percpu: convert most archs to dynamic percpu, take#2

index 1581ff2..bbe5b2c 100644
@@ -34,7 +34,7 @@
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)

@@ -80,7 +80,7 @@ extern ssize_t __init pcpu_embed_first_chunk(
 
 extern void *__alloc_reserved_percpu(size_t size, size_t align);
 
-#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 struct percpu_data {
 	void *ptrs[1];

@@ -94,11 +94,15 @@ struct percpu_data {
         (__typeof__(ptr))__p->ptrs[(cpu)];				\
 })
 
-#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 extern void *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void *__pdata);
 
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+extern void __init setup_per_cpu_areas(void);
+#endif
+
 #else /* CONFIG_SMP */
 
 #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })

@@ -119,6 +123,8 @@ static inline void free_percpu(void *p)
 	kfree(p);
 }
 
+static inline void __init setup_per_cpu_areas(void) { }
+
 #endif /* CONFIG_SMP */
 
 #define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \

index d721dad..adb46ee 100644
@@ -355,7 +355,6 @@ static void __init smp_init(void)
 #define smp_init()	do { } while (0)
 #endif
 
-static inline void setup_per_cpu_areas(void) { }
 static inline void setup_nr_cpu_ids(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 

@@ -376,29 +375,6 @@ static void __init setup_nr_cpu_ids(void)
 	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
 }
 
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_offset);
-
-static void __init setup_per_cpu_areas(void)
-{
-	unsigned long size, i;
-	char *ptr;
-	unsigned long nr_possible_cpus = num_possible_cpus();
-
-	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
-	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
-	for_each_possible_cpu(i) {
-		__per_cpu_offset[i] = ptr - __per_cpu_start;
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-		ptr += size;
-	}
-}
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
-
 /* Called by boot processor to activate the rest. */
 static void __init smp_init(void)
 {

index e797812..1559bd0 100644
@@ -359,7 +359,7 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 
 static void *percpu_modalloc(unsigned long size, unsigned long align,
 			     const char *name)

@@ -384,7 +384,7 @@ static void percpu_modfree(void *freeme)
 	free_percpu(freeme);
 }
 
-#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 /* Number of blocks used and allocated. */
 static unsigned int pcpu_num_used, pcpu_num_allocated;

@@ -519,7 +519,7 @@ static int percpu_modinit(void)
 }
 __initcall(percpu_modinit);
 
-#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 				 Elf_Shdr *sechdrs,

index dfdee6a..df34cea 100644
@@ -5,6 +5,8 @@
  */
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/bootmem.h>
+#include <asm/sections.h>
 
 #ifndef cache_line_size
 #define cache_line_size()	L1_CACHE_BYTES

@@ -147,3 +149,29 @@ void free_percpu(void *__pdata)
 	kfree(__percpu_disguise(__pdata));
 }
 EXPORT_SYMBOL_GPL(free_percpu);
+
+/*
+ * Generic percpu area setup.
+ */
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+
+EXPORT_SYMBOL(__per_cpu_offset);
+
+void __init setup_per_cpu_areas(void)
+{
+	unsigned long size, i;
+	char *ptr;
+	unsigned long nr_possible_cpus = num_possible_cpus();
+
+	/* Copy section for each CPU (we discard the original) */
+	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
+	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
+
+	for_each_possible_cpu(i) {
+		__per_cpu_offset[i] = ptr - __per_cpu_start;
+		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		ptr += size;
+	}
+}
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */

index f780bee..d9b4059 100644
@@ -43,7 +43,7 @@
  *
  * To use this allocator, arch code should do the followings.
  *
- * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+ * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
  *
  * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
  *   regular address to percpu pointer and back if they need to be

@@ -1276,3 +1276,41 @@ ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
 				      reserved_size, dyn_size,
 				      pcpue_unit_size, pcpue_ptr, NULL);
 }
+
+/*
+ * Generic percpu area setup.
+ *
+ * The embedding helper is used because its behavior closely resembles
+ * the original non-dynamic generic percpu area setup.  This is
+ * important because many archs have addressing restrictions and might
+ * fail if the percpu area is located far away from the previous
+ * location.  As an added bonus, in non-NUMA cases, embedding is
+ * generally a good idea TLB-wise because percpu area can piggy back
+ * on the physical linear memory mapping which uses large page
+ * mappings on applicable archs.
+ */
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+void __init setup_per_cpu_areas(void)
+{
+	size_t static_size = __per_cpu_end - __per_cpu_start;
+	ssize_t unit_size;
+	unsigned long delta;
+	unsigned int cpu;
+
+	/*
+	 * Always reserve area for module percpu variables.  That's
+	 * what the legacy allocator did.
+	 */
+	unit_size = pcpu_embed_first_chunk(static_size, PERCPU_MODULE_RESERVE,
+					   PERCPU_DYNAMIC_RESERVE, -1);
+	if (unit_size < 0)
+		panic("Failed to initialized percpu areas.");
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset[cpu] = delta + cpu * unit_size;
+}
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */

index 5230eaa..3e0840c 100644
@@ -58,7 +58,7 @@ static struct local_tlb_flush_counts {
 	unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned short, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
+static DEFINE_PER_CPU(unsigned short [NR_CPUS], shadow_flush_counts) ____cacheline_aligned;
 
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1

index e456f06..ece1bf9 100644
@@ -71,7 +71,7 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 DEFINE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
 EXPORT_PER_CPU_SYMBOL(__sn_hub_info);
 
-DEFINE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
+DEFINE_PER_CPU(short [MAX_COMPACT_NODES], __sn_cnodeid_to_nasid);
 EXPORT_PER_CPU_SYMBOL(__sn_cnodeid_to_nasid);
 
 DEFINE_PER_CPU(struct nodepda_s *, __sn_nodepda);

index 98cd1dc..6e9b69c 100644
@@ -31,7 +31,7 @@ struct stab_entry {
 
 #define NR_STAB_CACHE_ENTRIES 8
 static DEFINE_PER_CPU(long, stab_cache_ptr);
-static DEFINE_PER_CPU(long, stab_cache[NR_STAB_CACHE_ENTRIES]);
+static DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
 
 /*
  * Create a segment table entry for the given esid/vsid pair.

index a0927a3..6fcc499 100644
@@ -43,7 +43,7 @@ static irqreturn_t ipi_function_handler(int irq, void *msg)
   */
 
 #define MSG_COUNT 4
-static DEFINE_PER_CPU(unsigned int, ps3_ipi_virqs[MSG_COUNT]);
+static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs);
 
 static const char *names[MSG_COUNT] = {
 	"ipi call",

index 46e29ab..66f7471 100644
@@ -30,8 +30,8 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 
-static DEFINE_PER_CPU(struct cpu_cpuX_base, cpu_arr[CPU_REG_ALL_BIT]);
-static DEFINE_PER_CPU(struct cpu_private *, priv_arr[MAX_CPU_FILES]);
+static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
+static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
 static DEFINE_PER_CPU(unsigned, cpu_modelflag);
 static DEFINE_PER_CPU(int, cpu_priv_count);
 static DEFINE_PER_CPU(unsigned, cpu_model);

index 56dde9c..9fd9bf6 100644
@@ -69,7 +69,7 @@ struct threshold_bank {
 	struct threshold_block *blocks;
 	cpumask_var_t cpus;
 };
-static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
+static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
 
 #ifdef CONFIG_SMP
 static unsigned char shared_bank[NR_BANKS] = {

index 30963af..228a8bb 100644
@@ -47,10 +47,10 @@
 static DEFINE_SPINLOCK(irq_mapping_update_lock);
 
 /* IRQ <-> VIRQ mapping. */
-static DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]) = {[0 ... NR_VIRQS-1] = -1};
+static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 
 /* IRQ <-> IPI mapping */
-static DEFINE_PER_CPU(int, ipi_to_irq[XEN_NR_IPIS]) = {[0 ... XEN_NR_IPIS-1] = -1};
+static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
 
 /* Interrupt types. */
 enum xen_irq_type {

index e66d07d..6eedf7e 100644
@@ -19,7 +19,7 @@
 #include <linux/module.h>
 #include <linux/quicklist.h>
 
-DEFINE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK];
+DEFINE_PER_CPU(struct quicklist [CONFIG_NR_QUICK], quicklist);
 
 #define FRACTION_OF_NODE_MEM	16
 

index 65ffda5..fbcf929 100644
@@ -1987,8 +1987,8 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
  */
 #define NR_KMEM_CACHE_CPU 100
 
-static DEFINE_PER_CPU(struct kmem_cache_cpu,
-				kmem_cache_cpu)[NR_KMEM_CACHE_CPU];
+static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU],
+		      kmem_cache_cpu);
 
 static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
 static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);

index b35a950..ce629ed 100644
@@ -37,7 +37,7 @@ __initcall(init_syncookies);
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-static DEFINE_PER_CPU(__u32, cookie_scratch)[16 + 5 + SHA_WORKSPACE_WORDS];
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], cookie_scratch);
 
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)

index 711175e..4d995fe 100644
@@ -74,7 +74,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	return child;
 }
 
-static DEFINE_PER_CPU(__u32, cookie_scratch)[16 + 5 + SHA_WORKSPACE_WORDS];
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], cookie_scratch);
 
 static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)

index 72ba08d..00de1a0 100644
@@ -17,7 +17,7 @@ extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
  * registers like cr3 on the i386
  */
 
-extern volatile DEFINE_PER_CPU(pgd_t *,current_pgd); /* defined in arch/cris/mm/fault.c */
+DECLARE_PER_CPU(pgd_t *,current_pgd); /* defined in arch/cris/mm/fault.c */
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {

index c48fa67..96ff4d1 100644
@@ -146,7 +146,7 @@ enum arq_state {
 #define RQ_STATE(rq)	((enum arq_state)(rq)->elevator_private2)
 #define RQ_SET_STATE(rq, state)	((rq)->elevator_private2 = (void *) state)
 
-static DEFINE_PER_CPU(unsigned long, ioc_count);
+static DEFINE_PER_CPU(unsigned long, as_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 

@@ -161,7 +161,7 @@ static void as_antic_stop(struct as_data *ad);
 static void free_as_io_context(struct as_io_context *aic)
 {
 	kfree(aic);
-	elv_ioc_count_dec(ioc_count);
+	elv_ioc_count_dec(as_ioc_count);
 	if (ioc_gone) {
 		/*
 		 * AS scheduler is exiting, grab exit lock and check

@@ -169,7 +169,7 @@ static void free_as_io_context(struct as_io_context *aic)
 		 * complete ioc_gone and set it back to NULL.
 		 */
 		spin_lock(&ioc_gone_lock);
-		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+		if (ioc_gone && !elv_ioc_count_read(as_ioc_count)) {
 			complete(ioc_gone);
 			ioc_gone = NULL;
 		}

@@ -211,7 +211,7 @@ static struct as_io_context *alloc_as_io_context(void)
 		ret->seek_total = 0;
 		ret->seek_samples = 0;
 		ret->seek_mean = 0;
-		elv_ioc_count_inc(ioc_count);
+		elv_ioc_count_inc(as_ioc_count);
 	}
 
 	return ret;

