use the new percpu interface for shared data
Currently most of the per cpu data, which is accessed by different cpus,
has a ____cacheline_aligned_in_smp attribute. Move all this data to the
new per cpu shared data section: .data.percpu.shared_aligned.
This will seperate the percpu data which is referenced frequently by other
cpus from the local only percpu data.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/arch/i386/kernel/init_task.c b/arch/i386/kernel/init_task.c
index cff95d1..d26fc06 100644
--- a/arch/i386/kernel/init_task.c
+++ b/arch/i386/kernel/init_task.c
@@ -42,5 +42,5 @@
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
* no more per-task TSS's.
*/
-DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index d2daf67..ba44d40 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -21,7 +21,7 @@
#include <asm/apic.h>
#include <asm/uaccess.h>
-DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);
DEFINE_PER_CPU(struct pt_regs *, irq_regs);
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index b3a47f9..9f72838 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -82,7 +82,7 @@
#define IPI_KDUMP_CPU_STOP 3
/* This needs to be cacheline aligned because it is written to by *other* CPUs. */
-static DEFINE_PER_CPU(u64, ipi_operation) ____cacheline_aligned;
+static DEFINE_PER_CPU_SHARED_ALIGNED(u64, ipi_operation);
extern void cpu_halt (void);
diff --git a/arch/x86_64/kernel/init_task.c b/arch/x86_64/kernel/init_task.c
index 3dc5854..4ff33d4 100644
--- a/arch/x86_64/kernel/init_task.c
+++ b/arch/x86_64/kernel/init_task.c
@@ -44,7 +44,7 @@
* section. Since TSS's are completely CPU-local, we want them
* on exact cacheline boundaries, to eliminate cacheline ping-pong.
*/
-DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
/* Copies of the original ist values from the tss are only accessed during
* debugging, no special alignment required.
diff --git a/kernel/sched.c b/kernel/sched.c
index cb31fb4..645256b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -301,7 +301,7 @@
struct lock_class_key rq_lock_key;
};
-static DEFINE_PER_CPU(struct rq, runqueues) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
static DEFINE_MUTEX(sched_hotcpu_mutex);
static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)