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/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a546f55..77d5468 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -591,7 +591,7 @@
if (prev->gs | next->gs)
loadsegment(gs, next->gs);
- x86_write_percpu(current_task, next_p);
+ percpu_write(current_task, next_p);
return prev_p;
}
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index ec53818..e65449d 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -34,8 +34,8 @@
*/
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 @@
* 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 @@
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);
}