ddbf369c0a
When perf profiling a wide variety of different workloads, it was found that vmacache_find() had higher than expected cost: up to 0.08% of cpu utilization in some cases. This was found to rival other core VM functions such as alloc_pages_vma() with thp enabled and default mempolicy, and the conditionals in __get_vma_policy(). VMACACHE_HASH() determines which of the four per-task_struct slots a vma is cached for a particular address. This currently depends on the pfn, so pfn 5212 occupies a different vmacache slot than its neighboring pfn 5213. vmacache_find() iterates through all four of current's vmacache slots when looking up an address. Hashing based on pfn, an address has ~1/VMACACHE_SIZE chance of being cached in the first vmacache slot, or about 25%, *if* the vma is cached. This patch hashes an address by its pmd instead of pte to optimize for workloads with good spatial locality. This results in a higher probability of vmas being cached in the first slot that is checked: normally ~70% on the same workloads instead of 25%. [rientjes@google.com: various updates] Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1807231532290.109445@chino.kir.corp.google.com Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1807091749150.114630@chino.kir.corp.google.com Signed-off-by: David Rientjes <rientjes@google.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
33 lines
871 B
C
33 lines
871 B
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_VMACACHE_H
|
|
#define __LINUX_VMACACHE_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/mm.h>
|
|
|
|
static inline void vmacache_flush(struct task_struct *tsk)
|
|
{
|
|
memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas));
|
|
}
|
|
|
|
extern void vmacache_flush_all(struct mm_struct *mm);
|
|
extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
|
|
extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
|
|
unsigned long addr);
|
|
|
|
#ifndef CONFIG_MMU
|
|
extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
|
|
unsigned long start,
|
|
unsigned long end);
|
|
#endif
|
|
|
|
static inline void vmacache_invalidate(struct mm_struct *mm)
|
|
{
|
|
mm->vmacache_seqnum++;
|
|
|
|
/* deal with overflows */
|
|
if (unlikely(mm->vmacache_seqnum == 0))
|
|
vmacache_flush_all(mm);
|
|
}
|
|
|
|
#endif /* __LINUX_VMACACHE_H */
|