From: Zi Yan ziy@nvidia.com

It sets memcg information for the pages after the split. A new parameter new_nr is added to tell the number of subpages in the new page, always 1 for now. It prepares for upcoming changes to support split huge page to any lower order.

Signed-off-by: Zi Yan ziy@nvidia.com --- include/linux/memcontrol.h | 5 +++-- mm/huge_memory.c | 2 +- mm/memcontrol.c | 8 ++++---- mm/page_alloc.c | 2 +- 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index aa69ea98e2d8..ee1021129142 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1151,7 +1151,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, rcu_read_unlock(); }

-void split_page_memcg(struct page *head, unsigned int nr); +void split_page_memcg(struct page *head, unsigned int nr, unsigned int new_nr);

unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1588,7 +1588,8 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { }

-static inline void split_page_memcg(struct page *head, unsigned int nr) +static inline void split_page_memcg(struct page *head, unsigned int nr, + unsigned int new_nr) { }

diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 81a5689806af..30e3e300c42e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2515,7 +2515,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, int i;

/* complete memcg works before add pages to LRU */ - split_page_memcg(head, nr); + split_page_memcg(head, nr, 1);

if (PageAnon(head) && PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 681e7528a714..8e505201baf0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3414,7 +3414,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) /* * Because page_memcg(head) is not set on tails, set it now. */ -void split_page_memcg(struct page *head, unsigned int nr) +void split_page_memcg(struct page *head, unsigned int nr, unsigned int new_nr) { struct folio *folio = page_folio(head); struct mem_cgroup *memcg = folio_memcg(folio); @@ -3423,13 +3423,13 @@ void split_page_memcg(struct page *head, unsigned int nr) if (mem_cgroup_disabled() || !memcg) return;

- for (i = 1; i < nr; i++) + for (i = new_nr; i < nr; i += new_nr) folio_page(folio, i)->memcg_data = folio->memcg_data;

if (folio_memcg_kmem(folio)) - obj_cgroup_get_many(__folio_objcg(folio), nr - 1); + obj_cgroup_get_many(__folio_objcg(folio), nr / new_nr - 1); else - css_get_many(&memcg->css, nr - 1); + css_get_many(&memcg->css, nr / new_nr - 1); }

#ifdef CONFIG_SWAP diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2e72fdbdd8db..59c2b6696698 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3531,7 +3531,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); split_page_owner(page, 1 << order); - split_page_memcg(page, 1 << order); + split_page_memcg(page, 1 << order, 1); } EXPORT_SYMBOL_GPL(split_page);

From: Zi Yan ziy@nvidia.com

To split a THP to any lower order pages, we need to reform THPs on subpages at given order and add page refcount based on the new page order. Also we need to reinitialize page_deferred_list after removing the page from the split_queue, otherwise a subsequent split will see list corruption when checking the page_deferred_list again.

It has many uses, like minimizing the number of pages after truncating a huge pagecache page. For anonymous THPs, we can only split them to order-0 like before until we add support for any size anonymous THPs.

Signed-off-by: Zi Yan ziy@nvidia.com --- include/linux/huge_mm.h | 10 ++-- mm/huge_memory.c | 103 +++++++++++++++++++++++++++++----------- 2 files changed, 82 insertions(+), 31 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 20284387b841..32c91e1b59cd 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -147,10 +147,11 @@ void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page);

bool can_split_folio(struct folio *folio, int *pextra_pins); -int split_huge_page_to_list(struct page *page, struct list_head *list); +int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, + unsigned int new_order); static inline int split_huge_page(struct page *page) { - return split_huge_page_to_list(page, NULL); + return split_huge_page_to_list_to_order(page, NULL, 0); } void deferred_split_folio(struct folio *folio);

@@ -297,7 +298,8 @@ can_split_folio(struct folio *folio, int *pextra_pins) return false; } static inline int -split_huge_page_to_list(struct page *page, struct list_head *list) +split_huge_page_to_list_to_order(struct page *page, struct list_head *list, + unsigned int new_order) { return 0; } @@ -397,7 +399,7 @@ static inline bool thp_migration_supported(void) static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { - return split_huge_page_to_list(&folio->page, list); + return split_huge_page_to_list_to_order(&folio->page, list, 0); }

static inline int split_folio(struct folio *folio) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 710189885402..f119b9be33f2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2359,11 +2359,13 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,

static void unmap_folio(struct folio *folio) { - enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | - TTU_SYNC; + enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC;

VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);

+ if (folio_order(folio) >= HPAGE_PMD_ORDER) + ttu_flags |= TTU_SPLIT_HUGE_PMD; + /* * Anon pages need migration entries to preserve them, but file * pages can simply be left unmapped, then faulted back on demand. @@ -2395,7 +2397,6 @@ static void lru_add_page_tail(struct page *head, struct page *tail, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_PAGE(!PageHead(head), head); - VM_BUG_ON_PAGE(PageCompound(tail), head); VM_BUG_ON_PAGE(PageLRU(tail), head); lockdep_assert_held(&lruvec->lru_lock);

