powerpc: Replace __get_cpu_var uses

This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.

V2->V2
  - Fix up to work against 3.18-rc1

__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 :

__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)

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
      assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 11 insertions, 11 deletions

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 7505599..9f8ea61 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -458,9 +458,9 @@ static inline void clear_irq_work_pending(void)
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()	__this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
 #endif /* 32 vs 64 bit */
 
@@ -482,8 +482,8 @@ void arch_irq_work_raise(void)
 static void __timer_interrupt(void)
 {
 	struct pt_regs *regs = get_irq_regs();
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
 	u64 now;
 
 	trace_timer_interrupt_entry(regs);
@@ -498,7 +498,7 @@ static void __timer_interrupt(void)
 		*next_tb = ~(u64)0;
 		if (evt->event_handler)
 			evt->event_handler(evt);
-		__get_cpu_var(irq_stat).timer_irqs_event++;
+		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
 		if (now <= DECREMENTER_MAX)
@@ -506,13 +506,13 @@ static void __timer_interrupt(void)
 		/* We may have raced with new irq work */
 		if (test_irq_work_pending())
 			set_dec(1);
-		__get_cpu_var(irq_stat).timer_irqs_others++;
+		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 
 #ifdef CONFIG_PPC64
 	/* collect purr register values often, for accurate calculations */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		cu->current_tb = mfspr(SPRN_PURR);
 	}
 #endif
@@ -527,7 +527,7 @@ static void __timer_interrupt(void)
 void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -813,7 +813,7 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
+	__this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt);
 	set_dec(evt);
 
 	/* We may have raced with new irq work */
@@ -833,7 +833,7 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 /* Interrupt handler for the timer broadcast IPI */
 void tick_broadcast_ipi_handler(void)
 {
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	*next_tb = get_tb_or_rtc();
 	__timer_interrupt();