On Wed, Aug 14, 2024 at 11:20 PM Barry Song <baohua@xxxxxxxxxx> wrote:
>
> On Wed, Aug 14, 2024 at 11:11 PM Usama Arif <usamaarif642@xxxxxxxxx> wrote:
> >
> >
> >
> > On 14/08/2024 11:44, Barry Song wrote:
> > > On Wed, Aug 14, 2024 at 12:03 AM Usama Arif <usamaarif642@xxxxxxxxx> wrote:
> > >>
> > >> Currently folio->_deferred_list is used to keep track of
> > >> partially_mapped folios that are going to be split under memory
> > >> pressure. In the next patch, all THPs that are faulted in and collapsed
> > >> by khugepaged are also going to be tracked using _deferred_list.
> > >>
> > >> This patch introduces a pageflag to be able to distinguish between
> > >> partially mapped folios and others in the deferred_list at split time in
> > >> deferred_split_scan. Its needed as __folio_remove_rmap decrements
> > >> _mapcount, _large_mapcount and _entire_mapcount, hence it won't be
> > >> possible to distinguish between partially mapped folios and others in
> > >> deferred_split_scan.
> > >>
> > >> Eventhough it introduces an extra flag to track if the folio is
> > >> partially mapped, there is no functional change intended with this
> > >> patch and the flag is not useful in this patch itself, it will
> > >> become useful in the next patch when _deferred_list has non partially
> > >> mapped folios.
> > >>
> > >> Signed-off-by: Usama Arif <usamaarif642@xxxxxxxxx>
> > >> ---
> > >> include/linux/huge_mm.h | 4 ++--
> > >> include/linux/page-flags.h | 3 +++
> > >> mm/huge_memory.c | 21 +++++++++++++--------
> > >> mm/hugetlb.c | 1 +
> > >> mm/internal.h | 4 +++-
> > >> mm/memcontrol.c | 3 ++-
> > >> mm/migrate.c | 3 ++-
> > >> mm/page_alloc.c | 5 +++--
> > >> mm/rmap.c | 3 ++-
> > >> mm/vmscan.c | 3 ++-
> > >> 10 files changed, 33 insertions(+), 17 deletions(-)
> > >>
> > >> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> > >> index 4c32058cacfe..969f11f360d2 100644
> > >> --- a/include/linux/huge_mm.h
> > >> +++ b/include/linux/huge_mm.h
> > >> @@ -321,7 +321,7 @@ static inline int split_huge_page(struct page *page)
> > >> {
> > >> return split_huge_page_to_list_to_order(page, NULL, 0);
> > >> }
> > >> -void deferred_split_folio(struct folio *folio);
> > >> +void deferred_split_folio(struct folio *folio, bool partially_mapped);
> > >>
> > >> void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
> > >> unsigned long address, bool freeze, struct folio *folio);
> > >> @@ -495,7 +495,7 @@ static inline int split_huge_page(struct page *page)
> > >> {
> > >> return 0;
> > >> }
> > >> -static inline void deferred_split_folio(struct folio *folio) {}
> > >> +static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {}
> > >> #define split_huge_pmd(__vma, __pmd, __address) \
> > >> do { } while (0)
> > >>
> > >> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> > >> index a0a29bd092f8..cecc1bad7910 100644
> > >> --- a/include/linux/page-flags.h
> > >> +++ b/include/linux/page-flags.h
> > >> @@ -182,6 +182,7 @@ enum pageflags {
> > >> /* At least one page in this folio has the hwpoison flag set */
> > >> PG_has_hwpoisoned = PG_active,
> > >> PG_large_rmappable = PG_workingset, /* anon or file-backed */
> > >> + PG_partially_mapped, /* was identified to be partially mapped */
> > >> };
> > >>
> > >> #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1)
> > >> @@ -861,8 +862,10 @@ static inline void ClearPageCompound(struct page *page)
> > >> ClearPageHead(page);
> > >> }
> > >> FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE)
> > >> +FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
> > >> #else
> > >> FOLIO_FLAG_FALSE(large_rmappable)
> > >> +FOLIO_FLAG_FALSE(partially_mapped)
> > >> #endif
> > >>
> > >> #define PG_head_mask ((1UL << PG_head))
> > >> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> > >> index 6df0e9f4f56c..c024ab0f745c 100644
> > >> --- a/mm/huge_memory.c
> > >> +++ b/mm/huge_memory.c
> > >> @@ -3397,6 +3397,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
> > >> * page_deferred_list.
