Merge tag 'v3.18-rc1' into x86/urgent

Reason:
Need to apply audit patch on top of v3.18-rc1.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

49 files changed, 325 insertions, 514 deletions

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 711de084ab57..8ffba18395c8 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -198,12 +198,12 @@ sysexit_from_sys_call:
 
 #ifdef CONFIG_AUDITSYSCALL
 	.macro auditsys_entry_common
-	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
-	movl %edx,%r8d			/* 5th arg: 3rd syscall arg */
-	/* (already in %ecx)		   4th arg: 2nd syscall arg */
-	movl %ebx,%edx			/* 3rd arg: 1st syscall arg */
-	movl %eax,%esi			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_I386,%edi	/* 1st arg: audit arch */
+	movl %esi,%r8d			/* 5th arg: 4th syscall arg */
+	movl %ecx,%r9d			/*swap with edx*/
+	movl %edx,%ecx			/* 4th arg: 3rd syscall arg */
+	movl %r9d,%edx			/* 3rd arg: 2nd syscall arg */
+	movl %ebx,%esi			/* 2nd arg: 1st syscall arg */
+	movl %eax,%edi			/* 1st arg: syscall number */
 	call __audit_syscall_entry
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall number */
 	cmpq $(IA32_NR_syscalls-1),%rax
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 3bf000fab0ae..d55a210a49bf 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -6,6 +6,7 @@ genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
 generic-y += cputime.h
+generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
 generic-y += scatterlist.h
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/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
deleted file mode 100644
index b4b38bacb404..000000000000
--- a/arch/x86/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASMX86_DMA_CONTIGUOUS_H
-#define ASMX86_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
-#endif
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 53cdfb2857ab..4421b5da409d 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -27,7 +27,6 @@
 #include <asm/insn.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
-#define  ARCH_SUPPORTS_KPROBES_ON_FTRACE
 
 struct pt_regs;
 struct kprobe;
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 24b5894396a0..ba6cc041edb1 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 700f958652f8..4b4f78c9ba19 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -964,6 +964,7 @@ static void vgetcpu_set_mode(void)
 		vgetcpu_mode = VGETCPU_LSL;
 }
 
+#ifdef CONFIG_IA32_EMULATION
 /* May not be __init: called during resume */
 static void syscall32_cpu_init(void)
 {
@@ -975,7 +976,8 @@ static void syscall32_cpu_init(void)
 
 	wrmsrl(MSR_CSTAR, ia32_cstar_target);
 }
-#endif
+#endif		/* CONFIG_IA32_EMULATION */
+#endif		/* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_32
 void enable_sep_cpu(void)
@@ -1198,9 +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/crash.c b/arch/x86/kernel/crash.c
index a618fcd2c07d..f5ab56d14287 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -237,7 +237,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 	ced->max_nr_ranges++;
 
 	/* If crashk_low_res is not 0, another range split possible */
-	if (crashk_low_res.end != 0)
+	if (crashk_low_res.end)
 		ced->max_nr_ranges++;
 }
 
@@ -335,9 +335,11 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
 	if (ret)
 		return ret;
 
-	ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
-	if (ret)
-		return ret;
+	if (crashk_low_res.end) {
+		ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+		if (ret)
+			return ret;
+	}
 
 	/* Exclude GART region */
 	if (ced->gart_end) {
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4b0e1dfa2226..b553ed89e5f5 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -449,12 +449,11 @@ sysenter_audit:
 	jnz syscall_trace_entry
 	addl $4,%esp
 	CFI_ADJUST_CFA_OFFSET -4
-	/* %esi already in 8(%esp)	   6th arg: 4th syscall arg */
-	/* %edx already in 4(%esp)	   5th arg: 3rd syscall arg */
-	/* %ecx already in 0(%esp)	   4th arg: 2nd syscall arg */
-	movl %ebx,%ecx			/* 3rd arg: 1st syscall arg */
-	movl %eax,%edx			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_I386,%eax	/* 1st arg: audit arch */
+	movl %esi,4(%esp)		/* 5th arg: 4th syscall arg */
+	movl %edx,(%esp)		/* 4th arg: 3rd syscall arg */
+	/* %ecx already in %ecx		   3rd arg: 2nd syscall arg */
+	movl %ebx,%edx			/* 2nd arg: 1st syscall arg */
+	/* %eax already in %eax		   1st arg: syscall number */
 	call __audit_syscall_entry
 	pushl_cfi %ebx
 	movl PT_EAX(%esp),%eax		/* reload syscall number */
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/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 9642b9b33655..ca05f86481aa 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -26,6 +26,7 @@
 #include <asm/setup.h>
 #include <asm/crash.h>
 #include <asm/efi.h>
+#include <asm/kexec-bzimage64.h>
 
