Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (34 commits)
  m68k: rename global variable vmalloc_end to m68k_vmalloc_end
  percpu: add missing per_cpu_ptr_to_phys() definition for UP
  percpu: Fix kdump failure if booted with percpu_alloc=page
  percpu: make misc percpu symbols unique
  percpu: make percpu symbols in ia64 unique
  percpu: make percpu symbols in powerpc unique
  percpu: make percpu symbols in x86 unique
  percpu: make percpu symbols in xen unique
  percpu: make percpu symbols in cpufreq unique
  percpu: make percpu symbols in oprofile unique
  percpu: make percpu symbols in tracer unique
  percpu: make percpu symbols under kernel/ and mm/ unique
  percpu: remove some sparse warnings
  percpu: make alloc_percpu() handle array types
  vmalloc: fix use of non-existent percpu variable in put_cpu_var()
  this_cpu: Use this_cpu_xx in trace_functions_graph.c
  this_cpu: Use this_cpu_xx for ftrace
  this_cpu: Use this_cpu_xx in nmi handling
  this_cpu: Use this_cpu operations in RCU
  this_cpu: Use this_cpu ops for VM statistics
  ...

Fix up trivial (famous last words) global per-cpu naming conflicts in
	arch/x86/kvm/svm.c
	mm/slab.c

kernel/lockdep.c

@@ -140,7 +140,8 @@ 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);
+static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
+		      cpu_lock_stats);
 
 static inline u64 lockstat_clock(void)
 {
@@ -198,7 +199,7 @@ struct lock_class_stats lock_stats(struct lock_class *class)
 	memset(&stats, 0, sizeof(struct lock_class_stats));
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *pcs =
-			&per_cpu(lock_stats, cpu)[class - lock_classes];
+			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
 		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
 			stats.contention_point[i] += pcs->contention_point[i];
@@ -225,7 +226,7 @@ void clear_lock_stats(struct lock_class *class)
 
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *cpu_stats =
-			&per_cpu(lock_stats, cpu)[class - lock_classes];
+			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
 		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
 	}
@@ -235,12 +236,12 @@ void clear_lock_stats(struct lock_class *class)
 
 static struct lock_class_stats *get_lock_stats(struct lock_class *class)
 {
-	return &get_cpu_var(lock_stats)[class - lock_classes];
+	return &get_cpu_var(cpu_lock_stats)[class - lock_classes];
 }
 
 static void put_lock_stats(struct lock_class_stats *stats)
 {
-	put_cpu_var(lock_stats);
+	put_cpu_var(cpu_lock_stats);
 }
 
 static void lock_release_holdtime(struct held_lock *hlock)

kernel/module.c

@@ -370,8 +370,6 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
 static void *percpu_modalloc(unsigned long size, unsigned long align,
 			     const char *name)
 {
@@ -395,154 +393,6 @@ static void percpu_modfree(void *freeme)
 	free_percpu(freeme);
 }
 
