diff options
Diffstat (limited to 'mm/migrate.c')
| -rw-r--r-- | mm/migrate.c | 3825 |
1 files changed, 1606 insertions, 2219 deletions
diff --git a/mm/migrate.c b/mm/migrate.c index c7da064b4781..5169f9717f60 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -16,12 +16,10 @@ #include <linux/migrate.h> #include <linux/export.h> #include <linux/swap.h> -#include <linux/swapops.h> +#include <linux/leafops.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/mm_inline.h> -#include <linux/nsproxy.h> -#include <linux/pagevec.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/topology.h> @@ -36,32 +34,90 @@ #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/hugetlb.h> -#include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> -#include <linux/pagewalk.h> -#include <linux/pfn_t.h> -#include <linux/memremap.h> -#include <linux/userfaultfd_k.h> -#include <linux/balloon_compaction.h> -#include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/page_owner.h> #include <linux/sched/mm.h> #include <linux/ptrace.h> -#include <linux/oom.h> #include <linux/memory.h> -#include <linux/random.h> +#include <linux/sched/sysctl.h> +#include <linux/memory-tiers.h> +#include <linux/pagewalk.h> #include <asm/tlbflush.h> -#define CREATE_TRACE_POINTS #include <trace/events/migrate.h> #include "internal.h" +#include "swap.h" + +static const struct movable_operations *offline_movable_ops; +static const struct movable_operations *zsmalloc_movable_ops; + +int set_movable_ops(const struct movable_operations *ops, enum pagetype type) +{ + /* + * We only allow for selected types and don't handle concurrent + * registration attempts yet. + */ + switch (type) { + case PGTY_offline: + if (offline_movable_ops && ops) + return -EBUSY; + offline_movable_ops = ops; + break; + case PGTY_zsmalloc: + if (zsmalloc_movable_ops && ops) + return -EBUSY; + zsmalloc_movable_ops = ops; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL_GPL(set_movable_ops); + +static const struct movable_operations *page_movable_ops(struct page *page) +{ + VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); -int isolate_movable_page(struct page *page, isolate_mode_t mode) + /* + * If we enable page migration for a page of a certain type by marking + * it as movable, the page type must be sticky until the page gets freed + * back to the buddy. + */ + if (PageOffline(page)) + /* Only balloon compaction sets PageOffline pages movable. */ + return offline_movable_ops; + if (PageZsmalloc(page)) + return zsmalloc_movable_ops; + + return NULL; +} + +/** + * isolate_movable_ops_page - isolate a movable_ops page for migration + * @page: The page. + * @mode: The isolation mode. + * + * Try to isolate a movable_ops page for migration. Will fail if the page is + * not a movable_ops page, if the page is already isolated for migration + * or if the page was just was released by its owner. + * + * Once isolated, the page cannot get freed until it is either putback + * or migrated. + * + * Returns true if isolation succeeded, otherwise false. + */ +bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode) { - struct address_space *mapping; + /* + * TODO: these pages will not be folios in the future. All + * folio dependencies will have to be removed. + */ + struct folio *folio = folio_get_nontail_page(page); + const struct movable_operations *mops; /* * Avoid burning cycles with pages that are yet under __free_pages(), @@ -72,16 +128,20 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) * the put_page() at the end of this block will take care of * release this page, thus avoiding a nasty leakage. */ - if (unlikely(!get_page_unless_zero(page))) + if (!folio) goto out; /* - * Check PageMovable before holding a PG_lock because page's owner - * assumes anybody doesn't touch PG_lock of newly allocated page - * so unconditionally grabbing the lock ruins page's owner side. + * Check for movable_ops pages before taking the page lock because + * we use non-atomic bitops on newly allocated page flags so + * unconditionally grabbing the lock ruins page's owner side. + * + * Note that once a page has movable_ops, it will stay that way + * until the page was freed. */ - if (unlikely(!__PageMovable(page))) - goto out_putpage; + if (unlikely(!page_has_movable_ops(page))) + goto out_putfolio; + /* * As movable pages are not isolated from LRU lists, concurrent * compaction threads can race against page migration functions @@ -93,40 +153,97 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) * lets be sure we have the page lock * before proceeding with the movable page isolation steps. */ - if (unlikely(!trylock_page(page))) - goto out_putpage; + if (unlikely(!folio_trylock(folio))) + goto out_putfolio; - if (!PageMovable(page) || PageIsolated(page)) + VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); + if (PageMovableOpsIsolated(page)) goto out_no_isolated; - mapping = page_mapping(page); - VM_BUG_ON_PAGE(!mapping, page); + mops = page_movable_ops(page); + if (WARN_ON_ONCE(!mops)) + goto out_no_isolated; - if (!mapping->a_ops->isolate_page(page, mode)) + if (!mops->isolate_page(page, mode)) goto out_no_isolated; - /* Driver shouldn't use PG_isolated bit of page->flags */ - WARN_ON_ONCE(PageIsolated(page)); - __SetPageIsolated(page); - unlock_page(page); + /* Driver shouldn't use the isolated flag */ + VM_WARN_ON_ONCE_PAGE(PageMovableOpsIsolated(page), page); + SetPageMovableOpsIsolated(page); + folio_unlock(folio); - return 0; + return true; out_no_isolated: - unlock_page(page); -out_putpage: - put_page(page); + folio_unlock(folio); +out_putfolio: + folio_put(folio); out: - return -EBUSY; + return false; } -static void putback_movable_page(struct page *page) +/** + * putback_movable_ops_page - putback an isolated movable_ops page + * @page: The isolated page. + * + * Putback an isolated movable_ops page. + * + * After the page was putback, it might get freed instantly. + */ +static void putback_movable_ops_page(struct page *page) +{ + /* + * TODO: these pages will not be folios in the future. All + * folio dependencies will have to be removed. + */ + struct folio *folio = page_folio(page); + + VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); + VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(page), page); + folio_lock(folio); + page_movable_ops(page)->putback_page(page); + ClearPageMovableOpsIsolated(page); + folio_unlock(folio); + folio_put(folio); +} + +/** + * migrate_movable_ops_page - migrate an isolated movable_ops page + * @dst: The destination page. + * @src: The source page. + * @mode: The migration mode. + * + * Migrate an isolated movable_ops page. + * + * If the src page was already released by its owner, the src page is + * un-isolated (putback) and migration succeeds; the migration core will be the + * owner of both pages. + * + * If the src page was not released by its owner and the migration was + * successful, the owner of the src page and the dst page are swapped and + * the src page is un-isolated. + * + * If migration fails, the ownership stays unmodified and the src page + * remains isolated: migration may be retried later or the page can be putback. + * + * TODO: migration core will treat both pages as folios and lock them before + * this call to unlock them after this call. Further, the folio refcounts on + * src and dst are also released by migration core. These pages will not be + * folios in the future, so that must be reworked. + * + * Returns 0 on success, otherwise a negative error code. + */ +static int migrate_movable_ops_page(struct page *dst, struct page *src, + enum migrate_mode mode) { - struct address_space *mapping; + int rc; - mapping = page_mapping(page); - mapping->a_ops->putback_page(page); - __ClearPageIsolated(page); + VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(src), src); + VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(src), src); + rc = page_movable_ops(src)->migrate_page(dst, src, mode); + if (!rc) + ClearPageMovableOpsIsolated(src); + return rc; } /* @@ -135,88 +252,151 @@ static void putback_movable_page(struct page *page) * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() - * and isolate_huge_page(). + * and folio_isolate_hugetlb(). */ void putback_movable_pages(struct list_head *l) { - struct page *page; - struct page *page2; + struct folio *folio; + struct folio *folio2; - list_for_each_entry_safe(page, page2, l, lru) { - if (unlikely(PageHuge(page))) { - putback_active_hugepage(page); + list_for_each_entry_safe(folio, folio2, l, lru) { + if (unlikely(folio_test_hugetlb(folio))) { + folio_putback_hugetlb(folio); continue; } - list_del(&page->lru); - /* - * We isolated non-lru movable page so here we can use - * __PageMovable because LRU page's mapping cannot have - * PAGE_MAPPING_MOVABLE. - */ - if (unlikely(__PageMovable(page))) { - VM_BUG_ON_PAGE(!PageIsolated(page), page); - lock_page(page); - if (PageMovable(page)) - putback_movable_page(page); - else - __ClearPageIsolated(page); - unlock_page(page); - put_page(page); + list_del(&folio->lru); + if (unlikely(page_has_movable_ops(&folio->page))) { + putback_movable_ops_page(&folio->page); } else { - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + - page_is_file_lru(page), -thp_nr_pages(page)); - putback_lru_page(page); + node_stat_mod_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio), -folio_nr_pages(folio)); + folio_putback_lru(folio); } } } +/* Must be called with an elevated refcount on the non-hugetlb folio */ +bool isolate_folio_to_list(struct folio *folio, struct list_head *list) +{ + if (folio_test_hugetlb(folio)) + return folio_isolate_hugetlb(folio, list); + + if (page_has_movable_ops(&folio->page)) { + if (!isolate_movable_ops_page(&folio->page, + ISOLATE_UNEVICTABLE)) + return false; + } else { + if (!folio_isolate_lru(folio)) + return false; + node_stat_add_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); + } + list_add(&folio->lru, list); + return true; +} + +static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, + struct folio *folio, pte_t old_pte, unsigned long idx) +{ + struct page *page = folio_page(folio, idx); + pte_t newpte; + + if (PageCompound(page) || PageHWPoison(page)) + return false; + + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(pte_present(old_pte), page); + VM_WARN_ON_ONCE_FOLIO(folio_is_device_private(folio), folio); + + if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || + mm_forbids_zeropage(pvmw->vma->vm_mm)) + return false; + + /* + * The pmd entry mapping the old thp was flushed and the pte mapping + * this subpage has been non present. If the subpage is only zero-filled + * then map it to the shared zeropage. + */ + if (!pages_identical(page, ZERO_PAGE(0))) + return false; + + newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address), + pvmw->vma->vm_page_prot)); + + if (pte_swp_soft_dirty(old_pte)) + newpte = pte_mksoft_dirty(newpte); + if (pte_swp_uffd_wp(old_pte)) + newpte = pte_mkuffd_wp(newpte); + + set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); + + dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); + return true; +} + +struct rmap_walk_arg { + struct folio *folio; + bool map_unused_to_zeropage; +}; + /* * Restore a potential migration pte to a working pte entry */ -static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, - unsigned long addr, void *old) +static bool remove_migration_pte(struct folio *folio, + struct vm_area_struct *vma, unsigned long addr, void *arg) { - struct page_vma_mapped_walk pvmw = { - .page = old, - .vma = vma, - .address = addr, - .flags = PVMW_SYNC | PVMW_MIGRATION, - }; - struct page *new; - pte_t pte; - swp_entry_t entry; + struct rmap_walk_arg *rmap_walk_arg = arg; + DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); - VM_BUG_ON_PAGE(PageTail(page), page); while (page_vma_mapped_walk(&pvmw)) { - if (PageKsm(page)) - new = page; - else - new = page - pvmw.page->index + - linear_page_index(vma, pvmw.address); + rmap_t rmap_flags = RMAP_NONE; + pte_t old_pte; + pte_t pte; + softleaf_t entry; + struct page *new; + unsigned long idx = 0; + + /* pgoff is invalid for ksm pages, but they are never large */ + if (folio_test_large(folio) && !folio_test_hugetlb(folio)) + idx = linear_page_index(vma, pvmw.address) - pvmw.pgoff; + new = folio_page(folio, idx); #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte) { - VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); + VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || + !folio_test_pmd_mappable(folio), folio); remove_migration_pmd(&pvmw, new); continue; } #endif + old_pte = ptep_get(pvmw.pte); + if (rmap_walk_arg->map_unused_to_zeropage && + try_to_map_unused_to_zeropage(&pvmw, folio, old_pte, idx)) + continue; - get_page(new); - pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); - if (pte_swp_soft_dirty(*pvmw.pte)) + folio_get(folio); + pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); + + entry = softleaf_from_pte(old_pte); + if (!softleaf_is_migration_young(entry)) + pte = pte_mkold(pte); + if (folio_test_dirty(folio) && softleaf_is_migration_dirty(entry)) + pte = pte_mkdirty(pte); + if (pte_swp_soft_dirty(old_pte)) pte = pte_mksoft_dirty(pte); + else + pte = pte_clear_soft_dirty(pte); - /* - * Recheck VMA as permissions can change since migration started - */ - entry = pte_to_swp_entry(*pvmw.pte); - if (is_writable_migration_entry(entry)) - pte = maybe_mkwrite(pte, vma); - else if (pte_swp_uffd_wp(*pvmw.pte)) + if (softleaf_is_migration_write(entry)) + pte = pte_mkwrite(pte, vma); + else if (pte_swp_uffd_wp(old_pte)) pte = pte_mkuffd_wp(pte); + if (folio_test_anon(folio) && !softleaf_is_migration_read(entry)) + rmap_flags |= RMAP_EXCLUSIVE; + if (unlikely(is_device_private_page(new))) { if (pte_write(pte)) entry = make_writable_device_private_entry( @@ -224,38 +404,42 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, else entry = make_readable_device_private_entry( page_to_pfn(new)); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*pvmw.pte)) + pte = softleaf_to_pte(entry); + if (pte_swp_soft_dirty(old_pte)) pte = pte_swp_mksoft_dirty(pte); - if (pte_swp_uffd_wp(*pvmw.pte)) + if (pte_swp_uffd_wp(old_pte)) pte = pte_swp_mkuffd_wp(pte); } #ifdef CONFIG_HUGETLB_PAGE - if (PageHuge(new)) { - unsigned int shift = huge_page_shift(hstate_vma(vma)); + if (folio_test_hugetlb(folio)) { + struct hstate *h = hstate_vma(vma); + unsigned int shift = huge_page_shift(h); + unsigned long psize = huge_page_size(h); - pte = pte_mkhuge(pte); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); - if (PageAnon(new)) - hugepage_add_anon_rmap(new, vma, pvmw.address); + if (folio_test_anon(folio)) + hugetlb_add_anon_rmap(folio, vma, pvmw.address, + rmap_flags); else - page_dup_rmap(new, true); - set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); + hugetlb_add_file_rmap(folio); + set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, + psize); } else #endif { - if (PageAnon(new)) - page_add_anon_rmap(new, vma, pvmw.address, false); + if (folio_test_anon(folio)) + folio_add_anon_rmap_pte(folio, new, vma, + pvmw.address, rmap_flags); else - page_add_file_rmap(new, false); + folio_add_file_rmap_pte(folio, new, vma); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } - if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) - mlock_vma_page(new); + if (READ_ONCE(vma->vm_flags) & VM_LOCKED) + mlock_drain_local(); - if (PageTransHuge(page) && PageMlocked(page)) - clear_page_mlock(page); + trace_remove_migration_pte(pvmw.address, pte_val(pte), + compound_order(new)); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); @@ -268,17 +452,24 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, * Get rid of all migration entries and replace them by * references to the indicated page. */ -void remove_migration_ptes(struct page *old, struct page *new, bool locked) +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags) { + struct rmap_walk_arg rmap_walk_arg = { + .folio = src, + .map_unused_to_zeropage = flags & RMP_USE_SHARED_ZEROPAGE, + }; + struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, - .arg = old, + .arg = &rmap_walk_arg, }; - if (locked) - rmap_walk_locked(new, &rwc); + VM_BUG_ON_FOLIO((flags & RMP_USE_SHARED_ZEROPAGE) && (src != dst), src); + + if (flags & RMP_LOCKED) + rmap_walk_locked(dst, &rwc); else - rmap_walk(new, &rwc); + rmap_walk(dst, &rwc); } /* @@ -286,41 +477,72 @@ void remove_migration_ptes(struct page *old, struct page *new, bool locked) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, - spinlock_t *ptl) +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) { + spinlock_t *ptl; + pte_t *ptep; pte_t pte; - swp_entry_t entry; + softleaf_t entry; - spin_lock(ptl); - pte = *ptep; - if (!is_swap_pte(pte)) + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!ptep) + return; + + pte = ptep_get(ptep); + pte_unmap(ptep); + + if (pte_none(pte) || pte_present(pte)) goto out; - entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry)) + entry = softleaf_from_pte(pte); + if (!softleaf_is_migration(entry)) goto out; - migration_entry_wait_on_locked(entry, ptep, ptl); + migration_entry_wait_on_locked(entry, ptl); return; out: - pte_unmap_unlock(ptep, ptl); + spin_unlock(ptl); } -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +#ifdef CONFIG_HUGETLB_PAGE +/* + * The vma read lock must be held upon entry. Holding that lock prevents either + * the pte or the ptl from being freed. + * + * This function will release the vma lock before returning. + */ +void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - spinlock_t *ptl = pte_lockptr(mm, pmd); - pte_t *ptep = pte_offset_map(pmd, address); - __migration_entry_wait(mm, ptep, ptl); -} + spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, ptep); + softleaf_t entry; + pte_t pte; -void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte) -{ - spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte); - __migration_entry_wait(mm, pte, ptl); + hugetlb_vma_assert_locked(vma); + spin_lock(ptl); + pte = huge_ptep_get(vma->vm_mm, addr, ptep); + + if (huge_pte_none(pte)) + goto fail; + + entry = softleaf_from_pte(pte); + if (softleaf_is_migration(entry)) { + /* + * If migration entry existed, safe to release vma lock + * here because the pgtable page won't be freed without the + * pgtable lock released. See comment right above pgtable + * lock release in migration_entry_wait_on_locked(). + */ + hugetlb_vma_unlock_read(vma); + migration_entry_wait_on_locked(entry, ptl); + return; + } + +fail: + spin_unlock(ptl); + hugetlb_vma_unlock_read(vma); } +#endif #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) @@ -328,113 +550,120 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) spinlock_t *ptl; ptl = pmd_lock(mm, pmd); - if (!is_pmd_migration_entry(*pmd)) + if (!pmd_is_migration_entry(*pmd)) goto unlock; - migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), NULL, ptl); + migration_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl); return; unlock: spin_unlock(ptl); } #endif -static int expected_page_refs(struct address_space *mapping, struct page *page) -{ - int expected_count = 1; - - /* - * Device private pages have an extra refcount as they are - * ZONE_DEVICE pages. - */ - expected_count += is_device_private_page(page); - if (mapping) - expected_count += compound_nr(page) + page_has_private(page); - - return expected_count; -} - /* - * Replace the page in the mapping. + * Replace the folio in the mapping. * * The number of remaining references must be: - * 1 for anonymous pages without a mapping - * 2 for pages with a mapping - * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. + * 1 for anonymous folios without a mapping + * 2 for folios with a mapping + * 3 for folios with a mapping and the private flag set. */ -int folio_migrate_mapping(struct address_space *mapping, - struct folio *newfolio, struct folio *folio, int extra_count) +static int __folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int expected_count) { - XA_STATE(xas, &mapping->i_pages, folio_index(folio)); + XA_STATE(xas, &mapping->i_pages, folio->index); + struct swap_cluster_info *ci = NULL; struct zone *oldzone, *newzone; int dirty; - int expected_count = expected_page_refs(mapping, &folio->page) + extra_count; long nr = folio_nr_pages(folio); if (!mapping) { - /* Anonymous page without mapping */ - if (folio_ref_count(folio) != expected_count) - return -EAGAIN; + /* Take off deferred split queue while frozen and memcg set */ + if (folio_test_large(folio) && + folio_test_large_rmappable(folio)) { + if (!folio_ref_freeze(folio, expected_count)) + return -EAGAIN; + folio_unqueue_deferred_split(folio); + folio_ref_unfreeze(folio, expected_count); + } /* No turning back from here */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; + if (folio_test_anon(folio) && folio_test_large(folio)) + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); - return MIGRATEPAGE_SUCCESS; + return 0; } oldzone = folio_zone(folio); newzone = folio_zone(newfolio); - xas_lock_irq(&xas); + if (folio_test_swapcache(folio)) + ci = swap_cluster_get_and_lock_irq(folio); + else + xas_lock_irq(&xas); + if (!folio_ref_freeze(folio, expected_count)) { - xas_unlock_irq(&xas); + if (ci) + swap_cluster_unlock_irq(ci); + else + xas_unlock_irq(&xas); return -EAGAIN; } + /* Take off deferred split queue while frozen and memcg set */ + folio_unqueue_deferred_split(folio); + /* * Now we know that no one else is looking at the folio: * no turning back from here. */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; + if (folio_test_anon(folio) && folio_test_large(folio)) + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); folio_ref_add(newfolio, nr); /* add cache reference */ - if (folio_test_swapbacked(folio)) { + if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); - if (folio_test_swapcache(folio)) { - folio_set_swapcache(newfolio); - newfolio->private = folio_get_private(folio); - } - } else { - VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); + if (folio_test_swapcache(folio)) { + folio_set_swapcache(newfolio); + newfolio->private = folio_get_private(folio); } - /* Move dirty while page refs frozen and newpage not yet exposed */ + /* Move dirty while folio refs frozen and newfolio not yet exposed */ dirty = folio_test_dirty(folio); if (dirty) { folio_clear_dirty(folio); folio_set_dirty(newfolio); } - xas_store(&xas, newfolio); + if (folio_test_swapcache(folio)) + __swap_cache_replace_folio(ci, folio, newfolio); + else + xas_store(&xas, newfolio); /* - * Drop cache reference from old page by unfreezing + * Drop cache reference from old folio by unfreezing * to one less reference. * We know this isn't the last reference. */ folio_ref_unfreeze(folio, expected_count - nr); - xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ + if (ci) + swap_cluster_unlock(ci); + else + xas_unlock(&xas); /* * If moved to a different zone then also account - * the page for that zone. Other VM counters will be + * the folio for that zone. Other VM counters will be * taken care of when we establish references to the - * new page and drop references to the old page. + * new folio and drop references to the old folio. * - * Note that anonymous pages are accounted for + * Note that anonymous folios are accounted for * via NR_FILE_PAGES and NR_ANON_MAPPED if they * are mapped to swap space. */ @@ -446,28 +675,44 @@ int folio_migrate_mapping(struct address_space *mapping, old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); - __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); - __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); + mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); + mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) { - __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); - __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); + mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); + mod_lruvec_state(new_lruvec, NR_SHMEM, nr); + + if (folio_test_pmd_mappable(folio)) { + mod_lruvec_state(old_lruvec, NR_SHMEM_THPS, -nr); + mod_lruvec_state(new_lruvec, NR_SHMEM_THPS, nr); + } } #ifdef CONFIG_SWAP if (folio_test_swapcache(folio)) { - __mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr); - __mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr); + mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr); + mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr); } #endif if (dirty && mapping_can_writeback(mapping)) { - __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); + mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr); - __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr); + mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr); __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr); } } local_irq_enable(); - return MIGRATEPAGE_SUCCESS; + return 0; +} + +int folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int extra_count) +{ + int expected_count = folio_expected_ref_count(folio) + extra_count + 1; + + if (folio_ref_count(folio) != expected_count) + return -EAGAIN; + + return __folio_migrate_mapping(mapping, newfolio, folio, expected_count); } EXPORT_SYMBOL(folio_migrate_mapping); @@ -476,35 +721,36 @@ EXPORT_SYMBOL(folio_migrate_mapping); * of folio_migrate_mapping(). */ int migrate_huge_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page) + struct folio *dst, struct folio *src) { - XA_STATE(xas, &mapping->i_pages, page_index(page)); - int expected_count; + XA_STATE(xas, &mapping->i_pages, src->index); + int rc, expected_count = folio_expected_ref_count(src) + 1; - xas_lock_irq(&xas); - expected_count = 2 + page_has_private(page); - if (page_count(page) != expected_count || xas_load(&xas) != page) { - xas_unlock_irq(&xas); + if (folio_ref_count(src) != expected_count) return -EAGAIN; - } - if (!page_ref_freeze(page, expected_count)) { + rc = folio_mc_copy(dst, src); + if (unlikely(rc)) + return rc; + + xas_lock_irq(&xas); + if (!folio_ref_freeze(src, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; } - newpage->index = page->index; - newpage->mapping = page->mapping; + dst->index = src->index; + dst->mapping = src->mapping; - get_page(newpage); + folio_ref_add(dst, folio_nr_pages(dst)); - xas_store(&xas, newpage); + xas_store(&xas, dst); - page_ref_unfreeze(page, expected_count - 1); + folio_ref_unfreeze(src, expected_count - folio_nr_pages(src)); xas_unlock_irq(&xas); - return MIGRATEPAGE_SUCCESS; + return 0; } /* @@ -514,8 +760,6 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) { int cpupid; - if (folio_test_error(folio)) - folio_set_error(newfolio); if (folio_test_referenced(folio)) folio_set_referenced(newfolio); if (folio_test_uptodate(folio)) @@ -529,6 +773,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_workingset(newfolio); if (folio_test_checked(folio)) folio_set_checked(newfolio); + /* + * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via + * migration entries. We can still have PG_anon_exclusive set on an + * effectively unmapped and unreferenced first sub-pages of an + * anonymous THP: we can simply copy it here via PG_mappedtodisk. + */ if (folio_test_mappedtodisk(folio)) folio_set_mappedtodisk(newfolio); @@ -541,17 +791,31 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) if (folio_test_idle(folio)) folio_set_idle(newfolio); + folio_migrate_refs(newfolio, folio); /* * Copy NUMA information to the new page, to prevent over-eager * future migrations of this same page. */ - cpupid = page_cpupid_xchg_last(&folio->page, -1); - page_cpupid_xchg_last(&newfolio->page, cpupid); + cpupid = folio_xchg_last_cpupid(folio, -1); + /* + * For memory tiering mode, when migrate between slow and fast + * memory node, reset cpupid, because that is used to record + * page access time in slow memory node. + */ + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) { + bool f_toptier = node_is_toptier(folio_nid(folio)); + bool t_toptier = node_is_toptier(folio_nid(newfolio)); + + if (f_toptier != t_toptier) + cpupid = -1; + } + folio_xchg_last_cpupid(newfolio, cpupid); folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's - * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). + * ksm_get_folio() depends upon ksm_migrate_page() and the + * swapcache flag. */ if (folio_test_swapcache(folio)) folio_clear_swapcache(folio); @@ -577,118 +841,124 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_readahead(newfolio); folio_copy_owner(newfolio, folio); + pgalloc_tag_swap(newfolio, folio); - if (!folio_test_hugetlb(folio)) - mem_cgroup_migrate(folio, newfolio); + mem_cgroup_migrate(folio, newfolio); } EXPORT_SYMBOL(folio_migrate_flags); -void folio_migrate_copy(struct folio *newfolio, struct folio *folio) -{ - folio_copy(newfolio, folio); - folio_migrate_flags(newfolio, folio); -} -EXPORT_SYMBOL(folio_migrate_copy); - /************************************************************ * Migration functions ***********************************************************/ -/* - * Common logic to directly migrate a single LRU page suitable for - * pages that do not use PagePrivate/PagePrivate2. - * - * Pages are locked upon entry and exit. - */ -int migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, - enum migrate_mode mode) +static int __migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, void *src_private, + enum migrate_mode mode) { - struct folio *newfolio = page_folio(newpage); - struct folio *folio = page_folio(page); - int rc; + int rc, expected_count = folio_expected_ref_count(src) + 1; - BUG_ON(folio_test_writeback(folio)); /* Writeback must be complete */ + /* Check whether src does not have extra refs before we do more work */ + if (folio_ref_count(src) != expected_count) + return -EAGAIN; - rc = folio_migrate_mapping(mapping, newfolio, folio, 0); + rc = folio_mc_copy(dst, src); + if (unlikely(rc)) + return rc; - if (rc != MIGRATEPAGE_SUCCESS) + rc = __folio_migrate_mapping(mapping, dst, src, expected_count); + if (rc) return rc; - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(newfolio, folio); - else - folio_migrate_flags(newfolio, folio); - return MIGRATEPAGE_SUCCESS; + if (src_private) + folio_attach_private(dst, folio_detach_private(src)); + + folio_migrate_flags(dst, src); + return 0; +} + +/** + * migrate_folio() - Simple folio migration. + * @mapping: The address_space containing the folio. + * @dst: The folio to migrate the data to. + * @src: The folio containing the current data. + * @mode: How to migrate the page. + * + * Common logic to directly migrate a single LRU folio suitable for + * folios that do not have private