 #define MAX_ELFCOREHDR_STR_LEN	30	/* elfcorehdr=0x<64bit-value> */
 
@@ -267,7 +268,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	return ret;
 }
 
-int bzImage64_probe(const char *buf, unsigned long len)
+static int bzImage64_probe(const char *buf, unsigned long len)
 {
 	int ret = -ENOEXEC;
 	struct setup_header *header;
@@ -325,10 +326,10 @@ int bzImage64_probe(const char *buf, unsigned long len)
 	return ret;
 }
 
-void *bzImage64_load(struct kimage *image, char *kernel,
-		     unsigned long kernel_len, char *initrd,
-		     unsigned long initrd_len, char *cmdline,
-		     unsigned long cmdline_len)
+static void *bzImage64_load(struct kimage *image, char *kernel,
+			    unsigned long kernel_len, char *initrd,
+			    unsigned long initrd_len, char *cmdline,
+			    unsigned long cmdline_len)
 {
 
 	struct setup_header *header;
@@ -514,7 +515,7 @@ out_free_params:
 }
 
 /* This cleanup function is called after various segments have been loaded */
-int bzImage64_cleanup(void *loader_data)
+static int bzImage64_cleanup(void *loader_data)
 {
 	struct bzimage64_data *ldata = loader_data;
 
@@ -528,7 +529,7 @@ int bzImage64_cleanup(void *loader_data)
 }
 
 #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG
-int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
+static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 {
 	bool trusted;
 	int ret;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 3dd8e2c4d74a..f6945bef2cd1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/kprobes.h>
 #include <linux/debugfs.h>
+#include <linux/nmi.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -243,9 +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;
@@ -318,7 +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);
 }
@@ -329,13 +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());
 	}
@@ -344,8 +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);
 	}
@@ -356,11 +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());
@@ -499,6 +500,13 @@ void __init kvm_guest_init(void)
 #else
 	kvm_guest_cpu_init();
 #endif
+
+	/*
+	 * Hard lockup detection is enabled by default. Disable it, as guests
+	 * can get false positives too easily, for example if the host is
+	 * overcommitted.
+	 */
+	watchdog_enable_hardlockup_detector(false);
 }
 
 static noinline uint32_t __kvm_cpuid_base(void)
@@ -716,7 +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/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 29576c244699..749b0e423419 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1445,12 +1445,12 @@ static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
 {
 #ifdef CONFIG_X86_64
 	if (arch == AUDIT_ARCH_X86_64) {
-		audit_syscall_entry(arch, regs->orig_ax, regs->di,
+		audit_syscall_entry(regs->orig_ax, regs->di,
 				    regs->si, regs->dx, regs->r10);
 	} else
 #endif
 	{
-		audit_syscall_entry(arch, regs->orig_ax, regs->bx,
+		audit_syscall_entry(regs->orig_ax, regs->bx,
 				    regs->cx, regs->dx, regs->si);
 	}
 }
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..0acac81f198b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -472,6 +472,7 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
+		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -1626,7 +1627,7 @@ 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 +1673,7 @@ 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 +1803,7 @@ 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 +1833,7 @@ 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 +2772,7 @@ 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;
 }
@@ -4267,11 +4268,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	u32 low32, high32;
 	unsigned long tmpl;
 	struct desc_ptr dt;
+	unsigned long cr4;
 
 	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
-	vmcs_writel(HOST_CR4, read_cr4());  /* 22.2.3, 22.2.5 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
+	/* Save the most likely value for this task's CR4 in the VMCS. */
+	cr4 = read_cr4();
+	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
+	vmx->host_state.vmcs_host_cr4 = cr4;
+
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
 	/*
@@ -7514,7 +7520,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long debugctlmsr;
+	unsigned long debugctlmsr, cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
@@ -7540,6 +7546,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
+	cr4 = read_cr4();
+	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+		vmcs_writel(HOST_CR4, cr4);
+		vmx->host_state.vmcs_host_cr4 = cr4;
+	}
+
 	/* When single-stepping over STI and MOV SS, we must clear the
 	 * corresponding interruptibility bits in the guest state. Otherwise
 	 * vmentry fails as it then expects bit 14 (BS) in pending debug
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/ioremap.c b/arch/x86/mm/ioremap.c
index baff1da354e0..af78e50ca6ce 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -86,6 +86,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
+	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -108,12 +109,23 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	pfn      = phys_addr >> PAGE_SHIFT;
-	last_pfn = last_addr >> PAGE_SHIFT;
-	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-				  __ioremap_check_ram) == 1)
+	/* First check if whole region can be identified as RAM or not */
+	ram_region = region_is_ram(phys_addr, size);
+	if (ram_region > 0) {
+		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
+				(unsigned long int)phys_addr,
+				(unsigned long int)last_addr);
 		return NULL;
+	}
 
