149 files changed, 560 insertions, 547 deletions

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index c52e7f0ee5f6..5c218aa3f3df 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 ee39cee8064c..643a9dcdf093 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 dfc32130bc44..93090213c71c 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 f820e9f25520..a94ece4a72c8 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 17b5e92e3bc6..fe1160fbff91 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 ea2032013cc2..1e9c8b0bf486 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 694619365265..dd2af74aff80 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 ba6c30d8534d..8ad3e90cc8fc 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 029bab36cd91..668786e84af8 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 7caa1f44cd95..31eb784866f8 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 ee118b901de4..7c8b4710f071 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 d38c7ea5eea5..e8f3585e7e7a 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 53e9dfacd073..2a88c7204e52 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 f2c418281130..812a1e6b3179 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 03ea78ed64a9..698d8fefde6c 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 074fde49c9e6..c7c51445c3be 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 db7b36bb068b..8bfd36af46f8 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 deed6fa96bb0..b51514957620 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 d3636e67a98e..6f7d4a4dcf24 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 36182c84363c..5f6b6b48c1d5 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 68c845411624..f9c8d9fc5939 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 02c08737f6aa..2478ec6d23c9 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 1b82ac6921e0..741734049675 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 0195745b4b1b..3ee347713307 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 1f8187ab0997..212f46f2014e 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 b63f2482f288..a8f9cdc6f8b0 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 df9e2bd9b2c2..06bb5ed6d80a 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 74e827b4ec8f..d8c63af6c7cc 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 6c840ceab820..e2452550bcb1 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 e787cc1bff8f..b0d5f0a97a01 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 fa91e0097458..933355e0d091 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 c846aee7372f..7559f1beab29 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 27ae5433fe4d..014d4729b134 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 db96b418160a..dd1c24ceda50 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 d3194de7ae1e..56fdad479115 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 ea0c7b2ef030..08e761318c17 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 edefead3b43a..dbdd33ee0102 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 69e980de0f62..005d665fe4a5 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 e53c6f268807..ff9b4eb34589 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 0300d94c25b3..05f366379f53 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 0e594076912c..a6e424d185d0 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 98d712843413..cd83be527586 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 018ef11f57df..ea2bad306f93 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 5b1151dcba13..a9973bb4a1b2 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 d07f6b29aed8..49d33b178793 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 c9759ad3f34a..46a5e4508752 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 d5c319553fd0..9d98e5002a09 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 3fddf64c7fc6..59da0c3ea788 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 b89aba217e3b..9df2190c097e 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 71af5747874d..60d62a292fce 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 4734215e2ad4..f67753db1f78 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 637f2ffaa5f5..ba85765e1436 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 7867266f9716..ac950be1318e 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 2bf6c9c135c1..bb509cee3b59 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 16ed58948757..0050cbc1d9de 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 112ababa9e55..b9736ded06f2 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 de07fa7d1315..6cb2ce31b5a2 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 19eaa62d456a..d3c4ed780ce2 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 732e9d138661..0d59a1b60c74 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 c1b362277fb7..b854a1cd0079 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 0dc218294770..6aa2f2625447 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 a092e393bd20..caa270165f86 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 4b528a970bd4..61fd18b83b6c 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 85e13ccf15c4..d725382c2ae0 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 c63e925fd6b7..a00ad8f2a657 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 af5b08ab3b71..5972b108f15a 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 67760275544b..00853b254ab0 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 6ce600f9bc78..e658f21681c8 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 3eff36f719fb..4b4f78c9ba19 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 5ac2d1fb28bc..4cfba4371a71 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 bd9ccda8087f..61a9668cebfd 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 1e49f8f41276..5d4999f95aec 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 3bdb95ae8c43..b3c97bafc123 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 16c73022306e..1b8299dd3d91 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 beeb7cc07044..28926311aac1 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 3851def5057c..a73947c53b65 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 b1553d05a5cb..46211bcc813e 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 4af10617de33..45fa730a5283 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 619f7699487a..d64f275fe274 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 838fa8772c62..5b0c232d1ee6 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 5d466b7d8609..f2e56783af3d 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 5f9cf20cdb68..3d5fb509bdeb 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 4d1c746892eb..e4b503d5558c 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 95c3cb16af3e..f6945bef2cd1 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 f7f6a4a157a6..65510f624dfe 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 04fa1b8298c8..d9dcfa27aa84 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 5430e4b0af29..34c8f94331f8 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 dd89a13f1051..b4f2e7e9e907 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 379e8bd0deea..1d2e6392f5fa 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 98ab13058f89..ad1d91f475ab 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 c89c93320c12..c6b146e67116 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 5c86786bbfd2..a244237f3cfa 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 acb0effd8077..1a3f0445432a 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 0d82003e76ad..ea54a08d8301 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 0ba5f3b967f0..23b45eb9a89c 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 5718b0b58b60..a1d430b112b3 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)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index c18d41db83d8..82759cef9043 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -874,7 +874,7 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
 void add_interrupt_randomness(int irq, int irq_flags)
 {
         struct entropy_store    *r;
-        struct fast_pool        *fast_pool = &__get_cpu_var(irq_randomness);
+        struct fast_pool        *fast_pool = this_cpu_ptr(&irq_randomness);
         struct pt_regs          *regs = get_irq_regs();
         unsigned long           now = jiffies;
         cycles_t                cycles = random_get_entropy();
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index ad3572541728..31990600fcff 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -28,7 +28,7 @@ static void dummy_timer_set_mode(enum clock_event_mode mode,
 static void dummy_timer_setup(void)
 {
         int cpu = smp_processor_id();
-        struct clock_event_device *evt = __this_cpu_ptr(&dummy_timer_evt);
+        struct clock_event_device *evt = raw_cpu_ptr(&dummy_timer_evt);
 
         evt->name       = "dummy_timer";
         evt->features   = CLOCK_EVT_FEAT_PERIODIC |
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index 9e4db41abe3c..b7384b853e5a 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -90,7 +90,7 @@ static struct clocksource clocksource_metag = {
 
 static irqreturn_t metag_timer_interrupt(int irq, void *dummy)
 {
-        struct clock_event_device *evt = &__get_cpu_var(local_clockevent);
+        struct clock_event_device *evt = this_cpu_ptr(&local_clockevent);
 
         evt->event_handler(evt);
 
