block: 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.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

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)

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-iopoll.c

@@ -35,7 +35,7 @@ void blk_iopoll_sched(struct blk_iopoll *iop)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll));
+	list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
 	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 	local_irq_restore(flags);
 }
@@ -79,7 +79,7 @@ EXPORT_SYMBOL(blk_iopoll_complete);
 
 static void blk_iopoll_softirq(struct softirq_action *h)
 {
-	struct list_head *list = &__get_cpu_var(blk_cpu_iopoll);
+	struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll);
 	int rearm = 0, budget = blk_iopoll_budget;
 	unsigned long start_time = jiffies;
 
@@ -201,7 +201,7 @@ static int blk_iopoll_cpu_notify(struct notifier_block *self,
 
 		local_irq_disable();
 		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
-				 &__get_cpu_var(blk_cpu_iopoll));
+				 this_cpu_ptr(&blk_cpu_iopoll));
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 		local_irq_enable();
 	}

block/blk-softirq.c

@@ -23,7 +23,7 @@ static void blk_done_softirq(struct softirq_action *h)
 	struct list_head *cpu_list, local_list;
 
 	local_irq_disable();
-	cpu_list = &__get_cpu_var(blk_cpu_done);
+	cpu_list = this_cpu_ptr(&blk_cpu_done);
 	list_replace_init(cpu_list, &local_list);
 	local_irq_enable();
 
@@ -44,7 +44,7 @@ static void trigger_softirq(void *data)
 	struct list_head *list;
 
 	local_irq_save(flags);
-	list = &__get_cpu_var(blk_cpu_done);
+	list = this_cpu_ptr(&blk_cpu_done);
 	list_add_tail(&rq->csd.list, list);
 
 	if (list->next == &rq->csd.list)
@@ -90,7 +90,7 @@ static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
 
 		local_irq_disable();
 		list_splice_init(&per_cpu(blk_cpu_done, cpu),
-				 &__get_cpu_var(blk_cpu_done));
+				 this_cpu_ptr(&blk_cpu_done));
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 		local_irq_enable();
 	}
@@ -135,7 +135,7 @@ void __blk_complete_request(struct request *req)
 	if (ccpu == cpu || shared) {
 		struct list_head *list;
 do_local:
-		list = &__get_cpu_var(blk_cpu_done);
+		list = this_cpu_ptr(&blk_cpu_done);
 		list_add_tail(&req->csd.list, list);
 
 		/*

fs/fscache/object.c

@@ -796,7 +796,7 @@ void fscache_enqueue_object(struct fscache_object *object)
  */
 bool fscache_object_sleep_till_congested(signed long *timeoutp)
 {
-	wait_queue_head_t *cong_wq = &__get_cpu_var(fscache_object_cong_wait);
+	wait_queue_head_t *cong_wq = this_cpu_ptr(&fscache_object_cong_wait);
 	DEFINE_WAIT(wait);
 
 	if (fscache_object_congested())