wmb();
 		cvmx_write_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2), *pen);
 	} else {
-		pen = &__get_cpu_var(octeon_irq_ciu1_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu1_en_mirror);
 		__set_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -296,13 +296,13 @@ static void octeon_irq_ciu_disable_local(struct irq_data *data)
 	unsigned long *pen;
 	unsigned long flags;
 	union octeon_ciu_chip_data cd;
-	raw_spinlock_t *lock = &__get_cpu_var(octeon_irq_ciu_spinlock);
+	raw_spinlock_t *lock = this_cpu_ptr(&octeon_irq_ciu_spinlock);
 
 	cd.p = irq_data_get_irq_chip_data(data);
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (cd.s.line == 0) {
-		pen = &__get_cpu_var(octeon_irq_ciu0_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu0_en_mirror);
 		__clear_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -311,7 +311,7 @@ static void octeon_irq_ciu_disable_local(struct irq_data *data)
 		wmb();
 		cvmx_write_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2), *pen);
 	} else {
-		pen = &__get_cpu_var(octeon_irq_ciu1_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu1_en_mirror);
 		__clear_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -431,11 +431,11 @@ static void octeon_irq_ciu_enable_local_v2(struct irq_data *data)
 
 	if (cd.s.line == 0) {
 		int index = cvmx_get_core_num() * 2;
-		set_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu0_en_mirror));
+		set_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu0_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1S(index), mask);
 	} else {
 		int index = cvmx_get_core_num() * 2 + 1;
-		set_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu1_en_mirror));
+		set_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu1_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1S(index), mask);
 	}
 }
@@ -450,11 +450,11 @@ static void octeon_irq_ciu_disable_local_v2(struct irq_data *data)
 
 	if (cd.s.line == 0) {
 		int index = cvmx_get_core_num() * 2;
-		clear_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu0_en_mirror));
+		clear_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu0_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1C(index), mask);
 	} else {
 		int index = cvmx_get_core_num() * 2 + 1;
-		clear_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu1_en_mirror));
+		clear_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu1_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1C(index), mask);
 	}
 }
@@ -1063,7 +1063,7 @@ static void octeon_irq_ip2_ciu(void)
 	const unsigned long core_id = cvmx_get_core_num();
 	u64 ciu_sum = cvmx_read_csr(CVMX_CIU_INTX_SUM0(core_id * 2));
 
-	ciu_sum &= __get_cpu_var(octeon_irq_ciu0_en_mirror);
+	ciu_sum &= __this_cpu_read(octeon_irq_ciu0_en_mirror);
 	if (likely(ciu_sum)) {
 		int bit = fls64(ciu_sum) - 1;
 		int irq = octeon_irq_ciu_to_irq[0][bit];
@@ -1080,7 +1080,7 @@ static void octeon_irq_ip3_ciu(void)
 {
 	u64 ciu_sum = cvmx_read_csr(CVMX_CIU_INT_SUM1);
 
-	ciu_sum &= __get_cpu_var(octeon_irq_ciu1_en_mirror);
+	ciu_sum &= __this_cpu_read(octeon_irq_ciu1_en_mirror);
 	if (likely(ciu_sum)) {
 		int bit = fls64(ciu_sum) - 1;
 		int irq = octeon_irq_ciu_to_irq[1][bit];
@@ -1129,10 +1129,10 @@ static void octeon_irq_init_ciu_percpu(void)
 	int coreid = cvmx_get_core_num();
 
 
-	__get_cpu_var(octeon_irq_ciu0_en_mirror) = 0;
-	__get_cpu_var(octeon_irq_ciu1_en_mirror) = 0;
+	__this_cpu_write(octeon_irq_ciu0_en_mirror, 0);
+	__this_cpu_write(octeon_irq_ciu1_en_mirror, 0);
 	wmb();
-	raw_spin_lock_init(&__get_cpu_var(octeon_irq_ciu_spinlock));
+	raw_spin_lock_init(this_cpu_ptr(&octeon_irq_ciu_spinlock));
 	/*
 	 * Disable All CIU Interrupts. The ones we need will be
 	 * enabled later.  Read the SUM register so we know the write
diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h
index 0195745..3ee3477 100644
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@@ -33,17 +33,17 @@
 #ifdef CONFIG_DEBUG_FS
 
 struct mips_fpu_emulator_stats {
-	local_t emulated;
-	local_t loads;
-	local_t stores;
-	local_t cp1ops;
-	local_t cp1xops;
-	local_t errors;
-	local_t ieee754_inexact;
-	local_t ieee754_underflow;
-	local_t ieee754_overflow;
-	local_t ieee754_zerodiv;
-	local_t ieee754_invalidop;
+	unsigned long emulated;
+	unsigned long loads;
+	unsigned long stores;
+	unsigned long cp1ops;
+	unsigned long cp1xops;
+	unsigned long errors;
+	unsigned long ieee754_inexact;
+	unsigned long ieee754_underflow;
+	unsigned long ieee754_overflow;
+	unsigned long ieee754_zerodiv;
+	unsigned long ieee754_invalidop;
 };
 
 DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
@@ -51,7 +51,7 @@ DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
 #define MIPS_FPU_EMU_INC_STATS(M)					\
 do {									\
 	preempt_disable();						\
-	__local_inc(&__get_cpu_var(fpuemustats).M);			\
+	__this_cpu_inc(fpuemustats.M);					\
 	preempt_enable();						\
 } while (0)
 
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 1f8187a..212f46f 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -224,7 +224,7 @@ static void save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_old_SR = kcb->prev_kprobe.old_SR;
 	kcb->kprobe_saved_SR = kcb->prev_kprobe.saved_SR;
@@ -234,7 +234,7 @@ static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 			       struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_SR = kcb->kprobe_old_SR = (regs->cp0_status & ST0_IE);
 	kcb->kprobe_saved_epc = regs->cp0_epc;
 }
@@ -385,7 +385,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index b63f248..a8f9cdc 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -340,7 +340,7 @@ static int mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc,
 
 static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
 
@@ -360,7 +360,7 @@ static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 
 static void mipsxx_pmu_disable_event(int idx)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
@@ -460,7 +460,7 @@ static void mipspmu_stop(struct perf_event *event, int flags)
 
 static int mipspmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -496,7 +496,7 @@ out:
 
 static void mipspmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -1275,7 +1275,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static void pause_local_counters(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int ctr = mipspmu.num_counters;
 	unsigned long flags;
 
@@ -1291,7 +1291,7 @@ static void pause_local_counters(void)
 
 static void resume_local_counters(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int ctr = mipspmu.num_counters;
 
 	do {
@@ -1302,7 +1302,7 @@ static void resume_local_counters(void)
 
 static int mipsxx_pmu_handle_shared_irq(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_sample_data data;
 	unsigned int counters = mipspmu.num_counters;
 	u64 counter;
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index df9e2bd..06bb5ed 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -346,7 +346,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id)
 	int action, cpu = irq - IPI0_IRQ;
 
 	spin_lock_irqsave(&ipi_lock, flags);
-	action = __get_cpu_var(ipi_action_mask);
+	action = __this_cpu_read(ipi_action_mask);
 	per_cpu(ipi_action_mask, cpu) = 0;
 	clear_c0_cause(cpu ? C_SW1 : C_SW0);
 	spin_unlock_irqrestore(&ipi_lock, flags);
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index 74e827b..d8c63af 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -299,16 +299,16 @@ static void loongson3_init_secondary(void)
 	per_cpu(cpu_state, cpu) = CPU_ONLINE;
 
 	i = 0;
-	__get_cpu_var(core0_c0count) = 0;
+	__this_cpu_write(core0_c0count, 0);
 	loongson3_send_ipi_single(0, SMP_ASK_C0COUNT);
-	while (!__get_cpu_var(core0_c0count)) {
+	while (!__this_cpu_read(core0_c0count)) {
 		i++;
 		cpu_relax();
 	}
 
 	if (i > MAX_LOOPS)
 		i = MAX_LOOPS;
-	initcount = __get_cpu_var(core0_c0count) + i;
+	initcount = __this_cpu_read(core0_c0count) + i;
 	write_c0_count(initcount);
 }
 
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 6c840ce..e245255 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -58,10 +58,10 @@ static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 static inline cputime_t cputime_to_scaled(const cputime_t ct)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR) &&
-	    __get_cpu_var(cputime_last_delta))
+	    __this_cpu_read(cputime_last_delta))
 		return (__force u64) ct *
-			__get_cpu_var(cputime_scaled_last_delta) /
-			__get_cpu_var(cputime_last_delta);
+			__this_cpu_read(cputime_scaled_last_delta) /
+			__this_cpu_read(cputime_last_delta);
 	return ct;
 }
 
