On (23/09/21 17:41), Andrew Morton wrote:
> > Currently the madvise_cold_or_pageout_pte_range() function exhibits
> > significant latency under memory pressure, which can be effectively
> > reduced by adding cond_resched() within the loop.
> >
> > When the batch_count reaches SWAP_CLUSTER_MAX, we reschedule
> > the task to ensure fairness and avoid long lock holding times.
> >
> > ...
> >
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -354,6 +354,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> > struct folio *folio = NULL;
> > LIST_HEAD(folio_list);
> > bool pageout_anon_only_filter;
> > + unsigned int batch_count = 0;
> >
> > if (fatal_signal_pending(current))
> > return -EINTR;
> > @@ -433,6 +434,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> > regular_folio:
> > #endif
> > tlb_change_page_size(tlb, PAGE_SIZE);
> > +restart:
> > start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
>
> The handling of start_pte looks OK.
>
> > if (!start_pte)
> > return 0;
> > @@ -441,6 +443,15 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
> > for (; addr < end; pte++, addr += PAGE_SIZE) {
> > ptent = ptep_get(pte);
> >
> > + if (++batch_count == SWAP_CLUSTER_MAX) {
> > + batch_count = 0;
> > + if (need_resched()) {
> > + pte_unmap_unlock(start_pte, ptl);
Shouldn't it leave lazy MMU mode here?
---
diff --git a/mm/madvise.c b/mm/madvise.c
index 0f222d464254..127f0c7b69ac 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -451,6 +451,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
if (++batch_count == SWAP_CLUSTER_MAX) {
batch_count = 0;
if (need_resched()) {
+ arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
cond_resched();
goto restart;
