| Message ID | 20250303163014.1128035-4-david@redhat.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm: MM owner tracking for large folios (!hugetlb) + CONFIG_NO_PAGE_MAPCOUNT | expand |
On 03.03.25 17:29, David Hildenbrand wrote: > Let's free up some more of the "unconditionally available on 64BIT" > space in order-1 folios by letting _folio_nr_pages overlay memcg_data in > the first tail page (second folio page). Consequently, we have the > optimization now whenever we have CONFIG_MEMCG, independent of 64BIT. > > We have to make sure that page->memcg on tail pages does not return > "surprises". page_memcg_check() already properly refuses PageTail(). > Let's do that earlier in print_page_owner_memcg() to avoid printing > wrong "Slab cache page" information. No other code should touch that > field on tail pages of compound pages. > > Reset the "_nr_pages" to 0 when splitting folios, or when freeing them > back to the buddy (to avoid false page->memcg_data "bad page" reports). > > Note that in __split_huge_page(), folio_nr_pages() would stop working > already as soon as we start messing with the subpages. > > Most kernel configs should have at least CONFIG_MEMCG enabled, even if > disabled at runtime. 64byte "struct memmap" is what we usually have > on 64BIT. > > While at it, rename "_folio_nr_pages" to "_nr_pages". > > Hopefully memdescs / dynamically allocating "strut folio" in the future > will further clean this up, e.g., making _nr_pages available in all > configs and maybe even in small folios. Doing that should be fairly easy > on top of this change. > > Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > Signed-off-by: David Hildenbrand <david@redhat.com> > --- > include/linux/mm.h | 4 ++-- > include/linux/mm_types.h | 30 ++++++++++++++++++++++-------- > mm/huge_memory.c | 16 +++++++++++++--- > mm/internal.h | 4 ++-- > mm/page_alloc.c | 6 +++++- > mm/page_owner.c | 2 +- > 6 files changed, 45 insertions(+), 17 deletions(-) > > diff --git a/include/linux/mm.h b/include/linux/mm.h > index a743321dc1a5d..694704217df8a 100644 > --- a/include/linux/mm.h > +++ b/include/linux/mm.h > @@ -1199,10 +1199,10 @@ static inline unsigned int folio_large_order(const struct folio *folio) > return folio->_flags_1 & 0xff; > } > > -#ifdef CONFIG_64BIT > +#ifdef NR_PAGES_IN_LARGE_FOLIO > static inline long folio_large_nr_pages(const struct folio *folio) > { > - return folio->_folio_nr_pages; > + return folio->_nr_pages; > } > #else > static inline long folio_large_nr_pages(const struct folio *folio) > diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h > index 689b2a7461892..e81be20bbabc6 100644 > --- a/include/linux/mm_types.h > +++ b/include/linux/mm_types.h > @@ -287,6 +287,11 @@ typedef struct { > unsigned long val; > } swp_entry_t; > > +#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT) > +/* We have some extra room after the refcount in tail pages. */ > +#define NR_PAGES_IN_LARGE_FOLIO > +#endif > + > /** > * struct folio - Represents a contiguous set of bytes. > * @flags: Identical to the page flags. > @@ -312,7 +317,7 @@ typedef struct { > * @_large_mapcount: Do not use directly, call folio_mapcount(). > * @_nr_pages_mapped: Do not use outside of rmap and debug code. > * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). > - * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). > + * @_nr_pages: Do not use directly, call folio_nr_pages(). > * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. > * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. > * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. > @@ -377,13 +382,20 @@ struct folio { > unsigned long _flags_1; > unsigned long _head_1; > /* public: */ > - atomic_t _large_mapcount; > - atomic_t _entire_mapcount; > - atomic_t _nr_pages_mapped; > - atomic_t _pincount; > -#ifdef CONFIG_64BIT > - unsigned int _folio_nr_pages; > -#endif > + union { > + struct { > + atomic_t _large_mapcount; > + atomic_t _entire_mapcount; > + atomic_t _nr_pages_mapped; > + atomic_t _pincount; > + }; > + unsigned long _usable_1[4]; > + }; > + atomic_t _mapcount_1; > + atomic_t _refcount_1; > +#ifdef NR_PAGES_IN_LARGE_FOLIO > + unsigned int _nr_pages; > +#endif /* NR_PAGES_IN_LARGE_FOLIO */ > /* private: the union with struct page is transitional */ @Andrew The following on top to make htmldoc happy. There will be two conflicts to be resolved in two patches because of the added "/* private: " under "_pincount". It's fairly straight forward to resolve (just keep "/* private:" below any changes), but let me know if I should resend a v4 instead for this. From 9d9ff38c2ea14f1b4dab29f099ec0f6be683f3fe Mon Sep 17 00:00:00 2001 From: David Hildenbrand <david@redhat.com> Date: Wed, 5 Mar 2025 11:14:52 +0100 Subject: [PATCH] fixup: mm: let _folio_nr_pages overlay memcg_data in first tail page Make "make htmldoc" happy by marking non-private placeholder entries private. Signed-off-by: David Hildenbrand <david@redhat.com> --- include/linux/mm_types.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e81be20bbabc..6062c12c3871 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -381,18 +381,20 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; - /* public: */ union { struct { + /* public: */ atomic_t _large_mapcount; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; + /* private: the union with struct page is transitional */ }; unsigned long _usable_1[4]; }; atomic_t _mapcount_1; atomic_t _refcount_1; + /* public: */ #ifdef NR_PAGES_IN_LARGE_FOLIO unsigned int _nr_pages; #endif /* NR_PAGES_IN_LARGE_FOLIO */
