ia64: 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: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: linux-ia64@vger.kernel.org
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

arch/ia64/include/asm/hw_irq.h

@@ -159,7 +159,7 @@ static inline ia64_vector __ia64_irq_to_vector(int irq)
 static inline unsigned int
 __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 

arch/ia64/include/asm/sn/arch.h

@@ -57,7 +57,7 @@ struct sn_hub_info_s {
 	u16 nasid_bitmask;
 };
 DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
-#define sn_hub_info 	(&__get_cpu_var(__sn_hub_info))
+#define sn_hub_info 	this_cpu_ptr(&__sn_hub_info)
 #define is_shub2()	(sn_hub_info->shub2)
 #define is_shub1()	(sn_hub_info->shub2 == 0)
 
@@ -72,7 +72,7 @@ DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
  * cpu.
  */
 DECLARE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
-#define sn_cnodeid_to_nasid	(&__get_cpu_var(__sn_cnodeid_to_nasid[0]))
+#define sn_cnodeid_to_nasid	this_cpu_ptr(&__sn_cnodeid_to_nasid[0])
 
 
 extern u8 sn_partition_id;

arch/ia64/include/asm/sn/nodepda.h

@@ -70,7 +70,7 @@ typedef struct nodepda_s nodepda_t;
  */
 
 DECLARE_PER_CPU(struct nodepda_s *, __sn_nodepda);
-#define sn_nodepda		(__get_cpu_var(__sn_nodepda))
+#define sn_nodepda		__this_cpu_read(__sn_nodepda)
 #define	NODEPDA(cnodeid)	(sn_nodepda->pernode_pdaindr[cnodeid])
 
 /*

arch/ia64/include/asm/switch_to.h

@@ -32,7 +32,7 @@ extern void ia64_load_extra (struct task_struct *task);
 
 #ifdef CONFIG_PERFMON
   DECLARE_PER_CPU(unsigned long, pfm_syst_info);
-# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
+# define PERFMON_IS_SYSWIDE() (__this_cpu_read(pfm_syst_info) & 0x1)
 #else
 # define PERFMON_IS_SYSWIDE() (0)
 #endif

arch/ia64/include/asm/uv/uv_hub.h

@@ -108,7 +108,7 @@ struct uv_hub_info_s {
 	unsigned char	n_val;
 };
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info 		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*

arch/ia64/kernel/irq.c

@@ -42,7 +42,7 @@ ia64_vector __ia64_irq_to_vector(int irq)
 
 unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 

arch/ia64/kernel/irq_ia64.c

@@ -330,7 +330,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 		int irq;
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
-		irq = __get_cpu_var(vector_irq)[vector];
+		irq = __this_cpu_read(vector_irq[vector]);
 		if (irq < 0)
 			continue;
 
@@ -344,7 +344,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 			goto unlock;
 
 		spin_lock_irqsave(&vector_lock, flags);
-		__get_cpu_var(vector_irq)[vector] = -1;
+		__this_cpu_write(vector_irq[vector], -1);
 		cpu_clear(me, vector_table[vector]);
 		spin_unlock_irqrestore(&vector_lock, flags);
 		cfg->move_cleanup_count--;

arch/ia64/kernel/kprobes.c

@@ -396,7 +396,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	unsigned int i;
 	i = atomic_read(&kcb->prev_kprobe_index);
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe[i-1].kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe[i-1].kp);
 	kcb->kprobe_status = kcb->prev_kprobe[i-1].status;
 	atomic_sub(1, &kcb->prev_kprobe_index);
 }
@@ -404,7 +404,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p,
 			struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static void kretprobe_trampoline(void)
@@ -823,7 +823,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			/*
 			 * jprobe instrumented function just completed
 			 */
-			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/ia64/kernel/mca.c

@@ -1341,7 +1341,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		ia64_mlogbuf_finish(1);
 	}
 
-	if (__get_cpu_var(ia64_mca_tr_reload)) {
+	if (__this_cpu_read(ia64_mca_tr_reload)) {
 		mca_insert_tr(0x1); /*Reload dynamic itrs*/
 		mca_insert_tr(0x2); /*Reload dynamic itrs*/
 	}
@@ -1868,14 +1868,14 @@ ia64_mca_cpu_init(void *cpu_data)
 		"MCA", cpu);
 	format_mca_init_stack(data, offsetof(struct ia64_mca_cpu, init_stack),
 		"INIT", cpu);
-	__get_cpu_var(ia64_mca_data) = __per_cpu_mca[cpu] = __pa(data);
+	__this_cpu_write(ia64_mca_data, (__per_cpu_mca[cpu] = __pa(data)));
 
 	/*
 	 * Stash away a copy of the PTE needed to map the per-CPU page.
 	 * We may need it during MCA recovery.
 	 */
-	__get_cpu_var(ia64_mca_per_cpu_pte) =
-		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_per_cpu_pte,
+		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL)));
 
