powerpc: 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)

tj: Folded a fix patch.
    http://lkml.kernel.org/g/alpine.DEB.2.11.1408172143020.9652@gentwo.org

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 9 insertions, 7 deletions

diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h
index 1bbb3013d6aa..8d907ba4fd05 100644
--- a/arch/powerpc/include/asm/hardirq.h
+++ b/arch/powerpc/include/asm/hardirq.h
@@ -21,7 +21,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define __ARCH_IRQ_STAT
 
-#define local_softirq_pending() __get_cpu_var(irq_stat).__softirq_pending
+#define local_softirq_pending() __this_cpu_read(irq_stat.__softirq_pending)
+#define set_softirq_pending(x) __this_cpu_write(irq_stat._softirq_pending, (x))
+#define or_softirq_pending(x) __this_cpu_or(irq_stat._softirq_pending, (x))
 
 static inline void ack_bad_irq(unsigned int irq)
 {
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 2def01ed0cb2..cd7c2719d3ef 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -107,14 +107,14 @@ extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
 
 static inline void arch_enter_lazy_mmu_mode(void)
 {
-        struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+        struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 
         batch->active = 1;
 }
 
 static inline void arch_leave_lazy_mmu_mode(void)
 {
-        struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+        struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 
         if (batch->index)
                 __flush_tlb_pending(batch);
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 282d43a0c855..5007ad0448ce 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -97,7 +97,7 @@ DECLARE_PER_CPU(struct xics_cppr, xics_cppr);
 
 static inline void xics_push_cppr(unsigned int vec)
 {
-        struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+        struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
         if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1))
                 return;
@@ -110,7 +110,7 @@ static inline void xics_push_cppr(unsigned int vec)
 
 static inline unsigned char xics_pop_cppr(void)
 {
-        struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+        struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
         if (WARN_ON(os_cppr->index < 1))
                 return LOWEST_PRIORITY;
@@ -120,7 +120,7 @@ static inline unsigned char xics_pop_cppr(void)
 
 static inline void xics_set_base_cppr(unsigned char cppr)
 {
-        struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+        struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
         /* we only really want to set the priority when there's
          * just one cppr value on the stack
@@ -132,7 +132,7 @@ static inline void xics_set_base_cppr(unsigned char cppr)
 
 static inline unsigned char xics_cppr_top(void)
 {
-        struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+        struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
         
         return os_cppr->stack[os_cppr->index];
 }