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 8d115db1e651..098c542e5c53 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -219,7 +219,7 @@ static void __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
                 }
 
                 /* Immediately configure the timer on the boot CPU */
-                msm_local_timer_setup(__this_cpu_ptr(msm_evt));
+                msm_local_timer_setup(raw_cpu_ptr(msm_evt));
         }
 
 err:
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 044ee0df5871..06b57c4c4d80 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -66,7 +66,7 @@ static inline void ladder_do_selection(struct ladder_device *ldev,
 static int ladder_select_state(struct cpuidle_driver *drv,
                                 struct cpuidle_device *dev)
 {
-        struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+        struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
         struct ladder_device_state *last_state;
         int last_residency, last_idx = ldev->last_state_idx;
         int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
@@ -170,7 +170,7 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
  */
 static void ladder_reflect(struct cpuidle_device *dev, int index)
 {
-        struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+        struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
         if (index > 0)
                 ldev->last_state_idx = index;
 }
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 34db2fb3ef1e..710a233b9b0d 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -289,7 +289,7 @@ again:
  */
 static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-        struct menu_device *data = &__get_cpu_var(menu_devices);
+        struct menu_device *data = this_cpu_ptr(&menu_devices);
         int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
         int i;
         unsigned int interactivity_req;
@@ -372,7 +372,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
  */
 static void menu_reflect(struct cpuidle_device *dev, int index)
 {
-        struct menu_device *data = &__get_cpu_var(menu_devices);
+        struct menu_device *data = this_cpu_ptr(&menu_devices);
         data->last_state_idx = index;
         if (index >= 0)
                 data->needs_update = 1;
@@ -385,7 +385,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
  */
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-        struct menu_device *data = &__get_cpu_var(menu_devices);
+        struct menu_device *data = this_cpu_ptr(&menu_devices);
         int last_idx = data->last_state_idx;
         struct cpuidle_state *target = &drv->states[last_idx];
         unsigned int measured_us;
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index f0a4800a15b0..38493ff28fa5 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -102,7 +102,7 @@ static struct gic_chip_data gic_data[MAX_GIC_NR] __read_mostly;
 #ifdef CONFIG_GIC_NON_BANKED
 static void __iomem *gic_get_percpu_base(union gic_base *base)
 {
-        return *__this_cpu_ptr(base->percpu_base);
+        return raw_cpu_read(*base->percpu_base);
 }
 
 static void __iomem *gic_get_common_base(union gic_base *base)
@@ -522,11 +522,11 @@ static void gic_cpu_save(unsigned int gic_nr)
         if (!dist_base || !cpu_base)
                 return;
 
-        ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+        ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
         for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
                 ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
-        ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+        ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
         for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
                 ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
 
@@ -548,11 +548,11 @@ static void gic_cpu_restore(unsigned int gic_nr)
         if (!dist_base || !cpu_base)
                 return;
 
-        ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+        ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
         for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
                 writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
-        ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+        ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
         for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
                 writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
 
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 28a90122a5a8..87f86c77b094 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -548,7 +548,7 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
                  * A race condition can at worst result in the merged flag being
                  * misrepresented, so we don't have to disable preemption here.
                  */
-                last = __this_cpu_ptr(stats->last);
+                last = raw_cpu_ptr(stats->last);
                 stats_aux->merged =
                         (bi_sector == (ACCESS_ONCE(last->last_sector) &&
                                        ((bi_rw & (REQ_WRITE | REQ_DISCARD)) ==
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 69557a26f749..049747f558c9 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -423,7 +423,7 @@ static void tile_net_pop_all_buffers(int instance, int stack)
 /* Provide linux buffers to mPIPE. */
 static void tile_net_provide_needed_buffers(void)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         int instance, kind;
         for (instance = 0; instance < NR_MPIPE_MAX &&
                      info->mpipe[instance].has_iqueue; instance++)      {
@@ -551,7 +551,7 @@ static inline bool filter_packet(struct net_device *dev, void *buf)
 static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb,
                                  gxio_mpipe_idesc_t *idesc, unsigned long len)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         struct tile_net_priv *priv = netdev_priv(dev);
         int instance = priv->instance;
 
@@ -585,7 +585,7 @@ static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb,
 /* Handle a packet.  Return true if "processed", false if "filtered". */
 static bool tile_net_handle_packet(int instance, gxio_mpipe_idesc_t *idesc)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         struct mpipe_data *md = &mpipe_data[instance];
         struct net_device *dev = md->tile_net_devs_for_channel[idesc->channel];
         uint8_t l2_offset;
@@ -651,7 +651,7 @@ drop:
  */
 static int tile_net_poll(struct napi_struct *napi, int budget)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         unsigned int work = 0;
         gxio_mpipe_idesc_t *idesc;
         int instance, i, n;
@@ -700,7 +700,7 @@ done:
 /* Handle an ingress interrupt from an instance on the current cpu. */
 static irqreturn_t tile_net_handle_ingress_irq(int irq, void *id)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         napi_schedule(&info->mpipe[(uint64_t)id].napi);
         return IRQ_HANDLED;
 }
@@ -763,7 +763,7 @@ static enum hrtimer_restart tile_net_handle_tx_wake_timer(struct hrtimer *t)
 /* Make sure the egress timer is scheduled. */
 static void tile_net_schedule_egress_timer(void)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 
         if (!info->egress_timer_scheduled) {
                 hrtimer_start(&info->egress_timer,
@@ -780,7 +780,7 @@ static void tile_net_schedule_egress_timer(void)
  */
 static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         unsigned long irqflags;
         bool pending = false;
         int i, instance;
@@ -1927,7 +1927,7 @@ static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue,
  */
 static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         struct tile_net_priv *priv = netdev_priv(dev);
         int channel = priv->echannel;
         int instance = priv->instance;
@@ -1996,7 +1996,7 @@ static unsigned int tile_net_tx_frags(struct frag *frags,
 /* Help the kernel transmit a packet. */
 static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         struct tile_net_priv *priv = netdev_priv(dev);
         int instance = priv->instance;
         struct mpipe_data *md = &mpipe_data[instance];
@@ -2138,7 +2138,7 @@ static int tile_net_set_mac_address(struct net_device *dev, void *p)
 static void tile_net_netpoll(struct net_device *dev)
 {
         int instance = mpipe_instance(dev);
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         struct mpipe_data *md = &mpipe_data[instance];
 