+	/* If could not be identified(-1), check page by page */
+	if (ram_region < 0) {
+		pfn      = phys_addr >> PAGE_SHIFT;
+		last_pfn = last_addr >> PAGE_SHIFT;
+		if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+					  __ioremap_check_ram) == 1)
+			return NULL;
+	}
 	/*
 	 * Mappings have to be page-aligned
 	 */
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/mm/numa.c b/arch/x86/mm/numa.c
index d221374d5ce8..1a883705a12a 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -463,6 +463,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+	unsigned long start, end;
+	struct memblock_region *r;
+
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
+	/* Mark all kernel nodes. */
+	for_each_memblock(reserved, r)
+		node_set(r->nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
 	unsigned long uninitialized_var(pfn_align);
@@ -481,6 +517,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	}
 
 	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, alloc node data won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
+	/*
 	 * If sections array is gonna be used for pfn -> nid mapping, check
 	 * whether its granularity is fine enough.
 	 */
@@ -548,41 +593,6 @@ static void __init numa_init_array(void)
 	}
 }
 
-static void __init numa_clear_kernel_node_hotplug(void)
-{
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
-	struct memblock_region *r;
-
-	/*
-	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
-	 */
-	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
-	}
-
-	/* Mark all kernel nodes. */
-	for_each_memblock(reserved, r)
-		node_set(r->nid, numa_kernel_nodes);
-
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
-	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
-
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
-
-		memblock_clear_hotplug(start, end - start);
-	}
-}
-
 static int __init numa_init(int (*init_func)(void))
 {
 	int i;
@@ -637,15 +647,6 @@ static int __init numa_init(int (*init_func)(void))
 	}
 	numa_init_array();
 
-	/*
-	 * At very early time, the kernel have to use some memory such as
-	 * loading the kernel image. We cannot prevent this anyway. So any
-	 * node the kernel resides in should be un-hotpluggable.
-	 *
-	 * And when we come here, numa_init() won't fail.
-	 */
-	numa_clear_kernel_node_hotplug();
-
 	return 0;
 }
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index d56cd1f515bd..3f627345d51c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -182,12 +182,17 @@ struct jit_context {
 	bool seen_ld_abs;
 };
 
+/* maximum number of bytes emitted while JITing one eBPF insn */
+#define BPF_MAX_INSN_SIZE	128
+#define BPF_INSN_SAFETY		64
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
 	struct bpf_insn *insn = bpf_prog->insnsi;
 	int insn_cnt = bpf_prog->len;
-	u8 temp[64];
+	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i;
 	int proglen = 0;
 	u8 *prog = temp;
@@ -225,7 +230,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	EMIT2(0x31, 0xc0); /* xor eax, eax */
 	EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
 
-	if (ctx->seen_ld_abs) {
+	if (seen_ld_abs) {
 		/* r9d : skb->len - skb->data_len (headlen)
 		 * r10 : skb->data
 		 */
@@ -685,7 +690,7 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
-			if (ctx->seen_ld_abs) {
+			if (seen_ld_abs) {
 				EMIT2(0x41, 0x52); /* push %r10 */
 				EMIT2(0x41, 0x51); /* push %r9 */
 				/* need to adjust jmp offset, since
@@ -699,7 +704,7 @@ xadd:			if (is_imm8(insn->off))
 				return -EINVAL;
 			}
 			EMIT1_off32(0xE8, jmp_offset);
-			if (ctx->seen_ld_abs) {
+			if (seen_ld_abs) {
 				EMIT2(0x41, 0x59); /* pop %r9 */
 				EMIT2(0x41, 0x5A); /* pop %r10 */
 			}
@@ -804,7 +809,8 @@ emit_jmp:
 			goto common_load;
 		case BPF_LD | BPF_ABS | BPF_W:
 			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load:		ctx->seen_ld_abs = true;
+common_load:
+			ctx->seen_ld_abs = seen_ld_abs = true;
 			jmp_offset = func - (image + addrs[i]);
 			if (!func || !is_simm32(jmp_offset)) {
 				pr_err("unsupported bpf func %d addr %p image %p\n",
@@ -878,6 +884,11 @@ common_load:		ctx->seen_ld_abs = true;
 		}
 
