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>

4 files changed, 12 insertions, 12 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0cb11fb5008..2628ee556756 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)