@@ -2416,9 +2417,10 @@ static void lru_add_page_tail(struct page *head, struct page *tail, }

static void __split_huge_page_tail(struct page *head, int tail, - struct lruvec *lruvec, struct list_head *list) + struct lruvec *lruvec, struct list_head *list, unsigned int new_order) { struct page *page_tail = head + tail; + unsigned long compound_head_flag = new_order ? (1L << PG_head) : 0;

VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);

@@ -2451,6 +2453,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_arch_3) | #endif (1L << PG_dirty) | + compound_head_flag | LRU_GEN_MASK | LRU_REFS_MASK));

/* ->mapping in first and second tail page is replaced by other uses */ @@ -2483,10 +2486,15 @@ static void __split_huge_page_tail(struct page *head, int tail, * which needs correct compound_head(). */ clear_compound_head(page_tail); + if (new_order) { + prep_compound_page(page_tail, new_order); + prep_transhuge_page(page_tail); + }

/* Finally unfreeze refcount. Additional reference from page cache. */ - page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || - PageSwapCache(head))); + page_ref_unfreeze(page_tail, 1 + ((!PageAnon(head) || + PageSwapCache(head)) ? + thp_nr_pages(page_tail) : 0));

if (page_is_young(head)) set_page_young(page_tail); @@ -2504,7 +2512,7 @@ static void __split_huge_page_tail(struct page *head, int tail, }

static void __split_huge_page(struct page *page, struct list_head *list, - pgoff_t end) + pgoff_t end, unsigned int new_order) { struct folio *folio = page_folio(page); struct page *head = &folio->page; @@ -2513,10 +2521,11 @@ static void __split_huge_page(struct page *page, struct list_head *list, unsigned long offset = 0; unsigned int order = thp_order(head); unsigned int nr = thp_nr_pages(head); + unsigned int new_nr = 1 << new_order; int i;

/* complete memcg works before add pages to LRU */ - split_page_memcg(head, nr, 1); + split_page_memcg(head, nr, new_nr);

if (PageAnon(head) && PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; @@ -2531,14 +2540,14 @@ static void __split_huge_page(struct page *page, struct list_head *list,

ClearPageHasHWPoisoned(head);

- for (i = nr - 1; i >= 1; i--) { - __split_huge_page_tail(head, i, lruvec, list); + for (i = nr - new_nr; i >= new_nr; i -= new_nr) { + __split_huge_page_tail(head, i, lruvec, list, new_order); /* Some pages can be beyond EOF: drop them from page cache */ if (head[i].index >= end) { struct folio *tail = page_folio(head + i);

if (shmem_mapping(head->mapping)) - shmem_uncharge(head->mapping->host, 1); + shmem_uncharge(head->mapping->host, new_nr); else if (folio_test_clear_dirty(tail)) folio_account_cleaned(tail, inode_to_wb(folio->mapping->host)); @@ -2548,29 +2557,38 @@ static void __split_huge_page(struct page *page, struct list_head *list, __xa_store(&head->mapping->i_pages, head[i].index, head + i, 0); } else if (swap_cache) { + /* + * split anonymous THPs (including swapped out ones) to + * non-zero order not supported + */ + VM_WARN_ONCE(new_order, + "Split swap-cached anon folio to non-0 order not supported"); __xa_store(&swap_cache->i_pages, offset + i, head + i, 0); } }

- ClearPageCompound(head); + if (!new_order) + ClearPageCompound(head); + else + set_compound_order(head, new_order); unlock_page_lruvec(lruvec); /* Caller disabled irqs, so they are still disabled here */

- split_page_owner(head, order, 0); + split_page_owner(head, order, new_order);

/* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { /* Additional pin to swap cache */ if (PageSwapCache(head)) { - page_ref_add(head, 2); + page_ref_add(head, 1 + new_nr); xa_unlock(&swap_cache->i_pages); } else { page_ref_inc(head); } } else { /* Additional pin to page cache */ - page_ref_add(head, 2); + page_ref_add(head, 1 + new_nr); xa_unlock(&head->mapping->i_pages); } local_irq_enable(); @@ -2583,7 +2601,14 @@ static void __split_huge_page(struct page *page, struct list_head *list, split_swap_cluster(entry); }

- for (i = 0; i < nr; i++) { + /* + * set page to its compound_head when split to THPs, so that GUP pin and + * PG_locked are transferred to the right after-split page + */ + if (new_order) + page = compound_head(page); + + for (i = 0; i < nr; i += new_nr) { struct page *subpage = head + i; if (subpage == page) continue; @@ -2617,29 +2642,31 @@ bool can_split_folio(struct folio *folio, int *pextra_pins) }

