percpu: remove per_cpu__ prefix.

Now that the return from alloc_percpu is compatible with the address
of per-cpu vars, it makes sense to hand around the address of per-cpu
variables.  To make this sane, we remove the per_cpu__ prefix we used
created to stop people accidentally using these vars directly.

Now we have sparse, we can use that (next patch).

tj: * Updated to convert stuff which were missed by or added after the
      original patch.

    * Kill per_cpu_var() macro.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>

24 files changed, 80 insertions, 90 deletions

diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index 1e7cac23e25f..a3ea7e9fe43b 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -835,8 +835,8 @@ ENDPROC(_resume)
 
 ENTRY(_ret_from_exception)
 #ifdef CONFIG_IPIPE
-        p2.l = _per_cpu__ipipe_percpu_domain;
-        p2.h = _per_cpu__ipipe_percpu_domain;
+        p2.l = _ipipe_percpu_domain;
+        p2.h = _ipipe_percpu_domain;
         r0.l = _ipipe_root;
         r0.h = _ipipe_root;
         r2 = [p2];
diff --git a/arch/cris/arch-v10/kernel/entry.S b/arch/cris/arch-v10/kernel/entry.S
index 2c18d08cd913..c52bef39e250 100644
--- a/arch/cris/arch-v10/kernel/entry.S
+++ b/arch/cris/arch-v10/kernel/entry.S
@@ -358,7 +358,7 @@ mmu_bus_fault:
 1:      btstq   12, $r1            ; Refill?
         bpl     2f
         lsrq    24, $r1     ; Get PGD index (bit 24-31)
-        move.d  [per_cpu__current_pgd], $r0 ; PGD for the current process
+        move.d  [current_pgd], $r0 ; PGD for the current process
         move.d  [$r0+$r1.d], $r0   ; Get PMD
         beq     2f
         nop
diff --git a/arch/cris/arch-v32/mm/mmu.S b/arch/cris/arch-v32/mm/mmu.S
index 2238d154bde3..f125d912e140 100644
--- a/arch/cris/arch-v32/mm/mmu.S
+++ b/arch/cris/arch-v32/mm/mmu.S
@@ -115,7 +115,7 @@
 #ifdef CONFIG_SMP
         move    $s7, $acr       ; PGD
 #else
-        move.d  per_cpu__current_pgd, $acr ; PGD
+        move.d  current_pgd, $acr ; PGD
 #endif
         ; Look up PMD in PGD
         lsrq    24, $r0 ; Get PMD index into PGD (bit 24-31)
diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h
index 30cf46534dd2..f7c00a5e0e2b 100644
--- a/arch/ia64/include/asm/percpu.h
+++ b/arch/ia64/include/asm/percpu.h
@@ -9,7 +9,7 @@
 #define PERCPU_ENOUGH_ROOM PERCPU_PAGE_SIZE
 
 #ifdef __ASSEMBLY__
-# define THIS_CPU(var)  (per_cpu__##var)  /* use this to mark accesses to per-CPU variables... */
+# define THIS_CPU(var)  (var)  /* use this to mark accesses to per-CPU variables... */
 #else /* !__ASSEMBLY__ */
 
 
@@ -39,7 +39,7 @@ extern void *per_cpu_init(void);
  * On the positive side, using __ia64_per_cpu_var() instead of __get_cpu_var() is slightly
  * more efficient.
  */
-#define __ia64_per_cpu_var(var) per_cpu__##var
+#define __ia64_per_cpu_var(var) var
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 461b99902bf6..7f4a0ed24152 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -30,9 +30,9 @@ EXPORT_SYMBOL(max_low_pfn);	/* defined by bootmem.c, but not exported by generic
 #endif
 
 #include <asm/processor.h>
-EXPORT_SYMBOL(per_cpu__ia64_cpu_info);
+EXPORT_SYMBOL(ia64_cpu_info);
 #ifdef CONFIG_SMP
-EXPORT_SYMBOL(per_cpu__local_per_cpu_offset);
+EXPORT_SYMBOL(local_per_cpu_offset);
 #endif
 
 #include <asm/uaccess.h>
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 19c4b2195dce..8d586d1e2515 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -459,7 +459,7 @@ static void __init initialize_pernode_data(void)
                 cpu = 0;
                 node = node_cpuid[cpu].nid;
                 cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
-                        ((char *)&per_cpu__ia64_cpu_info - __per_cpu_start));
+                        ((char *)&ia64_cpu_info - __per_cpu_start));
                 cpu0_cpu_info->node_data = mem_data[node].node_data;
         }
 #endif /* CONFIG_SMP */
diff --git a/arch/microblaze/include/asm/entry.h b/arch/microblaze/include/asm/entry.h
index 61abbd232640..ec89f2ad0fe1 100644
--- a/arch/microblaze/include/asm/entry.h
+++ b/arch/microblaze/include/asm/entry.h
@@ -21,7 +21,7 @@
  * places
  */
 