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index e787cc1..b0d5f0a 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -82,7 +82,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
 
 static __always_inline void inc_irq_stat(enum interruption_class irq)
 {
-	__get_cpu_var(irq_stat).irqs[irq]++;
+	__this_cpu_inc(irq_stat.irqs[irq]);
 }
 
 struct ext_code {
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index fa91e00..933355e 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -31,7 +31,7 @@
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
 		old__ = prev__;						\
@@ -70,7 +70,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
 		asm volatile(						\
@@ -97,7 +97,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
@@ -116,7 +116,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
@@ -138,7 +138,7 @@
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
 	preempt_enable();						\
 	ret__;								\
@@ -154,7 +154,7 @@
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
 	preempt_enable();						\
 	ret__;								\
@@ -173,8 +173,8 @@
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
 	preempt_disable();						\
-	p1__ = __this_cpu_ptr(&(pcp1));					\
-	p2__ = __this_cpu_ptr(&(pcp2));					\
+	p1__ = raw_cpu_ptr(&(pcp1));					\
+	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
 	preempt_enable();						\
 	ret__;								\
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index c846aee..7559f1b 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -21,7 +21,7 @@ static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
 void __kprobes enabled_wait(void)
 {
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
 	unsigned long long idle_time;
 	unsigned long psw_mask;
 
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 27ae5433..014d472 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -218,9 +218,9 @@ static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb,
  */
 static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
 {
-	kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe);
+	kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe);
 	kcb->prev_kprobe.status = kcb->kprobe_status;
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 /*
@@ -230,7 +230,7 @@ static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
  */
 static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
@@ -311,7 +311,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
 	} else if (kprobe_running()) {
-		p = __get_cpu_var(current_kprobe);
+		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
 			/*
 			 * Continuation after the jprobe completed and
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index db96b41..dd1c24c 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -54,8 +54,12 @@ void s390_handle_mcck(void)
 	 */
 	local_irq_save(flags);
 	local_mcck_disable();
-	mcck = __get_cpu_var(cpu_mcck);
-	memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct));
+	/*
+	 * Ummm... Does this make sense at all? Copying the percpu struct
+	 * and then zapping it one statement later?
+	 */
+	memcpy(&mcck, this_cpu_ptr(&cpu_mcck), sizeof(mcck));
+	memset(&mcck, 0, sizeof(struct mcck_struct));
 	clear_cpu_flag(CIF_MCCK_PENDING);
 	local_mcck_enable();
 	local_irq_restore(flags);
@@ -269,7 +273,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	nmi_enter();
 	inc_irq_stat(NMI_NMI);
 	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
-	mcck = &__get_cpu_var(cpu_mcck);
+	mcck = this_cpu_ptr(&cpu_mcck);
 	umode = user_mode(regs);
 
 	if (mci->sd) {
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index d3194de..56fdad4 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -173,7 +173,7 @@ static int validate_ctr_auth(const struct hw_perf_event *hwc)
  */
 static void cpumf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 
 	if (cpuhw->flags & PMU_F_ENABLED)
@@ -196,7 +196,7 @@ static void cpumf_pmu_enable(struct pmu *pmu)
  */
 static void cpumf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 	u64 inactive;
 
@@ -230,7 +230,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 		return;
 
 	inc_irq_stat(IRQEXT_CMC);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
@@ -250,7 +250,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 #define PMC_RELEASE   1
 static void setup_pmc_cpu(void *flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	switch (*((int *) flags)) {
 	case PMC_INIT:
@@ -475,7 +475,7 @@ static void cpumf_pmu_read(struct perf_event *event)
 
 static void cpumf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
@@ -506,7 +506,7 @@ static void cpumf_pmu_start(struct perf_event *event, int flags)
 
 static void cpumf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -527,7 +527,7 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags)
 
 static int cpumf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Check authorization for the counter set to which this
 	 * counter belongs.
@@ -551,7 +551,7 @@ static int cpumf_pmu_add(struct perf_event *event, int flags)
 
 static void cpumf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpumf_pmu_stop(event, PERF_EF_UPDATE);
 
@@ -575,7 +575,7 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
  */
 static void cpumf_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->flags |= PERF_EVENT_TXN;
@@ -589,7 +589,7 @@ static void cpumf_pmu_start_txn(struct pmu *pmu)
  */
 static void cpumf_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(cpuhw->tx_state != cpuhw->state);
 
@@ -604,7 +604,7 @@ static void cpumf_pmu_cancel_txn(struct pmu *pmu)
  */
 static int cpumf_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	u64 state;
 
 	/* check if the updated state can be scheduled */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ea0c7b2..08e7613 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -562,7 +562,7 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 static void setup_pmc_cpu(void *flags)
 {
 	int err;
-	struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpusf = this_cpu_ptr(&cpu_hw_sf);
 
 	err = 0;
 	switch (*((int *) flags)) {
@@ -849,7 +849,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 
 static void cpumsf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hw_perf_event *hwc;
 	int err;
 
@@ -898,7 +898,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 
 static void cpumsf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hws_lsctl_request_block inactive;
 	struct hws_qsi_info_block si;
 	int err;
@@ -1306,7 +1306,7 @@ static void cpumsf_pmu_read(struct perf_event *event)
  */
 static void cpumsf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
 		return;
@@ -1327,7 +1327,7 @@ static void cpumsf_pmu_start(struct perf_event *event, int flags)
  */
 static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	if (event->hw.state & PERF_HES_STOPPED)
 		return;
@@ -1346,7 +1346,7 @@ static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 
 static int cpumsf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	int err;
 
 	if (cpuhw->flags & PMU_F_IN_USE)
@@ -1397,7 +1397,7 @@ out:
 
 static void cpumsf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	perf_pmu_disable(event->pmu);
 	cpumsf_pmu_stop(event, PERF_EF_UPDATE);
@@ -1470,7 +1470,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 	if (!(alert & CPU_MF_INT_SF_MASK))
 		return;
 	inc_irq_stat(IRQEXT_CMS);
-	cpuhw = &__get_cpu_var(cpu_hw_sf);
+	cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index edefead..dbdd33e 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -23,7 +23,7 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id);
  */
 void cpu_init(void)
 {
-	struct cpuid *id = &__get_cpu_var(cpu_id);
+	struct cpuid *id = this_cpu_ptr(&cpu_id);
 
 	get_cpu_id(id);
 	atomic_inc(&init_mm.mm_count);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 69e980d..005d665 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -92,7 +92,7 @@ void clock_comparator_work(void)
 	struct clock_event_device *cd;
 
 	S390_lowcore.clock_comparator = -1ULL;
-	cd = &__get_cpu_var(comparators);
+	cd = this_cpu_ptr(&comparators);
 	cd->event_handler(cd);
 }
 
@@ -373,7 +373,7 @@ EXPORT_SYMBOL(get_sync_clock);
  */
 static void disable_sync_clock(void *dummy)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	/*
 	 * Clear the in-sync bit 2^31. All get_sync_clock calls will
 	 * fail until the sync bit is turned back on. In addition
@@ -390,7 +390,7 @@ static void disable_sync_clock(void *dummy)
  */
 static void enable_sync_clock(void)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	atomic_set_mask(0x80000000, sw_ptr);
 }
 
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index e53c6f2..ff9b4eb 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -178,7 +178,7 @@ static int smp_ctl_qsi(int cpu)
 static void hws_ext_handler(struct ext_code ext_code,
 			    unsigned int param32, unsigned long param64)
 {
-	struct hws_cpu_buffer *cb = &__get_cpu_var(sampler_cpu_buffer);
+	struct hws_cpu_buffer *cb = this_cpu_ptr(&sampler_cpu_buffer);
 
 	if (!(param32 & CPU_MF_INT_SF_MASK))
 		return;
diff --git a/arch/sparc/include/asm/cpudata_32.h b/arch/sparc/include/asm/cpudata_32.h
index 0300d94..05f3663 100644
--- a/arch/sparc/include/asm/cpudata_32.h
+++ b/arch/sparc/include/asm/cpudata_32.h
@@ -26,6 +26,6 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu) per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data() __get_cpu_var(__cpu_data)
+#define local_cpu_data() (*this_cpu_ptr(&__cpu_data))
 
 #endif /* _SPARC_CPUDATA_H */
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 0e59407..a6e424d 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -30,7 +30,7 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data()	__get_cpu_var(__cpu_data)
+#define local_cpu_data()	(*this_cpu_ptr(&__cpu_data))
 