-#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-/* Number of blocks used and allocated. */
-static unsigned int pcpu_num_used, pcpu_num_allocated;
-/* Size of each block.  -ve means used. */
-static int *pcpu_size;
-
-static int split_block(unsigned int i, unsigned short size)
-{
-	/* Reallocation required? */
-	if (pcpu_num_used + 1 > pcpu_num_allocated) {
-		int *new;
-
-		new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
-			       GFP_KERNEL);
-		if (!new)
-			return 0;
-
-		pcpu_num_allocated *= 2;
-		pcpu_size = new;
-	}
-
-	/* Insert a new subblock */
-	memmove(&pcpu_size[i+1], &pcpu_size[i],
-		sizeof(pcpu_size[0]) * (pcpu_num_used - i));
-	pcpu_num_used++;
-
-	pcpu_size[i+1] -= size;
-	pcpu_size[i] = size;
-	return 1;
-}
-
-static inline unsigned int block_size(int val)
-{
-	if (val < 0)
-		return -val;
-	return val;
-}
-
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-			     const char *name)
-{
-	unsigned long extra;
-	unsigned int i;
-	void *ptr;
-	int cpu;
-
-	if (align > PAGE_SIZE) {
-		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-		       name, align, PAGE_SIZE);
-		align = PAGE_SIZE;
-	}
-
-	ptr = __per_cpu_start;
-	for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
-		/* Extra for alignment requirement. */
-		extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
-		BUG_ON(i == 0 && extra != 0);
-
-		if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
-			continue;
-
-		/* Transfer extra to previous block. */
-		if (pcpu_size[i-1] < 0)
-			pcpu_size[i-1] -= extra;
-		else
-			pcpu_size[i-1] += extra;
-		pcpu_size[i] -= extra;
-		ptr += extra;
-
-		/* Split block if warranted */
-		if (pcpu_size[i] - size > sizeof(unsigned long))
-			if (!split_block(i, size))
-				return NULL;
-
-		/* add the per-cpu scanning areas */
-		for_each_possible_cpu(cpu)
-			kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
-				       GFP_KERNEL);
-
-		/* Mark allocated */
-		pcpu_size[i] = -pcpu_size[i];
-		return ptr;
-	}
-
-	printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
-	       size);
-	return NULL;
-}
-
-static void percpu_modfree(void *freeme)
-{
-	unsigned int i;
-	void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
-	int cpu;
-
-	/* First entry is core kernel percpu data. */
-	for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
-		if (ptr == freeme) {
-			pcpu_size[i] = -pcpu_size[i];
-			goto free;
-		}
-	}
-	BUG();
-
- free:
-	/* remove the per-cpu scanning areas */
-	for_each_possible_cpu(cpu)
-		kmemleak_free(freeme + per_cpu_offset(cpu));
-
-	/* Merge with previous? */
-	if (pcpu_size[i-1] >= 0) {
-		pcpu_size[i-1] += pcpu_size[i];
-		pcpu_num_used--;
-		memmove(&pcpu_size[i], &pcpu_size[i+1],
-			(pcpu_num_used - i) * sizeof(pcpu_size[0]));
-		i--;
-	}
-	/* Merge with next? */
-	if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
-		pcpu_size[i] += pcpu_size[i+1];
-		pcpu_num_used--;
-		memmove(&pcpu_size[i+1], &pcpu_size[i+2],
-			(pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
-	}
-}
-
-static int percpu_modinit(void)
-{
-	pcpu_num_used = 2;
-	pcpu_num_allocated = 2;
-	pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
-			    GFP_KERNEL);
-	/* Static in-kernel percpu data (used). */
-	pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
-	/* Free room. */
-	pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
-	if (pcpu_size[1] < 0) {
-		printk(KERN_ERR "No per-cpu room for modules.\n");
-		pcpu_num_used = 1;
-	}
-
-	return 0;
-}
-__initcall(percpu_modinit);
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 				 Elf_Shdr *sechdrs,
 				 const char *secstrings)

kernel/rcutorture.c

@@ -763,13 +763,13 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	++__get_cpu_var(rcu_torture_count)[pipe_count];
+	__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
 	completed = cur_ops->completed() - completed;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
-	++__get_cpu_var(rcu_torture_batch)[completed];
+	__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
 	preempt_enable();
 	cur_ops->readunlock(idx);
 }
@@ -818,13 +818,13 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		++__get_cpu_var(rcu_torture_count)[pipe_count];
+		__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
 		completed = cur_ops->completed() - completed;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
 		}
-		++__get_cpu_var(rcu_torture_batch)[completed];
+		__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();

kernel/sched.c

@@ -298,7 +298,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
 #endif /* CONFIG_RT_GROUP_SCHED */
 #else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
@@ -8286,14 +8286,14 @@ enum s_alloc {
  */
 #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);
+static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
 
 static int
 cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 		 struct sched_group **sg, struct cpumask *unused)
 {
 	if (sg)
-		*sg = &per_cpu(sched_group_cpus, cpu).sg;
+		*sg = &per_cpu(sched_groups, cpu).sg;
 	return cpu;
 }
 #endif /* CONFIG_SCHED_SMT */
@@ -9583,7 +9583,7 @@ void __init sched_init(void)
 #elif defined CONFIG_USER_SCHED
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
 		init_tg_rt_entry(&init_task_group,
-				&per_cpu(init_rt_rq, i),
+				&per_cpu(init_rt_rq_var, i),
 				&per_cpu(init_sched_rt_entity, i), i, 1,
 				root_task_group.rt_se[i]);
 #endif

kernel/softirq.c

@@ -697,7 +697,7 @@ void __init softirq_init(void)
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
 