@@ -1509,7 +1509,7 @@ static void __exit as_exit(void)
 	ioc_gone = &all_gone;
 	/* ioc_gone's update must be visible before reading ioc_count */
 	smp_wmb();
-	if (elv_ioc_count_read(ioc_count))
+	if (elv_ioc_count_read(as_ioc_count))
 		wait_for_completion(&all_gone);
 	synchronize_rcu();
 }

index a55a9bd..deea748 100644
@@ -48,7 +48,7 @@ static int cfq_slice_idle = HZ / 125;
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
 
-static DEFINE_PER_CPU(unsigned long, ioc_count);
+static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 

@@ -1423,7 +1423,7 @@ static void cfq_cic_free_rcu(struct rcu_head *head)
 	cic = container_of(head, struct cfq_io_context, rcu_head);
 
 	kmem_cache_free(cfq_ioc_pool, cic);
-	elv_ioc_count_dec(ioc_count);
+	elv_ioc_count_dec(cfq_ioc_count);
 
 	if (ioc_gone) {
 		/*

@@ -1432,7 +1432,7 @@ static void cfq_cic_free_rcu(struct rcu_head *head)
 		 * complete ioc_gone and set it back to NULL
 		 */
 		spin_lock(&ioc_gone_lock);
-		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
+		if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) {
 			complete(ioc_gone);
 			ioc_gone = NULL;
 		}

@@ -1558,7 +1558,7 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
 		INIT_HLIST_NODE(&cic->cic_list);
 		cic->dtor = cfq_free_io_context;
 		cic->exit = cfq_exit_io_context;
-		elv_ioc_count_inc(ioc_count);
+		elv_ioc_count_inc(cfq_ioc_count);
 	}
 
 	return cic;

@@ -2663,7 +2663,7 @@ static void __exit cfq_exit(void)
 	 * this also protects us from entering cfq_slab_kill() with
 	 * pending RCU callbacks
 	 */
-	if (elv_ioc_count_read(ioc_count))
+	if (elv_ioc_count_read(cfq_ioc_count))
 		wait_for_completion(&all_gone);
 	cfq_slab_kill();
 }

index 7a74d17..8191d04 100644
@@ -80,7 +80,7 @@ struct cpu_dbs_info_s {
 	int cpu;
 	unsigned int enable:1;
 };
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
+static DEFINE_PER_CPU(struct cpu_dbs_info_s, cs_cpu_dbs_info);
 
 static unsigned int dbs_enable;	/* number of CPUs using this policy */
 

@@ -153,7 +153,7 @@ dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		     void *data)
 {
 	struct cpufreq_freqs *freq = data;
-	struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cpu_dbs_info,
+	struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cs_cpu_dbs_info,
 							freq->cpu);
 
 	struct cpufreq_policy *policy;

@@ -326,7 +326,7 @@ static ssize_t store_ignore_nice_load(struct cpufreq_policy *policy,
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
 		struct cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(cpu_dbs_info, j);
+		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
 		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
 						&dbs_info->prev_cpu_wall);
 		if (dbs_tuners_ins.ignore_nice)

@@ -416,7 +416,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 		cputime64_t cur_wall_time, cur_idle_time;
 		unsigned int idle_time, wall_time;
 
-		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		j_dbs_info = &per_cpu(cs_cpu_dbs_info, j);
 
 		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
 

@@ -556,7 +556,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	unsigned int j;
 	int rc;
 
-	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+	this_dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
 
 	switch (event) {
 	case CPUFREQ_GOV_START:

@@ -576,7 +576,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 		for_each_cpu(j, policy->cpus) {
 			struct cpu_dbs_info_s *j_dbs_info;
-			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info = &per_cpu(cs_cpu_dbs_info, j);
 			j_dbs_info->cur_policy = policy;
 
 			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,

index e741c33..04de476 100644
@@ -87,7 +87,7 @@ struct cpu_dbs_info_s {
 	unsigned int enable:1,
 		sample_type:1;
 };
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
+static DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info);
 
 static unsigned int dbs_enable;	/* number of CPUs using this policy */
 

@@ -165,7 +165,8 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 	unsigned int freq_hi, freq_lo;
 	unsigned int index = 0;
 	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, policy->cpu);
+	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
+						   policy->cpu);
 
 	if (!dbs_info->freq_table) {
 		dbs_info->freq_lo = 0;

@@ -210,7 +211,7 @@ static void ondemand_powersave_bias_init(void)
 {
 	int i;
 	for_each_online_cpu(i) {
-		struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, i);
+		struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, i);
 		dbs_info->freq_table = cpufreq_frequency_get_table(i);
 		dbs_info->freq_lo = 0;
 	}

@@ -325,7 +326,7 @@ static ssize_t store_ignore_nice_load(struct cpufreq_policy *policy,
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
 		struct cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(cpu_dbs_info, j);
+		dbs_info = &per_cpu(od_cpu_dbs_info, j);
 		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
 						&dbs_info->prev_cpu_wall);
 		if (dbs_tuners_ins.ignore_nice)

@@ -419,7 +420,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 		unsigned int load, load_freq;
 		int freq_avg;
 
-		j_dbs_info = &per_cpu(cpu_dbs_info, j);
+		j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
 
 		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
 

@@ -576,7 +577,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	unsigned int j;
 	int rc;
 
-	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
+	this_dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 
 	switch (event) {
 	case CPUFREQ_GOV_START:

@@ -598,7 +599,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 		for_each_cpu(j, policy->cpus) {
 			struct cpu_dbs_info_s *j_dbs_info;
-			j_dbs_info = &per_cpu(cpu_dbs_info, j);
+			j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
 			j_dbs_info->cur_policy = policy;
 
 			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,

index 228a8bb..dbfed85 100644
@@ -596,6 +596,8 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static DEFINE_PER_CPU(unsigned, xed_nesting_count);
+
 /*
  * Search the CPUs pending events bitmasks.  For each one found, map
  * the event number to an irq, and feed it into do_IRQ() for

@@ -611,7 +613,6 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	struct shared_info *s = HYPERVISOR_shared_info;
 	struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);
-	static DEFINE_PER_CPU(unsigned, nesting_count);
  	unsigned count;
 
 	exit_idle();

@@ -622,7 +623,7 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 
 		vcpu_info->evtchn_upcall_pending = 0;
 
-		if (__get_cpu_var(nesting_count)++)
+		if (__get_cpu_var(xed_nesting_count)++)
 			goto out;
 
 #ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */

@@ -647,8 +648,8 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 
 		BUG_ON(!irqs_disabled());
 
-		count = __get_cpu_var(nesting_count);
-		__get_cpu_var(nesting_count) = 0;
+		count = __get_cpu_var(xed_nesting_count);
+		__get_cpu_var(xed_nesting_count) = 0;
 	} while(count != 1);
 
 out:

index bb553c3..0e0c9de 100644
@@ -606,6 +606,8 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite)
 	}
 }
 
+static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
+
 /**
  * balance_dirty_pages_ratelimited_nr - balance dirty memory state
  * @mapping: address_space which was dirtied

@@ -623,7 +625,6 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite)
 void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 					unsigned long nr_pages_dirtied)
 {
-	static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
 	unsigned long ratelimit;
 	unsigned long *p;
 

@@ -636,7 +637,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	 * tasks in balance_dirty_pages(). Period.
 	 */
 	preempt_disable();
-	p =  &__get_cpu_var(ratelimits);
+	p =  &__get_cpu_var(bdp_ratelimits);
 	*p += nr_pages_dirtied;
 	if (unlikely(*p >= ratelimit)) {
 		*p = 0;

index ce629ed..a3c045c 100644
@@ -37,12 +37,13 @@ __initcall(init_syncookies);
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], cookie_scratch);
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
+		      ipv4_cookie_scratch);
 
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)
 {
-	__u32 *tmp = __get_cpu_var(cookie_scratch);
+	__u32 *tmp = __get_cpu_var(ipv4_cookie_scratch);
 
 	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
 	tmp[0] = (__force u32)saddr;

index 4d995fe..e2bcff0 100644
@@ -74,12 +74,13 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	return child;
 }
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], cookie_scratch);
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
+		      ipv6_cookie_scratch);
 
 static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)
 {
-	__u32 *tmp = __get_cpu_var(cookie_scratch);
+	__u32 *tmp = __get_cpu_var(ipv6_cookie_scratch);
 
 	/*
 	 * we have 320 bits of information to hash, copy in the remaining

index 72ba08d..476cd9e 100644
@@ -17,7 +17,8 @@ extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
  * registers like cr3 on the i386
  */
 
-extern volatile DEFINE_PER_CPU(pgd_t *,current_pgd); /* defined in arch/cris/mm/fault.c */
+/* defined in arch/cris/mm/fault.c */
+extern DEFINE_PER_CPU(pgd_t *, current_pgd);
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {

index c4c76db..84d22ae 100644
@@ -29,7 +29,7 @@ extern void die_if_kernel(const char *, struct pt_regs *, long);
 
 /* current active page directory */
 
-volatile DEFINE_PER_CPU(pgd_t *,current_pgd);
+DEFINE_PER_CPU(pgd_t *, current_pgd);
 unsigned long cris_signal_return_page;
 
 /*

index 6014dfd..eb1026e 100644
@@ -50,7 +50,7 @@ struct ipi_data {
 	unsigned long bits;
 };
 
-static DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
+DEFINE_PER_CPU(struct ipi_data, ipi_data) = {
 	.lock	= SPIN_LOCK_UNLOCKED,
 };
 

index 1c01d13..4afd165 100644
@@ -24,7 +24,7 @@
 #include <mach/hardware.h>
 #include <asm/irq.h>
 
-static DEFINE_PER_CPU(struct clock_event_device, local_clockevent);
+DEFINE_PER_CPU(struct clock_event_device, local_clockevent);
 
 /*
  * Used on SMP for either the local timer or IPI_TIMER

index e84faff..fbc8c92 100644
@@ -18,7 +18,7 @@
 #include <asm/setup.h>
 #include <asm/sysreg.h>
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 #ifdef CONFIG_PERFORMANCE_COUNTERS
 

index 93eab61..0527cba 100644
@@ -93,7 +93,7 @@ struct ipi_message_queue {
 	unsigned long count;
 };
 
-static DEFINE_PER_CPU(struct ipi_message_queue, ipi_msg_queue);
+DEFINE_PER_CPU(struct ipi_message_queue, ipi_msg_queue);
 
 static void ipi_cpu_stop(unsigned int cpu)
 {

index 530d139..e954244 100644
@@ -42,9 +42,9 @@
 #include <asm/mem_map.h>
 #include "blackfin_sram.h"
 
-static DEFINE_PER_CPU(spinlock_t, l1sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_data_sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_inst_sram_lock) ____cacheline_aligned_in_smp;
+DEFINE_PER_CPU(spinlock_t, l1sram_lock) ____cacheline_aligned_in_smp;
+DEFINE_PER_CPU(spinlock_t, l1_data_sram_lock) ____cacheline_aligned_in_smp;
+DEFINE_PER_CPU(spinlock_t, l1_inst_sram_lock) ____cacheline_aligned_in_smp;
 static spinlock_t l2_sram_lock ____cacheline_aligned_in_smp;
 