         disable_percpu_irq(md->ingress_irq);
@@ -2237,7 +2237,7 @@ static void tile_net_dev_init(const char *name, const uint8_t *mac)
 /* Per-cpu module initialization. */
 static void tile_net_init_module_percpu(void *unused)
 {
-        struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+        struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
         int my_cpu = smp_processor_id();
         int instance;
 
diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c
index 88818d5054ab..fb12d31cfcf6 100644
--- a/drivers/net/ethernet/tile/tilepro.c
+++ b/drivers/net/ethernet/tile/tilepro.c
@@ -996,13 +996,13 @@ static void tile_net_register(void *dev_ptr)
         PDEBUG("tile_net_register(queue_id %d)\n", queue_id);
 
         if (!strcmp(dev->name, "xgbe0"))
-                info = &__get_cpu_var(hv_xgbe0);
+                info = this_cpu_ptr(&hv_xgbe0);
         else if (!strcmp(dev->name, "xgbe1"))
-                info = &__get_cpu_var(hv_xgbe1);
+                info = this_cpu_ptr(&hv_xgbe1);
         else if (!strcmp(dev->name, "gbe0"))
-                info = &__get_cpu_var(hv_gbe0);
+                info = this_cpu_ptr(&hv_gbe0);
         else if (!strcmp(dev->name, "gbe1"))
-                info = &__get_cpu_var(hv_gbe1);
+                info = this_cpu_ptr(&hv_gbe1);
         else
                 BUG();
 
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 8aa73fac6ad4..0581461c3a67 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -45,7 +45,7 @@ unsigned long oprofile_get_cpu_buffer_size(void)
 
 void oprofile_cpu_buffer_inc_smpl_lost(void)
 {
-        struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+        struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
         cpu_buf->sample_lost_overflow++;
 }
@@ -297,7 +297,7 @@ __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
                           unsigned long event, int is_kernel,
                           struct task_struct *task)
 {
-        struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+        struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
         unsigned long backtrace = oprofile_backtrace_depth;
 
         /*
@@ -357,7 +357,7 @@ oprofile_write_reserve(struct op_entry *entry, struct pt_regs * const regs,
 {
         struct op_sample *sample;
         int is_kernel = !user_mode(regs);
-        struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+        struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
         cpu_buf->sample_received++;
 
@@ -412,13 +412,13 @@ int oprofile_write_commit(struct op_entry *entry)
 
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
-        struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+        struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
         log_sample(cpu_buf, pc, 0, is_kernel, event, NULL);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-        struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+        struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
         if (!cpu_buf->tracing)
                 return;
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 61be1d9c16c8..bdef916e5dda 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -32,7 +32,7 @@ static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
 
 static void __oprofile_hrtimer_start(void *unused)
 {
-        struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
+        struct hrtimer *hrtimer = this_cpu_ptr(&oprofile_hrtimer);
 
         if (!ctr_running)
                 return;
diff --git a/drivers/s390/cio/ccwreq.c b/drivers/s390/cio/ccwreq.c
index 07676c22d514..79f59915f71b 100644
--- a/drivers/s390/cio/ccwreq.c
+++ b/drivers/s390/cio/ccwreq.c
@@ -252,7 +252,7 @@ static void ccwreq_log_status(struct ccw_device *cdev, enum io_status status)
  */
 void ccw_request_handler(struct ccw_device *cdev)
 {
-        struct irb *irb = &__get_cpu_var(cio_irb);
+        struct irb *irb = this_cpu_ptr(&cio_irb);
         struct ccw_request *req = &cdev->private->req;
         enum io_status status;
         int rc = -EOPNOTSUPP;
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 3d22d2a4ce14..213159dec89e 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -58,7 +58,7 @@ static void chsc_subchannel_irq(struct subchannel *sch)
 {
         struct chsc_private *private = dev_get_drvdata(&sch->dev);
         struct chsc_request *request = private->request;
-        struct irb *irb = &__get_cpu_var(cio_irb);
+        struct irb *irb = this_cpu_ptr(&cio_irb);
 
         CHSC_LOG(4, "irb");
         CHSC_LOG_HEX(4, irb, sizeof(*irb));
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index d5a6f287d2fe..10eb738fc81a 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -563,7 +563,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 
         set_cpu_flag(CIF_NOHZ_DELAY);
         tpi_info = (struct tpi_info *) &get_irq_regs()->int_code;
-        irb = &__get_cpu_var(cio_irb);
+        irb = this_cpu_ptr(&cio_irb);
         sch = (struct subchannel *)(unsigned long) tpi_info->intparm;
         if (!sch) {
                 /* Clear pending interrupt condition. */
@@ -613,7 +613,7 @@ void cio_tsch(struct subchannel *sch)
         struct irb *irb;
         int irq_context;
 
-        irb = &__get_cpu_var(cio_irb);
+        irb = this_cpu_ptr(&cio_irb);
         /* Store interrupt response block to lowcore. */
         if (tsch(sch->schid, irb) != 0)
                 /* Not status pending or not operational. */
@@ -751,7 +751,7 @@ __clear_io_subchannel_easy(struct subchannel_id schid)
                 struct tpi_info ti;
 
                 if (tpi(&ti)) {
-                        tsch(ti.schid, &__get_cpu_var(cio_irb));
+                        tsch(ti.schid, this_cpu_ptr(&cio_irb));
                         if (schid_equal(&ti.schid, &schid))
                                 return 0;
                 }
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 0bc902b3cd84..83da53c8e54c 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -739,7 +739,7 @@ ccw_device_irq(struct ccw_device *cdev, enum dev_event dev_event)
         struct irb *irb;
         int is_cmd;
 
