forked from luck/tmp_suning_uos_patched
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>
157 lines
3.7 KiB
C
157 lines
3.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2014 Davidlohr Bueso.
|
|
*/
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/vmacache.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
/*
|
|
* Hash based on the pmd of addr if configured with MMU, which provides a good
|
|
* hit rate for workloads with spatial locality. Otherwise, use pages.
|
|
*/
|
|
#ifdef CONFIG_MMU
|
|
#define VMACACHE_SHIFT PMD_SHIFT
|
|
#else
|
|
#define VMACACHE_SHIFT PAGE_SHIFT
|
|
#endif
|
|
#define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK)
|
|
|
|
/*
|
|
* Flush vma caches for threads that share a given mm.
|
|
*
|
|
* The operation is safe because the caller holds the mmap_sem
|
|
* exclusively and other threads accessing the vma cache will
|
|
* have mmap_sem held at least for read, so no extra locking
|
|
* is required to maintain the vma cache.
|
|
*/
|
|
void vmacache_flush_all(struct mm_struct *mm)
|
|
{
|
|
struct task_struct *g, *p;
|
|
|
|
count_vm_vmacache_event(VMACACHE_FULL_FLUSHES);
|
|
|
|
/*
|
|
* Single threaded tasks need not iterate the entire
|
|
* list of process. We can avoid the flushing as well
|
|
* since the mm's seqnum was increased and don't have
|
|
* to worry about other threads' seqnum. Current's
|
|
* flush will occur upon the next lookup.
|
|
*/
|
|
if (atomic_read(&mm->mm_users) == 1)
|
|
return;
|
|
|
|
rcu_read_lock();
|
|
for_each_process_thread(g, p) {
|
|
/*
|
|
* Only flush the vmacache pointers as the
|
|
* mm seqnum is already set and curr's will
|
|
* be set upon invalidation when the next
|
|
* lookup is done.
|
|
*/
|
|
if (mm == p->mm)
|
|
vmacache_flush(p);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* This task may be accessing a foreign mm via (for example)
|
|
* get_user_pages()->find_vma(). The vmacache is task-local and this
|
|
* task's vmacache pertains to a different mm (ie, its own). There is
|
|
* nothing we can do here.
|
|
*
|
|
* Also handle the case where a kernel thread has adopted this mm via use_mm().
|
|
* That kernel thread's vmacache is not applicable to this mm.
|
|
*/
|
|
static inline bool vmacache_valid_mm(struct mm_struct *mm)
|
|
{
|
|
return current->mm == mm && !(current->flags & PF_KTHREAD);
|
|
}
|
|
|
|
void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
|
|
{
|
|
if (vmacache_valid_mm(newvma->vm_mm))
|
|
current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma;
|
|
}
|
|
|
|
static bool vmacache_valid(struct mm_struct *mm)
|
|
{
|
|
struct task_struct *curr;
|
|
|
|
if (!vmacache_valid_mm(mm))
|
|
return false;
|
|
|
|
curr = current;
|
|
if (mm->vmacache_seqnum != curr->vmacache.seqnum) {
|
|
/*
|
|
* First attempt will always be invalid, initialize
|
|
* the new cache for this task here.
|
|
*/
|
|
curr->vmacache.seqnum = mm->vmacache_seqnum;
|
|
vmacache_flush(curr);
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
int idx = VMACACHE_HASH(addr);
|
|
int i;
|
|
|
|
count_vm_vmacache_event(VMACACHE_FIND_CALLS);
|
|
|
|
if (!vmacache_valid(mm))
|
|
return NULL;
|
|
|
|
for (i = 0; i < VMACACHE_SIZE; i++) {
|
|
struct vm_area_struct *vma = current->vmacache.vmas[idx];
|
|
|
|
if (vma) {
|
|
#ifdef CONFIG_DEBUG_VM_VMACACHE
|
|
if (WARN_ON_ONCE(vma->vm_mm != mm))
|
|
break;
|
|
#endif
|
|
if (vma->vm_start <= addr && vma->vm_end > addr) {
|
|
count_vm_vmacache_event(VMACACHE_FIND_HITS);
|
|
return vma;
|
|
}
|
|
}
|
|
if (++idx == VMACACHE_SIZE)
|
|
idx = 0;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
#ifndef CONFIG_MMU
|
|
struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
|
|
unsigned long start,
|
|
unsigned long end)
|
|
{
|
|
int idx = VMACACHE_HASH(start);
|
|
int i;
|
|
|
|
count_vm_vmacache_event(VMACACHE_FIND_CALLS);
|
|
|
|
if (!vmacache_valid(mm))
|
|
return NULL;
|
|
|
|
for (i = 0; i < VMACACHE_SIZE; i++) {
|
|
struct vm_area_struct *vma = current->vmacache.vmas[idx];
|
|
|
|
if (vma && vma->vm_start == start && vma->vm_end == end) {
|
|
count_vm_vmacache_event(VMACACHE_FIND_HITS);
|
|
return vma;
|
|
}
|
|
if (++idx == VMACACHE_SIZE)
|
|
idx = 0;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
#endif
|