powerpc: Replace __get_cpu_var uses

This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.

V2->V2
  - Fix up to work against 3.18-rc1

__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x).  This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.

Other use cases are for storing and retrieving data from the current
processors percpu area.  __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.

__get_cpu_var() is defined as :

__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.

This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset.  Thereby address calculations are avoided and less registers
are used when code is generated.

At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.

The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e.  using a global
register that may be set to the per cpu base.

Transformations done to __get_cpu_var()

1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);

2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);

3. Retrieve the content of the current processors instance of a per cpu
variable.

	DEFINE_PER_CPU(int, y);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);

4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(&x, this_cpu_ptr(&y), sizeof(x));

5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	__this_cpu_write(y, x);

6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	__this_cpu_inc(y)

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
      assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/hardirq.h

@@ -21,7 +21,12 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define __ARCH_IRQ_STAT
 
-#define local_softirq_pending()	__get_cpu_var(irq_stat).__softirq_pending
+#define local_softirq_pending()	__this_cpu_read(irq_stat.__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING
+
+#define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x))
 
 static inline void ack_bad_irq(unsigned int irq)
 {

arch/powerpc/include/asm/tlbflush.h

@@ -107,14 +107,14 @@ extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
 
 static inline void arch_enter_lazy_mmu_mode(void)
 {
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 
 	batch->active = 1;
 }
 
 static inline void arch_leave_lazy_mmu_mode(void)
 {
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
 
 	if (batch->index)
 		__flush_tlb_pending(batch);

arch/powerpc/include/asm/xics.h

@@ -98,7 +98,7 @@ DECLARE_PER_CPU(struct xics_cppr, xics_cppr);
 
 static inline void xics_push_cppr(unsigned int vec)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1))
 		return;
@@ -111,7 +111,7 @@ static inline void xics_push_cppr(unsigned int vec)
 
 static inline unsigned char xics_pop_cppr(void)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	if (WARN_ON(os_cppr->index < 1))
 		return LOWEST_PRIORITY;
@@ -121,7 +121,7 @@ static inline unsigned char xics_pop_cppr(void)
 
 static inline void xics_set_base_cppr(unsigned char cppr)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	/* we only really want to set the priority when there's
 	 * just one cppr value on the stack
@@ -133,7 +133,7 @@ static inline void xics_set_base_cppr(unsigned char cppr)
 
 static inline unsigned char xics_cppr_top(void)
 {
-	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+	struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr);
 
 	return os_cppr->stack[os_cppr->index];
 }

arch/powerpc/kernel/dbell.c

@@ -41,7 +41,7 @@ void doorbell_exception(struct pt_regs *regs)
 
 	may_hard_irq_enable();
 
-	__get_cpu_var(irq_stat).doorbell_irqs++;
+	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();
 

arch/powerpc/kernel/hw_breakpoint.c

@@ -63,7 +63,7 @@ int hw_breakpoint_slots(int type)
 int arch_install_hw_breakpoint(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
 
 	*slot = bp;
 
@@ -88,7 +88,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
  */
 void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 {
-	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+	struct perf_event **slot = this_cpu_ptr(&bp_per_reg);
 
 	if (*slot != bp) {
 		WARN_ONCE(1, "Can't find the breakpoint");
@@ -226,7 +226,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	 */
 	rcu_read_lock();
 
-	bp = __get_cpu_var(bp_per_reg);
+	bp = __this_cpu_read(bp_per_reg);
 	if (!bp)
 		goto out;
 	info = counter_arch_bp(bp);

arch/powerpc/kernel/iommu.c

@@ -208,7 +208,7 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	 * We don't need to disable preemption here because any CPU can
 	 * safely use any IOMMU pool.
 	 */
-	pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1);
+	pool_nr = __this_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1);
 
 	if (largealloc)
 		pool = &(tbl->large_pool);

arch/powerpc/kernel/irq.c

@@ -114,7 +114,7 @@ static inline notrace void set_soft_enabled(unsigned long enable)
 static inline notrace int decrementer_check_overflow(void)
 {
  	u64 now = get_tb_or_rtc();
- 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	return now >= *next_tb;
 }
@@ -499,7 +499,7 @@ void __do_irq(struct pt_regs *regs)
 