-        irb = &__get_cpu_var(cio_irb);
+        irb = this_cpu_ptr(&cio_irb);
         is_cmd = !scsw_is_tm(&irb->scsw);
         /* Check for unsolicited interrupt. */
         if (!scsw_is_solicited(&irb->scsw)) {
@@ -805,7 +805,7 @@ ccw_device_w4sense(struct ccw_device *cdev, enum dev_event dev_event)
 {
         struct irb *irb;
 
-        irb = &__get_cpu_var(cio_irb);
+        irb = this_cpu_ptr(&cio_irb);
         /* Check for unsolicited interrupt. */
         if (scsw_stctl(&irb->scsw) ==
             (SCSW_STCTL_STATUS_PEND | SCSW_STCTL_ALERT_STATUS)) {
diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c
index c4f7bf3e24c2..37f0834300ea 100644
--- a/drivers/s390/cio/eadm_sch.c
+++ b/drivers/s390/cio/eadm_sch.c
@@ -134,7 +134,7 @@ static void eadm_subchannel_irq(struct subchannel *sch)
 {
         struct eadm_private *private = get_eadm_private(sch);
         struct eadm_scsw *scsw = &sch->schib.scsw.eadm;
-        struct irb *irb = &__get_cpu_var(cio_irb);
+        struct irb *irb = this_cpu_ptr(&cio_irb);
         int error = 0;
 
         EADM_LOG(6, "irq");
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8b0f9ef517d6..748c9136a60a 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4134,7 +4134,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
          * per cpu locality group is to reduce the contention between block
          * request from multiple CPUs.
          */
-        ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
+        ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups);
 
         /* we're going to use group allocation */
         ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 2997af6d2ccd..0a9a6da21e74 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -666,10 +666,19 @@ static inline size_t cpumask_size(void)
  *
  * This code makes NR_CPUS length memcopy and brings to a memory corruption.
  * cpumask_copy() provide safe copy functionality.
+ *
+ * Note that there is another evil here: If you define a cpumask_var_t
+ * as a percpu variable then the way to obtain the address of the cpumask
+ * structure differently influences what this_cpu_* operation needs to be
+ * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
+ * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
+ * other type of cpumask_var_t implementation is configured.
  */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 typedef struct cpumask *cpumask_var_t;
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
@@ -681,6 +690,8 @@ void free_bootmem_cpumask_var(cpumask_var_t mask);
 #else
 typedef struct cpumask cpumask_var_t[1];
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
+
 static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
         return true;
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ecbc52f9ff77..8422b4ed6882 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -44,8 +44,8 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
 /* Must have preemption disabled for this to be meaningful. */
-#define kstat_this_cpu (&__get_cpu_var(kstat))
-#define kcpustat_this_cpu (&__get_cpu_var(kernel_cpustat))
+#define kstat_this_cpu this_cpu_ptr(&kstat)
+#define kcpustat_this_cpu this_cpu_ptr(&kernel_cpustat)
 #define kstat_cpu(cpu) per_cpu(kstat, cpu)
 #define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index cfd56046ecec..420032d41d27 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -257,9 +257,6 @@ do {									\
 #define __raw_get_cpu_var(var)  (*raw_cpu_ptr(&(var)))
 #define __get_cpu_var(var)      (*this_cpu_ptr(&(var)))
 
-/* keep until we have removed all uses of __this_cpu_ptr */
-#define __this_cpu_ptr(ptr)     raw_cpu_ptr(ptr)
-
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
  * we force a syntax error here if it isn't.
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 37252f71a380..c8a7db605e03 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -242,7 +242,7 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
 static inline struct nf_conn *nf_ct_untracked_get(void)
 {
-        return &__raw_get_cpu_var(nf_conntrack_untracked);
+        return raw_cpu_ptr(&nf_conntrack_untracked);
 }
 void nf_ct_untracked_status_or(unsigned long bits);
 
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 8fd2f498782e..35512ac6dcfb 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -164,7 +164,7 @@ struct linux_xfrm_mib {
 
 #define SNMP_ADD_STATS64_BH(mib, field, addend)                         \
         do {                                                            \
-                __typeof__(*mib) *ptr = __this_cpu_ptr(mib);            \
+                __typeof__(*mib) *ptr = raw_cpu_ptr(mib);               \
                 u64_stats_update_begin(&ptr->syncp);                    \
                 ptr->mibs[field] += addend;                             \
                 u64_stats_update_end(&ptr->syncp);                      \
@@ -185,8 +185,8 @@ struct linux_xfrm_mib {
 #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1)
 #define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)                  \
         do {                                                            \
-                __typeof__(*mib) *ptr;                                  \
-                ptr = __this_cpu_ptr(mib);                              \
+                __typeof__(*mib) *ptr;                          \
+                ptr = raw_cpu_ptr((mib));                               \
                 u64_stats_update_begin(&ptr->syncp);                    \
                 ptr->mibs[basefield##PKTS]++;                           \
                 ptr->mibs[basefield##OCTETS] += addend;                 \
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index f2a88de87a49..d659487254d5 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -137,7 +137,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
         int cpu;
         struct callchain_cpus_entries *entries;
 
-        *rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+        *rctx = get_recursion_context(this_cpu_ptr(callchain_recursion));
         if (*rctx == -1)
                 return NULL;
 
@@ -153,7 +153,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 static void
 put_callchain_entry(int rctx)
 {
-        put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+        put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
 }
 
 struct perf_callchain_entry *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 094df8c0742d..1425d07018de 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -249,7 +249,7 @@ static void perf_duration_warn(struct irq_work *w)
         u64 avg_local_sample_len;
         u64 local_samples_len;
 
-        local_samples_len = __get_cpu_var(running_sample_length);
+        local_samples_len = __this_cpu_read(running_sample_length);
         avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
 
         printk_ratelimited(KERN_WARNING
@@ -271,10 +271,10 @@ void perf_sample_event_took(u64 sample_len_ns)
                 return;
 