-#define PER_CPU(var) per_cpu__##var
+#define PER_CPU(var) var
 
 # ifndef __ASSEMBLY__
 DECLARE_PER_CPU(unsigned int, KSP); /* Saved kernel stack pointer */
diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S
index d172d4245cdc..f8c45cc2947d 100644
--- a/arch/parisc/lib/fixup.S
+++ b/arch/parisc/lib/fixup.S
@@ -36,8 +36,8 @@
 #endif
         /* t2 = &__per_cpu_offset[smp_processor_id()]; */
         LDREGX \t2(\t1),\t2 
-        addil LT%per_cpu__exception_data,%r27
-        LDREG RT%per_cpu__exception_data(%r1),\t1
+        addil LT%exception_data,%r27
+        LDREG RT%exception_data(%r1),\t1
         /* t1 = &__get_cpu_var(exception_data) */
         add,l \t1,\t2,\t1
         /* t1 = t1->fault_ip */
@@ -46,8 +46,8 @@
 #else
         .macro  get_fault_ip t1 t2
         /* t1 = &__get_cpu_var(exception_data) */
-        addil LT%per_cpu__exception_data,%r27
-        LDREG RT%per_cpu__exception_data(%r1),\t2
+        addil LT%exception_data,%r27
+        LDREG RT%exception_data(%r1),\t2
         /* t1 = t2->fault_ip */
         LDREG EXCDATA_IP(\t2), \t1
         .endm
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index c1427b3634ec..580f789cae7f 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -55,7 +55,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
         /* calculate address of stat structure r4 = opcode */   \
         srdi    r4,r4,2;                /* index into array */  \
         mulli   r4,r4,HCALL_STAT_SIZE;                          \
-        LOAD_REG_ADDR(r7, per_cpu__hcall_stats);                \
+        LOAD_REG_ADDR(r7, hcall_stats);                         \
         add     r4,r4,r7;                                       \
         ld      r7,PACA_DATA_OFFSET(r13); /* per cpu offset */  \
         add     r4,r4,r7;                                       \
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index f30f4a1ead23..2ad288ff99a4 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -112,13 +112,13 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
                 touched = 1;
         }
         if (!touched && __get_cpu_var(last_irq_sum) == sum) {
-                __this_cpu_inc(per_cpu_var(alert_counter));
-                if (__this_cpu_read(per_cpu_var(alert_counter)) == 30 * nmi_hz)
+                __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(per_cpu_var(alert_counter), 0);
+                __this_cpu_write(alert_counter, 0);
         }
         if (__get_cpu_var(wd_enabled)) {
                 write_pic(picl_value(nmi_hz));
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index fd3cee4d117c..1ddec403f512 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -149,11 +149,11 @@ rtrap_nmi:	ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
 rtrap_irq:
 rtrap:
 #ifndef CONFIG_SMP
-                sethi                   %hi(per_cpu____cpu_data), %l0
-                lduw                    [%l0 + %lo(per_cpu____cpu_data)], %l1
+                sethi                   %hi(__cpu_data), %l0
+                lduw                    [%l0 + %lo(__cpu_data)], %l1
 #else
-                sethi                   %hi(per_cpu____cpu_data), %l0
-                or                      %l0, %lo(per_cpu____cpu_data), %l0
+                sethi                   %hi(__cpu_data), %l0
+                or                      %l0, %lo(__cpu_data), %l0
                 lduw                    [%l0 + %g5], %l1
 #endif
                 cmp                     %l1, 0
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0c44196b78ac..4c170ccc72ed 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -25,19 +25,18 @@
  */
 #ifdef CONFIG_SMP
 #define PER_CPU(var, reg)                                               \
-        __percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg;       \
-        lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)        %__percpu_seg:per_cpu__##var
+        __percpu_mov_op %__percpu_seg:this_cpu_off, reg;                \
+        lea var(reg), reg
+#define PER_CPU_VAR(var)        %__percpu_seg:var
 #else /* ! SMP */
-#define PER_CPU(var, reg)                                               \
-        __percpu_mov_op $per_cpu__##var, reg
-#define PER_CPU_VAR(var)        per_cpu__##var
+#define PER_CPU(var, reg)       __percpu_mov_op $var, reg
+#define PER_CPU_VAR(var)        var
 #endif  /* SMP */
 