 #endif /* !(__ASSEMBLY__) */
 
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 98d7128..cd83be5 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -83,7 +83,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_orig_tnpc = kcb->prev_kprobe.orig_tnpc;
 	kcb->kprobe_orig_tstate_pil = kcb->prev_kprobe.orig_tstate_pil;
@@ -92,7 +92,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 				struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_orig_tnpc = regs->tnpc;
 	kcb->kprobe_orig_tstate_pil = (regs->tstate & TSTATE_PIL);
 }
@@ -155,7 +155,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 018ef11..ea2bad3 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -343,7 +343,7 @@ static void leon_ipi_resched(int cpu)
 
 void leonsmp_ipi_interrupt(void)
 {
-	struct leon_ipi_work *work = &__get_cpu_var(leon_ipi_work);
+	struct leon_ipi_work *work = this_cpu_ptr(&leon_ipi_work);
 
 	if (work->single) {
 		work->single = 0;
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 5b1151d..a9973bb 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -100,20 +100,20 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
 
 	sum = local_cpu_data().irq0_irqs;
-	if (__get_cpu_var(nmi_touch)) {
-		__get_cpu_var(nmi_touch) = 0;
+	if (__this_cpu_read(nmi_touch)) {
+		__this_cpu_write(nmi_touch, 0);
 		touched = 1;
 	}
-	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+	if (!touched && __this_cpu_read(last_irq_sum) == sum) {
 		__this_cpu_inc(alert_counter);
 		if (__this_cpu_read(alert_counter) == 30 * nmi_hz)
 			die_nmi("BUG: NMI Watchdog detected LOCKUP",
 				regs, panic_on_timeout);
 	} else {
-		__get_cpu_var(last_irq_sum) = sum;
+		__this_cpu_write(last_irq_sum, sum);
 		__this_cpu_write(alert_counter, 0);
 	}
-	if (__get_cpu_var(wd_enabled)) {
+	if (__this_cpu_read(wd_enabled)) {
 		pcr_ops->write_pic(0, pcr_ops->nmi_picl_value(nmi_hz));
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_enable);
 	}
@@ -154,7 +154,7 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 void stop_nmi_watchdog(void *unused)
 {
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
-	__get_cpu_var(wd_enabled) = 0;
+	__this_cpu_write(wd_enabled, 0);
 	atomic_dec(&nmi_active);
 }
 
@@ -207,7 +207,7 @@ error:
 
 void start_nmi_watchdog(void *unused)
 {
-	__get_cpu_var(wd_enabled) = 1;
+	__this_cpu_write(wd_enabled, 1);
 	atomic_inc(&nmi_active);
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
@@ -218,7 +218,7 @@ void start_nmi_watchdog(void *unused)
 
 static void nmi_adjust_hz_one(void *unused)
 {
-	if (!__get_cpu_var(wd_enabled))
+	if (!__this_cpu_read(wd_enabled))
 		return;
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index d07f6b2..49d33b1 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -48,7 +48,7 @@ static int iommu_batch_initialized;
 /* Interrupts must be disabled.  */
 static inline void iommu_batch_start(struct device *dev, unsigned long prot, unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	p->dev		= dev;
 	p->prot		= prot;
@@ -94,7 +94,7 @@ static long iommu_batch_flush(struct iommu_batch *p)
 
 static inline void iommu_batch_new_entry(unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	if (p->entry + p->npages == entry)
 		return;
@@ -106,7 +106,7 @@ static inline void iommu_batch_new_entry(unsigned long entry)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_add(u64 phys_page)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
@@ -120,7 +120,7 @@ static inline long iommu_batch_add(u64 phys_page)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_end(void)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index c9759ad..46a5e45 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1013,7 +1013,7 @@ static void update_pcrs_for_enable(struct cpu_hw_events *cpuc)
 
 static void sparc_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (cpuc->enabled)
@@ -1031,7 +1031,7 @@ static void sparc_pmu_enable(struct pmu *pmu)
 
 static void sparc_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (!cpuc->enabled)
@@ -1065,7 +1065,7 @@ static int active_event_index(struct cpu_hw_events *cpuc,
 
 static void sparc_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (flags & PERF_EF_RELOAD) {
@@ -1080,7 +1080,7 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
 
 static void sparc_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -1096,7 +1096,7 @@ static void sparc_pmu_stop(struct perf_event *event, int flags)
 
 static void sparc_pmu_del(struct perf_event *event, int _flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 	int i;
 
@@ -1133,7 +1133,7 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 
 static void sparc_pmu_read(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -1145,7 +1145,7 @@ static DEFINE_MUTEX(pmc_grab_mutex);
 
 static void perf_stop_nmi_watchdog(void *unused)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	stop_nmi_watchdog(NULL);
@@ -1356,7 +1356,7 @@ static int collect_events(struct perf_event *group, int max_count,
 
 static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
@@ -1498,7 +1498,7 @@ static int sparc_pmu_event_init(struct perf_event *event)
  */
 static void sparc_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
@@ -1511,7 +1511,7 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
  */
 static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
@@ -1524,13 +1524,13 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu)
  */
 static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n;
 
 	if (!sparc_pmu)
 		return -EINVAL;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 	n = cpuc->n_events;
 	if (check_excludes(cpuc->event, 0, n))
 		return -EINVAL;
@@ -1601,7 +1601,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* If the PMU has the TOE IRQ enable bits, we need to do a
 	 * dummy write to the %pcr to clear the overflow bits and thus
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index d5c3195..9d98e50 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -204,7 +204,7 @@ static void __init smp4d_ipi_init(void)
 
 void sun4d_ipi_interrupt(void)
 {
-	struct sun4d_ipi_work *work = &__get_cpu_var(sun4d_ipi_work);
+	struct sun4d_ipi_work *work = this_cpu_ptr(&sun4d_ipi_work);
 
 	if (work->single) {
 		work->single = 0;
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 3fddf64..59da0c3 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -765,7 +765,7 @@ void setup_sparc64_timer(void)
 			     : /* no outputs */
 			     : "r" (pstate));
 
-	sevt = &__get_cpu_var(sparc64_events);
+	sevt = this_cpu_ptr(&sparc64_events);
 
 	memcpy(sevt, &sparc64_clockevent, sizeof(*sevt));
 	sevt->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b89aba2..9df2190c 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -52,14 +52,14 @@ out:
 
 void arch_enter_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	tb->active = 1;
 }
 
 void arch_leave_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	if (tb->tlb_nr)
 		flush_tlb_pending();
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index 71af574..60d62a2 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -140,12 +140,12 @@ extern unsigned int debug_smp_processor_id(void);
 
 /*
  * Read the set of maskable interrupts.
- * We avoid the preemption warning here via __this_cpu_ptr since even
+ * We avoid the preemption warning here via raw_cpu_ptr since even
  * if irqs are already enabled, it's harmless to read the wrong cpu's
  * enabled mask.
  */
 #define arch_local_irqs_enabled() \
-	(*__this_cpu_ptr(&interrupts_enabled_mask))
+	(*raw_cpu_ptr(&interrupts_enabled_mask))
 
 /* Re-enable all maskable interrupts. */
 #define arch_local_irq_enable() \
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index 4734215..f67753d 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -84,7 +84,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *t)
 	 * clear any pending DMA interrupts.
 	 */
 	if (current->thread.tile_dma_state.enabled)
-		install_page_table(mm->pgd, __get_cpu_var(current_asid));
+		install_page_table(mm->pgd, __this_cpu_read(current_asid));
 #endif
 }
 
@@ -96,12 +96,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		int cpu = smp_processor_id();
 
 		/* Pick new ASID. */
-		int asid = __get_cpu_var(current_asid) + 1;
+		int asid = __this_cpu_read(current_asid) + 1;
 		if (asid > max_asid) {
 			asid = min_asid;
 			local_flush_tlb();
 		}
-		__get_cpu_var(current_asid) = asid;
+		__this_cpu_write(current_asid, asid);
 
 		/* Clear cpu from the old mm, and set it in the new one. */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 637f2ff..ba85765 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -73,7 +73,7 @@ static DEFINE_PER_CPU(int, irq_depth);
  */
 void tile_dev_intr(struct pt_regs *regs, int intnum)
 {
-	int depth = __get_cpu_var(irq_depth)++;
+	int depth = __this_cpu_inc_return(irq_depth);
 	unsigned long original_irqs;
 	unsigned long remaining_irqs;
 	struct pt_regs *old_regs;
@@ -120,7 +120,7 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 
 		/* Count device irqs; Linux IPIs are counted elsewhere. */
 		if (irq != IRQ_RESCHEDULE)
-			__get_cpu_var(irq_stat).irq_dev_intr_count++;
+			__this_cpu_inc(irq_stat.irq_dev_intr_count);
 
 		generic_handle_irq(irq);
 	}
@@ -130,10 +130,10 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 	 * including any that were reenabled during interrupt
 	 * handling.
 	 */
-	if (depth == 0)
-		unmask_irqs(~__get_cpu_var(irq_disable_mask));
+	if (depth == 1)
+		unmask_irqs(~__this_cpu_read(irq_disable_mask));
 