         /* decay the counter by 1 average sample */
-        local_samples_len = __get_cpu_var(running_sample_length);
+        local_samples_len = __this_cpu_read(running_sample_length);
         local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES;
         local_samples_len += sample_len_ns;
-        __get_cpu_var(running_sample_length) = local_samples_len;
+        __this_cpu_write(running_sample_length, local_samples_len);
 
         /*
          * note: this will be biased artifically low until we have
@@ -882,7 +882,7 @@ static DEFINE_PER_CPU(struct list_head, rotation_list);
 static void perf_pmu_rotate_start(struct pmu *pmu)
 {
         struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-        struct list_head *head = &__get_cpu_var(rotation_list);
+        struct list_head *head = this_cpu_ptr(&rotation_list);
 
         WARN_ON(!irqs_disabled());
 
@@ -2462,7 +2462,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
          * to check if we have to switch out PMU state.
          * cgroup event are system-wide mode only
          */
-        if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+        if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
                 perf_cgroup_sched_out(task, next);
 }
 
@@ -2705,11 +2705,11 @@ void __perf_event_task_sched_in(struct task_struct *prev,
          * to check if we have to switch in PMU state.
          * cgroup event are system-wide mode only
          */
-        if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+        if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
                 perf_cgroup_sched_in(prev, task);
 
         /* check for system-wide branch_stack events */
-        if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+        if (atomic_read(this_cpu_ptr(&perf_branch_stack_events)))
                 perf_branch_stack_sched_in(prev, task);
 }
 
@@ -2964,7 +2964,7 @@ bool perf_event_can_stop_tick(void)
 
 void perf_event_task_tick(void)
 {
-        struct list_head *head = &__get_cpu_var(rotation_list);
+        struct list_head *head = this_cpu_ptr(&rotation_list);
         struct perf_cpu_context *cpuctx, *tmp;
         struct perf_event_context *ctx;
         int throttled;
@@ -5833,7 +5833,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
                                     struct perf_sample_data *data,
                                     struct pt_regs *regs)
 {
-        struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+        struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
         struct perf_event *event;
         struct hlist_head *head;
 
@@ -5852,7 +5852,7 @@ end:
 
 int perf_swevent_get_recursion_context(void)
 {
-        struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+        struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 
         return get_recursion_context(swhash->recursion);
 }
@@ -5860,7 +5860,7 @@ EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 inline void perf_swevent_put_recursion_context(int rctx)
 {
-        struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+        struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 
         put_recursion_context(swhash->recursion, rctx);
 }
@@ -5889,7 +5889,7 @@ static void perf_swevent_read(struct perf_event *event)
 
 static int perf_swevent_add(struct perf_event *event, int flags)
 {
-        struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+        struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
         struct hw_perf_event *hwc = &event->hw;
         struct hlist_head *head;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 8fb52e9bddc1..e5202f00cabc 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -699,7 +699,7 @@ void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc)
 {
         struct irq_chip *chip = irq_desc_get_chip(desc);
         struct irqaction *action = desc->action;
-        void *dev_id = __this_cpu_ptr(action->percpu_dev_id);
+        void *dev_id = raw_cpu_ptr(action->percpu_dev_id);
         irqreturn_t res;
 
         kstat_incr_irqs_this_cpu(irq, desc);
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 385b85aded19..3ab9048483fa 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -95,11 +95,11 @@ bool irq_work_queue(struct irq_work *work)
 
         /* If the work is "lazy", handle it from next tick if any */
         if (work->flags & IRQ_WORK_LAZY) {
-                if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) &&
+                if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
                     tick_nohz_tick_stopped())
                         arch_irq_work_raise();
         } else {
-                if (llist_add(&work->llnode, &__get_cpu_var(raised_list)))
+                if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
                         arch_irq_work_raise();
         }
 
@@ -113,8 +113,8 @@ bool irq_work_needs_cpu(void)
 {
         struct llist_head *raised, *lazy;
 
-        raised = &__get_cpu_var(raised_list);
-        lazy = &__get_cpu_var(lazy_list);
+        raised = this_cpu_ptr(&raised_list);
+        lazy = this_cpu_ptr(&lazy_list);
 
         if (llist_empty(raised) || arch_irq_work_has_interrupt())
                 if (llist_empty(lazy))
@@ -168,8 +168,8 @@ static void irq_work_run_list(struct llist_head *list)
  */
 void irq_work_run(void)
 {
-        irq_work_run_list(&__get_cpu_var(raised_list));
-        irq_work_run_list(&__get_cpu_var(lazy_list));
+        irq_work_run_list(this_cpu_ptr(&raised_list));
+        irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index e3962d63e368..ced2b84b1cb7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2622,7 +2622,7 @@ void wake_up_klogd(void)
         preempt_disable();
         if (waitqueue_active(&log_wait)) {
                 this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-                irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+                irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
         }
         preempt_enable();
 }
@@ -2638,7 +2638,7 @@ int printk_deferred(const char *fmt, ...)
         va_end(args);
 
         __this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
-        irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+        irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
         preempt_enable();
 
         return r;
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 3ef6451e972e..c27e4f8f4879 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -134,7 +134,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
 
 static inline struct sched_clock_data *this_scd(void)
 {
-        return &__get_cpu_var(sched_clock_data);
+        return this_cpu_ptr(&sched_clock_data);
 }
 
 static inline struct sched_clock_data *cpu_sdc(int cpu)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index abfaf3d9a29f..256e577faf1b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1153,7 +1153,7 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 static int find_later_rq(struct task_struct *task)
 {
         struct sched_domain *sd;
-        struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+        struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
         int this_cpu = smp_processor_id();
         int best_cpu, cpu = task_cpu(task);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b78280c59b46..0b069bf3e708 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6615,7 +6615,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
         struct sched_group *group;
         struct rq *busiest;
         unsigned long flags;
-        struct cpumask *cpus = __get_cpu_var(load_balance_mask);
+        struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
 
