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/include/asm/current.h b/arch/x86/include/asm/current.h
index 0930b4f..0728480 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -10,7 +10,7 @@
DECLARE_PER_CPU(struct task_struct *, current_task);
static __always_inline struct task_struct *get_current(void)
{
- return x86_read_percpu(current_task);
+ return percpu_read(current_task);
}
#else /* X86_32 */
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
index 86afd74..d7ed33ee 100644
--- a/arch/x86/include/asm/irq_regs_32.h
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -15,7 +15,7 @@
static inline struct pt_regs *get_irq_regs(void)
{
- return x86_read_percpu(irq_regs);
+ return percpu_read(irq_regs);
}
static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
@@ -23,7 +23,7 @@
struct pt_regs *old_regs;
old_regs = get_irq_regs();
- x86_write_percpu(irq_regs, new_regs);
+ percpu_write(irq_regs, new_regs);
return old_regs;
}
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
index 7e98ce1..08b5345 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 @@
/* 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 @@
}
#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
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
index e3d3a08..47f274f 100644
--- a/arch/x86/include/asm/pda.h
+++ b/arch/x86/include/asm/pda.h
@@ -45,11 +45,11 @@
#define cpu_pda(cpu) (&per_cpu(__pda, cpu))
-#define read_pda(field) x86_read_percpu(__pda.field)
-#define write_pda(field, val) x86_write_percpu(__pda.field, val)
-#define add_pda(field, val) x86_add_percpu(__pda.field, val)
-#define sub_pda(field, val) x86_sub_percpu(__pda.field, val)
-#define or_pda(field, val) x86_or_percpu(__pda.field, val)
+#define read_pda(field) percpu_read(__pda.field)
+#define write_pda(field, val) percpu_write(__pda.field, val)
+#define add_pda(field, val) percpu_add(__pda.field, val)
+#define sub_pda(field, val) percpu_sub(__pda.field, val)
+#define or_pda(field, val) percpu_or(__pda.field, val)
/* This is not atomic against other CPUs -- CPU preemption needs to be off */
#define test_and_clear_bit_pda(bit, field) \
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 328b31a..03aa4b0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -40,16 +40,11 @@
#ifdef CONFIG_SMP
#define __percpu_seg_str "%%"__stringify(__percpu_seg)":"
-#define __my_cpu_offset x86_read_percpu(this_cpu_off)
+#define __my_cpu_offset percpu_read(this_cpu_off)
#else
#define __percpu_seg_str
#endif
-#include <asm-generic/percpu.h>
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
-
/* For arch-specific code, we can use direct single-insn ops (they
* don't give an lvalue though). */
extern void __bad_percpu_size(void);
@@ -115,11 +110,13 @@
ret__; \
})
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
+#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
+#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
+#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
+#define percpu_and(var, val) percpu_to_op("and", per_cpu__##var, val)
+#define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_xor(var, val) percpu_to_op("xor", per_cpu__##var, val)
/* This is not atomic against other CPUs -- CPU preemption needs to be off */
#define x86_test_and_clear_bit_percpu(bit, var) \
@@ -131,6 +128,11 @@
old__; \
})
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
#ifdef CONFIG_X86_64
extern void load_pda_offset(int cpu);
#else
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 1274154..c7bbbbe 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -160,7 +160,7 @@
* from the initial startup. We map APIC_BASE very early in page_setup(),
* so this is correct in the x86 case.
*/
-#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+#define raw_smp_processor_id() (percpu_read(cpu_number))
extern int safe_smp_processor_id(void);
#elif defined(CONFIG_X86_64_SMP)