[PATCH] Change maxaligned_in_smp alignemnt macros to internodealigned_in_smp macros

____cacheline_maxaligned_in_smp is currently used to align critical structures
and avoid false sharing.  It uses per-arch L1_CACHE_SHIFT_MAX and people find
L1_CACHE_SHIFT_MAX useless.

However, we have been using ____cacheline_maxaligned_in_smp to align
structures on the internode cacheline size.  As per Andi's suggestion,
following patch kills ____cacheline_maxaligned_in_smp and introduces
INTERNODE_CACHE_SHIFT, which defaults to L1_CACHE_SHIFT for all arches.
Arches needing L3/Internode cacheline alignment can define
INTERNODE_CACHE_SHIFT in the arch asm/cache.h.  Patch replaces
____cacheline_maxaligned_in_smp with ____cacheline_internodealigned_in_smp

With this patch, L1_CACHE_SHIFT_MAX can be killed

Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/i386/kernel/init_task.c b/arch/i386/kernel/init_task.c
index 9caa8e8..cff95d1 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_maxaligned_in_smp = INIT_TSS;
+DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS;
 
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index 1a201a93..f3a9c78 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -19,7 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 
-DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp;
+DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
 #ifndef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86_64/kernel/init_task.c b/arch/x86_64/kernel/init_task.c
index e0ba5c1..ce31d90 100644
--- a/arch/x86_64/kernel/init_task.c
+++ b/arch/x86_64/kernel/init_task.c
@@ -44,6 +44,6 @@
  * 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_maxaligned_in_smp = INIT_TSS;
+DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_internodealigned_in_smp = INIT_TSS;
 
 #define ALIGN_TO_4K __attribute__((section(".data.init_task")))
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 0b7ecf3..ffe5221 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -45,12 +45,21 @@
 #endif /* CONFIG_SMP */
 #endif
 
-#if !defined(____cacheline_maxaligned_in_smp)
+/*
+ * The maximum alignment needed for some critical structures
+ * These could be inter-node cacheline sizes/L3 cacheline
+ * size etc.  Define this in asm/cache.h for your arch
+ */
+#ifndef INTERNODE_CACHE_SHIFT
+#define INTERNODE_CACHE_SHIFT L1_CACHE_SHIFT
+#endif
+
+#if !defined(____cacheline_internodealigned_in_smp)
 #if defined(CONFIG_SMP)
-#define ____cacheline_maxaligned_in_smp \
-	__attribute__((__aligned__(1 << (L1_CACHE_SHIFT_MAX))))
+#define ____cacheline_internodealigned_in_smp \
+	__attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))
 #else
-#define ____cacheline_maxaligned_in_smp
+#define ____cacheline_internodealigned_in_smp
 #endif
 #endif
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 7b6a6a5..4dd6694 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -801,7 +801,7 @@
 	unsigned dma;
 
 	void (*led_act)(void *data, int rw);
-} ____cacheline_maxaligned_in_smp ide_hwif_t;
+} ____cacheline_internodealigned_in_smp ide_hwif_t;
 
 /*
  *  internal ide interrupt handler type
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2a89c13..7e4ae6a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -38,7 +38,7 @@
 #if defined(CONFIG_SMP)
 struct zone_padding {
 	char x[0];
-} ____cacheline_maxaligned_in_smp;
+} ____cacheline_internodealigned_in_smp;
 #define ZONE_PADDING(name)	struct zone_padding name;
 #else
 #define ZONE_PADDING(name)
@@ -233,7 +233,7 @@
 	 * rarely used fields:
 	 */
 	char			*name;
-} ____cacheline_maxaligned_in_smp;
+} ____cacheline_internodealigned_in_smp;
 
 
 /*
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a471f3b..51747cd 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -65,7 +65,7 @@
 	long	cur;		/* Current batch number.                      */
 	long	completed;	/* Number of the last completed batch         */
 	int	next_pending;	/* Is the next batch already waiting?         */
-} ____cacheline_maxaligned_in_smp;
+} ____cacheline_internodealigned_in_smp;
 
 /* Is batch a before batch b ? */
 static inline int rcu_batch_before(long a, long b)
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 48d3bce..c9afc61 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -61,9 +61,9 @@
 	                              /* for current batch to proceed.        */
 };
 
-static struct rcu_state rcu_state ____cacheline_maxaligned_in_smp =
+static struct rcu_state rcu_state ____cacheline_internodealigned_in_smp =
 	  {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE };
-static struct rcu_state rcu_bh_state ____cacheline_maxaligned_in_smp =
+static struct rcu_state rcu_bh_state ____cacheline_internodealigned_in_smp =
 	  {.lock = SPIN_LOCK_UNLOCKED, .cpumask = CPU_MASK_NONE };
 
 DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
diff --git a/mm/sparse.c b/mm/sparse.c
index 72079b5..0a51f36 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -18,10 +18,10 @@
  */
 #ifdef CONFIG_SPARSEMEM_EXTREME
 struct mem_section *mem_section[NR_SECTION_ROOTS]
-	____cacheline_maxaligned_in_smp;
+	____cacheline_internodealigned_in_smp;
 #else
 struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
-	____cacheline_maxaligned_in_smp;
+	____cacheline_internodealigned_in_smp;
 #endif
 EXPORT_SYMBOL(mem_section);