powerpc: Optimise per cpu accesses on 64bit

Now we dynamically allocate the paca array, it takes an extra load
whenever we want to access another cpu's paca. One place we do that a lot
is per cpu variables. A simple example:

DEFINE_PER_CPU(unsigned long, vara);
unsigned long test4(int cpu)
{
	return per_cpu(vara, cpu);
}

This takes 4 loads, 5 if you include the actual load of the per cpu variable:

    ld r11,-32760(r30)  # load address of paca pointer
    ld r9,-32768(r30)   # load link address of percpu variable
    sldi r3,r29,9       # get offset into paca (each entry is 512 bytes)
    ld r0,0(r11)        # load paca pointer
    add r3,r0,r3        # paca + offset
    ld r11,64(r3)       # load paca[cpu].data_offset

    ldx r3,r9,r11       # load per cpu variable

If we remove the ppc64 specific per_cpu_offset(), we get the generic one
which indexes into a statically allocated array. This removes one load and
one add:

    ld r11,-32760(r30)  # load address of __per_cpu_offset
    ld r9,-32768(r30)   # load link address of percpu variable
    sldi r3,r29,3       # get offset into __per_cpu_offset (each entry 8 bytes)
    ldx r11,r11,r3      # load __per_cpu_offset[cpu]

    ldx r3,r9,r11       # load per cpu variable

Having all the offsets in one array also helps when iterating over a per cpu
variable across a number of cpus, such as in the scheduler. Before we would
need to load one paca cacheline when calculating each per cpu offset. Now we
have 16 (128 / sizeof(long)) per cpu offsets in each cacheline.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/include/asm/percpu.h

 #ifndef _ASM_POWERPC_PERCPU_H_
 #define _ASM_POWERPC_PERCPU_H_
 #ifdef __powerpc64__
-#include <linux/compiler.h>
 
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
@@ -12,9 +11,7 @@
 
 #include <asm/paca.h>
 
-#define __per_cpu_offset(cpu) (paca[cpu].data_offset)
 #define __my_cpu_offset local_paca->data_offset
-#define per_cpu_offset(x) (__per_cpu_offset(x))
 
 #endif /* CONFIG_SMP */
 #endif /* __powerpc64__ */

arch/powerpc/kernel/asm-offsets.c

@@ -194,7 +194,6 @@ int main(void)
 	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
-	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu));

arch/powerpc/kernel/setup_64.c

@@ -600,6 +600,9 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 		return REMOTE_DISTANCE;
 }
 
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
 void __init setup_per_cpu_areas(void)
 {
 	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
@@ -624,8 +627,10 @@ void __init setup_per_cpu_areas(void)
 		panic("cannot initialize percpu area (err=%d)", rc);
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
-	for_each_possible_cpu(cpu)
-		paca[cpu].data_offset = delta + pcpu_unit_offsets[cpu];
+	for_each_possible_cpu(cpu) {
+                __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+		paca[cpu].data_offset = __per_cpu_offset[cpu];
+	}
 }
 #endif