 	/*
 	 * Also, stash away a copy of the PAL address and the PTE
@@ -1884,10 +1884,10 @@ ia64_mca_cpu_init(void *cpu_data)
 	pal_vaddr = efi_get_pal_addr();
 	if (!pal_vaddr)
 		return;
-	__get_cpu_var(ia64_mca_pal_base) =
-		GRANULEROUNDDOWN((unsigned long) pal_vaddr);
-	__get_cpu_var(ia64_mca_pal_pte) = pte_val(mk_pte_phys(__pa(pal_vaddr),
-							      PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_pal_base,
+		GRANULEROUNDDOWN((unsigned long) pal_vaddr));
+	__this_cpu_write(ia64_mca_pal_pte, pte_val(mk_pte_phys(__pa(pal_vaddr),
+							      PAGE_KERNEL)));
 }
 
 static void ia64_mca_cmc_vector_adjust(void *dummy)

arch/ia64/kernel/process.c

@@ -215,7 +215,7 @@ static inline void play_dead(void)
 	unsigned int this_cpu = smp_processor_id();
 
 	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 
 	max_xtp();
 	local_irq_disable();
@@ -273,7 +273,7 @@ ia64_save_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_save_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE)
 		pfm_syst_wide_update_task(task, info, 0);
 #endif
@@ -293,7 +293,7 @@ ia64_load_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_load_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE) 
 		pfm_syst_wide_update_task(task, info, 1);
 #endif

arch/ia64/kernel/traps.c

@@ -299,7 +299,7 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 
 	if (!(current->thread.flags & IA64_THREAD_FPEMU_NOPRINT))  {
 		unsigned long count, current_jiffies = jiffies;
-		struct fpu_swa_msg *cp = &__get_cpu_var(cpulast);
+		struct fpu_swa_msg *cp = this_cpu_ptr(&cpulast);
 
 		if (unlikely(current_jiffies > cp->time))
 			cp->count = 0;

arch/ia64/sn/kernel/sn2/sn2_smp.c

@@ -134,8 +134,8 @@ sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 	itc = ia64_get_itc();
 	smp_flush_tlb_cpumask(*mm_cpumask(mm));
 	itc = ia64_get_itc() - itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes_itc_clocks += itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes++;
+	__this_cpu_add(ptcstats.shub_ipi_flushes_itc_clocks, itc);
+	__this_cpu_inc(ptcstats.shub_ipi_flushes);
 }
 
 /**
@@ -199,14 +199,14 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 			start += (1UL << nbits);
 		} while (start < end);
 		ia64_srlz_i();
-		__get_cpu_var(ptcstats).ptc_l++;
+		__this_cpu_inc(ptcstats.ptc_l);
 		preempt_enable();
 		return;
 	}
 
 	if (atomic_read(&mm->mm_users) == 1 && mymm) {
 		flush_tlb_mm(mm);
-		__get_cpu_var(ptcstats).change_rid++;
+		__this_cpu_inc(ptcstats.change_rid);
 		preempt_enable();
 		return;
 	}
@@ -250,11 +250,11 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	spin_lock_irqsave(PTC_LOCK(shub1), flags);
 	itc2 = ia64_get_itc();
 
-	__get_cpu_var(ptcstats).lock_itc_clocks += itc2 - itc;
-	__get_cpu_var(ptcstats).shub_ptc_flushes++;
-	__get_cpu_var(ptcstats).nodes_flushed += nix;
+	__this_cpu_add(ptcstats.lock_itc_clocks, itc2 - itc);
+	__this_cpu_inc(ptcstats.shub_ptc_flushes);
+	__this_cpu_add(ptcstats.nodes_flushed, nix);
 	if (!mymm)
-		 __get_cpu_var(ptcstats).shub_ptc_flushes_not_my_mm++;
+		 __this_cpu_inc(ptcstats.shub_ptc_flushes_not_my_mm);
 
 	if (use_cpu_ptcga && !mymm) {
 		old_rr = ia64_get_rr(start);
@@ -299,9 +299,9 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 
 done:
 	itc2 = ia64_get_itc() - itc2;
-	__get_cpu_var(ptcstats).shub_itc_clocks += itc2;
-	if (itc2 > __get_cpu_var(ptcstats).shub_itc_clocks_max)
-		__get_cpu_var(ptcstats).shub_itc_clocks_max = itc2;
+	__this_cpu_add(ptcstats.shub_itc_clocks, itc2);
+	if (itc2 > __this_cpu_read(ptcstats.shub_itc_clocks_max))
+		__this_cpu_write(ptcstats.shub_itc_clocks_max, itc2);
 
 	if (old_rr) {
 		ia64_set_rr(start, old_rr);
@@ -311,7 +311,7 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	spin_unlock_irqrestore(PTC_LOCK(shub1), flags);
 
 	if (flush_opt == 1 && deadlock) {
-		__get_cpu_var(ptcstats).deadlocks++;
+		__this_cpu_inc(ptcstats.deadlocks);
 		sn2_ipi_flush_all_tlb(mm);
 	}
 
@@ -334,7 +334,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 	short nasid, i;
 	unsigned long *piows, zeroval, n;
 
-	__get_cpu_var(ptcstats).deadlocks++;
+	__this_cpu_inc(ptcstats.deadlocks);
 
 	piows = (unsigned long *) pda->pio_write_status_addr;
 	zeroval = pda->pio_write_status_val;
@@ -349,7 +349,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 			ptc1 = CHANGE_NASID(nasid, ptc1);
 
 		n = sn2_ptc_deadlock_recovery_core(ptc0, data0, ptc1, data1, piows, zeroval);
-		__get_cpu_var(ptcstats).deadlocks2 += n;
+		__this_cpu_add(ptcstats.deadlocks2, n);
 	}
 
 }