data. + * + * Folios are locked upon entry and exit. + */ +int migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode) +{ + BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ + return __migrate_folio(mapping, dst, src, NULL, mode); } -EXPORT_SYMBOL(migrate_page); +EXPORT_SYMBOL(migrate_folio); -#ifdef CONFIG_BLOCK +#ifdef CONFIG_BUFFER_HEAD /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, enum migrate_mode mode) { struct buffer_head *bh = head; + struct buffer_head *failed_bh; - /* Simple case, sync compaction */ - if (mode != MIGRATE_ASYNC) { - do { - lock_buffer(bh); - bh = bh->b_this_page; - - } while (bh != head); - - return true; - } - - /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { if (!trylock_buffer(bh)) { - /* - * We failed to lock the buffer and cannot stall in - * async migration. Release the taken locks - */ - struct buffer_head *failed_bh = bh; - bh = head; - while (bh != failed_bh) { - unlock_buffer(bh); - bh = bh->b_this_page; - } - return false; + if (mode == MIGRATE_ASYNC) + goto unlock; + if (mode == MIGRATE_SYNC_LIGHT && !buffer_uptodate(bh)) + goto unlock; + lock_buffer(bh); } bh = bh->b_this_page; } while (bh != head); + return true; + +unlock: + /* We failed to lock the buffer and cannot stall. */ + failed_bh = bh; + bh = head; + while (bh != failed_bh) { + unlock_buffer(bh); + bh = bh->b_this_page; + } + + return false; } -static int __buffer_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, enum migrate_mode mode, +static int __buffer_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, enum migrate_mode mode, bool check_refs) { struct buffer_head *bh, *head; int rc; int expected_count; - if (!page_has_buffers(page)) - return migrate_page(mapping, newpage, page, mode); + head = folio_buffers(src); + if (!head) + return migrate_folio(mapping, dst, src, mode); /* Check whether page does not have extra refs before we do more work */ - expected_count = expected_page_refs(mapping, page); - if (page_count(page) != expected_count) + expected_count = folio_expected_ref_count(src) + 1; + if (folio_ref_count(src) != expected_count) return -EAGAIN; - head = page_buffers(page); if (!buffer_migrate_lock_buffers(head, mode)) return -EAGAIN; if (check_refs) { - bool busy; + bool busy, migrating; bool invalidated = false; + migrating = test_and_set_bit_lock(BH_Migrate, &head->b_state); + VM_WARN_ON_ONCE(migrating); recheck_buffers: busy = false; - spin_lock(&mapping->private_lock); + spin_lock(&mapping->i_private_lock); bh = head; do { if (atomic_read(&bh->b_count)) { @@ -697,243 +967,259 @@ recheck_buffers: } bh = bh->b_this_page; } while (bh != head); + spin_unlock(&mapping->i_private_lock); if (busy) { if (invalidated) { rc = -EAGAIN; goto unlock_buffers; } - spin_unlock(&mapping->private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; } } - rc = migrate_page_move_mapping(mapping, newpage, page, 0); - if (rc != MIGRATEPAGE_SUCCESS) + rc = filemap_migrate_folio(mapping, dst, src, mode); + if (rc) goto unlock_buffers; - attach_page_private(newpage, detach_page_private(page)); - bh = head; do { - set_bh_page(bh, newpage, bh_offset(bh)); + folio_set_bh(bh, dst, bh_offset(bh)); bh = bh->b_this_page; - } while (bh != head); - if (mode != MIGRATE_SYNC_NO_COPY) - migrate_page_copy(newpage, page); - else - migrate_page_states(newpage, page); - - rc = MIGRATEPAGE_SUCCESS; unlock_buffers: if (check_refs) - spin_unlock(&mapping->private_lock); + clear_bit_unlock(BH_Migrate, &head->b_state); bh = head; do { unlock_buffer(bh); bh = bh->b_this_page; - } while (bh != head); return rc; } -/* - * Migration function for pages with buffers. This function can only be used - * if the underlying filesystem guarantees that no other references to "page" - * exist. For example attached buffer heads are accessed only under page lock. +/** + * buffer_migrate_folio() - Migration function for folios with buffers. + * @mapping: The address space containing @src. + * @dst: The folio to migrate to. + * @src: The folio to migrate from. + * @mode: How to migrate the folio. + * + * This function can only be used if the underlying filesystem guarantees + * that no other references to @src exist. For example attached buffer + * heads are accessed only under the folio lock. If your filesystem cannot + * provide this guarantee, buffer_migrate_folio_norefs() may be more + * appropriate. + * + * Return: 0 on success or a negative errno on failure. */ -int buffer_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, enum migrate_mode mode) +int buffer_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, enum migrate_mode mode) { - return __buffer_migrate_page(mapping, newpage, page, mode, false); + return __buffer_migrate_folio(mapping, dst, src, mode, false); } -EXPORT_SYMBOL(buffer_migrate_page); +EXPORT_SYMBOL(buffer_migrate_folio); -/* - * Same as above except that this variant is more careful and checks that there - * are also no buffer head references. This function is the right one for - * mappings where buffer heads are directly looked up and referenced (such as - * block device mappings). +/** + * buffer_migrate_folio_norefs() - Migration function for folios with buffers. + * @mapping: The address space containing @src. + * @dst: The folio to migrate to. + * @src: The folio to migrate from. + * @mode: How to migrate the folio. + * + * Like buffer_migrate_folio() except that this variant is more careful + * and checks that there are also no buffer head references. This function + * is the right one for mappings where buffer heads are directly looked + * up and referenced (such as block device mappings). + * + * Return: 0 on success or a negative errno on failure. */ -int buffer_migrate_page_norefs(struct address_space *mapping, - struct page *newpage, struct page *page, enum migrate_mode mode) +int buffer_migrate_folio_norefs(struct address_space *mapping, + struct folio *dst, struct folio *src, enum migrate_mode mode) { - return __buffer_migrate_page(mapping, newpage, page, mode, true); + return __buffer_migrate_folio(mapping, dst, src, mode, true); } -#endif +EXPORT_SYMBOL_GPL(buffer_migrate_folio_norefs); +#endif /* CONFIG_BUFFER_HEAD */ -/* - * Writeback a page to clean the dirty state - */ -static int writeout(struct address_space *mapping, struct page *page) +int filemap_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, enum migrate_mode mode) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = 1, - .range_start = 0, - .range_end = LLONG_MAX, - .for_reclaim = 1 - }; - int rc; - - if (!mapping->a_ops->writepage) - /* No write method for the address space */ - return -EINVAL; - - if (!clear_page_dirty_for_io(page)) - /* Someone else already triggered a write */ - return -EAGAIN; - - /* - * A dirty page may imply that the underlying filesystem has - * the page on some queue. So the page must be clean for - * migration. Writeout may mean we loose the lock and the - * page state is no longer what we checked for earlier. - * At this point we know that the migration attempt cannot - * be successful. - */ - remove_migration_ptes(page, page, false); - - rc = mapping->a_ops->writepage(page, &wbc); - - if (rc != AOP_WRITEPAGE_ACTIVATE) - /* unlocked. Relock */ - lock_page(page); - - return (rc < 0) ? -EIO : -EAGAIN; + return __migrate_folio(mapping, dst, src, folio_get_private(src), mode); } +EXPORT_SYMBOL_GPL(filemap_migrate_folio); /* * Default handling if a filesystem does not provide a migration function. */ -static int fallback_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, enum migrate_mode mode) +static int fallback_migrate_folio(struct address_space *mapping, + struct folio *dst, struct folio *src, enum migrate_mode mode) { - if (PageDirty(page)) { - /* Only writeback pages in full synchronous migration */ - switch (mode) { - case MIGRATE_SYNC: - case MIGRATE_SYNC_NO_COPY: - break; - default: - return -EBUSY; - } - return writeout(mapping, page); - } + WARN_ONCE(mapping->a_ops->writepages, + "%ps does not implement migrate_folio\n", + mapping->a_ops); + if (folio_test_dirty(src)) + return -EBUSY; /* - * Buffers may be managed in a filesystem specific way. - * We must have no buffers or drop them. + * Filesystem may have private data at folio->private that we + * can't migrate automatically. */ - if (page_has_private(page) && - !try_to_release_page(page, GFP_KERNEL)) + if (!filemap_release_folio(src, GFP_KERNEL)) return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY; - return migrate_page(mapping, newpage, page, mode); + return migrate_folio(mapping, dst, src, mode); } /* - * Move a page to a newly allocated page - * The page is locked and all ptes have been successfully removed. + * Move a src folio to a newly allocated dst folio. + * + * The src and dst folios are locked and the src folios was unmapped from + * the page tables. * - * The new page will have replaced the old page if this function - * is successful. + * On success, the src folio was replaced by the dst folio. * * Return value: * < 0 - error code - * MIGRATEPAGE_SUCCESS - success + * 0 - success */ -static int move_to_new_page(struct page *newpage, struct page *page, +static int move_to_new_folio(struct folio *dst, struct folio *src, enum migrate_mode mode) { - struct address_space *mapping; + struct address_space *mapping = folio_mapping(src); int rc = -EAGAIN; - bool is_lru = !