         struct lb_env env = {
                 .sd             = sd,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 87ea5bf1b87f..d024e6ce30ba 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1525,7 +1525,7 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 static int find_lowest_rq(struct task_struct *task)
 {
         struct sched_domain *sd;
-        struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
+        struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
         int this_cpu = smp_processor_id();
         int cpu      = task_cpu(task);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6130251de280..24156c8434d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -663,10 +663,10 @@ static inline int cpu_of(struct rq *rq)
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 #define cpu_rq(cpu)             (&per_cpu(runqueues, (cpu)))
-#define this_rq()               (&__get_cpu_var(runqueues))
+#define this_rq()               this_cpu_ptr(&runqueues)
 #define task_rq(p)              cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)           (cpu_rq(cpu)->curr)
-#define raw_rq()                (&__raw_get_cpu_var(runqueues))
+#define raw_rq()                raw_cpu_ptr(&runqueues)
 
 static inline u64 rq_clock(struct rq *rq)
 {
diff --git a/kernel/smp.c b/kernel/smp.c
index 9e0d0b289118..f38a1e692259 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -165,7 +165,7 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
         if (!csd) {
                 csd = &csd_stack;
                 if (!wait)
-                        csd = &__get_cpu_var(csd_data);
+                        csd = this_cpu_ptr(&csd_data);
         }
 
         csd_lock(csd);
@@ -230,7 +230,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 
         WARN_ON(!irqs_disabled());
 
-        head = &__get_cpu_var(call_single_queue);
+        head = this_cpu_ptr(&call_single_queue);
         entry = llist_del_all(head);
         entry = llist_reverse_order(entry);
 
@@ -420,7 +420,7 @@ void smp_call_function_many(const struct cpumask *mask,
                 return;
         }
 
-        cfd = &__get_cpu_var(cfd_data);
+        cfd = this_cpu_ptr(&cfd_data);
 
         cpumask_and(cfd->cpumask, mask, cpu_online_mask);
         cpumask_clear_cpu(this_cpu, cfd->cpumask);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 348ec763b104..0699add19164 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -485,7 +485,7 @@ static void tasklet_action(struct softirq_action *a)
         local_irq_disable();
         list = __this_cpu_read(tasklet_vec.head);
         __this_cpu_write(tasklet_vec.head, NULL);
-        __this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head);
+        __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
         local_irq_enable();
 
         while (list) {
@@ -521,7 +521,7 @@ static void tasklet_hi_action(struct softirq_action *a)
         local_irq_disable();
         list = __this_cpu_read(tasklet_hi_vec.head);
         __this_cpu_write(tasklet_hi_vec.head, NULL);
-        __this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head);
+        __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head));
         local_irq_enable();
 
         while (list) {
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13d2f7cd65db..b312fcc73024 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -638,7 +638,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
                 fill_tgid_exit(tsk);
         }
 
-        listeners = __this_cpu_ptr(&listener_array);
+        listeners = raw_cpu_ptr(&listener_array);
         if (list_empty(&listeners->list))
                 return;
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index ab370ffffd53..37e50aadd471 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -558,7 +558,7 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 static int hrtimer_reprogram(struct hrtimer *timer,
                              struct hrtimer_clock_base *base)
 {
-        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
         ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
         int res;
 
@@ -629,7 +629,7 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
  */
 static void retrigger_next_event(void *arg)
 {
-        struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
         if (!hrtimer_hres_active())
                 return;
@@ -903,7 +903,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
                  */
                 debug_deactivate(timer);
                 timer_stats_hrtimer_clear_start_info(timer);
-                reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
+                reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
                 /*
                  * We must preserve the CALLBACK state flag here,
                  * otherwise we could move the timer base in
@@ -963,7 +963,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
                  * on dynticks target.
                  */
                 wake_up_nohz_cpu(new_base->cpu_base->cpu);
-        } else if (new_base->cpu_base == &__get_cpu_var(hrtimer_bases) &&
+        } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
                         hrtimer_reprogram(timer, new_base)) {
                 /*
                  * Only allow reprogramming if the new base is on this CPU.
@@ -1103,7 +1103,7 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
  */
 ktime_t hrtimer_get_next_event(void)
 {
-        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
         struct hrtimer_clock_base *base = cpu_base->clock_base;
         ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
         unsigned long flags;
@@ -1144,7 +1144,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 
         memset(timer, 0, sizeof(struct hrtimer));
 
-        cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+        cpu_base = raw_cpu_ptr(&hrtimer_bases);
 
         if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
                 clock_id = CLOCK_MONOTONIC;
@@ -1187,7 +1187,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
         struct hrtimer_cpu_base *cpu_base;
         int base = hrtimer_clockid_to_base(which_clock);
 
-        cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+        cpu_base = raw_cpu_ptr(&hrtimer_bases);
         *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
         return 0;
@@ -1242,7 +1242,7 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
  */
 void hrtimer_interrupt(struct clock_event_device *dev)
 {
-        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
         ktime_t expires_next, now, entry_time, delta;
         int i, retries = 0;
 
@@ -1376,7 +1376,7 @@ static void __hrtimer_peek_ahead_timers(void)
         if (!hrtimer_hres_active())
                 return;
 
-        td = &__get_cpu_var(tick_cpu_device);
+        td = this_cpu_ptr(&tick_cpu_device);
         if (td && td->evtdev)
                 hrtimer_interrupt(td->evtdev);
 }
@@ -1440,7 +1440,7 @@ void hrtimer_run_pending(void)
 void hrtimer_run_queues(void)
 {
         struct timerqueue_node *node;
-        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+        struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
         struct hrtimer_clock_base *base;
         int index, gettime = 1;
 
