percpu: add optimized generic percpu accessors

It is an optimization and a cleanup, and adds the following new
generic percpu methods:

  percpu_read()
  percpu_write()
  percpu_add()
  percpu_sub()
  percpu_and()
  percpu_or()
  percpu_xor()

and implements support for them on x86. (other architectures will fall
back to a default implementation)

The advantage is that for example to read a local percpu variable,
instead of this sequence:

 return __get_cpu_var(var);

 ffffffff8102ca2b:	48 8b 14 fd 80 09 74 	mov    -0x7e8bf680(,%rdi,8),%rdx
 ffffffff8102ca32:	81
 ffffffff8102ca33:	48 c7 c0 d8 59 00 00 	mov    $0x59d8,%rax
 ffffffff8102ca3a:	48 8b 04 10          	mov    (%rax,%rdx,1),%rax

We can get a single instruction by using the optimized variants:

 return percpu_read(var);

 ffffffff8102ca3f:	65 48 8b 05 91 8f fd 	mov    %gs:0x7efd8f91(%rip),%rax

I also cleaned up the x86-specific APIs and made the x86 code use
these new generic percpu primitives.

tj: * fixed generic percpu_sub() definition as Roel Kluin pointed out
    * added percpu_and() for completeness's sake
    * made generic percpu ops atomic against preemption

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 6 insertions, 6 deletions

diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
index 7e98ce1d2c0..08b53454f83 100644
--- a/arch/x86/include/asm/mmu_context_32.h
+++ b/arch/x86/include/asm/mmu_context_32.h
@@ -4,8 +4,8 @@
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
-	if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
 }
 
@@ -19,8 +19,8 @@ static inline void switch_mm(struct mm_struct *prev,
 		/* stop flush ipis for the previous mm */
 		cpu_clear(cpu, prev->cpu_vm_mask);
 #ifdef CONFIG_SMP
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		x86_write_percpu(cpu_tlbstate.active_mm, next);
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		percpu_write(cpu_tlbstate.active_mm, next);
 #endif
 		cpu_set(cpu, next->cpu_vm_mask);
 
@@ -35,8 +35,8 @@ static inline void switch_mm(struct mm_struct *prev,
 	}
 #ifdef CONFIG_SMP
 	else {
-		x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
+		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
 
 		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
 			/* We were in lazy tlb mode and leave_mm disabled