/* - * This function splits huge page into normal pages. @page can point to any - * subpage of huge page to split. Split doesn't change the position of @page. + * This function splits huge page into pages in @new_order. @page can point to + * any subpage of huge page to split. Split doesn't change the position of + * @page. * * Only caller must hold pin on the @page, otherwise split fails with -EBUSY. * The huge page must be locked. * * If @list is null, tail pages will be added to LRU list, otherwise, to @list. * - * Both head page and tail pages will inherit mapping, flags, and so on from - * the hugepage. + * Pages in new_order will inherit mapping, flags, and so on from the hugepage. * - * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if - * they are not mapped. + * GUP pin and PG_locked transferred to @page or the compound page @page belongs + * to. Rest subpages can be freed if they are not mapped. * * Returns 0 if the hugepage is split successfully. * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under * us. */ -int split_huge_page_to_list(struct page *page, struct list_head *list) +int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, + unsigned int new_order) { struct folio *folio = page_folio(page); struct deferred_split *ds_queue = get_deferred_split_queue(folio); - XA_STATE(xas, &folio->mapping->i_pages, folio->index); + /* reset xarray order to new order after split */ + XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; int extra_pins, ret; @@ -2649,6 +2676,18 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);

+ /* Cannot split THP to order-1 (no order-1 THPs) */ + if (new_order == 1) { + VM_WARN_ONCE(1, "Cannot split to order-1 folio"); + return -EINVAL; + } + + /* Split anonymous folio to non-zero order not support */ + if (folio_test_anon(folio) && new_order) { + VM_WARN_ONCE(1, "Split anon folio to non-0 order not support"); + return -EINVAL; + } + is_hzp = is_huge_zero_page(&folio->page); VM_WARN_ON_ONCE_FOLIO(is_hzp, folio); if (is_hzp) @@ -2744,7 +2783,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (folio_ref_freeze(folio, 1 + extra_pins)) { if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(&folio->_deferred_list); + /* + * Reinitialize page_deferred_list after removing the + * page from the split_queue, otherwise a subsequent + * split will see list corruption when checking the + * page_deferred_list. + */ + list_del_init(&folio->_deferred_list); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { @@ -2754,14 +2799,18 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); - } else { + } else if (!new_order) { + /* + * Decrease THP stats only if split to normal + * pages + */ __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } }

- __split_huge_page(page, list, end); + __split_huge_page(page, list, end, new_order); ret = 0; } else { spin_unlock(&ds_queue->split_queue_lock);

From: Zi Yan ziy@nvidia.com

To minimize the number of pages after a huge page truncation, we do not need to split it all the way down to order-0. The huge page has at most three parts, the part before offset, the part to be truncated, the part remaining at the end. Find the greatest common divisor of them to calculate the new page order from it, so we can split the huge page to this order and keep the remaining pages as large and as few as possible.

Signed-off-by: Zi Yan ziy@nvidia.com --- mm/truncate.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/mm/truncate.c b/mm/truncate.c index 86de31ed4d32..817efd5e94b4 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -22,6 +22,7 @@ #include <linux/buffer_head.h> /* grr. try_to_release_page */ #include <linux/shmem_fs.h> #include <linux/rmap.h> +#include <linux/gcd.h> #include "internal.h"

/* @@ -211,7 +212,8 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio) bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); - unsigned int offset, length; + unsigned int offset, length, remaining; + unsigned int new_order = folio_order(folio);

if (pos < start) offset = start - pos; @@ -222,6 +224,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) length = length - offset; else length = end + 1 - pos - offset; + remaining = folio_size(folio) - offset - length;

folio_wait_writeback(folio); if (length == folio_size(folio)) { @@ -236,11 +239,25 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) */ folio_zero_range(folio, offset, length);

+ /* + * Use the greatest common divisor of offset, length, and remaining + * as the smallest page size and compute the new order from it. So we + * can truncate a subpage as large as possible. Round up gcd to + * PAGE_SIZE, otherwise ilog2 can give -1 when gcd/PAGE_SIZE is 0. + */ + new_order = ilog2(round_up(gcd(gcd(offset, length), remaining), + PAGE_SIZE) / PAGE_SIZE); + + /* order-1 THP not supported, downgrade to order-0 */ + if (new_order == 1) + new_order = 0; + + if (folio_has_private(folio)) folio_invalidate(folio, offset, length); if (!folio_test_large(folio)) return true; - if (split_folio(folio) == 0) + if (split_huge_page_to_list_to_order(&folio->page, NULL, new_order) == 0) return true; if (folio_test_dirty(folio)) return false;