__PageMovable(page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(src), src); + VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst); - mapping = page_mapping(page); + if (!mapping) + rc = migrate_folio(mapping, dst, src, mode); + else if (mapping_inaccessible(mapping)) + rc = -EOPNOTSUPP; + else if (mapping->a_ops->migrate_folio) + /* + * Most folios have a mapping and most filesystems + * provide a migrate_folio callback. Anonymous folios + * are part of swap space which also has its own + * migrate_folio callback. This is the most common path + * for page migration. + */ + rc = mapping->a_ops->migrate_folio(mapping, dst, src, + mode); + else + rc = fallback_migrate_folio(mapping, dst, src, mode); - if (likely(is_lru)) { - if (!mapping) - rc = migrate_page(mapping, newpage, page, mode); - else if (mapping->a_ops->migratepage) - /* - * Most pages have a mapping and most filesystems - * provide a migratepage callback. Anonymous pages - * are part of swap space which also has its own - * migratepage callback. This is the most common path - * for page migration. - */ - rc = mapping->a_ops->migratepage(mapping, newpage, - page, mode); - else - rc = fallback_migrate_page(mapping, newpage, - page, mode); - } else { + if (!rc) { /* - * In case of non-lru page, it could be released after - * isolation step. In that case, we shouldn't try migration. + * For pagecache folios, src->mapping must be cleared before src + * is freed. Anonymous folios must stay anonymous until freed. */ - VM_BUG_ON_PAGE(!PageIsolated(page), page); - if (!PageMovable(page)) { - rc = MIGRATEPAGE_SUCCESS; - __ClearPageIsolated(page); - goto out; - } + if (!folio_test_anon(src)) + src->mapping = NULL; - rc = mapping->a_ops->migratepage(mapping, newpage, - page, mode); - WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && - !PageIsolated(page)); + if (likely(!folio_is_zone_device(dst))) + flush_dcache_folio(dst); } + return rc; +} - /* - * When successful, old pagecache page->mapping must be cleared before - * page is freed; but stats require that PageAnon be left as PageAnon. - */ - if (rc == MIGRATEPAGE_SUCCESS) { - if (__PageMovable(page)) { - VM_BUG_ON_PAGE(!PageIsolated(page), page); +/* + * To record some information during migration, we use unused private + * field of struct folio of the newly allocated destination folio. + * This is safe because nobody is using it except us. + */ +enum { + PAGE_WAS_MAPPED = BIT(0), + PAGE_WAS_MLOCKED = BIT(1), + PAGE_OLD_STATES = PAGE_WAS_MAPPED | PAGE_WAS_MLOCKED, +}; - /* - * We clear PG_movable under page_lock so any compactor - * cannot try to migrate this page. - */ - __ClearPageIsolated(page); - } +static void __migrate_folio_record(struct folio *dst, + int old_page_state, + struct anon_vma *anon_vma) +{ + dst->private = (void *)anon_vma + old_page_state; +} - /* - * Anonymous and movable page->mapping will be cleared by - * free_pages_prepare so don't reset it here for keeping - * the type to work PageAnon, for example. - */ - if (!PageMappingFlags(page)) - page->mapping = NULL; +static void __migrate_folio_extract(struct folio *dst, + int *old_page_state, + struct anon_vma **anon_vmap) +{ + unsigned long private = (unsigned long)dst->private; - if (likely(!is_zone_device_page(newpage))) - flush_dcache_page(newpage); + *anon_vmap = (struct anon_vma *)(private & ~PAGE_OLD_STATES); + *old_page_state = private & PAGE_OLD_STATES; + dst->private = NULL; +} - } -out: - return rc; +/* Restore the source folio to the original state upon failure */ +static void migrate_folio_undo_src(struct folio *src, + int page_was_mapped, + struct anon_vma *anon_vma, + bool locked, + struct list_head *ret) +{ + if (page_was_mapped) + remove_migration_ptes(src, src, 0); + /* Drop an anon_vma reference if we took one */ + if (anon_vma) + put_anon_vma(anon_vma); + if (locked) + folio_unlock(src); + if (ret) + list_move_tail(&src->lru, ret); +} + +/* Restore the destination folio to the original state upon failure */ +static void migrate_folio_undo_dst(struct folio *dst, bool locked, + free_folio_t put_new_folio, unsigned long private) +{ + if (locked) + folio_unlock(dst); + if (put_new_folio) + put_new_folio(dst, private); + else + folio_put(dst); +} + +/* Cleanup src folio upon migration success */ +static void migrate_folio_done(struct folio *src, + enum migrate_reason reason) +{ + if (likely(!page_has_movable_ops(&src->page)) && reason != MR_DEMOTION) + mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + + folio_is_file_lru(src), -folio_nr_pages(src)); + + if (reason != MR_MEMORY_FAILURE) + /* We release the page in page_handle_poison. */ + folio_put(src); } -static int __unmap_and_move(struct page *page, struct page *newpage, - int force, enum migrate_mode mode) +/* Obtain the lock on page, remove all ptes. */ +static int migrate_folio_unmap(new_folio_t get_new_folio, + free_folio_t put_new_folio, unsigned long private, + struct folio *src, struct folio **dstp, enum migrate_mode mode, + struct list_head *ret) { + struct folio *dst; int rc = -EAGAIN; - bool page_was_mapped = false; + int old_page_state = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__PageMovable(page); + bool locked = false; + bool dst_locked = false; + + dst = get_new_folio(src, private); + if (!dst) + return -ENOMEM; + *dstp = dst; - if (!trylock_page(page)) { - if (!force || mode == MIGRATE_ASYNC) + dst->private = NULL; + + if (!folio_trylock(src)) { + if (mode == MIGRATE_ASYNC) goto out; /* @@ -952,10 +1238,21 @@ static int __unmap_and_move(struct page *page, struct page *newpage, if (current->flags & PF_MEMALLOC) goto out; - lock_page(page); + /* + * In "light" mode, we can wait for transient locks (eg + * inserting a page into the page table), but it's not + * worth waiting for I/O. + */ + if (mode == MIGRATE_SYNC_LIGHT && !folio_test_uptodate(src)) + goto out; + + folio_lock(src); } + locked = true; + if (folio_test_mlocked(src)) + old_page_state |= PAGE_WAS_MLOCKED; - if (PageWriteback(page)) { + if (folio_test_writeback(src)) { /* * Only in the case of a full synchronous migration is it * necessary to wait for PageWriteback. In the async case, @@ -964,55 +1261,53 @@ static int __unmap_and_move(struct page *page, struct page *newpage, */ switch (mode) { case MIGRATE_SYNC: - case MIGRATE_SYNC_NO_COPY: break; default: rc = -EBUSY; - goto out_unlock; + goto out; } - if (!force) - goto out_unlock; - wait_on_page_writeback(page); + folio_wait_writeback(src); } /* - * By try_to_migrate(), page->mapcount goes down to 0 here. In this case, - * we cannot notice that anon_vma is freed while we migrates a page. + * By try_to_migrate(), src->mapcount goes down to 0 here. In this case, + * we cannot notice that anon_vma is freed while we migrate a page. * This get_anon_vma() delays freeing anon_vma pointer until the end * of migration. File cache pages are no problem because of page_lock() * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. * - * Only page_get_anon_vma() understands the subtleties of + * Only folio_get_anon_vma() understands the subtleties of * getting a hold on an anon_vma from outside one of its mms. * But if we cannot get anon_vma, then we won't need it anyway, * because that implies that the anon page is no longer mapped * (and cannot be remapped so long as we hold the page lock). */ - if (PageAnon(page) && !PageKsm(page)) - anon_vma = page_get_anon_vma(page); + if (folio_test_anon(src) && !folio_test_ksm(src)) + anon_vma = folio_get_anon_vma(src); /* * Block others from accessing the new page when we get around to * establishing additional references. We are usually the only one - * holding a reference to newpage at this point. We used to have a BUG - * here if trylock_page(newpage) fails, but would like to allow for - * cases where there might be a race with the previous use of newpage. + * holding a reference to dst at this point. We used to have a BUG + * here if folio_trylock(dst) fails, but would like to allow for + * cases where there might be a race with the previous use of dst. * This is much like races on refcount of oldpage: just don't BUG(). */ - if (unlikely(!trylock_page(newpage))) - goto out_unlock; + if (unlikely(!folio_trylock(dst))) + goto out; + dst_locked = true; - if (unlikely(!is_lru)) { - rc = move_to_new_page(newpage, page, mode); - goto out_unlock_both; + if (unlikely(page_has_movable_ops(&src->page))) { + __migrate_folio_record(dst, old_page_state, anon_vma); + return 0; } /* * Corner case handling: * 1. When a new swap-cache page is read into, it is added to the LRU * and treated as swapcache but it has no rmap yet. - * Calling try_to_unmap() against a page->mapping==NULL page will + * Calling try_to_unmap() against a src->mapping==NULL page will * trigger a BUG. So handle it here. * 2. An orphaned page (see truncate_cleanup_page) might have * fs-private metadata. The page can be picked up due to memory @@ -1020,132 +1315,118 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * invisible to the vm, so the page can not be migrated. So try to * free the metadata, so the page can be freed. */ - if (!page->mapping) { - VM_BUG_ON_PAGE(PageAnon(page), page); - if (page_has_private(page)) { - try_to_free_buffers(page); - goto out_unlock_both; + if (!src->mapping) { + if (folio_test_private(src)) { + try_to_free_buffers(src); + goto out; } - } else if (page_mapped(page)) { + } else if (folio_mapped(src)) { /* Establish migration ptes */ - VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma, - page); - try_to_migrate(page, 0); - page_was_mapped = true; + VM_BUG_ON_FOLIO(folio_test_anon(src) && + !folio_test_ksm(src) && !anon_vma, src); + try_to_migrate(src, mode == MIGRATE_ASYNC ? TTU_BATCH_FLUSH : 0); + old_page_state |= PAGE_WAS_MAPPED; } - if (!page_mapped(page)) - rc = move_to_new_page(newpage, page, mode); - - if (page_was_mapped) - remove_migration_ptes(page, - rc == MIGRATEPAGE_SUCCESS ? newpage : page, false); + if (!folio_mapped(src)) { + __migrate_folio_record(dst, old_page_state, anon_vma); + return 0; + } -out_unlock_both: - unlock_page(newpage); -out_unlock: - /* Drop an anon_vma reference if we took one */ - if (anon_vma) - put_anon_vma(anon_vma); - unlock_page(page); out: /* - * If migration is successful, decrease refcount of the newpage - * which will not free the page because new page owner increased - * refcounter. As well, if it is LRU page, add the page to LRU - * list in here. Use the old state of the isolated source page to - * determine if we migrated a LRU page. newpage was already unlocked - * and possibly modified by its owner - don't rely on the page - * state. + * A folio that has not been unmapped will be restored to + * right list unless we want to retry. */ - if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(!is_lru)) - put_page(newpage); - else - putback_lru_page(newpage); - } + if (rc == -EAGAIN) + ret = NULL; + + migrate_folio_undo_src(src, old_page_state & PAGE_WAS_MAPPED, + anon_vma, locked, ret); + migrate_folio_undo_dst(dst, dst_locked, put_new_folio, private); return