-	__get_cpu_var(irq_depth)--;
+	__this_cpu_dec(irq_depth);
 
 	/*
 	 * Track time spent against the current process again and
@@ -151,7 +151,7 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 static void tile_irq_chip_enable(struct irq_data *d)
 {
 	get_cpu_var(irq_disable_mask) &= ~(1UL << d->irq);
-	if (__get_cpu_var(irq_depth) == 0)
+	if (__this_cpu_read(irq_depth) == 0)
 		unmask_irqs(1UL << d->irq);
 	put_cpu_var(irq_disable_mask);
 }
@@ -197,7 +197,7 @@ static void tile_irq_chip_ack(struct irq_data *d)
  */
 static void tile_irq_chip_eoi(struct irq_data *d)
 {
-	if (!(__get_cpu_var(irq_disable_mask) & (1UL << d->irq)))
+	if (!(__this_cpu_read(irq_disable_mask) & (1UL << d->irq)))
 		unmask_irqs(1UL << d->irq);
 }
 
diff --git a/arch/tile/kernel/messaging.c b/arch/tile/kernel/messaging.c
index 7867266..ac950be 100644
--- a/arch/tile/kernel/messaging.c
+++ b/arch/tile/kernel/messaging.c
@@ -28,7 +28,7 @@ static DEFINE_PER_CPU(HV_MsgState, msg_state);
 void init_messaging(void)
 {
 	/* Allocate storage for messages in kernel space */
-	HV_MsgState *state = &__get_cpu_var(msg_state);
+	HV_MsgState *state = this_cpu_ptr(&msg_state);
 	int rc = hv_register_message_state(state);
 	if (rc != HV_OK)
 		panic("hv_register_message_state: error %d", rc);
@@ -96,7 +96,7 @@ void hv_message_intr(struct pt_regs *regs, int intnum)
 			struct hv_driver_cb *cb =
 				(struct hv_driver_cb *)him->intarg;
 			cb->callback(cb, him->intdata);
-			__get_cpu_var(irq_stat).irq_hv_msg_count++;
+			__this_cpu_inc(irq_stat.irq_hv_msg_count);
 		}
 	}
 
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index 2bf6c9c..bb509ce 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -590,7 +590,7 @@ static int tile_event_set_period(struct perf_event *event)
  */
 static void tile_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -616,7 +616,7 @@ static void tile_pmu_stop(struct perf_event *event, int flags)
  */
 static void tile_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = event->hw.idx;
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -650,7 +650,7 @@ static void tile_pmu_start(struct perf_event *event, int flags)
  */
 static int tile_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc;
 	unsigned long mask;
 	int b, max_cnt;
@@ -706,7 +706,7 @@ static int tile_pmu_add(struct perf_event *event, int flags)
  */
 static void tile_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	/*
@@ -880,14 +880,14 @@ static struct pmu tilera_pmu = {
 int tile_pmu_handle_irq(struct pt_regs *regs, int fault)
 {
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	u64 val;
 	unsigned long status;
 	int bit;
 
-	__get_cpu_var(perf_irqs)++;
+	__this_cpu_inc(perf_irqs);
 
 	if (!atomic_read(&tile_active_events))
 		return 0;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 16ed589..0050cbc 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -64,7 +64,7 @@ early_param("idle", idle_setup);
 
 void arch_cpu_idle(void)
 {
-	__get_cpu_var(irq_stat).idle_timestamp = jiffies;
+	__this_cpu_write(irq_stat.idle_timestamp, jiffies);
 	_cpu_idle();
 }
 
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 112abab..b9736de 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1218,7 +1218,8 @@ static void __init validate_hv(void)
 	 * various asid variables to their appropriate initial states.
 	 */
 	asid_range = hv_inquire_asid(0);
-	__get_cpu_var(current_asid) = min_asid = asid_range.start;
+	min_asid = asid_range.start;
+	__this_cpu_write(current_asid, min_asid);
 	max_asid = asid_range.start + asid_range.size - 1;
 
 	if (hv_confstr(HV_CONFSTR_CHIP_MODEL, (HV_VirtAddr)chip_model,
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index de07fa7..6cb2ce3 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -740,7 +740,7 @@ static DEFINE_PER_CPU(unsigned long, ss_saved_pc);
 
 void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 {
-	unsigned long *ss_pc = &__get_cpu_var(ss_saved_pc);
+	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	struct thread_info *info = (void *)current_thread_info();
 	int is_single_step = test_ti_thread_flag(info, TIF_SINGLESTEP);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
@@ -766,7 +766,7 @@ void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 
 void single_step_once(struct pt_regs *regs)
 {
-	unsigned long *ss_pc = &__get_cpu_var(ss_saved_pc);
+	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
 
 	*ss_pc = regs->pc;
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index 19eaa62..d3c4ed7 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(flush_icache_range);
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	__get_cpu_var(irq_stat).irq_resched_count++;
+	__this_cpu_inc(irq_stat.irq_resched_count);
 	scheduler_ipi();
 
 	return IRQ_HANDLED;
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index 732e9d1..0d59a1b 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -41,7 +41,7 @@ void __init smp_prepare_boot_cpu(void)
 	int cpu = smp_processor_id();
 	set_cpu_online(cpu, 1);
 	set_cpu_present(cpu, 1);
-	__get_cpu_var(cpu_state) = CPU_ONLINE;
+	__this_cpu_write(cpu_state, CPU_ONLINE);
 
 	init_messaging();
 }
@@ -158,7 +158,7 @@ static void start_secondary(void)
 	/* printk(KERN_DEBUG "Initializing CPU#%d\n", cpuid); */
 
 	/* Initialize the current asid for our first page table. */
-	__get_cpu_var(current_asid) = min_asid;
+	__this_cpu_write(current_asid, min_asid);
 
 	/* Set up this thread as another owner of the init_mm */
 	atomic_inc(&init_mm.mm_count);
@@ -201,7 +201,7 @@ void online_secondary(void)
 	notify_cpu_starting(smp_processor_id());
 
 	set_cpu_online(smp_processor_id(), 1);
-	__get_cpu_var(cpu_state) = CPU_ONLINE;
+	__this_cpu_write(cpu_state, CPU_ONLINE);
 
 	/* Set up tile-specific state for this cpu. */
 	setup_cpu(0);
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index c1b3622..b854a1c 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -162,7 +162,7 @@ static DEFINE_PER_CPU(struct clock_event_device, tile_timer) = {
 
 void setup_tile_timer(void)
 {
-	struct clock_event_device *evt = &__get_cpu_var(tile_timer);
+	struct clock_event_device *evt = this_cpu_ptr(&tile_timer);
 
 	/* Fill in fields that are speed-specific. */
 	clockevents_calc_mult_shift(evt, cycles_per_sec, TILE_MINSEC);
@@ -182,7 +182,7 @@ void setup_tile_timer(void)
 void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct clock_event_device *evt = &__get_cpu_var(tile_timer);
+	struct clock_event_device *evt = this_cpu_ptr(&tile_timer);
 
 	/*
 	 * Mask the timer interrupt here, since we are a oneshot timer
@@ -194,7 +194,7 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 	irq_enter();
 
 	/* Track interrupt count. */
-	__get_cpu_var(irq_stat).irq_timer_count++;
+	__this_cpu_inc(irq_stat.irq_timer_count);
 
 	/* Call the generic timer handler */
 	evt->event_handler(evt);
@@ -235,7 +235,7 @@ cycles_t ns2cycles(unsigned long nsecs)
 	 * We do not have to disable preemption here as each core has the same
 	 * clock frequency.
 	 */
-	struct clock_event_device *dev = &__raw_get_cpu_var(tile_timer);
+	struct clock_event_device *dev = raw_cpu_ptr(&tile_timer);
 
 	/*
 	 * as in clocksource.h and x86's timer.h, we split the calculation
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 0dc2182..6aa2f26 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -103,7 +103,7 @@ static void kmap_atomic_register(struct page *page, int type,
 	spin_lock(&amp_lock);
 