 /* the data structure for L1 scratchpad and DATA SRAM */

@@ -55,22 +55,22 @@ struct sram_piece {
 	struct sram_piece *next;
 };
 
-static DEFINE_PER_CPU(struct sram_piece, free_l1_ssram_head);
-static DEFINE_PER_CPU(struct sram_piece, used_l1_ssram_head);
+DEFINE_PER_CPU(struct sram_piece, free_l1_ssram_head);
+DEFINE_PER_CPU(struct sram_piece, used_l1_ssram_head);
 
 #if L1_DATA_A_LENGTH != 0
-static DEFINE_PER_CPU(struct sram_piece, free_l1_data_A_sram_head);
-static DEFINE_PER_CPU(struct sram_piece, used_l1_data_A_sram_head);
+DEFINE_PER_CPU(struct sram_piece, free_l1_data_A_sram_head);
+DEFINE_PER_CPU(struct sram_piece, used_l1_data_A_sram_head);
 #endif
 
 #if L1_DATA_B_LENGTH != 0
-static DEFINE_PER_CPU(struct sram_piece, free_l1_data_B_sram_head);
-static DEFINE_PER_CPU(struct sram_piece, used_l1_data_B_sram_head);
+DEFINE_PER_CPU(struct sram_piece, free_l1_data_B_sram_head);
+DEFINE_PER_CPU(struct sram_piece, used_l1_data_B_sram_head);
 #endif
 
 #if L1_CODE_LENGTH != 0
-static DEFINE_PER_CPU(struct sram_piece, free_l1_inst_sram_head);
-static DEFINE_PER_CPU(struct sram_piece, used_l1_inst_sram_head);
+DEFINE_PER_CPU(struct sram_piece, free_l1_inst_sram_head);
+DEFINE_PER_CPU(struct sram_piece, used_l1_inst_sram_head);
 #endif
 
 #if L2_LENGTH != 0

index f065093..9ba4aa4 100644
@@ -50,7 +50,7 @@ final_note(void *buf)
 
 extern void ia64_dump_cpu_regs(void *);
 
-static DEFINE_PER_CPU(struct elf_prstatus, elf_prstatus);
+DEFINE_PER_CPU(struct elf_prstatus, elf_prstatus);
 
 void
 crash_save_this_cpu(void)

index 3e0840c..0681840 100644
@@ -58,7 +58,7 @@ static struct local_tlb_flush_counts {
 	unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned short [NR_CPUS], shadow_flush_counts) ____cacheline_aligned;
+DEFINE_PER_CPU(unsigned short [NR_CPUS], shadow_flush_counts) ____cacheline_aligned;
 
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1

@@ -66,7 +66,7 @@ static DEFINE_PER_CPU(unsigned short [NR_CPUS], shadow_flush_counts) ____cacheli
 #define IPI_KDUMP_CPU_STOP	3
 
 /* This needs to be cacheline aligned because it is written to by *other* CPUs.  */
-static DEFINE_PER_CPU_SHARED_ALIGNED(u64, ipi_operation);
+DEFINE_PER_CPU_SHARED_ALIGNED(u64, ipi_operation);
 
 extern void cpu_halt (void);
 

index f0cda76..08274f1 100644
@@ -276,7 +276,7 @@ struct fpu_swa_msg {
 	unsigned long count;
 	unsigned long time;
 };
-static DEFINE_PER_CPU(struct fpu_swa_msg, cpulast);
+DEFINE_PER_CPU(struct fpu_swa_msg, cpulast);
 DECLARE_PER_CPU(struct fpu_swa_msg, cpulast);
 static struct fpu_swa_msg last __cacheline_aligned;
 

index d20a5db..64d414f 100644
@@ -59,7 +59,7 @@ static long vp_env_info;
 
 static struct kvm_vmm_info *kvm_vmm_info;
 
-static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
+DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }

index af93aad..92e2c2f 100644
@@ -63,19 +63,19 @@ xen_free_irq_vector(int vector)
 }
 
 
-static DEFINE_PER_CPU(int, timer_irq) = -1;
-static DEFINE_PER_CPU(int, ipi_irq) = -1;
-static DEFINE_PER_CPU(int, resched_irq) = -1;
-static DEFINE_PER_CPU(int, cmc_irq) = -1;
-static DEFINE_PER_CPU(int, cmcp_irq) = -1;
-static DEFINE_PER_CPU(int, cpep_irq) = -1;
+DEFINE_PER_CPU(int, timer_irq) = -1;
+DEFINE_PER_CPU(int, ipi_irq) = -1;
+DEFINE_PER_CPU(int, resched_irq) = -1;
+DEFINE_PER_CPU(int, cmc_irq) = -1;
+DEFINE_PER_CPU(int, cmcp_irq) = -1;
+DEFINE_PER_CPU(int, cpep_irq) = -1;
 #define NAME_SIZE	15
-static DEFINE_PER_CPU(char[NAME_SIZE], timer_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], ipi_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], resched_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cmc_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cmcp_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cpep_name);
+DEFINE_PER_CPU(char[NAME_SIZE], timer_name);
+DEFINE_PER_CPU(char[NAME_SIZE], ipi_name);
+DEFINE_PER_CPU(char[NAME_SIZE], resched_name);
+DEFINE_PER_CPU(char[NAME_SIZE], cmc_name);
+DEFINE_PER_CPU(char[NAME_SIZE], cmcp_name);
+DEFINE_PER_CPU(char[NAME_SIZE], cpep_name);
 #undef NAME_SIZE
 
 struct saved_irq {

index a5182a2..cf43bc7 100644
@@ -103,9 +103,9 @@ static irqreturn_t sibyte_counter_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static DEFINE_PER_CPU(struct clock_event_device, sibyte_hpt_clockevent);
-static DEFINE_PER_CPU(struct irqaction, sibyte_hpt_irqaction);
-static DEFINE_PER_CPU(char [18], sibyte_hpt_name);
+DEFINE_PER_CPU(struct clock_event_device, sibyte_hpt_clockevent);
+DEFINE_PER_CPU(struct irqaction, sibyte_hpt_irqaction);
+DEFINE_PER_CPU(char [18], sibyte_hpt_name);
 
 void __cpuinit sb1480_clockevent_init(void)
 {

index 340f53e..e3c7dce 100644
@@ -101,9 +101,9 @@ static irqreturn_t sibyte_counter_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static DEFINE_PER_CPU(struct clock_event_device, sibyte_hpt_clockevent);
-static DEFINE_PER_CPU(struct irqaction, sibyte_hpt_irqaction);
-static DEFINE_PER_CPU(char [18], sibyte_hpt_name);
+DEFINE_PER_CPU(struct clock_event_device, sibyte_hpt_clockevent);
+DEFINE_PER_CPU(struct irqaction, sibyte_hpt_irqaction);
+DEFINE_PER_CPU(char [18], sibyte_hpt_name);
 
 void __cpuinit sb1250_clockevent_init(void)
 {

index 660e44e..38f9a0b 100644
@@ -5,7 +5,7 @@
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static int __init topology_init(void)
 {

index f10a7cd..af7379d 100644
@@ -84,8 +84,8 @@ static void rt_set_mode(enum clock_event_mode mode,
 
 int rt_timer_irq;
 
-static DEFINE_PER_CPU(struct clock_event_device, hub_rt_clockevent);
-static DEFINE_PER_CPU(char [11], hub_rt_name);
+DEFINE_PER_CPU(struct clock_event_device, hub_rt_clockevent);
+DEFINE_PER_CPU(char [11], hub_rt_name);
 
 static irqreturn_t hub_rt_counter_handler(int irq, void *dev_id)
 {

index 4ea4229..f32c727 100644
@@ -50,7 +50,7 @@ static volatile unsigned long cpu_eiem = 0;
 ** between ->ack() and ->end() of the interrupt to prevent
 ** re-interruption of a processing interrupt.
 */
-static DEFINE_PER_CPU(unsigned long, local_ack_eiem) = ~0UL;
+DEFINE_PER_CPU(unsigned long, local_ack_eiem) = ~0UL;
 
 static void cpu_disable_irq(unsigned int irq)
 {

index f515938..4f61986 100644
@@ -22,7 +22,7 @@
 #include <linux/cpu.h>
 #include <linux/cache.h>
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static int __init topology_init(void)
 {

index bb37b1d..ec89cdc 100644
@@ -113,7 +113,7 @@ struct cache {
 	struct cache *next_local;      /* next cache of >= level */
 };
 
-static DEFINE_PER_CPU(struct cache_dir *, cache_dir_pcpu);
+DEFINE_PER_CPU(struct cache_dir *, cache_dir_pcpu);
 
 /* traversal/modification of this list occurs only at cpu hotplug time;
  * access is serialized by cpu hotplug locking

index 7b44a33..a1fc420 100644
@@ -274,7 +274,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address,
 	force_sig_info(SIGTRAP, &info, current);
 }
 
-static DEFINE_PER_CPU(unsigned long, current_dabr);
+DEFINE_PER_CPU(unsigned long, current_dabr);
 
 int set_dabr(unsigned long dabr)
 {

index f41aec8..d5d4925 100644
@@ -25,7 +25,7 @@
 #include <asm/lppaca.h>
 #endif
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 /*
  * SMT snooze delay stuff, 64-bit only for now

@@ -119,7 +119,7 @@ __setup("smt-snooze-delay=", setup_smt_snooze_delay);
  * it the first time we write to the PMCs.
  */
 
-static DEFINE_PER_CPU(char, pmcs_enabled);
+DEFINE_PER_CPU(char, pmcs_enabled);
 
 void ppc_enable_pmcs(void)
 {

index 48571ac..d0c72a7 100644
@@ -122,7 +122,7 @@ struct decrementer_clock {
 	u64 next_tb;
 };
 
-static DEFINE_PER_CPU(struct decrementer_clock, decrementers);
+DEFINE_PER_CPU(struct decrementer_clock, decrementers);
 
 #ifdef CONFIG_PPC_ISERIES
 static unsigned long __initdata iSeries_recal_titan;

@@ -172,7 +172,7 @@ EXPORT_SYMBOL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
 
 static u64 tb_last_jiffy __cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(u64, last_jiffy);
+DEFINE_PER_CPU(u64, last_jiffy);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /*

@@ -298,7 +298,7 @@ struct cpu_purr_data {
  * each others' cpu_purr_data, disabling local interrupts is
  * sufficient to serialize accesses.
  */
-static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
+DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
 
 static void snapshot_tb_and_purr(void *data)
 {

index ae1d67c..5454968 100644
@@ -30,7 +30,7 @@
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
+DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
 static unsigned long pte_freelist_forced_free;
 
 struct pte_freelist_batch

index 6e9b69c..0124998 100644
@@ -30,8 +30,8 @@ struct stab_entry {
 };
 
 #define NR_STAB_CACHE_ENTRIES 8
-static DEFINE_PER_CPU(long, stab_cache_ptr);
-static DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
+DEFINE_PER_CPU(long, stab_cache_ptr);
+DEFINE_PER_CPU(long [NR_STAB_CACHE_ENTRIES], stab_cache);
 
