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, 4 insertions, 4 deletions

diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index bb042608c602..2e8271431e1a 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -39,7 +39,7 @@ static unsigned long xen_save_fl(void)
         struct vcpu_info *vcpu;
         unsigned long flags;
 
-        vcpu = x86_read_percpu(xen_vcpu);
+        vcpu = percpu_read(xen_vcpu);
 
         /* flag has opposite sense of mask */
         flags = !vcpu->evtchn_upcall_mask;
@@ -62,7 +62,7 @@ static void xen_restore_fl(unsigned long flags)
            make sure we're don't switch CPUs between getting the vcpu
            pointer and updating the mask. */
         preempt_disable();
-        vcpu = x86_read_percpu(xen_vcpu);
+        vcpu = percpu_read(xen_vcpu);
         vcpu->evtchn_upcall_mask = flags;
         preempt_enable_no_resched();
 
@@ -83,7 +83,7 @@ static void xen_irq_disable(void)
            make sure we're don't switch CPUs between getting the vcpu
            pointer and updating the mask. */
         preempt_disable();
-        x86_read_percpu(xen_vcpu)->evtchn_upcall_mask = 1;
+        percpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
         preempt_enable_no_resched();
 }
 
@@ -96,7 +96,7 @@ static void xen_irq_enable(void)
            the caller is confused and is trying to re-enable interrupts
            on an indeterminate processor. */
 
-        vcpu = x86_read_percpu(xen_vcpu);
+        vcpu = percpu_read(xen_vcpu);
         vcpu->evtchn_upcall_mask = 0;
 
         /* Doesn't matter if we get preempted here, because any