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>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 312414e..75b9413 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -695,17 +695,17 @@
static void xen_write_cr2(unsigned long cr2)
{
- x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
+ percpu_read(xen_vcpu)->arch.cr2 = cr2;
}
static unsigned long xen_read_cr2(void)
{
- return x86_read_percpu(xen_vcpu)->arch.cr2;
+ return percpu_read(xen_vcpu)->arch.cr2;
}
static unsigned long xen_read_cr2_direct(void)
{
- return x86_read_percpu(xen_vcpu_info.arch.cr2);
+ return percpu_read(xen_vcpu_info.arch.cr2);
}
static void xen_write_cr4(unsigned long cr4)
@@ -718,12 +718,12 @@
static unsigned long xen_read_cr3(void)
{
- return x86_read_percpu(xen_cr3);
+ return percpu_read(xen_cr3);
}
static void set_current_cr3(void *v)
{
- x86_write_percpu(xen_current_cr3, (unsigned long)v);
+ percpu_write(xen_current_cr3, (unsigned long)v);
}
static void __xen_write_cr3(bool kernel, unsigned long cr3)
@@ -748,7 +748,7 @@
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
if (kernel) {
- x86_write_percpu(xen_cr3, cr3);
+ percpu_write(xen_cr3, cr3);
/* Update xen_current_cr3 once the batch has actually
been submitted. */
@@ -764,7 +764,7 @@
/* Update while interrupts are disabled, so its atomic with
respect to ipis */
- x86_write_percpu(xen_cr3, cr3);
+ percpu_write(xen_cr3, cr3);
__xen_write_cr3(true, cr3);