-static int ksoftirqd(void * __bind_cpu)
+static int run_ksoftirqd(void * __bind_cpu)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 
@@ -810,7 +810,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
+		p = kthread_create(run_ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
 		if (IS_ERR(p)) {
 			printk("ksoftirqd for %i failed\n", hotcpu);
 			return NOTIFY_BAD;

kernel/softlockup.c

@@ -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);
+static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
+static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
+static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 
 static int __read_mostly did_panic;
 int __read_mostly softlockup_thresh = 60;
@@ -70,12 +70,12 @@ static void __touch_softlockup_watchdog(void)
 {
 	int this_cpu = raw_smp_processor_id();
 
-	__raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu);
+	__raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu);
 }
 
 void touch_softlockup_watchdog(void)
 {
-	__raw_get_cpu_var(touch_timestamp) = 0;
+	__raw_get_cpu_var(softlockup_touch_ts) = 0;
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
@@ -85,7 +85,7 @@ void touch_all_softlockup_watchdogs(void)
 
 	/* Cause each CPU to re-update its timestamp rather than complain */
 	for_each_online_cpu(cpu)
-		per_cpu(touch_timestamp, cpu) = 0;
+		per_cpu(softlockup_touch_ts, cpu) = 0;
 }
 EXPORT_SYMBOL(touch_all_softlockup_watchdogs);
 
@@ -104,28 +104,28 @@ int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
 void softlockup_tick(void)
 {
 	int this_cpu = smp_processor_id();
-	unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
-	unsigned long print_timestamp;
+	unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu);
+	unsigned long print_ts;
 	struct pt_regs *regs = get_irq_regs();
 	unsigned long now;
 
 	/* Is detection switched off? */
-	if (!per_cpu(watchdog_task, this_cpu) || softlockup_thresh <= 0) {
+	if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) {
 		/* Be sure we don't false trigger if switched back on */
-		if (touch_timestamp)
-			per_cpu(touch_timestamp, this_cpu) = 0;
+		if (touch_ts)
+			per_cpu(softlockup_touch_ts, this_cpu) = 0;
 		return;
 	}
 
-	if (touch_timestamp == 0) {
+	if (touch_ts == 0) {
 		__touch_softlockup_watchdog();
 		return;
 	}
 
-	print_timestamp = per_cpu(print_timestamp, this_cpu);
+	print_ts = per_cpu(softlockup_print_ts, this_cpu);
 
 	/* report at most once a second */
-	if (print_timestamp == touch_timestamp || did_panic)
+	if (print_ts == touch_ts || did_panic)
 		return;
 
 	/* do not print during early bootup: */
@@ -140,18 +140,18 @@ void softlockup_tick(void)
 	 * Wake up the high-prio watchdog task twice per
 	 * threshold timespan.
 	 */
-	if (now > touch_timestamp + softlockup_thresh/2)
-		wake_up_process(per_cpu(watchdog_task, this_cpu));
+	if (now > touch_ts + softlockup_thresh/2)
+		wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
 
 	/* Warn about unreasonable delays: */
-	if (now <= (touch_timestamp + softlockup_thresh))
+	if (now <= (touch_ts + softlockup_thresh))
 		return;
 
