966a967116
struct call_single_data is used in IPIs to transfer information between CPUs. Its size is bigger than sizeof(unsigned long) and less than cache line size. Currently it is not allocated with any explicit alignment requirements. This makes it possible for allocated call_single_data to cross two cache lines, which results in double the number of the cache lines that need to be transferred among CPUs. This can be fixed by requiring call_single_data to be aligned with the size of call_single_data. Currently the size of call_single_data is the power of 2. If we add new fields to call_single_data, we may need to add padding to make sure the size of new definition is the power of 2 as well. Fortunately, this is enforced by GCC, which will report bad sizes. To set alignment requirements of call_single_data to the size of call_single_data, a struct definition and a typedef is used. To test the effect of the patch, I used the vm-scalability multiple thread swap test case (swap-w-seq-mt). The test will create multiple threads and each thread will eat memory until all RAM and part of swap is used, so that huge number of IPIs are triggered when unmapping memory. In the test, the throughput of memory writing improves ~5% compared with misaligned call_single_data, because of faster IPIs. Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Huang, Ying <ying.huang@intel.com> [ Add call_single_data_t and align with size of call_single_data. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Aaron Lu <aaron.lu@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/87bmnqd6lz.fsf@yhuang-mobile.sh.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
102 lines
2 KiB
C
102 lines
2 KiB
C
/*
|
|
* Uniprocessor-only support functions. The counterpart to kernel/smp.c
|
|
*/
|
|
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/export.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/hypervisor.h>
|
|
|
|
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
|
|
int wait)
|
|
{
|
|
unsigned long flags;
|
|
|
|
WARN_ON(cpu != 0);
|
|
|
|
local_irq_save(flags);
|
|
func(info);
|
|
local_irq_restore(flags);
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(smp_call_function_single);
|
|
|
|
int smp_call_function_single_async(int cpu, call_single_data_t *csd)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
csd->func(csd->info);
|
|
local_irq_restore(flags);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(smp_call_function_single_async);
|
|
|
|
int on_each_cpu(smp_call_func_t func, void *info, int wait)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
func(info);
|
|
local_irq_restore(flags);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(on_each_cpu);
|
|
|
|
/*
|
|
* Note we still need to test the mask even for UP
|
|
* because we actually can get an empty mask from
|
|
* code that on SMP might call us without the local
|
|
* CPU in the mask.
|
|
*/
|
|
void on_each_cpu_mask(const struct cpumask *mask,
|
|
smp_call_func_t func, void *info, bool wait)
|
|
{
|
|
unsigned long flags;
|
|
|
|
if (cpumask_test_cpu(0, mask)) {
|
|
local_irq_save(flags);
|
|
func(info);
|
|
local_irq_restore(flags);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(on_each_cpu_mask);
|
|
|
|
/*
|
|
* Preemption is disabled here to make sure the cond_func is called under the
|
|
* same condtions in UP and SMP.
|
|
*/
|
|
void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
|
|
smp_call_func_t func, void *info, bool wait,
|
|
gfp_t gfp_flags)
|
|
{
|
|
unsigned long flags;
|
|
|
|
preempt_disable();
|
|
if (cond_func(0, info)) {
|
|
local_irq_save(flags);
|
|
func(info);
|
|
local_irq_restore(flags);
|
|
}
|
|
preempt_enable();
|
|
}
|
|
EXPORT_SYMBOL(on_each_cpu_cond);
|
|
|
|
int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)
|
|
{
|
|
int ret;
|
|
|
|
if (cpu != 0)
|
|
return -ENXIO;
|
|
|
|
if (phys)
|
|
hypervisor_pin_vcpu(0);
|
|
ret = func(par);
|
|
if (phys)
|
|
hypervisor_pin_vcpu(-1);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(smp_call_on_cpu);
|