 	/* With interrupts disabled, now fill in the per-cpu info. */
-	amp = &__get_cpu_var(amps).per_type[type];
+	amp = this_cpu_ptr(&amps.per_type[type]);
 	amp->page = page;
 	amp->cpu = smp_processor_id();
 	amp->va = va;
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index a092e39..caa2701 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -593,14 +593,14 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 	interrupt_mask_set_mask(-1ULL);
 	rc = flush_and_install_context(__pa(pgtables),
 				       init_pgprot((unsigned long)pgtables),
-				       __get_cpu_var(current_asid),
+				       __this_cpu_read(current_asid),
 				       cpumask_bits(my_cpu_mask));
 	interrupt_mask_restore_mask(irqmask);
 	BUG_ON(rc != 0);
 
 	/* Copy the page table back to the normal swapper_pg_dir. */
 	memcpy(pgd_base, pgtables, sizeof(pgtables));
-	__install_page_table(pgd_base, __get_cpu_var(current_asid),
+	__install_page_table(pgd_base, __this_cpu_read(current_asid),
 			     swapper_pgprot);
 
 	/*
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 4b528a9..61fd18b 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -97,11 +97,11 @@ extern void hw_breakpoint_restore(void);
 DECLARE_PER_CPU(int, debug_stack_usage);
 static inline void debug_stack_usage_inc(void)
 {
-	__get_cpu_var(debug_stack_usage)++;
+	__this_cpu_inc(debug_stack_usage);
 }
 static inline void debug_stack_usage_dec(void)
 {
-	__get_cpu_var(debug_stack_usage)--;
+	__this_cpu_dec(debug_stack_usage);
 }
 int is_debug_stack(unsigned long addr);
 void debug_stack_set_zero(void);
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 85e13cc..d725382 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu)
 {
 #ifdef CONFIG_SMP
 	if (smp_num_siblings == 2)
-		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+		return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index c63e925..a00ad8f 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -164,7 +164,7 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
@@ -601,16 +601,16 @@ struct uv_hub_nmi_s {
 
 struct uv_cpu_nmi_s {
 	struct uv_hub_nmi_s	*hub;
-	atomic_t		state;
-	atomic_t		pinging;
+	int			state;
+	int			pinging;
 	int			queries;
 	int			pings;
 };
 
-DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-#define uv_cpu_nmi			(__get_cpu_var(__uv_cpu_nmi))
+DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+
 #define uv_hub_nmi			(uv_cpu_nmi.hub)
-#define uv_cpu_nmi_per(cpu)		(per_cpu(__uv_cpu_nmi, cpu))
+#define uv_cpu_nmi_per(cpu)		(per_cpu(uv_cpu_nmi, cpu))
 #define uv_hub_nmi_per(cpu)		(uv_cpu_nmi_per(cpu).hub)
 
 /* uv_cpu_nmi_states */
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index af5b08a..5972b10 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -146,7 +146,7 @@ static inline int is_apbt_capable(void)
 static int __init apbt_clockevent_register(void)
 {
 	struct sfi_timer_table_entry *mtmr;
-	struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev);
+	struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev);
 
 	mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
 	if (mtmr == NULL) {
@@ -200,7 +200,7 @@ void apbt_setup_secondary_clock(void)
 	if (!cpu)
 		return;
 
-	adev = &__get_cpu_var(cpu_apbt_dev);
+	adev = this_cpu_ptr(&cpu_apbt_dev);
 	if (!adev->timer) {
 		adev->timer = dw_apb_clockevent_init(cpu, adev->name,
 			APBT_CLOCKEVENT_RATING, adev_virt_addr(adev),
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6776027..00853b2 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -561,7 +561,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
  */
 static void setup_APIC_timer(void)
 {
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
 
 	if (this_cpu_has(X86_FEATURE_ARAT)) {
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
@@ -696,7 +696,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 static int __init calibrate_APIC_clock(void)
 {
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
 	void (*real_handler)(struct clock_event_device *dev);
 	unsigned long deltaj;
 	long delta, deltatsc;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 6ce600f..e658f21 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -42,7 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	 * We are to modify mask, so we need an own copy
 	 * and be sure it's manipulated with irq off.
 	 */
-	ipi_mask_ptr = __raw_get_cpu_var(ipi_mask);
+	ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
 	cpumask_copy(ipi_mask_ptr, mask);
 
 	/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3eff36f..4b4f78c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1200,9 +1200,9 @@ DEFINE_PER_CPU(int, debug_stack_usage);
 
 int is_debug_stack(unsigned long addr)
 {
-	return __get_cpu_var(debug_stack_usage) ||
-		(addr <= __get_cpu_var(debug_stack_addr) &&
-		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
+	return __this_cpu_read(debug_stack_usage) ||
+		(addr <= __this_cpu_read(debug_stack_addr) &&
+		 addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
 }
 NOKPROBE_SYMBOL(is_debug_stack);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 5ac2d1f..4cfba43 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -83,7 +83,7 @@ static DEFINE_MUTEX(mce_inject_mutex);
 static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 {
 	int cpu = smp_processor_id();
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 	if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
 		return NMI_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
@@ -97,7 +97,7 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 static void mce_irq_ipi(void *info)
 {
 	int cpu = smp_processor_id();
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 
 	if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
 			m->inject_flags & MCJ_EXCEPTION) {
@@ -109,7 +109,7 @@ static void mce_irq_ipi(void *info)
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 	int context = MCJ_CTX(m->inject_flags);
 	int ret = 0;
 	int cpu = m->extcpu;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bd9ccda..61a9668ce 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -400,7 +400,7 @@ static u64 mce_rdmsrl(u32 msr)
 
 		if (offset < 0)
 			return 0;
-		return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
+		return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
 	}
 
 	if (rdmsrl_safe(msr, &v)) {
@@ -422,7 +422,7 @@ static void mce_wrmsrl(u32 msr, u64 v)
 		int offset = msr_to_offset(msr);
 
 		if (offset >= 0)
-			*(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
+			*(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
 		return;
 	}
 	wrmsrl(msr, v);
@@ -478,7 +478,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring);
 /* Runs with CPU affinity in workqueue */
 static int mce_ring_empty(void)
 {
-	struct mce_ring *r = &__get_cpu_var(mce_ring);
+	struct mce_ring *r = this_cpu_ptr(&mce_ring);
 
 	return r->start == r->end;
 }
@@ -490,7 +490,7 @@ static int mce_ring_get(unsigned long *pfn)
 
 	*pfn = 0;
 	get_cpu();
-	r = &__get_cpu_var(mce_ring);
+	r = this_cpu_ptr(&mce_ring);
 	if (r->start == r->end)
 		goto out;
 	*pfn = r->ring[r->start];
@@ -504,7 +504,7 @@ out:
 /* Always runs in MCE context with preempt off */
 static int mce_ring_add(unsigned long pfn)
 {
-	struct mce_ring *r = &__get_cpu_var(mce_ring);
+	struct mce_ring *r = this_cpu_ptr(&mce_ring);
 	unsigned next;
 
 	next = (r->end + 1) % MCE_RING_SIZE;
@@ -526,7 +526,7 @@ int mce_available(struct cpuinfo_x86 *c)
 static void mce_schedule_work(void)
 {
 	if (!mce_ring_empty())
-		schedule_work(&__get_cpu_var(mce_work));
+		schedule_work(this_cpu_ptr(&mce_work));
 }
 
 DEFINE_PER_CPU(struct irq_work, mce_irq_work);
@@ -551,7 +551,7 @@ static void mce_report_event(struct pt_regs *regs)
 		return;
 	}
 
-	irq_work_queue(&__get_cpu_var(mce_irq_work));
+	irq_work_queue(this_cpu_ptr(&mce_irq_work));
 }
 
 /*
@@ -1045,7 +1045,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	mce_gather_info(&m, regs);
 
-	final = &__get_cpu_var(mces_seen);
+	final = this_cpu_ptr(&mces_seen);
 	*final = m;
 
 	memset(valid_banks, 0, sizeof(valid_banks));
@@ -1278,22 +1278,22 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) =
 
 static int cmc_error_seen(void)
 {
-	unsigned long *v = &__get_cpu_var(mce_polled_error);
+	unsigned long *v = this_cpu_ptr(&mce_polled_error);
 
 	return test_and_clear_bit(0, v);
 }
 
 static void mce_timer_fn(unsigned long data)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv;
 	int notify;
 
 	WARN_ON(smp_processor_id() != data);
 
-	if (mce_available(__this_cpu_ptr(&cpu_info))) {
+	if (mce_available(this_cpu_ptr(&cpu_info))) {
 		machine_check_poll(MCP_TIMESTAMP,
-				&__get_cpu_var(mce_poll_banks));
+				this_cpu_ptr(&mce_poll_banks));
 		mce_intel_cmci_poll();
 	}
 