 #ifdef CONFIG_X86_64_SMP
 #define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
 #else
-#define INIT_PER_CPU_VAR(var)  per_cpu__##var
+#define INIT_PER_CPU_VAR(var)  var
 #endif
 
 #else /* ...!ASSEMBLY */
@@ -60,12 +59,12 @@
  * There also must be an entry in vmlinux_64.lds.S
  */
 #define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
+       extern typeof(var) init_per_cpu_var(var)
 
 #ifdef CONFIG_X86_64_SMP
 #define init_per_cpu_var(var)  init_per_cpu__##var
 #else
-#define init_per_cpu_var(var)  per_cpu_var(var)
+#define init_per_cpu_var(var)  var
 #endif
 
 /* For arch-specific code, we can use direct single-insn ops (they
@@ -142,16 +141,14 @@ do {							\
  * per-thread variables implemented as per-cpu variables and thus
  * stable for the duration of the respective task.
  */
-#define percpu_read(var)        percpu_from_op("mov", per_cpu__##var,   \
-                                               "m" (per_cpu__##var))
-#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var,   \
-                                               "p" (&per_cpu__##var))
-#define percpu_write(var, val)  percpu_to_op("mov", per_cpu__##var, val)
-#define percpu_add(var, val)    percpu_to_op("add", per_cpu__##var, val)
-#define percpu_sub(var, val)    percpu_to_op("sub", per_cpu__##var, val)
-#define percpu_and(var, val)    percpu_to_op("and", per_cpu__##var, val)
-#define percpu_or(var, val)     percpu_to_op("or", per_cpu__##var, val)
-#define percpu_xor(var, val)    percpu_to_op("xor", per_cpu__##var, val)
+#define percpu_read(var)                percpu_from_op("mov", var, "m" (var))
+#define percpu_read_stable(var)         percpu_from_op("mov", var, "p" (&(var)))
+#define percpu_write(var, val)          percpu_to_op("mov", var, val)
+#define percpu_add(var, val)            percpu_to_op("add", var, val)
+#define percpu_sub(var, val)            percpu_to_op("sub", var, val)
+#define percpu_and(var, val)            percpu_to_op("and", var, val)
+#define percpu_or(var, val)             percpu_to_op("or", var, val)
+#define percpu_xor(var, val)            percpu_to_op("xor", var, val)
 
 #define __this_cpu_read_1(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
 #define __this_cpu_read_2(pcp)          percpu_from_op("mov", (pcp), "m"(pcp))
@@ -236,7 +233,7 @@ do {							\
 ({                                                                      \
         int old__;                                                      \
         asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"           \
-                     : "=r" (old__), "+m" (per_cpu__##var)              \
+                     : "=r" (old__), "+m" (var)                         \
                      : "dIr" (bit));                                    \
         old__;                                                          \
 })
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index f08f97374892..de10c19d9558 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -31,7 +31,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
         "movl %P[task_canary](%[next]), %%ebx\n\t"                      \
         "movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
 #define __switch_canary_oparam                                          \
-        , [stack_canary] "=m" (per_cpu_var(stack_canary.canary))
+        , [stack_canary] "=m" (stack_canary.canary)
 #define __switch_canary_iparam                                          \
         , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else   /* CC_STACKPROTECTOR */
@@ -113,7 +113,7 @@ do {									\
         "movq %P[task_canary](%%rsi),%%r8\n\t"                            \
         "movq %%r8,"__percpu_arg([gs_canary])"\n\t"
 #define __switch_canary_oparam                                            \
-        , [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary))
+        , [gs_canary] "=m" (irq_stack_union.stack_canary)
 #define __switch_canary_iparam                                            \
         , [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else   /* CC_STACKPROTECTOR */
@@ -134,7 +134,7 @@ do {									\
              __switch_canary                                              \
              "movq %P[thread_info](%%rsi),%%r8\n\t"                       \
              "movq %%rax,%%rdi\n\t"                                       \
-             "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"         \
+             "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"                 \
              "jnz   ret_from_fork\n\t"                                    \
              RESTORE_CONTEXT                                              \
              : "=a" (last)                                                \
@@ -144,7 +144,7 @@ do {									\
                [ti_flags] "i" (offsetof(struct thread_info, flags)),      \
                [_tif_fork] "i" (_TIF_FORK),                               \
                [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-               [current_task] "m" (per_cpu_var(current_task))             \
+               [current_task] "m" (current_task)                          \
                __switch_canary_iparam                                     \
              : "memory", "cc" __EXTRA_CLOBBER)
 #endif
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index e631cc4416f7..45404379d173 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -437,8 +437,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
                  * Ayiee, looks like this CPU is stuck ...
                  * wait a few IRQs (5 seconds) before doing the oops ...
                  */
-                __this_cpu_inc(per_cpu_var(alert_counter));
-                if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz)
+                __this_cpu_inc(alert_counter);
+                if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
                         /*
                          * die_nmi will return ONLY if NOTIFY_STOP happens..
                          */
@@ -446,7 +446,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
                                 regs, panic_on_timeout);
         } else {
                 __get_cpu_var(last_irq_sum) = sum;
-                __this_cpu_write(per_cpu_var(alert_counter), 0);
+                __this_cpu_write(alert_counter, 0);
         }
 