 		ilen = prog - temp;
+		if (ilen > BPF_MAX_INSN_SIZE) {
+			pr_err("bpf_jit_compile fatal insn size error\n");
+			return -EFAULT;
+		}
+
 		if (image) {
 			if (unlikely(proglen + ilen > oldproglen)) {
 				pr_err("bpf_jit_compile fatal error\n");
@@ -934,9 +945,11 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 			goto out;
 		}
 		if (image) {
-			if (proglen != oldproglen)
+			if (proglen != oldproglen) {
 				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
 				       proglen, oldproglen);
+				goto out;
+			}
 			break;
 		}
 		if (proglen == oldproglen) {
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/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 899dd2454256..f52e033557c9 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -18,8 +18,9 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 
 targets += kexec-purgatory.c
 
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
 quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = cat $(obj)/purgatory.ro | $(objtree)/scripts/basic/bin2c kexec_purgatory > $(obj)/kexec-purgatory.c
+      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
 
 $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
 	$(call if_changed,bin2c)
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index 54f8102ccde5..e59eef20647b 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -47,8 +47,6 @@ struct user_desc;
 
 #ifdef CONFIG_X86_32
 
-#define HOST_AUDIT_ARCH AUDIT_ARCH_I386
-
 extern int ptrace_get_thread_area(struct task_struct *child, int idx,
                                   struct user_desc __user *user_desc);
 
@@ -57,8 +55,6 @@ extern int ptrace_set_thread_area(struct task_struct *child, int idx,
 
 #else
 
-#define HOST_AUDIT_ARCH AUDIT_ARCH_X86_64
-
 #define PT_REGS_R8(r) UPT_R8(&(r)->regs)
 #define PT_REGS_R9(r) UPT_R9(&(r)->regs)
 #define PT_REGS_R10(r) UPT_R10(&(r)->regs)
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
new file mode 100644
index 000000000000..9fe77b7b5a0e
--- /dev/null
+++ b/arch/x86/um/asm/syscall.h
@@ -0,0 +1,15 @@
+#ifndef __UM_ASM_SYSCALL_H
+#define __UM_ASM_SYSCALL_H
+
+#include <uapi/linux/audit.h>
+
+static inline int syscall_get_arch(void)
+{
+#ifdef CONFIG_X86_32
+	return AUDIT_ARCH_I386;
+#else
+	return AUDIT_ARCH_X86_64;
+#endif
+}
+
+#endif /* __UM_ASM_SYSCALL_H */
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index 8d0c420465cc..fa4b8b9841ff 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -214,242 +214,3 @@ csum_partial:
 	ret
 				