@@ -1323,7 +1323,7 @@ static void mce_timer_fn(unsigned long data)
  */
 void mce_timer_kick(unsigned long interval)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long when = jiffies + interval;
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
@@ -1659,7 +1659,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 
 static void __mcheck_cpu_init_timer(void)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned int cpu = smp_processor_id();
 
 	setup_timer(t, mce_timer_fn, cpu);
@@ -1702,8 +1702,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_timer();
-	INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
-	init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb);
+	INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
+	init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
 }
 
 /*
@@ -1955,7 +1955,7 @@ static struct miscdevice mce_chrdev_device = {
 static void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
-	__clear_bit(bank, __get_cpu_var(mce_poll_banks));
+	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
 	cmci_disable_bank(bank);
 }
 
@@ -2065,7 +2065,7 @@ static void mce_syscore_shutdown(void)
 static void mce_syscore_resume(void)
 {
 	__mcheck_cpu_init_generic();
-	__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
+	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
 }
 
 static struct syscore_ops mce_syscore_ops = {
@@ -2080,7 +2080,7 @@ static struct syscore_ops mce_syscore_ops = {
 
 static void mce_cpu_restart(void *data)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_timer();
@@ -2096,14 +2096,14 @@ static void mce_restart(void)
 /* Toggle features for corrected errors */
 static void mce_disable_cmci(void *data)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	cmci_clear();
 }
 
 static void mce_enable_ce(void *all)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	cmci_reenable();
 	cmci_recheck();
@@ -2336,7 +2336,7 @@ static void mce_disable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
@@ -2354,7 +2354,7 @@ static void mce_reenable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1e49f8f..5d4999f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -310,7 +310,7 @@ static void amd_threshold_interrupt(void)
 			 * event.
 			 */
 			machine_check_poll(MCP_TIMESTAMP,
-					&__get_cpu_var(mce_poll_banks));
+					this_cpu_ptr(&mce_poll_banks));
 
 			if (high & MASK_OVERFLOW_HI) {
 				rdmsrl(address, m.misc);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 3bdb95a..b3c97ba 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -86,7 +86,7 @@ void mce_intel_cmci_poll(void)
 {
 	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
 		return;
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 }
 
 void mce_intel_hcpu_update(unsigned long cpu)
@@ -145,7 +145,7 @@ static void cmci_storm_disable_banks(void)
 	u64 val;
 
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = __get_cpu_var(mce_banks_owned);
+	owned = this_cpu_ptr(mce_banks_owned);
 	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
 		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 		val &= ~MCI_CTL2_CMCI_EN;
@@ -195,7 +195,7 @@ static void intel_threshold_interrupt(void)
 {
 	if (cmci_storm_detect())
 		return;
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 	mce_notify_irq();
 }
 
@@ -206,7 +206,7 @@ static void intel_threshold_interrupt(void)
  */
 static void cmci_discover(int banks)
 {
-	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+	unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
 	unsigned long flags;
 	int i;
 	int bios_wrong_thresh = 0;
@@ -228,7 +228,7 @@ static void cmci_discover(int banks)
 		/* Already owned by someone else? */
 		if (val & MCI_CTL2_CMCI_EN) {
 			clear_bit(i, owned);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
 			continue;
 		}
 
@@ -252,7 +252,7 @@ static void cmci_discover(int banks)
 		/* Did the enable bit stick? -- the bank supports CMCI */
 		if (val & MCI_CTL2_CMCI_EN) {
 			set_bit(i, owned);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
 			/*
 			 * We are able to set thresholds for some banks that
 			 * had a threshold of 0. This means the BIOS has not
@@ -263,7 +263,7 @@ static void cmci_discover(int banks)
 					(val & MCI_CTL2_CMCI_THRESHOLD_MASK))
 				bios_wrong_thresh = 1;
 		} else {
-			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
+			WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
 		}
 	}
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
@@ -284,10 +284,10 @@ void cmci_recheck(void)
 	unsigned long flags;
 	int banks;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
 		return;
 	local_irq_save(flags);
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 	local_irq_restore(flags);
 }
 
@@ -296,12 +296,12 @@ static void __cmci_disable_bank(int bank)
 {
 	u64 val;
 
-	if (!test_bit(bank, __get_cpu_var(mce_banks_owned)))
+	if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
 		return;
 	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_EN;
 	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	__clear_bit(bank, __get_cpu_var(mce_banks_owned));
+	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 16c7302..1b8299d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -494,7 +494,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
 
 void x86_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -512,7 +512,7 @@ void x86_pmu_disable_all(void)
 
 static void x86_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu_initialized())
 		return;
@@ -529,7 +529,7 @@ static void x86_pmu_disable(struct pmu *pmu)
 
 void x86_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -876,7 +876,7 @@ static void x86_pmu_start(struct perf_event *event, int flags);
 
 static void x86_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	int i, added = cpuc->n_added;
@@ -1030,7 +1030,7 @@ void x86_pmu_enable_event(struct perf_event *event)
  */
 static int x86_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc;
 	int assign[X86_PMC_IDX_MAX];
 	int n, n0, ret;
@@ -1081,7 +1081,7 @@ out:
 
 static void x86_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = event->hw.idx;
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -1160,7 +1160,7 @@ void perf_event_print_debug(void)
 
 void x86_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
@@ -1182,7 +1182,7 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 
 static void x86_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	/*
@@ -1237,7 +1237,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * Some chipsets need to unmask the LVTPC in a particular spot
@@ -1646,7 +1646,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
  */
 static int x86_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];
 	int n, ret;
 
@@ -2005,7 +2005,7 @@ static unsigned long get_segment_base(unsigned int segment)
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+		desc = raw_cpu_ptr(gdt_page.gdt);
 	}
 
 	return get_desc_base(desc + idx);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index beeb7cc..2892631 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -699,7 +699,7 @@ __init int amd_pmu_init(void)
 
 void amd_pmu_enable_virt(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	cpuc->perf_ctr_virt_mask = 0;
 
@@ -711,7 +711,7 @@ EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
 
 void amd_pmu_disable_virt(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * We only mask out the Host-only bit so that host-only counting works
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3851def..a73947c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1174,7 +1174,7 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
 
 static void intel_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
@@ -1187,7 +1187,7 @@ static void intel_pmu_disable_all(void)
 
 static void intel_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	intel_pmu_pebs_enable_all();
 	intel_pmu_lbr_enable_all();
@@ -1221,7 +1221,7 @@ static void intel_pmu_enable_all(int added)
  */
 static void intel_pmu_nhm_workaround(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	static const unsigned long nhm_magic[4] = {
 		0x4300B5,
 		0x4300D2,
@@ -1320,7 +1320,7 @@ static inline bool event_is_checkpointed(struct perf_event *event)
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
@@ -1384,7 +1384,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
 		if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -1478,7 +1478,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	u64 status;
 	int handled;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * No known reason to not always do late ACK,
@@ -1910,7 +1910,7 @@ EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
 
 static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
@@ -1931,7 +1931,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 
 static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 	int idx;
 
@@ -1965,7 +1965,7 @@ static void core_pmu_enable_event(struct perf_event *event)
 
 static void core_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index b1553d0..46211bc 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -474,7 +474,7 @@ void intel_pmu_enable_bts(u64 config)
 
 void intel_pmu_disable_bts(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long debugctlmsr;
 
 	if (!cpuc->ds)
@@ -491,7 +491,7 @@ void intel_pmu_disable_bts(void)
 
 int intel_pmu_drain_bts_buffer(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct bts_record {
 		u64	from;
@@ -669,7 +669,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
@@ -684,7 +684,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -702,7 +702,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 void intel_pmu_pebs_enable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -710,7 +710,7 @@ void intel_pmu_pebs_enable_all(void)
 
 void intel_pmu_pebs_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
@@ -718,7 +718,7 @@ void intel_pmu_pebs_disable_all(void)
 
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
@@ -829,7 +829,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * We cast to the biggest pebs_record but are careful not to
 	 * unconditionally access the 'extra' entries.
 	 */
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
@@ -916,7 +916,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event = cpuc->events[0]; /* PMC0 only */
 	struct pebs_record_core *at, *top;
@@ -957,7 +957,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event = NULL;
 	void *at, *top;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 4af1061..45fa730 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -133,7 +133,7 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
@@ -183,7 +183,7 @@ void intel_pmu_lbr_reset(void)
 
 void intel_pmu_lbr_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -203,7 +203,7 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 
 void intel_pmu_lbr_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -220,7 +220,7 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 
 void intel_pmu_lbr_enable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_users)
 		__intel_pmu_lbr_enable();
@@ -228,7 +228,7 @@ void intel_pmu_lbr_enable_all(void)
 
 void intel_pmu_lbr_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_users)
 		__intel_pmu_lbr_disable();
@@ -332,7 +332,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 void intel_pmu_lbr_read(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuc->lbr_users)
 		return;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 619f769..d64f275 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -187,7 +187,7 @@ static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
 
 static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct perf_event *event;
 	unsigned long flags;
 