 	/* And finally process it */
 	if (unlikely(irq == NO_IRQ))
-		__get_cpu_var(irq_stat).spurious_irqs++;
+		__this_cpu_inc(irq_stat.spurious_irqs);
 	else
 		generic_handle_irq(irq);
 

arch/powerpc/kernel/kgdb.c

@@ -155,7 +155,7 @@ static int kgdb_singlestep(struct pt_regs *regs)
 {
 	struct thread_info *thread_info, *exception_thread_info;
 	struct thread_info *backup_current_thread_info =
-		&__get_cpu_var(kgdb_thread_info);
+		this_cpu_ptr(&kgdb_thread_info);
 
 	if (user_mode(regs))
 		return 0;

arch/powerpc/kernel/kprobes.c

@@ -119,15 +119,15 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
 }
 
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 				struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_msr = regs->msr;
 }
 
@@ -192,7 +192,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs)) {
 				goto ss_probe;
 			}

arch/powerpc/kernel/mce.c

@@ -73,8 +73,8 @@ void save_mce_event(struct pt_regs *regs, long handled,
 		    uint64_t nip, uint64_t addr)
 {
 	uint64_t srr1;
-	int index = __get_cpu_var(mce_nest_count)++;
-	struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
+	int index = __this_cpu_inc_return(mce_nest_count);
+	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
 
 	/*
 	 * Return if we don't have enough space to log mce event.
@@ -143,7 +143,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
  */
 int get_mce_event(struct machine_check_event *mce, bool release)
 {
-	int index = __get_cpu_var(mce_nest_count) - 1;
+	int index = __this_cpu_read(mce_nest_count) - 1;
 	struct machine_check_event *mc_evt;
 	int ret = 0;
 
@@ -153,7 +153,7 @@ int get_mce_event(struct machine_check_event *mce, bool release)
 
 	/* Check if we have MCE info to process. */
 	if (index < MAX_MC_EVT) {
-		mc_evt = &__get_cpu_var(mce_event[index]);
+		mc_evt = this_cpu_ptr(&mce_event[index]);
 		/* Copy the event structure and release the original */
 		if (mce)
 			*mce = *mc_evt;
@@ -163,7 +163,7 @@ int get_mce_event(struct machine_check_event *mce, bool release)
 	}
 	/* Decrement the count to free the slot. */
 	if (release)
-		__get_cpu_var(mce_nest_count)--;
+		__this_cpu_dec(mce_nest_count);
 
 	return ret;
 }
@@ -184,13 +184,13 @@ void machine_check_queue_event(void)
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
 
-	index = __get_cpu_var(mce_queue_count)++;
+	index = __this_cpu_inc_return(mce_queue_count);
 	/* If queue is full, just return for now. */
 	if (index >= MAX_MC_EVT) {
-		__get_cpu_var(mce_queue_count)--;
+		__this_cpu_dec(mce_queue_count);
 		return;
 	}
-	__get_cpu_var(mce_event_queue[index]) = evt;
+	memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt));
 
 	/* Queue irq work to process this event later. */
 	irq_work_queue(&mce_event_process_work);
@@ -208,11 +208,11 @@ static void machine_check_process_queued_event(struct irq_work *work)
 	 * For now just print it to console.
 	 * TODO: log this error event to FSP or nvram.
 	 */
-	while (__get_cpu_var(mce_queue_count) > 0) {
-		index = __get_cpu_var(mce_queue_count) - 1;
+	while (__this_cpu_read(mce_queue_count) > 0) {
+		index = __this_cpu_read(mce_queue_count) - 1;
 		machine_check_print_event_info(
-				&__get_cpu_var(mce_event_queue[index]));
-		__get_cpu_var(mce_queue_count)--;
+				this_cpu_ptr(&mce_event_queue[index]));
+		__this_cpu_dec(mce_queue_count);
 	}
 }
 

arch/powerpc/kernel/process.c

@@ -499,7 +499,7 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk)
 