 /*
  * Create a segment table entry for the given esid/vsid pair.

index ae06c62..424e263 100644
@@ -139,7 +139,7 @@ static struct {
 #define GET_COUNT_CYCLES(x) (x & 0x00000001)
 #define GET_INPUT_CONTROL(x) ((x & 0x00000004) >> 2)
 
-static DEFINE_PER_CPU(unsigned long[NR_PHYS_CTRS], pmc_values);
+DEFINE_PER_CPU(unsigned long[NR_PHYS_CTRS], pmc_values);
 static unsigned long spu_pm_cnt[MAX_NUMNODES * NUM_SPUS_PER_NODE];
 static struct pmc_cntrl_data pmc_cntrl[NUM_THREADS][NR_PHYS_CTRS];
 

index 968c1c0..beee12e 100644
@@ -37,7 +37,7 @@ struct spu_gov_info_struct {
 	struct delayed_work work;
 	unsigned int poll_int;		/* µs */
 };
-static DEFINE_PER_CPU(struct spu_gov_info_struct, spu_gov_info);
+DEFINE_PER_CPU(struct spu_gov_info_struct, spu_gov_info);
 
 static struct workqueue_struct *kspugov_wq;
 

index 882e470..2b1d1bd 100644
@@ -54,7 +54,7 @@ struct iic {
 	struct device_node *node;
 };
 
-static DEFINE_PER_CPU(struct iic, iic);
+DEFINE_PER_CPU(struct iic, iic);
 #define IIC_NODE_COUNT	2
 static struct irq_host *iic_host;
 

index 8ec5ccf..fe5499e 100644
@@ -90,7 +90,7 @@ struct ps3_private {
 	u64 thread_id;
 };
 
-static DEFINE_PER_CPU(struct ps3_private, ps3_private);
+DEFINE_PER_CPU(struct ps3_private, ps3_private);
 
 /**
  * ps3_chip_mask - Set an interrupt mask bit in ps3_bmp.

index 6fcc499..29539b1 100644
@@ -43,7 +43,7 @@ static irqreturn_t ipi_function_handler(int irq, void *msg)
   */
 
 #define MSG_COUNT 4
-static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs);
+DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs);
 
 static const char *names[MSG_COUNT] = {
 	"ipi call",

index ab69925..9da02d5 100644
@@ -54,7 +54,7 @@ struct dtl {
 	int			buf_entries;
 	u64			last_idx;
 };
-static DEFINE_PER_CPU(struct dtl, dtl);
+DEFINE_PER_CPU(struct dtl, dtl);
 
 /*
  * Dispatch trace log event mask:

index 3ee01b4..c250cb4 100644
@@ -140,7 +140,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
-static DEFINE_PER_CPU(u64 *, tce_page) = NULL;
+DEFINE_PER_CPU(u64 *, tce_page) = NULL;
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,

index 1dfc710..23a0bac 100644
@@ -80,7 +80,7 @@ static struct ctl_table appldata_dir_table[] = {
 /*
  * Timer
  */
-static DEFINE_PER_CPU(struct vtimer_list, appldata_timer);
+DEFINE_PER_CPU(struct vtimer_list, appldata_timer);
 static atomic_t appldata_expire_count = ATOMIC_INIT(0);
 
 static DEFINE_SPINLOCK(appldata_timer_lock);

index 28cf196..9ae4930 100644
@@ -27,7 +27,7 @@ struct mcck_struct {
 	unsigned long long mcck_code;
 };
 
-static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
+DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
 
 static NORET_TYPE void s390_handle_damage(char *msg)
 {

index a985a3b..ef32579 100644
@@ -66,7 +66,7 @@ int smp_cpu_polarization[NR_CPUS];
 static int smp_cpu_state[NR_CPUS];
 static int cpu_management;
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static void smp_ext_bitcall(int, ec_bit_sig);
 

index ef596d0..6a91235 100644
@@ -65,7 +65,7 @@ u64 sched_clock_base_cc = -1;	/* Force to data section. */
 static ext_int_info_t ext_int_info_cc;
 static ext_int_info_t ext_int_etr_cc;
 
-static DEFINE_PER_CPU(struct clock_event_device, comparators);
+DEFINE_PER_CPU(struct clock_event_device, comparators);
 
 /*
  * Scheduler clock - returns current time in nanosec units.

@@ -340,7 +340,7 @@ static unsigned long long adjust_time(unsigned long long old,
 	return delta;
 }
 
-static DEFINE_PER_CPU(atomic_t, clock_sync_word);
+DEFINE_PER_CPU(atomic_t, clock_sync_word);
 static DEFINE_MUTEX(clock_sync_mutex);
 static unsigned long clock_sync_flags;
 

index c87f59b..1e73fb7 100644
@@ -27,7 +27,7 @@
 
 static ext_int_info_t ext_int_info_timer;
 
-static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer);
+DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer);
 
 DEFINE_PER_CPU(struct s390_idle_data, s390_idle) = {
 	.lock = __SPIN_LOCK_UNLOCKED(s390_idle.lock)

index 96e8eae..1339dcb 100644
@@ -24,7 +24,7 @@
 #include <linux/clockchips.h>
 #include <linux/irq.h>
 
-static DEFINE_PER_CPU(struct clock_event_device, local_clockevent);
+DEFINE_PER_CPU(struct clock_event_device, local_clockevent);
 
 /*
  * Used on SMP for either the local timer or SMP_MSG_TIMER

index 0838942..743dee7 100644
@@ -14,7 +14,7 @@
 #include <linux/node.h>
 #include <linux/nodemask.h>
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static int __init topology_init(void)
 {

index 2c0cc72..24d4243 100644
@@ -39,9 +39,9 @@ EXPORT_SYMBOL_GPL(nmi_usable);
 
 static unsigned int nmi_hz = HZ;
 
-static DEFINE_PER_CPU(unsigned int, last_irq_sum);
-static DEFINE_PER_CPU(local_t, alert_counter);
-static DEFINE_PER_CPU(int, nmi_touch);
+DEFINE_PER_CPU(unsigned int, last_irq_sum);
+DEFINE_PER_CPU(local_t, alert_counter);
+DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
 {

index 5db5ebe..4f86704 100644
@@ -41,7 +41,7 @@ struct iommu_batch {
 	unsigned long	npages;		/* Number of pages in list.	*/
 };
 
-static DEFINE_PER_CPU(struct iommu_batch, iommu_batch);
+DEFINE_PER_CPU(struct iommu_batch, iommu_batch);
 static int iommu_batch_initialized;
 
 /* Interrupts must be disabled.  */

index d28f496..fa55243 100644
@@ -12,7 +12,7 @@
 #include <asm/hypervisor.h>
 #include <asm/spitfire.h>
 
-static DEFINE_PER_CPU(struct hv_mmu_statistics, mmu_stats) __attribute__((aligned(64)));
+DEFINE_PER_CPU(struct hv_mmu_statistics, mmu_stats) __attribute__((aligned(64)));
 
 #define SHOW_MMUSTAT_ULONG(NAME) \
 static ssize_t show_##NAME(struct sys_device *dev, \

@@ -217,7 +217,7 @@ static struct sysdev_attribute cpu_core_attrs[] = {
 	_SYSDEV_ATTR(l2_cache_line_size,  0444, show_l2_cache_line_size, NULL),
 };
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static void register_cpu_online(unsigned int cpu)
 {

index 5c12e79..3416f4a 100644
@@ -630,7 +630,7 @@ struct freq_table {
 	unsigned long clock_tick_ref;
 	unsigned int ref_freq;
 };
-static DEFINE_PER_CPU(struct freq_table, sparc64_freq_table) = { 0, 0 };
+DEFINE_PER_CPU(struct freq_table, sparc64_freq_table) = { 0, 0 };
 
 unsigned long sparc64_get_clock_tick(unsigned int cpu)
 {

@@ -716,7 +716,7 @@ static struct clock_event_device sparc64_clockevent = {
 	.shift		= 30,
 	.irq		= -1,
 };
-static DEFINE_PER_CPU(struct clock_event_device, sparc64_events);
+DEFINE_PER_CPU(struct clock_event_device, sparc64_events);
 
 void timer_interrupt(int irq, struct pt_regs *regs)
 {

index f287092..d4e1c16 100644
@@ -173,7 +173,7 @@ static struct clock_event_device lapic_clockevent = {
 	.rating		= 100,
 	.irq		= -1,
 };
-static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
+DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
 static unsigned long apic_phys;
 

index ce4fbfa..81fff0e 100644
@@ -56,7 +56,7 @@ EXPORT_SYMBOL(nmi_watchdog);
 static int panic_on_timeout;
 
 static unsigned int nmi_hz = HZ;
-static DEFINE_PER_CPU(short, wd_enabled);
+DEFINE_PER_CPU(short, wd_enabled);
 static int endflag __initdata;
 
 static inline unsigned int get_nmi_count(int cpu)

@@ -360,9 +360,9 @@ void stop_apic_nmi_watchdog(void *unused)
  * [when there will be more tty-related locks, break them up here too!]
  */
 
-static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(local_t, alert_counter);
-static DEFINE_PER_CPU(int, nmi_touch);
+DEFINE_PER_CPU(unsigned, last_irq_sum);
+DEFINE_PER_CPU(local_t, alert_counter);
+DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
 {

index 77848d9..5770059 100644
@@ -997,7 +997,7 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
 	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
 	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ])
 	__aligned(PAGE_SIZE);
 

index 66f7471..1a97ae7 100644
@@ -30,11 +30,11 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 
-static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
-static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
-static DEFINE_PER_CPU(unsigned, cpu_modelflag);
-static DEFINE_PER_CPU(int, cpu_priv_count);
-static DEFINE_PER_CPU(unsigned, cpu_model);
+DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpu_arr);
+DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], priv_arr);
+DEFINE_PER_CPU(unsigned, cpu_modelflag);
+DEFINE_PER_CPU(int, cpu_priv_count);
+DEFINE_PER_CPU(unsigned, cpu_model);
 
 static DEFINE_MUTEX(cpu_debug_lock);
 

index 208ecf6..5cf61ea 100644
@@ -69,13 +69,13 @@ struct acpi_cpufreq_data {
 	unsigned int cpu_feature;
 };
 
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
 struct acpi_msr_data {
 	u64 saved_aperf, saved_mperf;
 };
 
-static DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
+DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
 
 DEFINE_TRACE(power_mark);
 

index f6b32d1..ab2a342 100644
@@ -49,7 +49,7 @@
 /* serialize freq changes  */
 static DEFINE_MUTEX(fidvid_mutex);
 
-static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
+DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static int cpu_family = CPU_OPTERON;
 

index c9f1fdc..6e57f01 100644
@@ -71,8 +71,8 @@ static int centrino_verify_cpu_id(const struct cpuinfo_x86 *c,
 				  const struct cpu_id *x);
 