@@ -1679,7 +1679,7 @@ static void migrate_hrtimers(int scpu)
 
         local_irq_disable();
         old_base = &per_cpu(hrtimer_bases, scpu);
-        new_base = &__get_cpu_var(hrtimer_bases);
+        new_base = this_cpu_ptr(&hrtimer_bases);
         /*
          * The caller is globally serialized and nobody else
          * takes two locks at once, deadlock is not possible.
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 64c5990fd500..066f0ec05e48 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -554,7 +554,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 void tick_check_oneshot_broadcast_this_cpu(void)
 {
         if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
-                struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+                struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
                 /*
                  * We might be in the middle of switching over from
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 052b4b53c3d6..7efeedf53ebd 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -224,7 +224,7 @@ static void tick_setup_device(struct tick_device *td,
 
 void tick_install_replacement(struct clock_event_device *newdev)
 {
-        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
         int cpu = smp_processor_id();
 
         clockevents_exchange_device(td->evtdev, newdev);
@@ -374,14 +374,14 @@ void tick_shutdown(unsigned int *cpup)
 
 void tick_suspend(void)
 {
-        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
         clockevents_shutdown(td->evtdev);
 }
 
 void tick_resume(void)
 {
-        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
         int broadcast = tick_resume_broadcast();
 
         clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 824109060a33..7ce740e78e1b 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -59,7 +59,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
  */
 int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 {
-        struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+        struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
         struct clock_event_device *dev = td->evtdev;
 
         if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a73efdf6f696..7b5741fc4110 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -205,7 +205,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now);
  */
 void __tick_nohz_full_check(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
         if (tick_nohz_full_cpu(smp_processor_id())) {
                 if (ts->tick_stopped && !is_idle_task(current)) {
@@ -573,7 +573,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
         unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
         ktime_t last_update, expires, ret = { .tv64 = 0 };
         unsigned long rcu_delta_jiffies;
-        struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+        struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
         u64 time_delta;
 
         time_delta = timekeeping_max_deferment();
@@ -841,7 +841,7 @@ void tick_nohz_idle_enter(void)
 
         local_irq_disable();
 
-        ts = &__get_cpu_var(tick_cpu_sched);
+        ts = this_cpu_ptr(&tick_cpu_sched);
         ts->inidle = 1;
         __tick_nohz_idle_enter(ts);
 
@@ -859,7 +859,7 @@ EXPORT_SYMBOL_GPL(tick_nohz_idle_enter);
  */
 void tick_nohz_irq_exit(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
         if (ts->inidle)
                 __tick_nohz_idle_enter(ts);
@@ -874,7 +874,7 @@ void tick_nohz_irq_exit(void)
  */
 ktime_t tick_nohz_get_sleep_length(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
         return ts->sleep_length;
 }
@@ -952,7 +952,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
  */
 void tick_nohz_idle_exit(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
         ktime_t now;
 
         local_irq_disable();
@@ -987,7 +987,7 @@ static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
  */
 static void tick_nohz_handler(struct clock_event_device *dev)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
         struct pt_regs *regs = get_irq_regs();
         ktime_t now = ktime_get();
 
@@ -1011,7 +1011,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
  */
 static void tick_nohz_switch_to_nohz(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
         ktime_t next;
 
         if (!tick_nohz_enabled)
@@ -1073,7 +1073,7 @@ static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
 
 static inline void tick_nohz_irq_enter(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
         ktime_t now;
 
         if (!ts->idle_active && !ts->tick_stopped)
@@ -1151,7 +1151,7 @@ early_param("skew_tick", skew_tick);
  */
 void tick_setup_sched_timer(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
         ktime_t now = ktime_get();
 
         /*
@@ -1220,7 +1220,7 @@ void tick_clock_notify(void)
  */
 void tick_oneshot_notify(void)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
         set_bit(0, &ts->check_clocks);
 }
@@ -1235,7 +1235,7 @@ void tick_oneshot_notify(void)
  */
 int tick_check_oneshot_change(int allow_nohz)
 {
-        struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+        struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
         if (!test_and_clear_bit(0, &ts->check_clocks))
                 return 0;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 9bbb8344ed3b..3260ffdb368f 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -655,7 +655,7 @@ static inline void debug_assert_init(struct timer_list *timer)
 static void do_init_timer(struct timer_list *timer, unsigned int flags,
                           const char *name, struct lock_class_key *key)
 {
-        struct tvec_base *base = __raw_get_cpu_var(tvec_bases);
+        struct tvec_base *base = raw_cpu_read(tvec_bases);
 
         timer->entry.next = NULL;
         timer->base = (void *)((unsigned long)base | flags);
diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c
index 394f70b17162..9586b670a5b2 100644
--- a/kernel/user-return-notifier.c
+++ b/kernel/user-return-notifier.c
@@ -14,7 +14,7 @@ static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
 void user_return_notifier_register(struct user_return_notifier *urn)
 {
         set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
-        hlist_add_head(&urn->link, &__get_cpu_var(return_notifier_list));
+        hlist_add_head(&urn->link, this_cpu_ptr(&return_notifier_list));
 }
 EXPORT_SYMBOL_GPL(user_return_notifier_register);
 
@@ -25,7 +25,7 @@ EXPORT_SYMBOL_GPL(user_return_notifier_register);
 void user_return_notifier_unregister(struct user_return_notifier *urn)
 {
         hlist_del(&urn->link);
-        if (hlist_empty(&__get_cpu_var(return_notifier_list)))
+        if (hlist_empty(this_cpu_ptr(&return_notifier_list)))
                 clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
 }
 EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 49e9537f3673..70bf11815f84 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -208,7 +208,7 @@ void touch_nmi_watchdog(void)
          * case we shouldn't have to worry about the watchdog
          * going off.
          */
-        __raw_get_cpu_var(watchdog_nmi_touch) = true;
+        raw_cpu_write(watchdog_nmi_touch, true);
         touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -217,8 +217,8 @@ EXPORT_SYMBOL(touch_nmi_watchdog);
 
 void touch_softlockup_watchdog_sync(void)
 {
-        __raw_get_cpu_var(softlockup_touch_sync) = true;
-        __raw_get_cpu_var(watchdog_touch_ts) = 0;
+        __this_cpu_write(softlockup_touch_sync, true);
+        __this_cpu_write(watchdog_touch_ts, 0);
 }
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
@@ -425,7 +425,7 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio)
 
 static void watchdog_enable(unsigned int cpu)
 {
-        struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+        struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
 
         /* kick off the timer for the hardlockup detector */
         hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -445,7 +445,7 @@ static void watchdog_enable(unsigned int cpu)
 
 static void watchdog_disable(unsigned int cpu)
 {
-        struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+        struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
 
         watchdog_set_prio(SCHED_NORMAL, 0);
         hrtimer_cancel(hrtimer);
@@ -585,7 +585,7 @@ static struct smp_hotplug_thread watchdog_threads = {
 
 static void restart_watchdog_hrtimer(void *info)
 {
-        struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+        struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
         int ret;
 
