sparc: Replace __get_cpu_var uses

__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 :

#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))

__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: sparclinux@vger.kernel.org
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

arch/sparc/include/asm/cpudata_32.h

@@ -26,6 +26,6 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu) per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data() __get_cpu_var(__cpu_data)
+#define local_cpu_data() (*this_cpu_ptr(&__cpu_data))
 
 #endif /* _SPARC_CPUDATA_H */

arch/sparc/include/asm/cpudata_64.h

@@ -30,7 +30,7 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data()	__get_cpu_var(__cpu_data)
+#define local_cpu_data()	(*this_cpu_ptr(&__cpu_data))
 
 #endif /* !(__ASSEMBLY__) */
 

arch/sparc/kernel/kprobes.c

@@ -83,7 +83,7 @@ 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_orig_tnpc = kcb->prev_kprobe.orig_tnpc;
 	kcb->kprobe_orig_tstate_pil = kcb->prev_kprobe.orig_tstate_pil;
@@ -92,7 +92,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 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_orig_tnpc = regs->tnpc;
 	kcb->kprobe_orig_tstate_pil = (regs->tstate & TSTATE_PIL);
 }
@@ -155,7 +155,7 @@ 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/sparc/kernel/leon_smp.c

@@ -343,7 +343,7 @@ static void leon_ipi_resched(int cpu)
 
 void leonsmp_ipi_interrupt(void)
 {
-	struct leon_ipi_work *work = &__get_cpu_var(leon_ipi_work);
+	struct leon_ipi_work *work = this_cpu_ptr(&leon_ipi_work);
 
 	if (work->single) {
 		work->single = 0;

arch/sparc/kernel/nmi.c

@@ -100,20 +100,20 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
 
 	sum = local_cpu_data().irq0_irqs;
-	if (__get_cpu_var(nmi_touch)) {
-		__get_cpu_var(nmi_touch) = 0;
+	if (__this_cpu_read(nmi_touch)) {
+		__this_cpu_write(nmi_touch, 0);
 		touched = 1;
 	}
-	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+	if (!touched && __this_cpu_read(last_irq_sum) == sum) {
 		__this_cpu_inc(alert_counter);
 		if (__this_cpu_read(alert_counter) == 30 * nmi_hz)
 			die_nmi("BUG: NMI Watchdog detected LOCKUP",
 				regs, panic_on_timeout);
 	} else {
-		__get_cpu_var(last_irq_sum) = sum;
+		__this_cpu_write(last_irq_sum, sum);
 		__this_cpu_write(alert_counter, 0);
 	}
-	if (__get_cpu_var(wd_enabled)) {
+	if (__this_cpu_read(wd_enabled)) {
 		pcr_ops->write_pic(0, pcr_ops->nmi_picl_value(nmi_hz));
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_enable);
 	}
@@ -154,7 +154,7 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 void stop_nmi_watchdog(void *unused)
 {
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
-	__get_cpu_var(wd_enabled) = 0;
+	__this_cpu_write(wd_enabled, 0);
 	atomic_dec(&nmi_active);
 }
 
@@ -207,7 +207,7 @@ error:
 
 void start_nmi_watchdog(void *unused)
 {
-	__get_cpu_var(wd_enabled) = 1;
+	__this_cpu_write(wd_enabled, 1);
 	atomic_inc(&nmi_active);
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
@@ -218,7 +218,7 @@ void start_nmi_watchdog(void *unused)
 
 static void nmi_adjust_hz_one(void *unused)
 {
-	if (!__get_cpu_var(wd_enabled))
+	if (!__this_cpu_read(wd_enabled))
 		return;
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);

arch/sparc/kernel/pci_sun4v.c

@@ -48,7 +48,7 @@ static int iommu_batch_initialized;
 /* Interrupts must be disabled.  */
 static inline void iommu_batch_start(struct device *dev, unsigned long prot, unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	p->dev		= dev;
 	p->prot		= prot;
@@ -94,7 +94,7 @@ static long iommu_batch_flush(struct iommu_batch *p)
 
 static inline void iommu_batch_new_entry(unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	if (p->entry + p->npages == entry)
 		return;
@@ -106,7 +106,7 @@ static inline void iommu_batch_new_entry(unsigned long entry)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_add(u64 phys_page)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
@@ -120,7 +120,7 @@ static inline long iommu_batch_add(u64 phys_page)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_end(void)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 

arch/sparc/kernel/perf_event.c

@@ -1013,7 +1013,7 @@ static void update_pcrs_for_enable(struct cpu_hw_events *cpuc)
 
 static void sparc_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (cpuc->enabled)
@@ -1031,7 +1031,7 @@ static void sparc_pmu_enable(struct pmu *pmu)
 
 static void sparc_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (!cpuc->enabled)
@@ -1065,7 +1065,7 @@ static int active_event_index(struct cpu_hw_events *cpuc,
 
 static void sparc_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (flags & PERF_EF_RELOAD) {
@@ -1080,7 +1080,7 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
 
 static void sparc_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -1096,7 +1096,7 @@ static void sparc_pmu_stop(struct perf_event *event, int flags)
 
 static void sparc_pmu_del(struct perf_event *event, int _flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 	int i;
 
@@ -1133,7 +1133,7 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 
 static void sparc_pmu_read(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -1145,7 +1145,7 @@ static DEFINE_MUTEX(pmc_grab_mutex);
 
 static void perf_stop_nmi_watchdog(void *unused)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	stop_nmi_watchdog(NULL);
@@ -1356,7 +1356,7 @@ static int collect_events(struct perf_event *group, int max_count,
 
 static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
@@ -1498,7 +1498,7 @@ static int sparc_pmu_event_init(struct perf_event *event)
  */
 static void sparc_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
@@ -1511,7 +1511,7 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
  */
 static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
@@ -1524,13 +1524,13 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu)
  */
 static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n;
 
 	if (!sparc_pmu)
 		return -EINVAL;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 	n = cpuc->n_events;
 	if (check_excludes(cpuc->event, 0, n))
 		return -EINVAL;
@@ -1601,7 +1601,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* If the PMU has the TOE IRQ enable bits, we need to do a
 	 * dummy write to the %pcr to clear the overflow bits and thus

arch/sparc/kernel/sun4d_smp.c

@@ -204,7 +204,7 @@ static void __init smp4d_ipi_init(void)
 
 void sun4d_ipi_interrupt(void)
 {
-	struct sun4d_ipi_work *work = &__get_cpu_var(sun4d_ipi_work);
+	struct sun4d_ipi_work *work = this_cpu_ptr(&sun4d_ipi_work);
 
 	if (work->single) {
 		work->single = 0;

arch/sparc/kernel/time_64.c

@@ -765,7 +765,7 @@ void setup_sparc64_timer(void)
 			     : /* no outputs */
 			     : "r" (pstate));
 
-	sevt = &__get_cpu_var(sparc64_events);
+	sevt = this_cpu_ptr(&sparc64_events);
 
 	memcpy(sevt, &sparc64_clockevent, sizeof(*sevt));
 	sevt->cpumask = cpumask_of(smp_processor_id());

arch/sparc/mm/tlb.c

@@ -52,14 +52,14 @@ out:
 
 void arch_enter_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	tb->active = 1;
 }
 
 void arch_leave_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	if (tb->tlb_nr)
 		flush_tlb_pending();