 /* Operating points for current CPU */
-static DEFINE_PER_CPU(struct cpu_model *, centrino_model);
-static DEFINE_PER_CPU(const struct cpu_id *, centrino_cpu);
+DEFINE_PER_CPU(struct cpu_model *, centrino_model);
+DEFINE_PER_CPU(const struct cpu_id *, centrino_cpu);
 
 static struct cpufreq_driver centrino_driver;
 

index 483eda9..3a4261d 100644
@@ -502,7 +502,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SYSFS
 
 /* pointer to _cpuid4_info array (for each cache leaf) */
-static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
+DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP

@@ -620,7 +620,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
 
 /* pointer to kobject for cpuX/cache */
-static DEFINE_PER_CPU(struct kobject *, cache_kobject);
+DEFINE_PER_CPU(struct kobject *, cache_kobject);
 
 struct _index_kobject {
 	struct kobject kobj;

@@ -629,7 +629,7 @@ struct _index_kobject {
 };
 
 /* pointer to array of kobjects for cpuX/cache/indexY */
-static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
+DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
 #define INDEX_KOBJECT_PTR(x, y)		(&((per_cpu(index_kobject, x))[y]))
 
 #define show_one_plus(file_name, object, val)				\

index 6fb0b35..5785175 100644
@@ -453,9 +453,9 @@ void mce_log_therm_throt_event(__u64 status)
  */
 
 static int check_interval = 5 * 60; /* 5 minutes */
-static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
+DEFINE_PER_CPU(int, next_interval); /* in jiffies */
 static void mcheck_timer(unsigned long);
-static DEFINE_PER_CPU(struct timer_list, mce_timer);
+DEFINE_PER_CPU(struct timer_list, mce_timer);
 
 static void mcheck_timer(unsigned long data)
 {

index 9fd9bf6..a4d7a81 100644
@@ -69,7 +69,7 @@ struct threshold_bank {
 	struct threshold_block *blocks;
 	cpumask_var_t cpus;
 };
-static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
+DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
 
 #ifdef CONFIG_SMP
 static unsigned char shared_bank[NR_BANKS] = {

@@ -77,7 +77,7 @@ static unsigned char shared_bank[NR_BANKS] = {
 };
 #endif
 
-static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
+DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
 static void amd_threshold_interrupt(void);
 

index cef3ee3..007b542 100644
@@ -95,7 +95,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
  * Also supports reliable discovery of shared banks.
  */
 
-static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
+DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
 
 /*
  * cmci_discover_lock protects against parallel discovery attempts

index d5ae224..42a85e1 100644
@@ -25,8 +25,8 @@
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL              (300 * HZ)
 
-static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
-static DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
+DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
+DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
 atomic_t therm_throt_en = ATOMIC_INIT(0);
 
 #ifdef CONFIG_SYSFS

index f6c70a1..ea636fa 100644
@@ -60,7 +60,7 @@ static const struct wd_ops *wd_ops;
 static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS);
 static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS);
 
-static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
+DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
 
 /* converts an msr to an appropriate reservation bit */
 static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)

index 87b67e3..a1d487c 100644
@@ -46,7 +46,7 @@ struct ds_configuration {
 	 * by enum ds_feature */
 	unsigned long ctl[dsf_ctl_max];
 };
-static DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
+DEFINE_PER_CPU(struct ds_configuration, ds_cfg_array);
 
 #define ds_cfg per_cpu(ds_cfg_array, smp_processor_id())
 

@@ -228,7 +228,7 @@ struct ds_context {
 	struct task_struct *task;
 };
 
-static DEFINE_PER_CPU(struct ds_context *, system_context_array);
+DEFINE_PER_CPU(struct ds_context *, system_context_array);
 
 #define system_context per_cpu(system_context_array, smp_processor_id())
 

index 81408b9..c76488d 100644
@@ -409,7 +409,7 @@ static int hpet_legacy_next_event(unsigned long delta,
  */
 #ifdef CONFIG_PCI_MSI
 
-static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
+DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev	*hpet_devs;
 
 void hpet_msi_unmask(unsigned int irq)

index 3b09634..85827e3 100644
@@ -58,11 +58,11 @@ union irq_ctx {
 	u32                     stack[THREAD_SIZE/sizeof(u32)];
 } __attribute__((aligned(PAGE_SIZE)));
 
-static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
-static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
+DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
+DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack);
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack);
+DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack);
+DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack);
 
 static void call_on_stack(void *func, void *stack)
 {

index 33019dd..acffaf2 100644
@@ -36,7 +36,7 @@ struct kvm_para_state {
 	enum paravirt_lazy_mode mode;
 };
 
-static DEFINE_PER_CPU(struct kvm_para_state, para_state);
+DEFINE_PER_CPU(struct kvm_para_state, para_state);
 
 static struct kvm_para_state *kvm_para_state(void)
 {

index 223af43..abe4ab8 100644
@@ -36,7 +36,7 @@ static int parse_no_kvmclock(char *arg)
 early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
+DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
 static struct pvclock_wall_clock wall_clock;
 
 /*

index 9faf43b..f889b91 100644
@@ -244,7 +244,7 @@ int paravirt_disable_iospace(void)
 	return request_resource(&ioport_resource, &reserve_ioports);
 }
 
-static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
 
 static inline void enter_lazy(enum paravirt_lazy_mode mode)
 {

index b751a41..4abbc34 100644
@@ -62,7 +62,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
 DEFINE_PER_CPU(unsigned long, old_rsp);
-static DEFINE_PER_CPU(unsigned char, is_idle);
+DEFINE_PER_CPU(unsigned char, is_idle);
 
 unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
 

index 58d24ef..19f8b7f 100644
@@ -84,7 +84,7 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 };
  * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
  * removed after init for !CONFIG_HOTPLUG_CPU.
  */
-static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
+DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
 #else

index ed0c337..0252522 100644
@@ -30,8 +30,8 @@ static int			uv_partition_base_pnode __read_mostly;
 
 static unsigned long		uv_mmask __read_mostly;
 
-static DEFINE_PER_CPU(struct ptc_stats, ptcstats);
-static DEFINE_PER_CPU(struct bau_control, bau_control);
+DEFINE_PER_CPU(struct ptc_stats, ptcstats);
+DEFINE_PER_CPU(struct bau_control, bau_control);
 
 /*
  * Determine the first node on a blade.

@@ -305,7 +305,7 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode,
 	return NULL;
 }
 
-static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
+DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
 
 /**
  * uv_flush_tlb_others - globally purge translation cache of a virtual

index 7e45159..a5d2d41 100644
@@ -31,7 +31,7 @@
 #include <linux/smp.h>
 #include <asm/cpu.h>
 
-static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
+DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
 
 #ifdef CONFIG_HOTPLUG_CPU
 int __ref arch_register_cpu(int num)

index 583f11d..73c9287 100644
@@ -54,7 +54,7 @@ static struct clock_event_device clock_event_device_uv = {
 	.event_handler	= NULL,
 };
 
-static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
+DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
 
 /* There is one of these allocated per node */
 struct uv_rtc_timer_head {

index 2b3eb82..2cbc815 100644
@@ -37,7 +37,7 @@
 #define VMI_ONESHOT  (VMI_ALARM_IS_ONESHOT  | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
 #define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
 
-static DEFINE_PER_CPU(struct clock_event_device, local_events);
+DEFINE_PER_CPU(struct clock_event_device, local_events);
 
 static inline u32 vmi_counter(u32 flags)
 {

index 1f8510c..f0b596c 100644
@@ -111,7 +111,7 @@ struct svm_cpu_data {
 	struct page *save_area;
 };
 
-static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
+DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
 static uint32_t svm_features;
 
 struct svm_init_data {

index bb48133..d9ebe9b 100644
@@ -107,9 +107,9 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 static int init_rmode(struct kvm *kvm);
 static u64 construct_eptp(unsigned long root_hpa);
 
-static DEFINE_PER_CPU(struct vmcs *, vmxarea);
-static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
-static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu);
+DEFINE_PER_CPU(struct vmcs *, vmxarea);
+DEFINE_PER_CPU(struct vmcs *, current_vmcs);
+DEFINE_PER_CPU(struct list_head, vcpus_on_cpu);
 
 static struct page *vmx_io_bitmap_a;
 static struct page *vmx_io_bitmap_b;

index 3944e91..00e8a6b 100644
@@ -622,7 +622,7 @@ static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *
 		 hv_clock->tsc_to_system_mul);
 }
 
-static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
+DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
 
 static void kvm_write_guest_time(struct kvm_vcpu *v)
 {

index 50dc802..d7ce69c 100644
@@ -72,7 +72,7 @@ static struct list_head *kmmio_page_list(unsigned long page)
 }
 
 /* Accessed per-cpu */
-static DEFINE_PER_CPU(struct kmmio_context, kmmio_ctx);
+DEFINE_PER_CPU(struct kmmio_context, kmmio_ctx);
 
 /*
  * this is basically a dynamic stabbing problem:

index c9342ed..4b143e8 100644
@@ -53,8 +53,8 @@ struct remap_trace {
 };
 
 /* Accessed per-cpu. */
-static DEFINE_PER_CPU(struct trap_reason, pf_reason);
-static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
+DEFINE_PER_CPU(struct trap_reason, pf_reason);
+DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
 
 static DEFINE_MUTEX(mmiotrace_mutex);
 static DEFINE_SPINLOCK(trace_lock);

index 202864a..ea53f07 100644
@@ -25,8 +25,8 @@
 #include "op_x86_model.h"
 
 static struct op_x86_model_spec const *model;
-static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
-static DEFINE_PER_CPU(unsigned long, saved_lvtpc);
+DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
+DEFINE_PER_CPU(unsigned long, saved_lvtpc);
 
 /* 0 == registered but off, 1 == registered and on */
 static int nmi_enabled = 0;

index f09e8c3..72af3ed 100644
@@ -443,7 +443,7 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
 }
 
 /* Locations of each CPU's IDT */
-static DEFINE_PER_CPU(struct desc_ptr, idt_desc);
+DEFINE_PER_CPU(struct desc_ptr, idt_desc);
 
 /* Set an IDT entry.  If the entry is part of the current IDT, then
    also update Xen. */

index 8bff7e7..3fba46a 100644
@@ -49,7 +49,7 @@ struct mc_buffer {
 	unsigned mcidx, argidx, cbidx;
 };
 
-static DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
+DEFINE_PER_CPU(struct mc_buffer, mc_buffer);
 DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 /* flush reasons 0- slots, 1- args, 2- callbacks */

index 429834e..e6ed68b 100644
@@ -35,10 +35,10 @@
 
 cpumask_var_t xen_cpu_initialized_map;
 
-static DEFINE_PER_CPU(int, resched_irq);
-static DEFINE_PER_CPU(int, callfunc_irq);
-static DEFINE_PER_CPU(int, callfuncsingle_irq);
-static DEFINE_PER_CPU(int, debug_irq) = -1;
+DEFINE_PER_CPU(int, resched_irq);
+DEFINE_PER_CPU(int, callfunc_irq);
+DEFINE_PER_CPU(int, callfuncsingle_irq);
+DEFINE_PER_CPU(int, debug_irq) = -1;
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
 static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);

index 5601506..75be10d 100644
@@ -147,8 +147,8 @@ static int xen_spin_trylock(struct raw_spinlock *lock)
 	return old == 0;
 }
 