         /* see if the nmi watchdog went off */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 050c278481b1..fd39eaf83b84 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -438,8 +438,8 @@ is386:	movl $2,%ecx		# set MP
          */
         cmpb $0,ready
         jne 1f
-        movl $per_cpu__gdt_page,%eax
-        movl $per_cpu__stack_canary,%ecx
+        movl $gdt_page,%eax
+        movl $stack_canary,%ecx
         movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
         shrl $16, %ecx
         movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
@@ -702,7 +702,7 @@ idt_descr:
         .word 0                         # 32 bit align gdt_desc.address
 ENTRY(early_gdt_descr)
         .word GDT_ENTRIES*8-1
-        .long per_cpu__gdt_page         /* Overwritten for secondary CPUs */
+        .long gdt_page                  /* Overwritten for secondary CPUs */
 
 /*
  * The boot_gdt must mirror the equivalent in setup.S and is
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 92929fb3f9fa..ecb92717c412 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -312,7 +312,7 @@ SECTIONS
  * Per-cpu symbols which need to be offset from __per_cpu_load
  * for the boot processor.
  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load
 INIT_PER_CPU(gdt_page);
 INIT_PER_CPU(irq_stack_union);
 
@@ -323,7 +323,7 @@ INIT_PER_CPU(irq_stack_union);
            "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-. = ASSERT((per_cpu__irq_stack_union == 0),
+. = ASSERT((irq_stack_union == 0),
            "irq_stack_union is not at start of per-cpu area");
 #endif
 
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 88e15deb8b82..22a2093b5862 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -90,9 +90,9 @@ ENTRY(xen_iret)
         GET_THREAD_INFO(%eax)
         movl TI_cpu(%eax), %eax
         movl __per_cpu_offset(,%eax,4), %eax
-        mov per_cpu__xen_vcpu(%eax), %eax
+        mov xen_vcpu(%eax), %eax
 #else
-        movl per_cpu__xen_vcpu, %eax
+        movl xen_vcpu, %eax
 #endif
 
         /* check IF state we're restoring */
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 8087b90d4673..ca6f0491412b 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -50,11 +50,11 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
  * offset.
  */
 #define per_cpu(var, cpu) \
-        (*SHIFT_PERCPU_PTR(&per_cpu_var(var), per_cpu_offset(cpu)))
+        (*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
 #define __get_cpu_var(var) \
-        (*SHIFT_PERCPU_PTR(&per_cpu_var(var), my_cpu_offset))
+        (*SHIFT_PERCPU_PTR(&(var), my_cpu_offset))
 #define __raw_get_cpu_var(var) \
-        (*SHIFT_PERCPU_PTR(&per_cpu_var(var), __my_cpu_offset))
+        (*SHIFT_PERCPU_PTR(&(var), __my_cpu_offset))
 
 #define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
 #define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
@@ -66,9 +66,9 @@ extern void setup_per_cpu_areas(void);
 
 #else /* ! SMP */
 
-#define per_cpu(var, cpu)                       (*((void)(cpu), &per_cpu_var(var)))
-#define __get_cpu_var(var)                      per_cpu_var(var)
-#define __raw_get_cpu_var(var)                  per_cpu_var(var)
+#define per_cpu(var, cpu)                       (*((void)(cpu), &(var)))
+#define __get_cpu_var(var)                      (var)
+#define __raw_get_cpu_var(var)                  (var)
 #define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
 #define __this_cpu_ptr(ptr) this_cpu_ptr(ptr)
 
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5a5d6ce4bd55..ee99f6c2cdcd 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -2,12 +2,6 @@
 #define _LINUX_PERCPU_DEFS_H
 