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
-	__get_cpu_var(current_brk) = *brk;
+	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
 
 	if (cpu_has_feature(CPU_FTR_DAWR))
 		set_dawr(brk);
@@ -842,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
  * schedule DABR
  */
 #ifndef CONFIG_HAVE_HW_BREAKPOINT
-	if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk)))
+	if (unlikely(!hw_brk_match(this_cpu_ptr(&current_brk), &new->thread.hw_brk)))
 		__set_breakpoint(&new->thread.hw_brk);
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 #endif
@@ -856,7 +856,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	 * Collect processor utilization data per process
 	 */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		long unsigned start_tb, current_tb;
 		start_tb = old_thread->start_tb;
 		cu->current_tb = current_tb = mfspr(SPRN_PURR);
@@ -866,7 +866,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	batch = &__get_cpu_var(ppc64_tlb_batch);
+	batch = this_cpu_ptr(&ppc64_tlb_batch);
 	if (batch->active) {
 		current_thread_info()->local_flags |= _TLF_LAZY_MMU;
 		if (batch->index)
@@ -889,7 +889,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
 		current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
-		batch = &__get_cpu_var(ppc64_tlb_batch);
+		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/kernel/smp.c

@@ -243,7 +243,7 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 
 irqreturn_t smp_ipi_demux(void)
 {
-	struct cpu_messages *info = &__get_cpu_var(ipi_message);
+	struct cpu_messages *info = this_cpu_ptr(&ipi_message);
 	unsigned int all;
 
 	mb();	/* order any irq clear */
@@ -442,9 +442,9 @@ void generic_mach_cpu_die(void)
 	idle_task_exit();
 	cpu = smp_processor_id();
 	printk(KERN_DEBUG "CPU%d offline\n", cpu);
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 	smp_wmb();
-	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
+	while (__this_cpu_read(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
 }
 

arch/powerpc/kernel/sysfs.c

@@ -394,10 +394,10 @@ void ppc_enable_pmcs(void)
 	ppc_set_pmu_inuse(1);
 
 	/* Only need to enable them once */
-	if (__get_cpu_var(pmcs_enabled))
+	if (__this_cpu_read(pmcs_enabled))
 		return;
 
-	__get_cpu_var(pmcs_enabled) = 1;
+	__this_cpu_write(pmcs_enabled, 1);
 
 	if (ppc_md.enable_pmcs)
 		ppc_md.enable_pmcs();

arch/powerpc/kernel/time.c

@@ -458,9 +458,9 @@ static inline void clear_irq_work_pending(void)
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()	__this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
 #endif /* 32 vs 64 bit */
 
@@ -482,8 +482,8 @@ void arch_irq_work_raise(void)
 static void __timer_interrupt(void)
 {
 	struct pt_regs *regs = get_irq_regs();
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-	struct clock_event_device *evt = &__get_cpu_var(decrementers);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+	struct clock_event_device *evt = this_cpu_ptr(&decrementers);
 	u64 now;
 
 	trace_timer_interrupt_entry(regs);
@@ -498,21 +498,21 @@ static void __timer_interrupt(void)
 		*next_tb = ~(u64)0;
 		if (evt->event_handler)
 			evt->event_handler(evt);
-		__get_cpu_var(irq_stat).timer_irqs_event++;
+		__this_cpu_inc(irq_stat.timer_irqs_event);
 	} else {
 		now = *next_tb - now;
 		if (now <= DECREMENTER_MAX)
 			set_dec((int)now);
 		/* We may have raced with new irq work */
 		if (test_irq_work_pending())
 			set_dec(1);
-		__get_cpu_var(irq_stat).timer_irqs_others++;
+		__this_cpu_inc(irq_stat.timer_irqs_others);
 	}
 
 #ifdef CONFIG_PPC64
 	/* collect purr register values often, for accurate calculations */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
-		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
+		struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array);
 		cu->current_tb = mfspr(SPRN_PURR);
 	}
 #endif
@@ -527,7 +527,7 @@ static void __timer_interrupt(void)
 void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -813,7 +813,7 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
+	__this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt);
 	set_dec(evt);
 
 	/* We may have raced with new irq work */
@@ -833,7 +833,7 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 /* Interrupt handler for the timer broadcast IPI */
 void tick_broadcast_ipi_handler(void)
 {
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
 
 	*next_tb = get_tb_or_rtc();
 	__timer_interrupt();