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);
+DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);
 
 /*
  * Mark a cpu as interested in a lock.  Returns the CPU's previous

index 0a5aa44..eca663a 100644
@@ -31,14 +31,14 @@
 #define NS_PER_TICK	(1000000000LL / HZ)
 
 /* runstate info updated by Xen */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
+DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
 
 /* snapshots of runstate info */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate_snapshot);
+DEFINE_PER_CPU(struct vcpu_runstate_info, runstate_snapshot);
 
 /* unused ns of stolen and blocked time */
-static DEFINE_PER_CPU(u64, residual_stolen);
-static DEFINE_PER_CPU(u64, residual_blocked);
+DEFINE_PER_CPU(u64, residual_stolen);
+DEFINE_PER_CPU(u64, residual_blocked);
 
 /* return an consistent snapshot of 64-bit time/counter value */
 static u64 get64(const u64 *p)

@@ -403,7 +403,7 @@ static const struct clock_event_device xen_vcpuop_clockevent = {
 
 static const struct clock_event_device *xen_clockevent =
 	&xen_timerop_clockevent;
-static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events);
+DEFINE_PER_CPU(struct clock_event_device, xen_clock_events);
 
 static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
 {

index 96ff4d1..59c6935 100644
@@ -146,7 +146,7 @@ enum arq_state {
 #define RQ_STATE(rq)	((enum arq_state)(rq)->elevator_private2)
 #define RQ_SET_STATE(rq, state)	((rq)->elevator_private2 = (void *) state)
 
-static DEFINE_PER_CPU(unsigned long, as_ioc_count);
+DEFINE_PER_CPU(unsigned long, as_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 

index ee9c216..412e064 100644
@@ -11,7 +11,7 @@
 
 #include "blk.h"
 
-static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
+DEFINE_PER_CPU(struct list_head, blk_cpu_done);
 
 /*
  * Softirq action handler - move entries to local list and loop over them

index deea748..0792ce6 100644
@@ -48,7 +48,7 @@ static int cfq_slice_idle = HZ / 125;
 static struct kmem_cache *cfq_pool;
 static struct kmem_cache *cfq_ioc_pool;
 
-static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
+DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
 static struct completion *ioc_gone;
 static DEFINE_SPINLOCK(ioc_gone_lock);
 

index 3bea38d..c208a1e 100644
@@ -27,7 +27,7 @@ struct sha512_ctx {
 	u8 buf[128];
 };
 
-static DEFINE_PER_CPU(u64[80], msg_schedule);
+DEFINE_PER_CPU(u64[80], msg_schedule);
 
 static inline u64 Ch(u64 x, u64 y, u64 z)
 {

index 45ad328..99d7820 100644
@@ -687,7 +687,7 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	return 0;
 }
 
-static DEFINE_PER_CPU(void *, processor_device_array);
+DEFINE_PER_CPU(void *, processor_device_array);
 
 static int __cpuinit acpi_processor_start(struct acpi_device *device)
 {

index 39838c6..0687f2e 100644
@@ -96,7 +96,7 @@ static int acpi_processor_apply_limit(struct acpi_processor *pr)
 #define CPUFREQ_THERMAL_MIN_STEP 0
 #define CPUFREQ_THERMAL_MAX_STEP 3
 
-static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
+DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
 static unsigned int acpi_thermal_cpufreq_is_init = 0;
 
 static int cpu_has_cpufreq(unsigned int cpu)

index e62a4cc..ef46a16 100644
@@ -18,7 +18,7 @@ struct sysdev_class cpu_sysdev_class = {
 };
 EXPORT_SYMBOL(cpu_sysdev_class);
 
-static DEFINE_PER_CPU(struct sys_device *, cpu_sys_devices);
+DEFINE_PER_CPU(struct sys_device *, cpu_sys_devices);
 
 #ifdef CONFIG_HOTPLUG_CPU
 static ssize_t show_online(struct sys_device *dev, struct sysdev_attribute *attr,

index 8c74448..612b9fc 100644
@@ -277,7 +277,7 @@ static int random_write_wakeup_thresh = 128;
 
 static int trickle_thresh __read_mostly = INPUT_POOL_WORDS * 28;
 
-static DEFINE_PER_CPU(int, trickle_count);
+DEFINE_PER_CPU(int, trickle_count);
 
 /*
  * A pool of size .poolwords is stirred with a primitive polynomial

index c5afc98..88f43c9 100644
@@ -38,7 +38,7 @@ static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
 static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
 
 /* proc_event_counts is used as the sequence number of the netlink message */
-static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
+DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
 
 static inline void get_seq(__u32 *ts, int *cpu)
 {

index 47d2ad0..b5088c4 100644
@@ -38,10 +38,10 @@
  * also protects the cpufreq_cpu_data array.
  */
 static struct cpufreq_driver *cpufreq_driver;
-static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
+DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 #ifdef CONFIG_HOTPLUG_CPU
 /* This one keeps track of the previously set governor of a removed CPU */
-static DEFINE_PER_CPU(struct cpufreq_governor *, cpufreq_cpu_governor);
+DEFINE_PER_CPU(struct cpufreq_governor *, cpufreq_cpu_governor);
 #endif
 static DEFINE_SPINLOCK(cpufreq_driver_lock);
 

@@ -62,8 +62,8 @@ static DEFINE_SPINLOCK(cpufreq_driver_lock);
  * - Governor routines that can be called in cpufreq hotplug path should not
  *   take this sem as top level hotplug notifier handler takes this.
  */
-static DEFINE_PER_CPU(int, policy_cpu);
-static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
+DEFINE_PER_CPU(int, policy_cpu);
+DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
 
 #define lock_policy_rwsem(mode, cpu)					\
 int lock_policy_rwsem_##mode						\

index 8191d04..8d3b1f7 100644
@@ -80,7 +80,7 @@ struct cpu_dbs_info_s {
 	int cpu;
 	unsigned int enable:1;
 };
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, cs_cpu_dbs_info);
+DEFINE_PER_CPU(struct cpu_dbs_info_s, cs_cpu_dbs_info);
 
 static unsigned int dbs_enable;	/* number of CPUs using this policy */
 

index 04de476..56525c0 100644
@@ -87,7 +87,7 @@ struct cpu_dbs_info_s {
 	unsigned int enable:1,
 		sample_type:1;
 };
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info);
+DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info);
 
 static unsigned int dbs_enable;	/* number of CPUs using this policy */
 

index 5a62d67..4cda242 100644
@@ -43,7 +43,7 @@ struct cpufreq_stats {
 #endif
 };
 
-static DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table);
+DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table);
 
 struct cpufreq_stats_attribute {
 	struct attribute attr;

index 66d2d1d..9170939 100644
@@ -27,12 +27,11 @@
 /**
  * A few values needed by the userspace governor
  */
-static DEFINE_PER_CPU(unsigned int, cpu_max_freq);
-static DEFINE_PER_CPU(unsigned int, cpu_min_freq);
-static DEFINE_PER_CPU(unsigned int, cpu_cur_freq); /* current CPU freq */
-static DEFINE_PER_CPU(unsigned int, cpu_set_freq); /* CPU freq desired by
-							userspace */
-static DEFINE_PER_CPU(unsigned int, cpu_is_managed);
+DEFINE_PER_CPU(unsigned int, cpu_max_freq);
+DEFINE_PER_CPU(unsigned int, cpu_min_freq);
+DEFINE_PER_CPU(unsigned int, cpu_cur_freq); /* current CPU freq */
+DEFINE_PER_CPU(unsigned int, cpu_set_freq); /* CPU freq desired by userspace */
+DEFINE_PER_CPU(unsigned int, cpu_is_managed);
 
 static DEFINE_MUTEX(userspace_mutex);
 static int cpus_using_userspace_governor;

index a9bd3a0..b3873b1 100644
@@ -174,7 +174,7 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);
 
-static DEFINE_PER_CPU(struct cpufreq_frequency_table *, show_table);
+DEFINE_PER_CPU(struct cpufreq_frequency_table *, show_table);
 /**
  * show_available_freqs - show available frequencies for the specified CPU
  */

index a4bec3f..2ec4150 100644
@@ -42,7 +42,7 @@ struct ladder_device {
 	int last_state_idx;
 };
 
-static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
+DEFINE_PER_CPU(struct ladder_device, ladder_devices);
 
 /**
  * ladder_do_selection - prepares private data for a state change

index f1df59f..7a44366 100644
@@ -27,7 +27,7 @@ struct menu_device {
 	unsigned int	elapsed_us;
 };
 
-static DEFINE_PER_CPU(struct menu_device, menu_devices);
+DEFINE_PER_CPU(struct menu_device, menu_devices);
 
 /**
  * menu_select - selects the next idle state to enter

index 856b3cc..692ed44 100644
@@ -51,7 +51,7 @@ struct aes_ctx {
 	u32 *D;
 };
 
-static DEFINE_PER_CPU(struct cword *, last_cword);
+DEFINE_PER_CPU(struct cword *, last_cword);
 
 /* Tells whether the ACE is capable to generate
    the extended key for a given key_len. */

index a059cf9..cccc8ca 100644
@@ -56,7 +56,7 @@
 /* We actually need a separate PTE page for each CPU.  Remember that after the
  * Switcher code itself comes two pages for each CPU, and we don't want this
  * CPU's guest to see the pages of any other CPU. */
-static DEFINE_PER_CPU(pte_t *, switcher_pte_pages);
+DEFINE_PER_CPU(pte_t *, switcher_pte_pages);
 #define switcher_pte_page(cpu) per_cpu(switcher_pte_pages, cpu)
 
 /*H:320 The page table code is curly enough to need helper functions to keep it

index eaf722f..27662e6 100644
@@ -67,7 +67,7 @@ static struct lguest_pages *lguest_pages(unsigned int cpu)
 		  (SWITCHER_ADDR + SHARED_SWITCHER_PAGES*PAGE_SIZE))[cpu]);
 }
 
-static DEFINE_PER_CPU(struct lg_cpu *, last_cpu);
+DEFINE_PER_CPU(struct lg_cpu *, last_cpu);
 
 /*S:010
  * We approach the Switcher.

index dbfed85..6ac2e0e 100644
@@ -47,10 +47,10 @@
 static DEFINE_SPINLOCK(irq_mapping_update_lock);
 
 /* IRQ <-> VIRQ mapping. */
-static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
+DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 
 /* IRQ <-> IPI mapping */
-static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
+DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
 
 /* Interrupt types. */
 enum xen_irq_type {

@@ -596,7 +596,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static DEFINE_PER_CPU(unsigned, xed_nesting_count);
+DEFINE_PER_CPU(unsigned, xed_nesting_count);
 
 /*
  * Search the CPUs pending events bitmasks.  For each one found, map

index aed2977..707a934 100644
@@ -1242,7 +1242,7 @@ struct bh_lru {
 	struct buffer_head *bhs[BH_LRU_SIZE];
 };
 
-static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};
+DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};
 