         /*
diff --git a/net/core/dev.c b/net/core/dev.c
index 4699dcfdc4ab..6470716ddba4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2153,7 +2153,7 @@ static inline void __netif_reschedule(struct Qdisc *q)
         unsigned long flags;
 
         local_irq_save(flags);
-        sd = &__get_cpu_var(softnet_data);
+        sd = this_cpu_ptr(&softnet_data);
         q->next_sched = NULL;
         *sd->output_queue_tailp = q;
         sd->output_queue_tailp = &q->next_sched;
@@ -3233,7 +3233,7 @@ static void rps_trigger_softirq(void *data)
 static int rps_ipi_queued(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-        struct softnet_data *mysd = &__get_cpu_var(softnet_data);
+        struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
         if (sd != mysd) {
                 sd->rps_ipi_next = mysd->rps_ipi_list;
@@ -3260,7 +3260,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
         if (qlen < (netdev_max_backlog >> 1))
                 return false;
 
-        sd = &__get_cpu_var(softnet_data);
+        sd = this_cpu_ptr(&softnet_data);
 
         rcu_read_lock();
         fl = rcu_dereference(sd->flow_limit);
@@ -3407,7 +3407,7 @@ EXPORT_SYMBOL(netif_rx_ni);
 
 static void net_tx_action(struct softirq_action *h)
 {
-        struct softnet_data *sd = &__get_cpu_var(softnet_data);
+        struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 
         if (sd->completion_queue) {
                 struct sk_buff *clist;
@@ -3832,7 +3832,7 @@ EXPORT_SYMBOL(netif_receive_skb);
 static void flush_backlog(void *arg)
 {
         struct net_device *dev = arg;
-        struct softnet_data *sd = &__get_cpu_var(softnet_data);
+        struct softnet_data *sd = this_cpu_ptr(&softnet_data);
         struct sk_buff *skb, *tmp;
 
         rps_lock(sd);
@@ -4379,7 +4379,7 @@ void __napi_schedule(struct napi_struct *n)
         unsigned long flags;
 
         local_irq_save(flags);
-        ____napi_schedule(&__get_cpu_var(softnet_data), n);
+        ____napi_schedule(this_cpu_ptr(&softnet_data), n);
         local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__napi_schedule);
@@ -4500,7 +4500,7 @@ EXPORT_SYMBOL(netif_napi_del);
 
 static void net_rx_action(struct softirq_action *h)
 {
-        struct softnet_data *sd = &__get_cpu_var(softnet_data);
+        struct softnet_data *sd = this_cpu_ptr(&softnet_data);
         unsigned long time_limit = jiffies + 2;
         int budget = netdev_budget;
         void *have;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 50f9a9db5792..252e155c837b 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -146,7 +146,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
         unsigned long flags;
 
         local_irq_save(flags);
-        data = &__get_cpu_var(dm_cpu_data);
+        data = this_cpu_ptr(&dm_cpu_data);
         spin_lock(&data->lock);
         dskb = data->skb;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 829d013745ab..61059a05ec95 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -345,7 +345,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
         unsigned long flags;
 
         local_irq_save(flags);
-        nc = &__get_cpu_var(netdev_alloc_cache);
+        nc = this_cpu_ptr(&netdev_alloc_cache);
         if (unlikely(!nc->frag.page)) {
 refill:
                 for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 793c0bb8c4fd..2d4ae469b471 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1311,7 +1311,7 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
         if (rt_is_input_route(rt)) {
                 p = (struct rtable **)&nh->nh_rth_input;
         } else {
-                p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+                p = (struct rtable **)raw_cpu_ptr(nh->nh_pcpu_rth_output);
         }
         orig = *p;
 
@@ -1939,7 +1939,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
                                 do_cache = false;
                                 goto add;
                         }
-                        prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+                        prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
                 }
                 rth = rcu_dereference(*prth);
                 if (rt_cache_valid(rth)) {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 0431a8f3c8f4..af660030e3c7 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -40,7 +40,7 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 
         net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
 
-        tmp  = __get_cpu_var(ipv4_cookie_scratch);
+        tmp  = this_cpu_ptr(ipv4_cookie_scratch);
         memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
         tmp[0] = (__force u32)saddr;
         tmp[1] = (__force u32)daddr;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 86023b9be47f..1bec4e76d88c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2941,7 +2941,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
         local_bh_disable();
         p = ACCESS_ONCE(tcp_md5sig_pool);
         if (p)
-                return __this_cpu_ptr(p);
+                return raw_cpu_ptr(p);
 
         local_bh_enable();
         return NULL;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8d4eac793700..becd98ce9a1c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -852,7 +852,7 @@ void tcp_wfree(struct sk_buff *skb)
 
                 /* queue this socket to tasklet queue */
                 local_irq_save(flags);
-                tsq = &__get_cpu_var(tsq_tasklet);
+                tsq = this_cpu_ptr(&tsq_tasklet);
                 list_add(&tp->tsq_node, &tsq->head);
                 tasklet_schedule(&tsq->tasklet);
                 local_irq_restore(flags);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 9a2838e93cc5..e25b633266c3 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -67,7 +67,7 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
 
         net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
 
-        tmp  = __get_cpu_var(ipv6_cookie_scratch);
+        tmp  = this_cpu_ptr(ipv6_cookie_scratch);
 
         /*
          * we have 320 bits of information to hash, copy in the remaining
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e8fdb172adbb..273b8bff6ba4 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -267,7 +267,7 @@ static inline struct rds_ib_mr *rds_ib_reuse_fmr(struct rds_ib_mr_pool *pool)
         unsigned long *flag;
 
         preempt_disable();
-        flag = &__get_cpu_var(clean_list_grace);
+        flag = this_cpu_ptr(&clean_list_grace);
         set_bit(CLEAN_LIST_BUSY_BIT, flag);
         ret = llist_del_first(&pool->clean_list);
         if (ret)