-	per_cpu(print_timestamp, this_cpu) = touch_timestamp;
+	per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
 
 	spin_lock(&print_lock);
 	printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n",
-			this_cpu, now - touch_timestamp,
+			this_cpu, now - touch_ts,
 			current->comm, task_pid_nr(current));
 	print_modules();
 	print_irqtrace_events(current);
@@ -209,32 +209,32 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		BUG_ON(per_cpu(watchdog_task, hotcpu));
+		BUG_ON(per_cpu(softlockup_watchdog, hotcpu));
 		p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
 		if (IS_ERR(p)) {
 			printk(KERN_ERR "watchdog for %i failed\n", hotcpu);
 			return NOTIFY_BAD;
 		}
-		per_cpu(touch_timestamp, hotcpu) = 0;
-		per_cpu(watchdog_task, hotcpu) = p;
+		per_cpu(softlockup_touch_ts, hotcpu) = 0;
+		per_cpu(softlockup_watchdog, hotcpu) = p;
 		kthread_bind(p, hotcpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		wake_up_process(per_cpu(watchdog_task, hotcpu));
+		wake_up_process(per_cpu(softlockup_watchdog, hotcpu));
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
-		if (!per_cpu(watchdog_task, hotcpu))
+		if (!per_cpu(softlockup_watchdog, hotcpu))
 			break;
 		/* Unbind so it can run.  Fall thru. */
-		kthread_bind(per_cpu(watchdog_task, hotcpu),
+		kthread_bind(per_cpu(softlockup_watchdog, hotcpu),
 			     cpumask_any(cpu_online_mask));
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		p = per_cpu(watchdog_task, hotcpu);
-		per_cpu(watchdog_task, hotcpu) = NULL;
+		p = per_cpu(softlockup_watchdog, hotcpu);
+		per_cpu(softlockup_watchdog, hotcpu) = NULL;
 		kthread_stop(p);
 		break;
 #endif /* CONFIG_HOTPLUG_CPU */

kernel/time/timer_stats.c

@@ -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);
+static DEFINE_PER_CPU(spinlock_t, tstats_lookup_lock);
 
 /*
  * Mutex to serialize state changes with show-stats activities:
@@ -245,7 +245,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	if (likely(!timer_stats_active))
 		return;
 
-	lock = &per_cpu(lookup_lock, raw_smp_processor_id());
+	lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
 
 	input.timer = timer;
 	input.start_func = startf;
@@ -348,9 +348,10 @@ static void sync_access(void)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		spin_lock_irqsave(&per_cpu(lookup_lock, cpu), flags);
+		spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
+		spin_lock_irqsave(lock, flags);
 		/* nothing */
-		spin_unlock_irqrestore(&per_cpu(lookup_lock, cpu), flags);
+		spin_unlock_irqrestore(lock, flags);
 	}
 }
 
@@ -408,7 +409,7 @@ void __init init_timer_stats(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		spin_lock_init(&per_cpu(lookup_lock, cpu));
+		spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
 }
 
 static int __init init_tstats_procfs(void)

kernel/trace/trace.c

@@ -86,17 +86,17 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
 	preempt_disable();
-	local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-	local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
 	preempt_enable();
 }
 
@@ -203,7 +203,7 @@ cycle_t ftrace_now(int cpu)
  */
 static struct trace_array	max_tr;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
 
 /* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;
@@ -1085,7 +1085,7 @@ trace_function(struct trace_array *tr,
 	struct ftrace_entry *entry;
 
 	/* If we are reading the ring buffer, don't trace */
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -4454,7 +4454,7 @@ __init static int tracer_alloc_buffers(void)
 	/* Allocate the first page for all buffers */
 	for_each_tracing_cpu(i) {
 		global_trace.data[i] = &per_cpu(global_trace_cpu, i);
-		max_tr.data[i] = &per_cpu(max_data, i);
+		max_tr.data[i] = &per_cpu(max_tr_data, i);
 	}
 
 	trace_init_cmdlines();

kernel/trace/trace.h

@@ -443,7 +443,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
 
 extern int ring_buffer_expanded;
 extern bool tracing_selftest_disabled;
-DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+DECLARE_PER_CPU(int, ftrace_cpu_disabled);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,

kernel/trace/trace_functions_graph.c

@@ -187,7 +187,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ent_entry *entry;
 
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return 0;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -251,7 +251,7 @@ static void __trace_graph_return(struct trace_array *tr,
 	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ret_entry *entry;
 
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,

kernel/trace/trace_hw_branches.c

@@ -20,10 +20,10 @@
 
 #define BTS_BUFFER_SIZE (1 << 13)
 
