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, 5 insertions, 5 deletions

diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index ec53818f4e3..e65449d0f7d 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -34,8 +34,8 @@ static DEFINE_SPINLOCK(tlbstate_lock);
  */
 void leave_mm(int cpu)
 {
-	BUG_ON(x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK);
-	cpu_clear(cpu, x86_read_percpu(cpu_tlbstate.active_mm)->cpu_vm_mask);
+	BUG_ON(percpu_read(cpu_tlbstate.state) == TLBSTATE_OK);
+	cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
 	load_cr3(swapper_pg_dir);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
@@ -103,8 +103,8 @@ void smp_invalidate_interrupt(struct pt_regs *regs)
 		 * BUG();
 		 */
 
-	if (flush_mm == x86_read_percpu(cpu_tlbstate.active_mm)) {
-		if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK) {
+	if (flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
+		if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 			if (flush_va == TLB_FLUSH_ALL)
 				local_flush_tlb();
 			else
@@ -222,7 +222,7 @@ static void do_flush_tlb_all(void *info)
 	unsigned long cpu = smp_processor_id();
 
 	__flush_tlb_all();
-	if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_LAZY)
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(cpu);
 }