 #ifdef CONFIG_SMP
 #define bh_lru_lock()	local_irq_disable()

@@ -3224,7 +3224,7 @@ struct bh_accounting {
 	int ratelimit;		/* Limit cacheline bouncing */
 };
 
-static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};
+DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0};
 
 static void recalc_bh_state(void)
 {

index f313314..62e29d9 100644
@@ -36,7 +36,7 @@ int sysctl_nr_open_max = 1024 * 1024; /* raised later */
  * the work_struct in fdtable itself which avoids a 64 byte (i386) increase in
  * this per-task structure.
  */
-static DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
+DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
 
 static inline void * alloc_fdmem(unsigned int size)
 {

index 134d494..5feb512 100644
@@ -181,7 +181,7 @@ struct mnt_writer {
 	unsigned long count;
 	struct vfsmount *mnt;
 } ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(struct mnt_writer, mnt_writers);
+DEFINE_PER_CPU(struct mnt_writer, mnt_writers);
 
 static int __init init_mnt_writers(void)
 {

index 8f921d7..c51e51b 100644
@@ -13,9 +13,12 @@
  * 'section' argument.  This may be used to affect the parameters governing the
  * variable's storage.
  *
- * NOTE!  The sections for the DECLARE and for the DEFINE must match, lest
- * linkage errors occur due the compiler generating the wrong code to access
- * that section.
+ * Some architectures (alpha and s390) need 'weak' attribute for percpu
+ * variables to force external references as space for percpu variables is
+ * allocated differently from regular variables.  To allow this, static percpu
+ * variables are not allowed - all perpcu variables must be global.  This is
+ * forced by implicitly doing DECLARE_PERCPU_SECTION() from
+ * DEFINE_PER_CPU_SECTION().
  */
 #define DECLARE_PER_CPU_SECTION(type, name, section)			\
 	extern								\

@@ -23,6 +26,7 @@
 	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 
 #define DEFINE_PER_CPU_SECTION(type, name, section)			\
+	DECLARE_PER_CPU_SECTION(type, name, section);			\
 	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
 	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 

index c0fa54b..92f67ff 100644
@@ -71,7 +71,7 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 static bool kprobes_all_disarmed;
 
 static DEFINE_MUTEX(kprobe_mutex);	/* Protects kprobe_table */
-static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
+DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
 static struct {
 	spinlock_t lock ____cacheline_aligned_in_smp;
 } kretprobe_table_locks[KPROBE_TABLE_SIZE];

index accb40c..4e6ae0e 100644
@@ -137,7 +137,7 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 }
 
 #ifdef CONFIG_LOCK_STAT
-static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
+DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
 static int lock_point(unsigned long points[], unsigned long ip)
 {

index 5052b54..ac90df5 100644
@@ -959,7 +959,7 @@ int is_console_locked(void)
 	return console_locked;
 }
 
-static DEFINE_PER_CPU(int, printk_pending);
+DEFINE_PER_CPU(int, printk_pending);
 
 void printk_tick(void)
 {

index 7724e04..e68fd20 100644
@@ -47,8 +47,8 @@ EXPORT_SYMBOL_GPL(prof_on);
 
 static cpumask_var_t prof_cpu_mask;
 #ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
-static DEFINE_PER_CPU(int, cpu_profile_flip);
+DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
+DEFINE_PER_CPU(int, cpu_profile_flip);
 static DEFINE_MUTEX(profile_flip_mutex);
 #endif /* CONFIG_SMP */
 

index 0f2b0b3..f913cb9 100644
@@ -74,8 +74,8 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cpumask = CPU_BITS_NONE,
 };
 
-static DEFINE_PER_CPU(struct rcu_data, rcu_data);
-static DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+DEFINE_PER_CPU(struct rcu_data, rcu_data);
+DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 /*
  * Increment the quiescent state counter.

index a967c9f..7b80734 100644
@@ -52,7 +52,7 @@ enum rcu_barrier {
 	RCU_BARRIER_SCHED,
 };
 
-static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
+DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;

index ce97a4d..4bb39c0 100644
@@ -155,7 +155,7 @@ struct rcu_dyntick_sched {
 	int sched_dynticks_snap;
 };
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = {
 	.dynticks = 1,
 };
 

@@ -190,7 +190,7 @@ void rcu_exit_nohz(void)
 #endif /* CONFIG_NO_HZ */
 
 
-static DEFINE_PER_CPU(struct rcu_data, rcu_data);
+DEFINE_PER_CPU(struct rcu_data, rcu_data);
 
 static struct rcu_ctrlblk rcu_ctrlblk = {
 	.fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock),

@@ -222,7 +222,7 @@ enum rcu_flip_flag_values {
 	rcu_flipped		/* Flip just completed, need confirmation. */
 				/* Only corresponding CPU can update. */
 };
-static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_flip_flag_values, rcu_flip_flag)
+DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_flip_flag_values, rcu_flip_flag)
 								= rcu_flip_seen;
 
 /*

@@ -237,7 +237,7 @@ enum rcu_mb_flag_values {
 	rcu_mb_needed		/* Flip just completed, need an mb(). */
 				/* Only corresponding CPU can update. */
 };
-static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_mb_flag_values, rcu_mb_flag)
+DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_mb_flag_values, rcu_mb_flag)
 								= rcu_mb_done;
 
 /*

@@ -472,7 +472,7 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
 }
 
 #ifdef CONFIG_NO_HZ
-static DEFINE_PER_CPU(int, rcu_update_flag);
+DEFINE_PER_CPU(int, rcu_update_flag);
 
 /**
  * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.

index 9b4a975..1fcf4fe 100644
@@ -114,9 +114,9 @@ static struct rcu_torture *rcu_torture_current = NULL;
 static long rcu_torture_current_version = 0;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
+DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) =
 	{ 0 };
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) =
+DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) =
 	{ 0 };
 static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
 static atomic_t n_rcu_torture_alloc;

index 26efa47..73a2246 100644
@@ -320,14 +320,14 @@ struct task_group root_task_group;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /* Default task group's sched entity on each cpu */
-static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
+DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
 /* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
-static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
+DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
+DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
 #endif /* CONFIG_RT_GROUP_SCHED */
 #else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group

@@ -661,7 +661,7 @@ struct rq {
 #endif
 };
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
 {

@@ -3839,7 +3839,7 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
 #define MAX_PINNED_INTERVAL	512
 
 /* Working cpumask for load_balance and load_balance_newidle. */
-static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
 
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move

@@ -7770,8 +7770,8 @@ struct static_sched_domain {
  * SMT sched-domains:
  */
 #ifdef CONFIG_SCHED_SMT
-static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
+DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
 
 static int
 cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,

@@ -7787,8 +7787,8 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
  * multi-core sched-domains:
  */
 #ifdef CONFIG_SCHED_MC
-static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
+DEFINE_PER_CPU(struct static_sched_domain, core_domains);
+DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
 #endif /* CONFIG_SCHED_MC */
 
 #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)

@@ -7815,8 +7815,8 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 }
 #endif
 
-static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
+DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
+DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
 
 static int
 cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,

@@ -7843,11 +7843,11 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
  * groups, so roll our own. Now each node has its own list of groups which
  * gets dynamically allocated.
  */
-static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
+DEFINE_PER_CPU(struct static_sched_domain, node_domains);
 static struct sched_group ***sched_group_nodes_bycpu;
 
-static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
+DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
+DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
 
 static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
 				 struct sched_group **sg,

index e1d16c9..759f269 100644
@@ -60,7 +60,7 @@ struct sched_clock_data {
 	u64			clock;
 };
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
 
 static inline struct sched_clock_data *this_scd(void)
 {

index f2c66f8..339ab0b 100644
@@ -1113,7 +1113,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 	return next;
 }
 
-static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
+DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
 static inline int pick_optimal_cpu(int this_cpu,
 				   const struct cpumask *mask)

index 858baac..4ef26e5 100644
@@ -12,7 +12,7 @@
 #include <linux/smp.h>
 #include <linux/cpu.h>
 
-static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
+DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
 
 static struct {
 	struct list_head	queue;

@@ -39,7 +39,7 @@ struct call_single_queue {
 	spinlock_t		lock;
 };
 
-static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
+DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
 	.lock			= __SPIN_LOCK_UNLOCKED(cfd_data.lock),
 };
 

@@ -257,7 +257,7 @@ void generic_smp_call_function_single_interrupt(void)
 	}
 }
 
-static DEFINE_PER_CPU(struct call_single_data, csd_data);
+DEFINE_PER_CPU(struct call_single_data, csd_data);
 
 /*
  * smp_call_function_single - Run a function on a specific CPU

index b525dd3..55f9452 100644
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(irq_stat);
 
 static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
 
-static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
 
 char *softirq_to_name[NR_SOFTIRQS] = {
 	"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK",

@@ -352,8 +352,8 @@ struct tasklet_head
 	struct tasklet_struct **tail;
 };
 
-static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
-static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
+DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
+DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
 
 void __tasklet_schedule(struct tasklet_struct *t)
 {

index 88796c3..997cf10 100644
@@ -22,9 +22,9 @@
 
 static DEFINE_SPINLOCK(print_lock);
 
-static DEFINE_PER_CPU(unsigned long, touch_timestamp);
-static DEFINE_PER_CPU(unsigned long, print_timestamp);
-static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
+DEFINE_PER_CPU(unsigned long, touch_timestamp);
+DEFINE_PER_CPU(unsigned long, print_timestamp);
+DEFINE_PER_CPU(struct task_struct *, watchdog_task);
 
 static int __read_mostly did_panic;
 int __read_mostly softlockup_thresh = 60;

index 888adbc..e7fc2cb 100644
@@ -35,7 +35,7 @@
  */
 #define TASKSTATS_CPUMASK_MAXLEN	(100+6*NR_CPUS)
 
-static DEFINE_PER_CPU(__u32, taskstats_seqnum);
+DEFINE_PER_CPU(__u32, taskstats_seqnum);
 static int family_registered;
 struct kmem_cache *taskstats_cache;
 

@@ -68,7 +68,7 @@ struct listener_list {
 	struct rw_semaphore sem;
 	struct list_head list;
 };
-static DEFINE_PER_CPU(struct listener_list, listener_array);
+DEFINE_PER_CPU(struct listener_list, listener_array);
 
 enum actions {
 	REGISTER,

index d3f1ef4..9d4b954 100644
@@ -29,7 +29,7 @@
 /*
  * Per cpu nohz control structure
  */
-static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
 /*
  * The time, when the last jiffy update happened. Protected by xtime_lock.

index c994530..2a6fdb7 100644
@@ -86,7 +86,7 @@ static DEFINE_SPINLOCK(table_lock);
 /*
  * Per-CPU lookup locks for fast hash lookup:
  */
-static DEFINE_PER_CPU(spinlock_t, lookup_lock);
+DEFINE_PER_CPU(spinlock_t, lookup_lock);
 
 /*
  * Mutex to serialize state changes with show-stats activities:

index cffffad..3dd1d5d 100644
@@ -79,7 +79,7 @@ struct tvec_base {
 
 struct tvec_base boot_tvec_bases;
 EXPORT_SYMBOL(boot_tvec_bases);
-static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
+DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
 