> > >> */
> > >> list_del_init(&folio->_deferred_list);
> > >> + folio_clear_partially_mapped(folio);
> > >> }
> > >> spin_unlock(&ds_queue->split_queue_lock);
> > >> if (mapping) {
> > >> @@ -3453,11 +3454,12 @@ void __folio_undo_large_rmappable(struct folio *folio)
> > >> if (!list_empty(&folio->_deferred_list)) {
> > >> ds_queue->split_queue_len--;
> > >> list_del_init(&folio->_deferred_list);
> > >> + folio_clear_partially_mapped(folio);
> > >> }
> > >> spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
> > >> }
> > >>
> > >> -void deferred_split_folio(struct folio *folio)
> > >> +void deferred_split_folio(struct folio *folio, bool partially_mapped)
> > >> {
> > >> struct deferred_split *ds_queue = get_deferred_split_queue(folio);
> > >> #ifdef CONFIG_MEMCG
> > >> @@ -3485,14 +3487,17 @@ void deferred_split_folio(struct folio *folio)
> > >> if (folio_test_swapcache(folio))
> > >> return;
> > >>
> > >> - if (!list_empty(&folio->_deferred_list))
> > >> - return;
> > >> -
> > >> spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
> > >> + if (partially_mapped)
> > >> + folio_set_partially_mapped(folio);
> > >> + else
> > >> + folio_clear_partially_mapped(folio);
> > >
> > > Hi Usama,
> > >
> > > Do we need this? When can a partially_mapped folio on deferred_list become
> > > non-partially-mapped and need a clear? I understand transferring from
> > > entirely_map
> > > to partially_mapped is a one way process? partially_mapped folios can't go back
> > > to entirely_mapped?
> > >
> > Hi Barry,
> >
> > deferred_split_folio function is called in 3 places after this series, at fault, collapse and partial mapping. partial mapping can only happen after fault/collapse, and we have FOLIO_FLAG_FALSE(partially_mapped), i.e. flag initialized to false, so technically its not needed. A partially_mapped folio on deferred list wont become non-partially mapped.
> >
> > I just did it as a precaution if someone ever changes the kernel and calls deferred_split_folio with partially_mapped set to false after it had been true. The function arguments of deferred_split_folio make it seem that passing partially_mapped=false as an argument would clear it, which is why I cleared it as well. I could change the patch to something like below if it makes things better? i.e. add a comment at the top of the function:
> >
>
> to me, it seems a BUG to call with false after a folio has been
> partially_mapped. So I'd rather
> VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio);
>
> The below should also fix the MTHP_STAT_SPLIT_DEFERRED
> counter this patch is breaking?
>
> @@ -3515,16 +3522,18 @@ void deferred_split_folio(struct folio *folio,
> bool partially_mapped)
> return;
>
> spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
> - if (partially_mapped)
> - folio_set_partially_mapped(folio);
> - else
> - folio_clear_partially_mapped(folio);
> - if (list_empty(&folio->_deferred_list)) {
> - if (partially_mapped) {
> + if (partially_mapped) {
> + if (!folio_test_set_partially_mapped(folio)) {
> + mod_mthp_stat(folio_order(folio),
> + MTHP_STAT_NR_SPLIT_DEFERRED, 1);
> if (folio_test_pmd_mappable(folio))
> count_vm_event(THP_DEFERRED_SPLIT_PAGE);
> count_mthp_stat(folio_order(folio),
> MTHP_STAT_SPLIT_DEFERRED);
> }
> + }
> + VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio);
sorry, I mean:
VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio) &&
!partially_mapped, folio);
> +
> + if (list_empty(&folio->_deferred_list)) {
> list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
> ds_queue->split_queue_len++;
> #ifdef CONFIG_MEMCG
>
>
> >
> > -void deferred_split_folio(struct folio *folio)
> > +/* partially_mapped=false won't clear PG_partially_mapped folio flag */
> > +void deferred_split_folio(struct folio *folio, bool partially_mapped)
> > {
> > struct deferred_split *ds_queue = get_deferred_split_queue(folio);
> > #ifdef CONFIG_MEMCG
> > @@ -3485,14 +3488,15 @@ void deferred_split_folio(struct folio *folio)
> > if (folio_test_swapcache(folio))
> > return;
> >
> > - if (!list_empty(&folio->_deferred_list))
> > - return;
> > -
> > spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
> > + if (partially_mapped)
> > + folio_set_partially_mapped(folio);
> > if (list_empty(&folio->_deferred_list)) {
> > - if (folio_test_pmd_mappable(folio))
> > - count_vm_event(THP_DEFERRED_SPLIT_PAGE);
> > - count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
> > + if (partially_mapped) {
> > + if (folio_test_pmd_mappable(folio))
> > + count_vm_event(THP_DEFERRED_SPLIT_PAGE);
> > + count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
> > + }
> > list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
> > ds_queue->split_queue_len++;
> > #ifdef CONFIG_MEMCG
> >
> >
> > > I am trying to rebase my NR_SPLIT_DEFERRED counter on top of your
> > > work, but this "clear" makes that job quite tricky. as I am not sure
> > > if this patch
> > > is going to clear the partially_mapped flag for folios on deferred_list.
> > >
> > > Otherwise, I can simply do the below whenever folio is leaving deferred_list
> > >
> > > ds_queue->split_queue_len--;
> > > list_del_init(&folio->_deferred_list);
> > > if (folio_test_clear_partially_mapped(folio))
> > > mod_mthp_stat(folio_order(folio),
> > > MTHP_STAT_NR_SPLIT_DEFERRED, -1);
> > >
> >
>
> Thanks
> Barry