diff --git a/include/linux/mm.h b/include/linux/mm.h index a743321dc1a5d..694704217df8a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1199,10 +1199,10 @@ static inline unsigned int folio_large_order(const struct folio *folio) return folio->_flags_1 & 0xff; } -#ifdef CONFIG_64BIT +#ifdef NR_PAGES_IN_LARGE_FOLIO static inline long folio_large_nr_pages(const struct folio *folio) { - return folio->_folio_nr_pages; + return folio->_nr_pages; } #else static inline long folio_large_nr_pages(const struct folio *folio) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 689b2a7461892..e81be20bbabc6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -287,6 +287,11 @@ typedef struct { unsigned long val; } swp_entry_t; +#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT) +/* We have some extra room after the refcount in tail pages. */ +#define NR_PAGES_IN_LARGE_FOLIO +#endif + /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. @@ -312,7 +317,7 @@ typedef struct { * @_large_mapcount: Do not use directly, call folio_mapcount(). * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). - * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). + * @_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. @@ -377,13 +382,20 @@ struct folio { unsigned long _flags_1; unsigned long _head_1; /* public: */ - atomic_t _large_mapcount; - atomic_t _entire_mapcount; - atomic_t _nr_pages_mapped; - atomic_t _pincount; -#ifdef CONFIG_64BIT - unsigned int _folio_nr_pages; -#endif + union { + struct { + atomic_t _large_mapcount; + atomic_t _entire_mapcount; + atomic_t _nr_pages_mapped; + atomic_t _pincount; + }; + unsigned long _usable_1[4]; + }; + atomic_t _mapcount_1; + atomic_t _refcount_1; +#ifdef NR_PAGES_IN_LARGE_FOLIO + unsigned int _nr_pages; +#endif /* NR_PAGES_IN_LARGE_FOLIO */ /* private: the union with struct page is transitional */ }; struct page __page_1; @@ -435,6 +447,8 @@ FOLIO_MATCH(_last_cpupid, _last_cpupid); offsetof(struct page, pg) + sizeof(struct page)) FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); +FOLIO_MATCH(_mapcount, _mapcount_1); +FOLIO_MATCH(_refcount, _refcount_1); #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6ac6d468af0d4..07d43ca6db1c6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3307,10 +3307,11 @@ bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) * It splits @folio into @new_order folios and copies the @folio metadata to * all the resulting folios. */ -static void __split_folio_to_order(struct folio *folio, int new_order) +static void __split_folio_to_order(struct folio *folio, int old_order, + int new_order) { - long nr_pages = folio_nr_pages(folio); long new_nr_pages = 1 << new_order; + long nr_pages = 1 << old_order; long index; /* @@ -3528,12 +3529,21 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, } } + /* + * Reset any memcg data overlay in the tail pages. + * folio_nr_pages() is unreliable until prep_compound_page() + * was called again. + */ +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif + /* complete memcg works before add pages to LRU */ split_page_memcg(&folio->page, old_order, split_order); split_page_owner(&folio->page, old_order, split_order); pgalloc_tag_split(folio, old_order, split_order); - __split_folio_to_order(folio, split_order); + __split_folio_to_order(folio, old_order, split_order); after_split: /* diff --git a/mm/internal.h b/mm/internal.h index bb9f3624cf952..bcda1f604038f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -682,8 +682,8 @@ static inline void folio_set_order(struct folio *folio, unsigned int order) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; -#ifdef CONFIG_64BIT - folio->_folio_nr_pages = 1U << order; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 1U << order; #endif } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dd7e280a61c69..ae0f2a2e87369 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1178,8 +1178,12 @@ __always_inline bool free_pages_prepare(struct page *page, if (unlikely(order)) { int i; - if (compound) + if (compound) { page[1].flags &= ~PAGE_FLAGS_SECOND; +#ifdef NR_PAGES_IN_LARGE_FOLIO + folio->_nr_pages = 0; +#endif + } for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_page_prepare(page, page + i); diff --git a/mm/page_owner.c b/mm/page_owner.c index 2d6360eaccbb6..a409e2561a8fd 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -507,7 +507,7 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret, rcu_read_lock(); memcg_data = READ_ONCE(page->memcg_data); - if (!memcg_data) + if (!memcg_data || PageTail(page)) goto out_unlock; if (memcg_data & MEMCG_DATA_OBJEXTS)