x86: Replace __get_cpu_var uses

__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

arch/x86/kernel/kvm.c

@@ -243,9 +243,9 @@ 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 +318,7 @@ 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 +329,13 @@ 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 +344,8 @@ 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 +356,11 @@ 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());
@@ -716,7 +716,7 @@ __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();