@@ -234,7 +234,7 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	unsigned long flags;
 
 	spin_lock_irqsave(&pmu->lock, flags);
@@ -244,7 +244,7 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
@@ -278,7 +278,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
@@ -696,7 +696,7 @@ static int __init rapl_pmu_init(void)
 		return -1;
 	}
 
-	pmu = __get_cpu_var(rapl_pmu);
+	pmu = __this_cpu_read(rapl_pmu);
 
 	pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
 		" API unit is 2^-32 Joules,"
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 838fa87..5b0c232 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -217,7 +217,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs)
 	int bit, loops;
 	u64 status;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	knc_pmu_disable_all();
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 5d466b7..f2e5678 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -915,7 +915,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 
 static void p4_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -984,7 +984,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
 
 static void p4_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -1004,7 +1004,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		int overflow;
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 5f9cf20..3d5fb50 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -108,7 +108,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	int i;
 
 	for (i = 0; i < HBP_NUM; i++) {
-		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
 		if (!*slot) {
 			*slot = bp;
@@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	set_debugreg(info->address, i);
 	__this_cpu_write(cpu_debugreg[i], info->address);
 
-	dr7 = &__get_cpu_var(cpu_dr7);
+	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 |= encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
@@ -146,7 +146,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	int i;
 
 	for (i = 0; i < HBP_NUM; i++) {
-		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
 		if (*slot == bp) {
 			*slot = NULL;
@@ -157,7 +157,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
 		return;
 
-	dr7 = &__get_cpu_var(cpu_dr7);
+	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 &= ~__encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 4d1c746..e4b503d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -52,13 +52,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	    regs->sp <= curbase + THREAD_SIZE)
 		return;
 
-	irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+	irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
 			STACK_TOP_MARGIN;
-	irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+	irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
 	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
 		return;
 
-	oist = &__get_cpu_var(orig_ist);
+	oist = this_cpu_ptr(&orig_ist);
 	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
 	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
 	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 95c3cb1..f6945bef 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -244,9 +244,9 @@ u32 kvm_read_and_reset_pf_reason(void)
 {
 	u32 reason = 0;
 
-	if (__get_cpu_var(apf_reason).enabled) {
-		reason = __get_cpu_var(apf_reason).reason;
-		__get_cpu_var(apf_reason).reason = 0;
+	if (__this_cpu_read(apf_reason.enabled)) {
+		reason = __this_cpu_read(apf_reason.reason);
+		__this_cpu_write(apf_reason.reason, 0);
 	}
 
 	return reason;
@@ -319,7 +319,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 	 * there's no need for lock or memory barriers.
 	 * An optimization barrier is implied in apic write.
 	 */
-	if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi)))
+	if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
 		return;
 	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
@@ -330,13 +330,13 @@ void kvm_guest_cpu_init(void)
 		return;
 
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
-		u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason));
+		u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
 
 #ifdef CONFIG_PREEMPT
 		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
 #endif
 		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
-		__get_cpu_var(apf_reason).enabled = 1;
+		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
 	}
@@ -345,8 +345,8 @@ void kvm_guest_cpu_init(void)
 		unsigned long pa;
 		/* Size alignment is implied but just to make it explicit. */
 		BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
-		__get_cpu_var(kvm_apic_eoi) = 0;
-		pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi))
+		__this_cpu_write(kvm_apic_eoi, 0);
+		pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
 			| KVM_MSR_ENABLED;
 		wrmsrl(MSR_KVM_PV_EOI_EN, pa);
 	}
@@ -357,11 +357,11 @@ void kvm_guest_cpu_init(void)
 
 static void kvm_pv_disable_apf(void)
 {
-	if (!__get_cpu_var(apf_reason).enabled)
+	if (!__this_cpu_read(apf_reason.enabled))
 		return;
 
 	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
-	__get_cpu_var(apf_reason).enabled = 0;
+	__this_cpu_write(apf_reason.enabled, 0);
 
 	printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
 	       smp_processor_id());
@@ -724,7 +724,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	if (in_nmi())
 		return;
 
-	w = &__get_cpu_var(klock_waiting);
+	w = this_cpu_ptr(&klock_waiting);
 	cpu = smp_processor_id();
 	start = spin_time_start();
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f7f6a4a..65510f6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -670,7 +670,7 @@ static int svm_hardware_enable(void)
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
-		__get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT;
+		__this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT);
 	}
 
 
@@ -1313,8 +1313,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR) &&
-	    svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) {
-		__get_cpu_var(current_tsc_ratio) = svm->tsc_ratio;
+	    svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
+		__this_cpu_write(current_tsc_ratio, svm->tsc_ratio);
 		wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio);
 	}
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 04fa1b8..d9dcfa2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1626,7 +1626,7 @@ static void reload_tss(void)
 	/*
 	 * VT restores TR but not its size.  Useless.
 	 */
-	struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *descs;
 
 	descs = (void *)gdt->address;
@@ -1672,7 +1672,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 
 static unsigned long segment_base(u16 selector)
 {
-	struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *d;
 	unsigned long table_base;
 	unsigned long v;
@@ -1802,7 +1802,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	 */
 	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
 		stts();
-	load_gdt(&__get_cpu_var(host_gdt));
+	load_gdt(this_cpu_ptr(&host_gdt));
 }
 
 static void vmx_load_host_state(struct vcpu_vmx *vmx)
@@ -1832,7 +1832,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	if (vmx->loaded_vmcs->cpu != cpu) {
-		struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+		struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 		unsigned long sysenter_esp;
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
@@ -2771,7 +2771,7 @@ static int hardware_enable(void)
 		ept_sync_global();
 	}
 
-	native_store_gdt(&__get_cpu_var(host_gdt));
+	native_store_gdt(this_cpu_ptr(&host_gdt));
 
 	return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5430e4b..34c8f94 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1559,7 +1559,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
 	if (unlikely(this_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index dd89a13..b4f2e7e 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -140,7 +140,7 @@ static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context);
 
 bool kmemcheck_active(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	return data->balance > 0;
 }
@@ -148,7 +148,7 @@ bool kmemcheck_active(struct pt_regs *regs)
 /* Save an address that needs to be shown/hidden */
 static void kmemcheck_save_addr(unsigned long addr)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr));
 	data->addr[data->n_addrs++] = addr;
@@ -156,7 +156,7 @@ static void kmemcheck_save_addr(unsigned long addr)
 
 static unsigned int kmemcheck_show_all(void)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	unsigned int i;
 	unsigned int n;
 
@@ -169,7 +169,7 @@ static unsigned int kmemcheck_show_all(void)
 
 static unsigned int kmemcheck_hide_all(void)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	unsigned int i;
 	unsigned int n;
 
@@ -185,7 +185,7 @@ static unsigned int kmemcheck_hide_all(void)
  */
 void kmemcheck_show(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	BUG_ON(!irqs_disabled());
 
@@ -226,7 +226,7 @@ void kmemcheck_show(struct pt_regs *regs)
  */
 void kmemcheck_hide(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	int n;
 
 	BUG_ON(!irqs_disabled());
@@ -528,7 +528,7 @@ static void kmemcheck_access(struct pt_regs *regs,
 	const uint8_t *insn_primary;
 	unsigned int size;
 
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	/* Recursive fault -- ouch. */
 	if (data->busy) {
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 379e8bd..1d2e639 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -64,11 +64,11 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
 {
 	if (ctr_running)
-		model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+		model->check_ctrs(regs, this_cpu_ptr(&cpu_msrs));
 	else if (!nmi_enabled)
 		return NMI_DONE;
 	else
-		model->stop(&__get_cpu_var(cpu_msrs));
+		model->stop(this_cpu_ptr(&cpu_msrs));
 	return NMI_HANDLED;
 }
 
@@ -91,7 +91,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs)
 
 static void nmi_cpu_start(void *dummy)
 {
-	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+	struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
 	if (!msrs->controls)
 		WARN_ON_ONCE(1);
 	else
@@ -111,7 +111,7 @@ static int nmi_start(void)
 
 static void nmi_cpu_stop(void *dummy)
 {
-	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+	struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
 	if (!msrs->controls)
 		WARN_ON_ONCE(1);
 	else
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 98ab130..ad1d91f 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -372,7 +372,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+	return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c89c933..c6b146e 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -63,8 +63,8 @@
 
 static struct uv_hub_nmi_s **uv_hub_nmi_list;
 