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
+static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
 
-#define this_tracer per_cpu(tracer, smp_processor_id())
+#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
 
 static int trace_hw_branches_enabled __read_mostly;
 static int trace_hw_branches_suspended __read_mostly;
@@ -32,12 +32,13 @@ static struct trace_array *hw_branch_trace __read_mostly;
 
 static void bts_trace_init_cpu(int cpu)
 {
-	per_cpu(tracer, cpu) =
-		ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
-				   NULL, (size_t)-1, BTS_KERNEL);
+	per_cpu(hwb_tracer, cpu) =
+		ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
+				   BTS_BUFFER_SIZE, NULL, (size_t)-1,
+				   BTS_KERNEL);
 
-	if (IS_ERR(per_cpu(tracer, cpu)))
-		per_cpu(tracer, cpu) = NULL;
+	if (IS_ERR(per_cpu(hwb_tracer, cpu)))
+		per_cpu(hwb_tracer, cpu) = NULL;
 }
 
 static int bts_trace_init(struct trace_array *tr)
@@ -51,7 +52,7 @@ static int bts_trace_init(struct trace_array *tr)
 	for_each_online_cpu(cpu) {
 		bts_trace_init_cpu(cpu);
 
-		if (likely(per_cpu(tracer, cpu)))
+		if (likely(per_cpu(hwb_tracer, cpu)))
 			trace_hw_branches_enabled = 1;
 	}
 	trace_hw_branches_suspended = 0;
@@ -67,9 +68,9 @@ static void bts_trace_reset(struct trace_array *tr)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
-		if (likely(per_cpu(tracer, cpu))) {
-			ds_release_bts(per_cpu(tracer, cpu));
-			per_cpu(tracer, cpu) = NULL;
+		if (likely(per_cpu(hwb_tracer, cpu))) {
+			ds_release_bts(per_cpu(hwb_tracer, cpu));
+			per_cpu(hwb_tracer, cpu) = NULL;
 		}
 	}
 	trace_hw_branches_enabled = 0;
@@ -83,8 +84,8 @@ static void bts_trace_start(struct trace_array *tr)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_resume_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_resume_bts(per_cpu(hwb_tracer, cpu));
 	trace_hw_branches_suspended = 0;
 	put_online_cpus();
 }
@@ -95,8 +96,8 @@ static void bts_trace_stop(struct trace_array *tr)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_suspend_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
 	trace_hw_branches_suspended = 1;
 	put_online_cpus();
 }
@@ -114,16 +115,16 @@ static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
 			bts_trace_init_cpu(cpu);
 
 			if (trace_hw_branches_suspended &&
-			    likely(per_cpu(tracer, cpu)))
-				ds_suspend_bts(per_cpu(tracer, cpu));
+			    likely(per_cpu(hwb_tracer, cpu)))
+				ds_suspend_bts(per_cpu(hwb_tracer, cpu));
 		}
 		break;
 
 	case CPU_DOWN_PREPARE:
 		/* The notification is sent with interrupts enabled. */
-		if (likely(per_cpu(tracer, cpu))) {
-			ds_release_bts(per_cpu(tracer, cpu));
-			per_cpu(tracer, cpu) = NULL;
+		if (likely(per_cpu(hwb_tracer, cpu))) {
+			ds_release_bts(per_cpu(hwb_tracer, cpu));
+			per_cpu(hwb_tracer, cpu) = NULL;
 		}
 	}
 
@@ -258,8 +259,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_suspend_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_suspend_bts(per_cpu(hwb_tracer, cpu));
 	/*
 	 * We need to collect the trace on the respective cpu since ftrace
 	 * implicitly adds the record for the current cpu.
@@ -268,8 +269,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
 	on_each_cpu(trace_bts_cpu, iter->tr, 1);
 
 	for_each_online_cpu(cpu)
-		if (likely(per_cpu(tracer, cpu)))
-			ds_resume_bts(per_cpu(tracer, cpu));
+		if (likely(per_cpu(hwb_tracer, cpu)))
+			ds_resume_bts(per_cpu(hwb_tracer, cpu));
 	put_online_cpus();
 }