 #endif
-
-/*
-unsigned int csum_partial_copy_generic (const char *src, char *dst,
-				  int len, int sum, int *src_err_ptr, int *dst_err_ptr)
- */ 
-
-/*
- * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- *	  DST definitions? It's damn hard to trigger all cases.  I hope I got
- *	  them all but there's no guarantee.
- */
-
-#define SRC(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE(9999b, 6001f)
-
-#define DST(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE(9999b, 6002f)
-
-.align 4
-
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
-#define ARGBASE 16		
-#define FP		12
-
-csum_partial_copy_generic_i386:
-	subl  $4,%esp	
-	pushl %edi
-	pushl %esi
-	pushl %ebx
-	movl ARGBASE+16(%esp),%eax	# sum
-	movl ARGBASE+12(%esp),%ecx	# len
-	movl ARGBASE+4(%esp),%esi	# src
-	movl ARGBASE+8(%esp),%edi	# dst
-
-	testl $2, %edi			# Check alignment. 
-	jz 2f				# Jump if alignment is ok.
-	subl $2, %ecx			# Alignment uses up two bytes.
-	jae 1f				# Jump if we had at least two bytes.
-	addl $2, %ecx			# ecx was < 2.  Deal with it.
-	jmp 4f
-SRC(1:	movw (%esi), %bx	)
-	addl $2, %esi
-DST(	movw %bx, (%edi)	)
-	addl $2, %edi
-	addw %bx, %ax	
-	adcl $0, %eax
-2:
-	movl %ecx, FP(%esp)
-	shrl $5, %ecx
-	jz 2f
-	testl %esi, %esi
-SRC(1:	movl (%esi), %ebx	)
-SRC(	movl 4(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 4(%edi)	)
-
-SRC(	movl 8(%esi), %ebx	)
-SRC(	movl 12(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 8(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 12(%edi)	)
-
-SRC(	movl 16(%esi), %ebx 	)
-SRC(	movl 20(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 16(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 20(%edi)	)
-
-SRC(	movl 24(%esi), %ebx	)
-SRC(	movl 28(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 24(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 28(%edi)	)
-
-	lea 32(%esi), %esi
-	lea 32(%edi), %edi
-	dec %ecx
-	jne 1b
-	adcl $0, %eax
-2:	movl FP(%esp), %edx
-	movl %edx, %ecx
-	andl $0x1c, %edx
-	je 4f
-	shrl $2, %edx			# This clears CF
-SRC(3:	movl (%esi), %ebx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
-	lea 4(%esi), %esi
-	lea 4(%edi), %edi
-	dec %edx
-	jne 3b
-	adcl $0, %eax
-4:	andl $3, %ecx
-	jz 7f
-	cmpl $2, %ecx
-	jb 5f
-SRC(	movw (%esi), %cx	)
-	leal 2(%esi), %esi
-DST(	movw %cx, (%edi)	)
-	leal 2(%edi), %edi
-	je 6f
-	shll $16,%ecx
-SRC(5:	movb (%esi), %cl	)
-DST(	movb %cl, (%edi)	)
-6:	addl %ecx, %eax
-	adcl $0, %eax
-7:
-5000:
-
-# Exception handler:
-.section .fixup, "ax"							
-
-6001:
-	movl ARGBASE+20(%esp), %ebx	# src_err_ptr
-	movl $-EFAULT, (%ebx)
-
-	# zero the complete destination - computing the rest
-	# is too much work 
-	movl ARGBASE+8(%esp), %edi	# dst
-	movl ARGBASE+12(%esp), %ecx	# len
-	xorl %eax,%eax
-	rep ; stosb
-
-	jmp 5000b
-
-6002:
-	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT,(%ebx)
-	jmp 5000b
-
-.previous
-
-	popl %ebx
-	popl %esi
-	popl %edi
-	popl %ecx			# equivalent to addl $4,%esp
-	ret	
-
-#else
-
-/* Version for PentiumII/PPro */
-
-#define ROUND1(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
-	addl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	; 
-
-#define ROUND(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
-	adcl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	;
-
-#define ARGBASE 12
-		
-csum_partial_copy_generic_i386:
-	pushl %ebx
-	pushl %edi
-	pushl %esi
-	movl ARGBASE+4(%esp),%esi	#src
-	movl ARGBASE+8(%esp),%edi	#dst	
-	movl ARGBASE+12(%esp),%ecx	#len
-	movl ARGBASE+16(%esp),%eax	#sum
-#	movl %ecx, %edx  
-	movl %ecx, %ebx  
-	movl %esi, %edx
-	shrl $6, %ecx     
-	andl $0x3c, %ebx  
-	negl %ebx
-	subl %ebx, %esi  
-	subl %ebx, %edi  
-	lea  -1(%esi),%edx
-	andl $-32,%edx
-	lea 3f(%ebx,%ebx), %ebx
-	testl %esi, %esi 
-	jmp *%ebx
-1:	addl $64,%esi
-	addl $64,%edi 
-	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
-	ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)	
-	ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)	
-	ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)	
-	ROUND (-16) ROUND(-12) ROUND(-8)  ROUND(-4)	
-3:	adcl $0,%eax
-	addl $64, %edx
-	dec %ecx
-	jge 1b
-4:	movl ARGBASE+12(%esp),%edx	#len
-	andl $3, %edx
-	jz 7f
-	cmpl $2, %edx
-	jb 5f
-SRC(	movw (%esi), %dx         )
-	leal 2(%esi), %esi
-DST(	movw %dx, (%edi)         )
-	leal 2(%edi), %edi
-	je 6f
-	shll $16,%edx
-5:
-SRC(	movb (%esi), %dl         )
-DST(	movb %dl, (%edi)         )
-6:	addl %edx, %eax
-	adcl $0, %eax
-7:
-.section .fixup, "ax"
-6001:	movl	ARGBASE+20(%esp), %ebx	# src_err_ptr	
-	movl $-EFAULT, (%ebx)
-	# zero the complete destination (computing the rest is too much work)
-	movl ARGBASE+8(%esp),%edi	# dst
-	movl ARGBASE+12(%esp),%ecx	# len
-	xorl %eax,%eax
-	rep; stosb
-	jmp 7b
-6002:	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT, (%ebx)
-	jmp  7b			
-.previous				
-
-	popl %esi
-	popl %edi
-	popl %ebx
-	ret
-				
-#undef ROUND
-#undef ROUND1		
-		
-#endif
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)