-DEFINE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_nmi);
+DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi);
 
 static unsigned long nmi_mmr;
 static unsigned long nmi_mmr_clear;
@@ -215,7 +215,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
 	int nmi = 0;
 
 	local64_inc(&uv_nmi_count);
-	uv_cpu_nmi.queries++;
+	this_cpu_inc(uv_cpu_nmi.queries);
 
 	do {
 		nmi = atomic_read(&hub_nmi->in_nmi);
@@ -293,7 +293,7 @@ static void uv_nmi_nr_cpus_ping(void)
 	int cpu;
 
 	for_each_cpu(cpu, uv_nmi_cpu_mask)
-		atomic_set(&uv_cpu_nmi_per(cpu).pinging, 1);
+		uv_cpu_nmi_per(cpu).pinging = 1;
 
 	apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI);
 }
@@ -304,8 +304,8 @@ static void uv_nmi_cleanup_mask(void)
 	int cpu;
 
 	for_each_cpu(cpu, uv_nmi_cpu_mask) {
-		atomic_set(&uv_cpu_nmi_per(cpu).pinging, 0);
-		atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_OUT);
+		uv_cpu_nmi_per(cpu).pinging =  0;
+		uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_OUT;
 		cpumask_clear_cpu(cpu, uv_nmi_cpu_mask);
 	}
 }
@@ -328,7 +328,7 @@ static int uv_nmi_wait_cpus(int first)
 		int loop_delay = uv_nmi_loop_delay;
 
 		for_each_cpu(j, uv_nmi_cpu_mask) {
-			if (atomic_read(&uv_cpu_nmi_per(j).state)) {
+			if (uv_cpu_nmi_per(j).state) {
 				cpumask_clear_cpu(j, uv_nmi_cpu_mask);
 				if (++k >= n)
 					break;
@@ -359,7 +359,7 @@ static int uv_nmi_wait_cpus(int first)
 static void uv_nmi_wait(int master)
 {
 	/* indicate this cpu is in */
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_IN);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN);
 
 	/* if not the first cpu in (the master), then we are a slave cpu */
 	if (!master)
@@ -419,7 +419,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
 			"UV:%sNMI process trace for CPU %d\n", dots, cpu);
 		show_regs(regs);
 	}
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
 }
 
 /* Trigger a slave cpu to dump it's state */
@@ -427,20 +427,20 @@ static void uv_nmi_trigger_dump(int cpu)
 {
 	int retry = uv_nmi_trigger_delay;
 
-	if (atomic_read(&uv_cpu_nmi_per(cpu).state) != UV_NMI_STATE_IN)
+	if (uv_cpu_nmi_per(cpu).state != UV_NMI_STATE_IN)
 		return;
 
-	atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP);
+	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP;
 	do {
 		cpu_relax();
 		udelay(10);
-		if (atomic_read(&uv_cpu_nmi_per(cpu).state)
+		if (uv_cpu_nmi_per(cpu).state
 				!= UV_NMI_STATE_DUMP)
 			return;
 	} while (--retry > 0);
 
 	pr_crit("UV: CPU %d stuck in process dump function\n", cpu);
-	atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP_DONE);
+	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE;
 }
 
 /* Wait until all cpus ready to exit */
@@ -488,7 +488,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
 	} else {
 		while (!atomic_read(&uv_nmi_slave_continue))
 			cpu_relax();
-		while (atomic_read(&uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
+		while (this_cpu_read(uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
 			cpu_relax();
 		uv_nmi_dump_state_cpu(cpu, regs);
 	}
@@ -615,7 +615,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 	local_irq_save(flags);
 
 	/* If not a UV System NMI, ignore */
-	if (!atomic_read(&uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
+	if (!this_cpu_read(uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
 		local_irq_restore(flags);
 		return NMI_DONE;
 	}
@@ -639,7 +639,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 		uv_call_kgdb_kdb(cpu, regs, master);
 
 	/* Clear per_cpu "in nmi" flag */
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_OUT);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT);
 
 	/* Clear MMR NMI flag on each hub */
 	uv_clear_nmi(cpu);
@@ -666,16 +666,16 @@ static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs)
 {
 	int ret;
 
-	uv_cpu_nmi.queries++;
-	if (!atomic_read(&uv_cpu_nmi.pinging)) {
+	this_cpu_inc(uv_cpu_nmi.queries);
+	if (!this_cpu_read(uv_cpu_nmi.pinging)) {
 		local64_inc(&uv_nmi_ping_misses);
 		return NMI_DONE;
 	}
 
-	uv_cpu_nmi.pings++;
+	this_cpu_inc(uv_cpu_nmi.pings);
 	local64_inc(&uv_nmi_ping_count);
 	ret = uv_handle_nmi(reason, regs);
-	atomic_set(&uv_cpu_nmi.pinging, 0);
+	this_cpu_write(uv_cpu_nmi.pinging, 0);
 	return ret;
 }
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 5c86786..a244237 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -365,7 +365,7 @@ __setup("uvrtcevt", uv_enable_evt_rtc);
 
 static __init void uv_rtc_register_clockevents(struct work_struct *dummy)
 {
-	struct clock_event_device *ced = &__get_cpu_var(cpu_ced);
+	struct clock_event_device *ced = this_cpu_ptr(&cpu_ced);
 
 	*ced = clock_event_device_uv;
 	ced->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index acb0eff..1a3f044 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -821,7 +821,7 @@ static void xen_convert_trap_info(const struct desc_ptr *desc,
 
 void xen_copy_trap_info(struct trap_info *traps)
 {
-	const struct desc_ptr *desc = &__get_cpu_var(idt_desc);
+	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
 
 	xen_convert_trap_info(desc, traps);
 }
@@ -838,7 +838,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
 
 	spin_lock(&lock);
 
-	__get_cpu_var(idt_desc) = *desc;
+	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
 
 	xen_convert_trap_info(desc, traps);
 
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 0d82003..ea54a08 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,7 +54,7 @@ DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 void xen_mc_flush(void)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_entry *mc;
 	int ret = 0;
 	unsigned long flags;
@@ -131,7 +131,7 @@ void xen_mc_flush(void)
 
 struct multicall_space __xen_mc_entry(size_t args)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_space ret;
 	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
@@ -162,7 +162,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 
 struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_space ret = { NULL, NULL };
 
 	BUG_ON(preemptible());
@@ -192,7 +192,7 @@ out:
 
 void xen_mc_callback(void (*fn)(void *), void *data)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct callback *cb;
 
 	if (b->cbidx == MC_BATCH) {
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 0ba5f3b..23b45eb 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -109,7 +109,7 @@ static bool xen_pvspin = true;
 __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
 	int irq = __this_cpu_read(lock_kicker_irq);
-	struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+	struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
 	int cpu = smp_processor_id();
 	u64 start;
 	unsigned long flags;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5718b0b..a1d430b 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -80,7 +80,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
 	BUG_ON(preemptible());
 
-	state = &__get_cpu_var(xen_runstate);
+	state = this_cpu_ptr(&xen_runstate);
 
 	/*
 	 * The runstate info is always updated by the hypervisor on
@@ -123,7 +123,7 @@ static void do_stolen_accounting(void)
 
 	WARN_ON(state.state != RUNSTATE_running);
 
-	snap = &__get_cpu_var(xen_runstate_snapshot);
+	snap = this_cpu_ptr(&xen_runstate_snapshot);
 
 	/* work out how much time the VCPU has not been runn*ing*  */
 	runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
@@ -158,7 +158,7 @@ cycle_t xen_clocksource_read(void)
 	cycle_t ret;
 
 	preempt_disable_notrace();
-	src = &__get_cpu_var(xen_vcpu)->time;
+	src = this_cpu_ptr(&xen_vcpu->time);
 	ret = pvclock_clocksource_read(src);
 	preempt_enable_notrace();
 	return ret;
@@ -397,7 +397,7 @@ static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.
 
 static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = &__get_cpu_var(xen_clock_events).evt;
+	struct clock_event_device *evt = this_cpu_ptr(&xen_clock_events.evt);
 	irqreturn_t ret;
 
 	ret = IRQ_NONE;
@@ -460,7 +460,7 @@ void xen_setup_cpu_clockevents(void)
 {
 	BUG_ON(preemptible());
 
-	clockevents_register_device(&__get_cpu_var(xen_clock_events).evt);
+	clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt));
 }
 
 void xen_timer_resume(void)