 /*
- * Determine the real variable name from the name visible in the
- * kernel sources.
- */
-#define per_cpu_var(var) per_cpu__##var
-
-/*
  * Base implementations of per-CPU variable declarations and definitions, where
  * the section in which the variable is to be placed is provided by the
  * 'sec' argument.  This may be used to affect the parameters governing the
@@ -56,24 +50,24 @@
  */
 #define DECLARE_PER_CPU_SECTION(type, name, sec)                        \
         extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name;             \
-        extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+        extern __PCPU_ATTRS(sec) __typeof__(type) name
 
 #define DEFINE_PER_CPU_SECTION(type, name, sec)                         \
         __PCPU_DUMMY_ATTRS char __pcpu_scope_##name;                    \
         extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name;            \
         __PCPU_DUMMY_ATTRS char __pcpu_unique_##name;                   \
         __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak                 \
-        __typeof__(type) per_cpu__##name
+        __typeof__(type) name
 #else
 /*
  * Normal declaration and definition macros.
  */
 #define DECLARE_PER_CPU_SECTION(type, name, sec)                        \
-        extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+        extern __PCPU_ATTRS(sec) __typeof__(type) name
 
 #define DEFINE_PER_CPU_SECTION(type, name, sec)                         \
         __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES                        \
-        __typeof__(type) per_cpu__##name
+        __typeof__(type) name
 #endif
 
 /*
@@ -137,8 +131,8 @@
 /*
  * Intermodule exports for per-CPU variables.
  */
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(var)
 
 
 #endif /* _LINUX_PERCPU_DEFS_H */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 522f421ec213..e12410e55e05 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -182,7 +182,7 @@ static inline void *pcpu_lpage_remapped(void *kaddr)
 #ifndef percpu_read
 # define percpu_read(var)                                               \
   ({                                                                    \
-        typeof(per_cpu_var(var)) __tmp_var__;                           \
+        typeof(var) __tmp_var__;                                        \
         __tmp_var__ = get_cpu_var(var);                                 \
         put_cpu_var(var);                                               \
         __tmp_var__;                                                    \
@@ -253,8 +253,7 @@ do {									\
 
 /*
  * Optimized manipulation for memory allocated through the per cpu
- * allocator or for addresses of per cpu variables (can be determined
- * using per_cpu_var(xx).
+ * allocator or for addresses of per cpu variables.
  *
  * These operation guarantee exclusivity of access for other operations
  * on the *same* processor. The assumption is that per cpu data is only
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d85889710f9b..3e489fda11a1 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -76,22 +76,22 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
 
 static inline void __count_vm_event(enum vm_event_item item)
 {
-        __this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
+        __this_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void count_vm_event(enum vm_event_item item)
 {
-        this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
+        this_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-        __this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
+        __this_cpu_add(vm_event_states.event[item], delta);
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
 {
-        this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
+        this_cpu_add(vm_event_states.event[item], delta);
 }
 
 extern void all_vm_events(unsigned long *);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 178967b6434e..e339ab349121 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -731,13 +731,13 @@ static void rcu_torture_timer(unsigned long unused)
                 /* Should not happen, but... */
                 pipe_count = RCU_TORTURE_PIPE_LEN;
         }
-        __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
+        __this_cpu_inc(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;
         }
-        __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
+        __this_cpu_inc(rcu_torture_batch[completed]);
         preempt_enable();
         cur_ops->readunlock(idx);
 }
@@ -786,13 +786,13 @@ rcu_torture_reader(void *arg)
                         /* Should not happen, but... */
                         pipe_count = RCU_TORTURE_PIPE_LEN;
                 }
-                __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
+                __this_cpu_inc(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;
                 }
-                __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
+                __this_cpu_inc(rcu_torture_batch[completed]);
                 preempt_enable();
                 cur_ops->readunlock(idx);
                 schedule();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 85a5ed70b5b2..b808177af816 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -91,12 +91,12 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 static inline void ftrace_disable_cpu(void)
 {
         preempt_disable();
-        __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
+        __this_cpu_inc(ftrace_cpu_disabled);
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-        __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
+        __this_cpu_dec(ftrace_cpu_disabled);
         preempt_enable();
 }
 
@@ -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(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
                 return;
 
         event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 90a6daa10962..8614e3241ff8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -176,7 +176,7 @@ static int __trace_graph_entry(struct trace_array *tr,
         struct ring_buffer *buffer = tr->buffer;
         struct ftrace_graph_ent_entry *entry;
 
-        if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
                 return 0;
 
         event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -240,7 +240,7 @@ static void __trace_graph_return(struct trace_array *tr,
         struct ring_buffer *buffer = tr->buffer;
         struct ftrace_graph_ret_entry *entry;
 
-        if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
                 return;
 
         event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,