 /*
  * Note that all tvec_bases are 2 byte aligned and lower bit of

index 960cbf4..91d73b3 100644
@@ -1458,7 +1458,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 }
 
-static DEFINE_PER_CPU(int, rb_need_resched);
+DEFINE_PER_CPU(int, rb_need_resched);
 
 /**
  * ring_buffer_lock_reserve - reserve a part of the buffer

index cda81ec..10635e0 100644
@@ -88,7 +88,7 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {

@@ -169,7 +169,7 @@ unsigned long long ns2usecs(cycle_t nsec)
  */
 static struct trace_array	global_trace;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
+DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
 cycle_t ftrace_now(int cpu)
 {

@@ -197,7 +197,7 @@ cycle_t ftrace_now(int cpu)
  */
 static struct trace_array	max_tr;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+DEFINE_PER_CPU(struct trace_array_cpu, max_data);
 
 /* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;

index 7bfdf4c..34cea28 100644
@@ -32,8 +32,8 @@
  * - read the trace from a single cpu
  */
 static DEFINE_SPINLOCK(bts_tracer_lock);
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
+DEFINE_PER_CPU(struct bts_tracer *, tracer);
+DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
 
 #define this_tracer per_cpu(tracer, smp_processor_id())
 #define this_buffer per_cpu(buffer, smp_processor_id())

index b923d13..8f3661d 100644
@@ -21,7 +21,7 @@
 static struct trace_array		*irqsoff_trace __read_mostly;
 static int				tracer_enabled __read_mostly;
 
-static DEFINE_PER_CPU(int, tracing_cpu);
+DEFINE_PER_CPU(int, tracing_cpu);
 
 static DEFINE_SPINLOCK(max_trace_lock);
 

index c750f65..bd78e95 100644
@@ -31,7 +31,7 @@ static raw_spinlock_t max_stack_lock =
 	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 
 static int stack_trace_disabled __read_mostly;
-static DEFINE_PER_CPU(int, trace_active);
+DEFINE_PER_CPU(int, trace_active);
 static DEFINE_MUTEX(stack_sysctl_mutex);
 
 int stack_tracer_enabled;

index 91fd19c..e27b8dd 100644
@@ -31,7 +31,7 @@ static DEFINE_MUTEX(sample_timer_lock);
 /*
  * Per CPU hrtimers that do the profiling:
  */
-static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer);
+DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer);
 
 struct stack_frame {
 	const void __user	*next_fp;

index 797201e..a70e65c 100644
@@ -38,7 +38,7 @@ struct workqueue_global_stats {
 /* Don't need a global lock because allocated before the workqueues, and
  * never freed.
  */
-static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
+DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
 #define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu))
 
 /* Insertion of a work */

index 4bb42a0..a7f5217 100644
@@ -81,7 +81,7 @@ struct radix_tree_preload {
 	int nr;
 	struct radix_tree_node *nodes[RADIX_TREE_MAX_PATH];
 };
-static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
+DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
 
 static inline gfp_t root_gfp_mask(struct radix_tree_root *root)
 {

index 217d5c4..ce97c36 100644
@@ -43,7 +43,7 @@ struct rnd_state {
 	u32 s1, s2, s3;
 };
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state);
+DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
 static u32 __random32(struct rnd_state *state)
 {

index 0e0c9de..23d6015 100644
@@ -606,7 +606,7 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite)
 	}
 }
 
-static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
+DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
 
 /**
  * balance_dirty_pages_ratelimited_nr - balance dirty memory state

index 9a90b00..42ccf81 100644
@@ -763,7 +763,7 @@ int slab_is_available(void)
 	return g_cpucache_up == FULL;
 }
 
-static DEFINE_PER_CPU(struct delayed_work, reap_work);
+DEFINE_PER_CPU(struct delayed_work, reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {

@@ -905,7 +905,7 @@ __setup("noaliencache", noaliencache_setup);
  * objects freed on different nodes from which they were allocated) and the
  * flushing of remote pcps by calling drain_node_pages.
  */
-static DEFINE_PER_CPU(unsigned long, reap_node);
+DEFINE_PER_CPU(unsigned long, reap_node);
 
 static void init_reap_node(int cpu)
 {

index fbcf929..2c130e5 100644
@@ -1987,10 +1987,8 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
  */
 #define NR_KMEM_CACHE_CPU 100
 
-static DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU],
-		      kmem_cache_cpu);
-
-static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
+DEFINE_PER_CPU(struct kmem_cache_cpu [NR_KMEM_CACHE_CPU], kmem_cache_cpu);
+DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
 static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);
 
 static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,

index cb29ae5..c92109a 100644
@@ -36,8 +36,8 @@
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
 
-static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
+DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
+DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
 
 /*
  * This path almost never happens for VM activity - pages are normally

index 083716e..9e0ad21 100644
@@ -678,7 +678,7 @@ struct vmap_block {
 };
 
 /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
-static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
+DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
 
 /*
  * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block

index 74d66db..809c5c8 100644
@@ -873,7 +873,7 @@ static const struct file_operations proc_vmstat_file_operations = {
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
+DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
 
 static void vmstat_update(struct work_struct *w)

index 9fd0dc3..c2ae1ec 100644
@@ -55,7 +55,7 @@ static struct genl_family net_drop_monitor_family = {
 	.maxattr        = NET_DM_CMD_MAX,
 };
 
-static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
+DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
 
 static int dm_hit_limit = 64;
 static int dm_delay = 1;

index 9601587..4254804 100644
@@ -39,7 +39,7 @@ atomic_t flow_cache_genid = ATOMIC_INIT(0);
 
 static u32 flow_hash_shift;
 #define flow_hash_size	(1 << flow_hash_shift)
-static DEFINE_PER_CPU(struct flow_cache_entry **, flow_tables) = { NULL };
+DEFINE_PER_CPU(struct flow_cache_entry **, flow_tables) = { NULL };
 
 #define flow_table(cpu) (per_cpu(flow_tables, cpu))
 

@@ -52,7 +52,7 @@ struct flow_percpu_info {
 	u32 hash_rnd;
 	int count;
 };
-static DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 };
+DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 };
 
 #define flow_hash_rnd_recalc(cpu) \
 	(per_cpu(flow_hash_info, cpu).hash_rnd_recalc)

@@ -69,7 +69,7 @@ struct flow_flush_info {
 	atomic_t cpuleft;
 	struct completion completion;
 };
-static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL };
+DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL };
 
 #define flow_flush_tasklet(cpu) (&per_cpu(flow_flush_tasklets, cpu))
 

index 7dbf3ff..4ea4d1f 100644
@@ -2049,7 +2049,7 @@ static __init int net_inuse_init(void)
 
 core_initcall(net_inuse_init);
 #else
-static DEFINE_PER_CPU(struct prot_inuse, prot_inuse);
+DEFINE_PER_CPU(struct prot_inuse, prot_inuse);
 
 void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
 {

index 28205e5..9bd897e 100644
@@ -253,7 +253,7 @@ static struct rt_hash_bucket 	*rt_hash_table __read_mostly;
 static unsigned			rt_hash_mask __read_mostly;
 static unsigned int		rt_hash_log  __read_mostly;
 
-static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
+DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
 #define RT_CACHE_STAT_INC(field) \
 	(__raw_get_cpu_var(rt_cache_stat).field++)
 

index a3c045c..c72b127 100644
@@ -37,8 +37,7 @@ __initcall(init_syncookies);
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
-		      ipv4_cookie_scratch);
+DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch);
 
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)

index e2bcff0..6043c63 100644
@@ -74,8 +74,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	return child;
 }
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
-		      ipv6_cookie_scratch);
+DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch);
 
 static u32 cookie_hash(struct in6_addr *saddr, struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)

index 791d71a..4249ae8 100644
@@ -153,7 +153,7 @@ static const struct net_proto_family *net_families[NPROTO] __read_mostly;
  *	Statistics counters of the socket lists
  */
 
-static DEFINE_PER_CPU(int, sockets_in_use) = 0;
+DEFINE_PER_CPU(int, sockets_in_use) = 0;
 
 /*
  * Support routines.

index 06c5c7a..7f0a9c4 100644
@@ -30,7 +30,6 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 
 #ifndef MODULE
 #define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
-#define PER_CPU_ATTRIBUTES
 #else
 /*
  * To calculate addresses of locally defined variables, GCC uses 32-bit

@@ -49,8 +48,6 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 		: "=&r"(__ptr), "=&r"(tmp_gp));		\
 	(typeof(&per_cpu_var(var)))(__ptr + (offset)); })
 
-#define PER_CPU_ATTRIBUTES	__used
-
 #endif /* MODULE */
 
 /*

@@ -71,8 +68,6 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define __get_cpu_var(var)		per_cpu_var(var)
 #define __raw_get_cpu_var(var)		per_cpu_var(var)
 
-#define PER_CPU_ATTRIBUTES
-
 #endif /* SMP */
 
 #ifdef CONFIG_SMP

106 lines not on this page · raw message

index 9d87aaa..e89e0c2 100644
@@ -2,6 +2,7 @@
 #define _ALPHA_TLBFLUSH_H
 
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <asm/compiler.h>
 #include <asm/pgalloc.h>
 

index 408d60b..36672ff 100644
@@ -1,37 +1,21 @@
 #ifndef __ARCH_S390_PERCPU__
 #define __ARCH_S390_PERCPU__
 
-#include <linux/compiler.h>
-#include <asm/lowcore.h>
-
 /*
  * s390 uses its own implementation for per cpu data, the offset of
  * the cpu local data area is cached in the cpu's lowcore memory.
- * For 64 bit module code s390 forces the use of a GOT slot for the
- * address of the per cpu variable. This is needed because the module
- * may be more than 4G above the per cpu area.
  */
-#if defined(__s390x__) && defined(MODULE)
-
-#define SHIFT_PERCPU_PTR(ptr,offset) (({			\
-	extern int simple_identifier_##var(void);	\
-	unsigned long *__ptr;				\
-	asm ( "larl %0, %1@GOTENT"		\
-	    : "=a" (__ptr) : "X" (ptr) );		\
-	(typeof(ptr))((*__ptr) + (offset));	}))
-
-#else
-
-#define SHIFT_PERCPU_PTR(ptr, offset) (({				\
-	extern int simple_identifier_##var(void);		\
-	unsigned long __ptr;					\
-	asm ( "" : "=a" (__ptr) : "0" (ptr) );			\
-	(typeof(ptr)) (__ptr + (offset)); }))
+#define __my_cpu_offset S390_lowcore.percpu_offset
 
+/*
+ * For 64 bit module code, the module may be more than 4G above the
+ * per cpu area, use "weak" attribute to force the compiler to
+ * generate an external reference.
+ */
+#if defined(CONFIG_SMP) && defined(__s390x__) && defined(MODULE)
+#define PER_CPU_ATTRIBUTES	__attribute__((weak))
 #endif
 
-#define __my_cpu_offset S390_lowcore.percpu_offset
-
 #include <asm-generic/percpu.h>
 
 #endif /* __ARCH_S390_PERCPU__ */