rc; } -/* - * Obtain the lock on page, remove all ptes and migrate the page - * to the newly allocated page in newpage. - */ -static int unmap_and_move(new_page_t get_new_page, - free_page_t put_new_page, - unsigned long private, struct page *page, - int force, enum migrate_mode mode, - enum migrate_reason reason, - struct list_head *ret) +/* Migrate the folio to the newly allocated folio in dst. */ +static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, + struct folio *src, struct folio *dst, + enum migrate_mode mode, enum migrate_reason reason, + struct list_head *ret) { - int rc = MIGRATEPAGE_SUCCESS; - struct page *newpage = NULL; + int rc; + int old_page_state = 0; + struct anon_vma *anon_vma = NULL; + struct list_head *prev; - if (!thp_migration_supported() && PageTransHuge(page)) - return -ENOSYS; + __migrate_folio_extract(dst, &old_page_state, &anon_vma); + prev = dst->lru.prev; + list_del(&dst->lru); - if (page_count(page) == 1) { - /* page was freed from under us. So we are done. */ - ClearPageActive(page); - ClearPageUnevictable(page); - if (unlikely(__PageMovable(page))) { - lock_page(page); - if (!PageMovable(page)) - __ClearPageIsolated(page); - unlock_page(page); - } - goto out; + if (unlikely(page_has_movable_ops(&src->page))) { + rc = migrate_movable_ops_page(&dst->page, &src->page, mode); + if (rc) + goto out; + goto out_unlock_both; } - newpage = get_new_page(page, private); - if (!newpage) - return -ENOMEM; + rc = move_to_new_folio(dst, src, mode); + if (rc) + goto out; - rc = __unmap_and_move(page, newpage, force, mode); - if (rc == MIGRATEPAGE_SUCCESS) - set_page_owner_migrate_reason(newpage, reason); + /* + * When successful, push dst to LRU immediately: so that if it + * turns out to be an mlocked page, remove_migration_ptes() will + * automatically build up the correct dst->mlock_count for it. + * + * We would like to do something similar for the old page, when + * unsuccessful, and other cases when a page has been temporarily + * isolated from the unevictable LRU: but this case is the easiest. + */ + folio_add_lru(dst); + if (old_page_state & PAGE_WAS_MLOCKED) + lru_add_drain(); -out: - if (rc != -EAGAIN) { - /* - * A page that has been migrated has all references - * removed and will be freed. A page that has not been - * migrated will have kept its references and be restored. - */ - list_del(&page->lru); - } + if (old_page_state & PAGE_WAS_MAPPED) + remove_migration_ptes(src, dst, 0); +out_unlock_both: + folio_unlock(dst); + folio_set_owner_migrate_reason(dst, reason); /* - * If migration is successful, releases reference grabbed during - * isolation. Otherwise, restore the page to right list unless - * we want to retry. + * If migration is successful, decrease refcount of dst, + * which will not free the page because new page owner increased + * refcounter. */ - if (rc == MIGRATEPAGE_SUCCESS) { - /* - * Compaction can migrate also non-LRU pages which are - * not accounted to NR_ISOLATED_*. They can be recognized - * as __PageMovable - */ - if (likely(!__PageMovable(page))) - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + - page_is_file_lru(page), -thp_nr_pages(page)); + folio_put(dst); - if (reason != MR_MEMORY_FAILURE) - /* - * We release the page in page_handle_poison. - */ - put_page(page); - } else { - if (rc != -EAGAIN) - list_add_tail(&page->lru, ret); + /* + * A folio that has been migrated has all references removed + * and will be freed. + */ + list_del(&src->lru); + /* Drop an anon_vma reference if we took one */ + if (anon_vma) + put_anon_vma(anon_vma); + folio_unlock(src); + migrate_folio_done(src, reason); - if (put_new_page) - put_new_page(newpage, private); - else - put_page(newpage); + return rc; +out: + /* + * A folio that has not been migrated will be restored to + * right list unless we want to retry. + */ + if (rc == -EAGAIN) { + list_add(&dst->lru, prev); + __migrate_folio_record(dst, old_page_state, anon_vma); + return rc; } + migrate_folio_undo_src(src, old_page_state & PAGE_WAS_MAPPED, + anon_vma, true, ret); + migrate_folio_undo_dst(dst, true, put_new_folio, private); + return rc; } @@ -1167,406 +1448,761 @@ out: * because then pte is replaced with migration swap entry and direct I/O code * will wait in the page fault for migration to complete. */ -static int unmap_and_move_huge_page(new_page_t get_new_page, - free_page_t put_new_page, unsigned long private, - struct page *hpage, int force, - enum migrate_mode mode, int reason, - struct list_head *ret) +static int unmap_and_move_huge_page(new_folio_t get_new_folio, + free_folio_t put_new_folio, unsigned long private, + struct folio *src, int force, enum migrate_mode mode, + int reason, struct list_head *ret) { + struct folio *dst; int rc = -EAGAIN; int page_was_mapped = 0; - struct page *new_hpage; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; - /* - * Migratability of hugepages depends on architectures and their size. - * This check is necessary because some callers of hugepage migration - * like soft offline and memory hotremove don't walk through page - * tables or check whether the hugepage is pmd-based or not before - * kicking migration. - */ - if (!hugepage_migration_supported(page_hstate(hpage))) { - list_move_tail(&hpage->lru, ret); - return -ENOSYS; - } - - if (page_count(hpage) == 1) { + if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ - putback_active_hugepage(hpage); - return MIGRATEPAGE_SUCCESS; + folio_putback_hugetlb(src); + return 0; } - new_hpage = get_new_page(hpage, private); - if (!new_hpage) + dst = get_new_folio(src, private); + if (!dst) return -ENOMEM; - if (!trylock_page(hpage)) { + if (!folio_trylock(src)) { if (!force) goto out; switch (mode) { case MIGRATE_SYNC: - case MIGRATE_SYNC_NO_COPY: break; default: goto out; } - lock_page(hpage); + folio_lock(src); } /* * Check for pages which are in the process of being freed. Without - * page_mapping() set, hugetlbfs specific move page routine will not + * folio_mapping() set, hugetlbfs specific move page routine will not * be called and we could leak usage counts for subpools. */ - if (hugetlb_page_subpool(hpage) && !page_mapping(hpage)) { + if (hugetlb_folio_subpool(src) && !folio_mapping(src)) { rc = -EBUSY; goto out_unlock; } - if (PageAnon(hpage)) - anon_vma = page_get_anon_vma(hpage); + if (folio_test_anon(src)) + anon_vma = folio_get_anon_vma(src); - if (unlikely(!trylock_page(new_hpage))) + if (unlikely(!folio_trylock(dst))) goto put_anon; - if (page_mapped(hpage)) { - bool mapping_locked = false; + if (folio_mapped(src)) { enum ttu_flags ttu = 0; - if (!PageAnon(hpage)) { + if (!folio_test_anon(src)) { /* * In shared mappings, try_to_unmap could potentially * call huge_pmd_unshare. Because of this, take * semaphore in write mode here and set TTU_RMAP_LOCKED * to let lower levels know we have taken the lock. */ - mapping = hugetlb_page_mapping_lock_write(hpage); + mapping = hugetlb_folio_mapping_lock_write(src); if (unlikely(!mapping)) goto unlock_put_anon; - mapping_locked = true; - ttu |= TTU_RMAP_LOCKED; + ttu = TTU_RMAP_LOCKED; } - try_to_migrate(hpage, ttu); + try_to_migrate(src, ttu); page_was_mapped = 1; - if (mapping_locked) + if (ttu & TTU_RMAP_LOCKED) i_mmap_unlock_write(mapping); } - if (!page_mapped(hpage)) - rc = move_to_new_page(new_hpage, hpage, mode); + if (!folio_mapped(src)) + rc = move_to_new_folio(dst, src, mode); if (page_was_mapped) - remove_migration_ptes(hpage, - rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); + remove_migration_ptes(src, !rc ? dst : src, 0); unlock_put_anon: - unlock_page(new_hpage); + folio_unlock(dst); put_anon: if (anon_vma) put_anon_vma(anon_vma); - if (rc == MIGRATEPAGE_SUCCESS) { - move_hugetlb_state(hpage, new_hpage, reason); - put_new_page = NULL; + if (!rc) { + move_hugetlb_state(src, dst, reason); + put_new_folio = NULL; } out_unlock: - unlock_page(hpage); + folio_unlock(src); out: - if (rc == MIGRATEPAGE_SUCCESS) - putback_active_hugepage(hpage); + if (!rc) + folio_putback_hugetlb(src); else if (rc != -EAGAIN) - list_move_tail(&hpage->lru, ret); + list_move_tail(&src->lru, ret); /* - * If migration was not successful and there's a freeing callback, use - * it. Otherwise, put_page() will drop the reference grabbed during - * isolation. + * If migration was not successful and there's a freeing callback, + * return the folio to that special allocator. Otherwise, simply drop + * our additional reference. */ - if (put_new_page) - put_new_page(new_hpage, private); + if (put_new_folio) + put_new_folio(dst, private); else - putback_active_hugepage(new_hpage); + folio_put(dst); return rc; } -static inline int try_split_thp(struct page *page, struct page **page2, - struct list_head *from) +static inline int try_split_folio(struct folio *folio, struct list_head *split_folios, + enum migrate_mode mode) { - int rc = 0; + int rc; - lock_page(page); - rc = split_huge_page_to_list(page, from); - unlock_page(page); + if (mode == MIGRATE_ASYNC) { + if (!folio_trylock(folio)) + return -EAGAIN; + } else { + folio_lock(folio); + } + rc = split_folio_to_list(folio, split_folios); + folio_unlock(folio); if (!rc) - list_safe_reset_next(page, *page2, lru); + list_move_tail(&folio->lru, split_folios); return rc; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define NR_MAX_BATCHED_MIGRATION HPAGE_PMD_NR +#else +#define NR_MAX_BATCHED_MIGRATION 512 +#endif +#define NR_MAX_MIGRATE_PAGES_RETRY 10 +#define NR_MAX_MIGRATE_ASYNC_RETRY 3 +#define NR_MAX_MIGRATE_SYNC_RETRY \ + (NR_MAX_MIGRATE_PAGES_RETRY - NR_MAX_MIGRATE_ASYNC_RETRY) + +struct migrate_pages_stats { + int nr_succeeded; /* Normal and large folios migrated successfully, in + units of base pages */ + int nr_failed_pages; /* Normal and large folios failed to be migrated, in + units of base pages. Untried folios aren't counted */ + int nr_thp_succeeded; /* THP migrated successfully */ + int nr_thp_failed; /* THP failed to be migrated */ + int nr_thp_split; /* THP split before migrating */ + int nr_split; /* Large folio (include THP) split before migrating */ +}; + /* - * migrate_pages - migrate the pages specified in a list, to the free pages - * supplied as the target for the page migration - * - * @from: The list of pages to be migrated. - * @get_new_page: The function used to allocate free pages to be used - * as the target of the page migration. - * @put_new_page: The function used to free target pages if migration - * fails, or NULL if no special handling is necessary. - * @private: Private data to be passed on to get_new_page() - * @mode: The migration mode that specifies the constraints for - * page migration, if any. - * @reason: The reason for page migration. - * @ret_succeeded: Set to the number of normal pages migrated successfully if - * the caller passes a non-NULL pointer. - * - * The function returns after 10 attempts or if no pages are movable any more - * because the list has become empty or no retryable pages exist any more. - * It is caller's responsibility to call putback_movable_pages() to return pages - * to the LRU or free list only if ret != 0. - * - * Returns the number of {normal page, THP, hugetlb} that were not migrated, or - * an error code. The number of THP splits will be considered as the number of - * non-migrated THP, no matter how many subpages of the THP are migrated successfully. + * Returns the number of hugetlb folios that were not migrated, or an error code + * after NR_MAX_MIGRATE_PAGES_RETRY attempts or if no hugetlb folios are movable + * any more because the list has become empty or no retryable hugetlb folios + * exist any more. It is caller's responsibility to call putback_movable_pages() + * only if ret != 0. */ -int migrate_pages(struct list_head *from, new_page_t get_new_page, - free_page_t put_new_page, unsigned long private, - enum migrate_mode mode, int reason, unsigned int *ret_succeeded) +static int migrate_hugetlbs(struct list_head *from, new_folio_t get_new_folio, + free_folio_t put_new_folio, unsigned long private, + enum migrate_mode mode, int reason, + struct migrate_pages_stats *stats, + struct list_head *ret_folios) { int retry = 1; - int thp_retry = 1; int nr_failed = 0; - int nr_failed_pages = 0; - int nr_succeeded = 0; - int nr_thp_succeeded = 0; - int nr_thp_failed = 0; - int nr_thp_split = 0; + int nr_retry_pages = 0; int pass = 0; - bool is_thp = false; - struct page *page; - struct page *page2; - int swapwrite = current->flags & PF_SWAPWRITE; - int rc, nr_subpages; - LIST_HEAD(ret_pages); - LIST_HEAD(thp_split_pages); - bool nosplit = (reason == MR_NUMA_MISPLACED); - bool no_subpage_counting = false; + struct folio *folio, *folio2; + int rc, nr_pages; - trace_mm_migrate_pages_start(mode, reason); + for (pass = 0; pass < NR_MAX_MIGRATE_PAGES_RETRY && retry; pass++) { + retry = 0; + nr_retry_pages = 0; - if (!swapwrite) - current->flags |= PF_SWAPWRITE; + list_for_each_entry_safe(folio, folio2, from, lru) { + if (!folio_test_hugetlb(folio)) + continue; -thp_subpage_migration: - for (pass = 0; pass < 10 && (retry || thp_retry); pass++) { - retry = 0; - thp_retry = 0; + nr_pages = folio_nr_pages(folio); + + cond_resched(); - list_for_each_entry_safe(page, page2, from, lru) { -retry: /* - * THP statistics is based on the source huge page. - * Capture required information that might get lost - * during migration. + * Migratability of hugepages depends on architectures and + * their size. This check is necessary because some callers + * of hugepage migration like soft offline and memory + * hotremove don't walk through page tables or check whether + * the hugepage is pmd-based or not before kicking migration. */ - is_thp = PageTransHuge(page) && !PageHuge(page); - nr_subpages = compound_nr(page); - cond_resched(); + if (!hugepage_migration_supported(folio_hstate(folio))) { + nr_failed++; + stats->nr_failed_pages += nr_pages; + list_move_tail(&folio->lru, ret_folios); + continue; + } - if (PageHuge(page)) - rc = unmap_and_move_huge_page(get_new_page, - put_new_page, private, page, - pass > 2, mode, reason, - &ret_pages); - else - rc = unmap_and_move(get_new_page, put_new_page, - private, page, pass > 2, mode, - reason, &ret_pages); + rc = unmap_and_move_huge_page(get_new_folio, + put_new_folio, private, + folio, pass > 2, mode, + reason, ret_folios); /* * The rules are: - * Success: non hugetlb page will be freed, hugetlb - * page will be put back + * 0: hugetlb folio will be put back * -EAGAIN: stay on the from list * -ENOMEM: stay on the from list - * Other errno: put on ret_pages list then splice to - * from list + * Other errno: put on ret_folios list */ switch(rc) { + case -ENOMEM: + /* + * When memory is low, don't bother to try to migrate + * other folios, just exit. + */ + stats->nr_failed_pages += nr_pages + nr_retry_pages; + return -ENOMEM; + case -EAGAIN: + retry++; + nr_retry_pages += nr_pages; + break; + case 0: + stats->nr_succeeded += nr_pages; + break; + default: + /* + * Permanent failure (-EBUSY, etc.): + * unlike -EAGAIN case, the failed folio is + * removed from migration folio list and not + * retried in the next outer loop. + */ + nr_failed++; + stats->nr_failed_pages += nr_pages; + break; + } + } + } + /* + * nr_failed is number of hugetlb folios failed to be migrated. After + * NR_MAX_MIGRATE_PAGES_RETRY attempts, give up and count retried hugetlb + * folios as failed. + */ + nr_failed += retry; + stats->nr_failed_pages += nr_retry_pages; + + return nr_failed; +} + +static void migrate_folios_move(struct list_head *src_folios, + struct list_head *dst_folios, + free_folio_t put_new_folio, unsigned long private, + enum migrate_mode mode, int reason, + struct list_head *ret_folios, + struct migrate_pages_stats *stats, + int *retry, int *thp_retry, int *nr_failed, + int *nr_retry_pages) +{ + struct folio *folio, *folio2, *dst, *dst2; + bool is_thp; + int nr_pages; + int rc; + + dst = list_first_entry(dst_folios, struct folio, lru); + dst2 = list_next_entry(dst, lru); + list_for_each_entry_safe(folio, folio2, src_folios, lru) { + is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio); + nr_pages = folio_nr_pages(folio); + + cond_resched(); + + rc = migrate_folio_move(put_new_folio, private, + folio, dst, mode, + reason, ret_folios); + /* + * The rules are: + * 0: folio will be freed + * -EAGAIN: stay on the unmap_folios list + * Other errno: put on ret_folios list + */ + switch (rc) { + case -EAGAIN: + *retry += 1; + *thp_retry += is_thp; + *nr_retry_pages += nr_pages; + break; + case 0: + stats->nr_succeeded += nr_pages; + stats->nr_thp_succeeded += is_thp; + break; + default: + *nr_failed += 1; + stats->nr_thp_failed += is_thp; + stats->nr_failed_pages += nr_pages; + break; + } + dst = dst2; + dst2 = list_next_entry(dst, lru); + } +} + +static void migrate_folios_undo(struct list_head *src_folios, + struct list_head *dst_folios, + free_folio_t put_new_folio, unsigned long private, + struct list_head *ret_folios) +{ + struct folio *folio, *folio2, *dst, *dst2; + + dst = list_first_entry(dst_folios, struct folio, lru); + dst2 = list_next_entry(dst, lru); + list_for_each_entry_safe(folio, folio2, src_folios, lru) { + int old_page_state = 0; + struct anon_vma *anon_vma = NULL; + + __migrate_folio_extract(dst, &old_page_state, &anon_vma); + migrate_folio_undo_src(folio, old_page_state & PAGE_WAS_MAPPED, + anon_vma, true, ret_folios); + list_del(&dst->lru); + migrate_folio_undo_dst(dst, true, put_new_folio, private); + dst = dst2; + dst2 = list_next_entry(dst, lru); + } +} + +/* + * migrate_pages_batch() first unmaps folios in the from list as many as + * possible, then move the unmapped folios. + * + * We only batch migration if mode == MIGRATE_ASYNC to avoid to wait a + * lock or bit when we have locked more than one folio. Which may cause + * deadlock (e.g., for loop device). So, if mode != MIGRATE_ASYNC, the + * length of the from list must be <= 1. + */ +static int migrate_pages_batch(struct list_head *from, + new_folio_t get_new_folio, free_folio_t put_new_folio, + unsigned long private, enum migrate_mode mode, int reason, + struct list_head *ret_folios, struct list_head *split_folios, + struct migrate_pages_stats *stats, int nr_pass) +{ + int retry = 1; + int thp_retry = 1; + int nr_failed = 0; + int nr_retry_pages = 0; + int pass = 0; + bool is_thp = false; + bool is_large = false; + struct folio *folio, *folio2, *dst = NULL; + int rc, rc_saved = 0, nr_pages; + LIST_HEAD(unmap_folios); + LIST_HEAD(dst_folios); + bool nosplit = (reason == MR_NUMA_MISPLACED); + + VM_WARN_ON_ONCE(mode != MIGRATE_ASYNC && + !list_empty(from) && !list_is_singular(from)); + + for (pass = 0; pass < nr_pass && retry; pass++) { + retry = 0; + thp_retry = 0; + nr_retry_pages = 0; + + list_for_each_entry_safe(folio, folio2, from, lru) { + is_large = folio_test_large(folio); + is_thp = folio_test_pmd_mappable(folio); + nr_pages = folio_nr_pages(folio); + + cond_resched(); + /* - * THP migration might be unsupported or the - * allocation could've failed so we should - * retry on the same page with the THP split - * to base pages. + * The rare folio on the deferred split list should + * be split now. It should not count as a failure: + * but increment nr_failed because, without doing so, + * migrate_pages() may report success with (split but + * unmigrated) pages still on its fromlist; whereas it + * always reports success when its fromlist is empty. + * stats->nr_thp_failed should be increased too, + * otherwise stats inconsistency will happen when + * migrate_pages_batch is called via migrate_pages() + * with MIGRATE_SYNC and MIGRATE_ASYNC. * - * Head page is retried immediately and tail - * pages are added to the tail of the list so - * we encounter them after the rest of the list - * is processed. + * Only check it without removing it from the list. + * Since the folio can be on deferred_split_scan() + * local list and removing it can cause the local list + * corruption. Folio split process below can handle it + * with the help of folio_ref_freeze(). + * + * nr_pages > 2 is needed to avoid checking order-1 + * page cache folios. They exist, in contrast to + * non-existent order-1 anonymous folios, and do not + * use _deferred_list. */ - case -ENOSYS: - /* THP migration is unsupported */ - if (is_thp) { - nr_thp_failed++; - if (!try_split_thp(page, &page2, &thp_split_pages)) { - nr_thp_split++; - goto retry; - } + if (nr_pages > 2 && + !list_empty(&folio->_deferred_list) && + folio_test_partially_mapped(folio)) { + if (!try_split_folio(folio, split_folios, mode)) { + nr_failed++; + stats->nr_thp_failed += is_thp; + stats->nr_thp_split += is_thp; + stats->nr_split++; + continue; + } + } - nr_failed_pages += nr_subpages; - break; + /* + * Large folio migration might be unsupported or + * the allocation might be failed so we should retry + * on the same folio with the large folio split + * to normal folios. + * + * Split folios are put in split_folios, and + * we will migrate them after the rest of the + * list is processed. + */ + if (!thp_migration_supported() && is_thp) { + nr_failed++; + stats->nr_thp_failed++; + if (!try_split_folio(folio, split_folios, mode)) { + stats->nr_thp_split++; + stats->nr_split++; + continue; } + stats->nr_failed_pages += nr_pages; + list_move_tail(&folio->lru, ret_folios); + continue; + } - /* Hugetlb migration is unsupported */ - if (!no_subpage_counting) - nr_failed++; - nr_failed_pages += nr_subpages; - break; + /* + * If we are holding the last folio reference, the folio + * was freed from under us, so just drop our reference. + */ + if (likely(!page_has_movable_ops(&folio->page)) && + folio_ref_count(folio) == 1) { + folio_clear_active(folio); + folio_clear_unevictable(folio); + list_del(&folio->lru); + migrate_folio_done(folio, reason); + stats->nr_succeeded += nr_pages; + stats->nr_thp_succeeded += is_thp; + continue; + } + + rc = migrate_folio_unmap(get_new_folio, put_new_folio, + private, folio, &dst, mode, ret_folios); + /* + * The rules are: + * 0: folio will be put on unmap_folios list, + * dst folio put on dst_folios list + * -EAGAIN: stay on the from list + * -ENOMEM: stay on the from list + * Other errno: put on ret_folios list + */ + switch(rc) { case -ENOMEM: /* * When memory is low, don't bother to try to migrate - * other pages, just exit. - * THP NUMA faulting doesn't split THP to retry. + * other folios, move unmapped folios, then exit. */ - if (is_thp && !nosplit) { - nr_thp_failed++; - if (!try_split_thp(page, &page2, &thp_split_pages)) { - nr_thp_split++; - goto retry; + nr_failed++; + stats->nr_thp_failed += is_thp; + /* Large folio NUMA faulting doesn't split to retry. */ + if (is_large && !nosplit) { + int ret = try_split_folio(folio, split_folios, mode); + + if (!ret) { + stats->nr_thp_split += is_thp; + stats->nr_split++; + break; + } else if (reason == MR_LONGTERM_PIN && + ret == -EAGAIN) { + /* + * Try again to split large folio to + * mitigate the failure of longterm pinning. + */ + retry++; + thp_retry += is_thp; + nr_retry_pages += nr_pages; + /* Undo duplicated failure counting. */ + nr_failed--; + stats->nr_thp_failed -= is_thp; + break; } - - nr_failed_pages += nr_subpages; - goto out; } - if (!no_subpage_counting) - nr_failed++; - nr_failed_pages += nr_subpages; - goto out; + stats->nr_failed_pages += nr_pages + nr_retry_pages; + /* nr_failed isn't updated for not used */ + stats->nr_thp_failed += thp_retry; + rc_saved = rc; + if (list_empty(&unmap_folios)) + goto out; + else + goto move; case -EAGAIN: - if (is_thp) { - thp_retry++; - break; - } retry++; + thp_retry += is_thp; + nr_retry_pages += nr_pages; break; - case MIGRATEPAGE_SUCCESS: - nr_succeeded += nr_subpages; - if (is_thp) { - nr_thp_succeeded++; - break; - } + case 0: + list_move_tail(&folio->lru, &unmap_folios); + list_add_tail(&dst->lru, &dst_folios); break; default: /* * Permanent failure (-EBUSY, etc.): - * unlike -EAGAIN case, the failed page is - * removed from migration page list and not + * unlike -EAGAIN case, the failed folio is + * removed from migration folio list and not * retried in the next outer loop. */ - if (is_thp) { - nr_thp_failed++; - nr_failed_pages += nr_subpages; - break; - } - - if (!no_subpage_counting) - nr_failed++; - nr_failed_pages += nr_subpages; + nr_failed++; + stats->nr_thp_failed += is_thp; + stats->nr_failed_pages += nr_pages; break; } } } nr_failed += retry; - nr_thp_failed += thp_retry; + stats->nr_thp_failed += thp_retry; + stats->nr_failed_pages += nr_retry_pages; +move: + /* Flush TLBs for all unmapped folios */ + try_to_unmap_flush(); + + retry = 1; + for (pass = 0; pass < nr_pass && retry; pass++) { + retry = 0; + thp_retry = 0; + nr_retry_pages = 0; + + /* Move the unmapped folios */ + migrate_folios_move(&unmap_folios, &dst_folios, + put_new_folio, private, mode, reason, + ret_folios, stats, &retry, &thp_retry, + &nr_failed, &nr_retry_pages); + } + nr_failed += retry; + stats->nr_thp_failed += thp_retry; + stats->nr_failed_pages += nr_retry_pages; + + rc = rc_saved ? : nr_failed; +out: + /* Cleanup remaining folios */ + migrate_folios_undo(&unmap_folios, &dst_folios, + put_new_folio, private, ret_folios); + + return rc; +} + +static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio, + free_folio_t put_new_folio, unsigned long private, + enum migrate_mode mode, int reason, + struct list_head *ret_folios, struct list_head *split_folios, + struct migrate_pages_stats *stats) +{ + int rc, nr_failed = 0; + LIST_HEAD(folios); + struct migrate_pages_stats astats; + + memset(&astats, 0, sizeof(astats)); + /* Try to migrate in batch with MIGRATE_ASYNC mode firstly */ + rc = migrate_pages_batch(from, get_new_folio, put_new_folio, private, MIGRATE_ASYNC, + reason, &folios, split_folios, &astats, + NR_MAX_MIGRATE_ASYNC_RETRY); + stats->nr_succeeded += astats.nr_succeeded; + stats->nr_thp_succeeded += astats.nr_thp_succeeded; + stats->nr_thp_split += astats.nr_thp_split; + stats->nr_split += astats.nr_split; + if (rc < 0) { + stats->nr_failed_pages += astats.nr_failed_pages; + stats->nr_thp_failed += astats.nr_thp_failed; + list_splice_tail(&folios, ret_folios); + return rc; + } + stats->nr_thp_failed += astats.nr_thp_split; + /* + * Do not count rc, as pages will be retried below. + * Count nr_split only, since it includes nr_thp_split. + */ + nr_failed += astats.nr_split; /* - * Try to migrate subpages of fail-to-migrate THPs, no nr_failed - * counting in this round, since all subpages of a THP is counted - * as 1 failure in the first round. + * Fall back to migrate all failed folios one by one synchronously. All + * failed folios except split THPs will be retried, so their failure + * isn't counted */ - if (!list_empty(&thp_split_pages)) { + list_splice_tail_init(&folios, from); + while (!list_empty(from)) { + list_move(from->next, &folios); + rc = migrate_pages_batch(&folios, get_new_folio, put_new_folio, + private, mode, reason, ret_folios, + split_folios, stats, NR_MAX_MIGRATE_SYNC_RETRY); + list_splice_tail_init(&folios, ret_folios); + if (rc < 0) + return rc; + nr_failed += rc; + } + + return nr_failed; +} + +/* + * migrate_pages - migrate the folios specified in a list, to the free folios + * supplied as the target for the page migration + * + * @from: The list of folios to be migrated. + * @get_new_folio: The function used to allocate free folios to be used + * as the target of the folio migration. + * @put_new_folio: The function used to free target folios if migration + * fails, or NULL if no special handling is necessary. + * @private: Private data to be passed on to get_new_folio() + * @mode: The migration mode that specifies the constraints for + * folio migration, if any. + * @reason: The reason for folio migration. + * @ret_succeeded: Set to the number of folios migrated successfully if + * the caller passes a non-NULL pointer. + * + * The function returns after NR_MAX_MIGRATE_PAGES_RETRY attempts or if no folios + * are movable any more because the list has become empty or no retryable folios + * exist any more. It is caller's responsibility to call putback_movable_pages() + * only if ret != 0. + * + * Returns the number of {normal folio, large folio, hugetlb} that were not + * migrated, or an error code. The number of large folio splits will be + * considered as the number of non-migrated large folio, no matter how many + * split folios of the large folio are migrated successfully. + */ +int migrate_pages(struct list_head *from, new_folio_t get_new_folio, + free_folio_t put_new_folio, unsigned long private, + enum migrate_mode mode, int reason, unsigned int *ret_succeeded) +{ + int rc, rc_gather; + int nr_pages; + struct folio *folio, *folio2; + LIST_HEAD(folios); + LIST_HEAD(ret_folios); + LIST_HEAD(split_folios); + struct migrate_pages_stats stats; + + trace_mm_migrate_pages_start(mode, reason); + + memset(&stats, 0, sizeof(stats)); + + rc_gather = migrate_hugetlbs(from, get_new_folio, put_new_folio, private, + mode, reason, &stats, &ret_folios); + if (rc_gather < 0) + goto out; + +again: + nr_pages = 0; + list_for_each_entry_safe(folio, folio2, from, lru) { + /* Retried hugetlb folios will be kept in list */ + if (folio_test_hugetlb(folio)) { + list_move_tail(&folio->lru, &ret_folios); + continue; + } + + nr_pages += folio_nr_pages(folio); + if (nr_pages >= NR_MAX_BATCHED_MIGRATION) + break; + } + if (nr_pages >= NR_MAX_BATCHED_MIGRATION) + list_cut_before(&folios, from, &folio2->lru); + else + list_splice_init(from, &folios); + if (mode == MIGRATE_ASYNC) + rc = migrate_pages_batch(&folios, get_new_folio, put_new_folio, + private, mode, reason, &ret_folios, + &split_folios, &stats, + NR_MAX_MIGRATE_PAGES_RETRY); + else + rc = migrate_pages_sync(&folios, get_new_folio, put_new_folio, + private, mode, reason, &ret_folios, + &split_folios, &stats); + list_splice_tail_init(&folios, &ret_folios); + if (rc < 0) { + rc_gather = rc; + list_splice_tail(&split_folios, &ret_folios); + goto out; + } + if (!list_empty(&split_folios)) { /* - * Move non-migrated pages (after 10 retries) to ret_pages - * to avoid migrating them again. + * Failure isn't counted since all split folios of a large folio + * is counted as 1 failure already. And, we only try to migrate + * with minimal effort, force MIGRATE_ASYNC mode and retry once. */ - list_splice_init(from, &ret_pages); - list_splice_init(&thp_split_pages, from); - no_subpage_counting = true; - retry = 1; - goto thp_subpage_migration; + migrate_pages_batch(&split_folios, get_new_folio, + put_new_folio, private, MIGRATE_ASYNC, reason, + &ret_folios, NULL, &stats, 1); + list_splice_tail_init(&split_folios, &ret_folios); } - - rc = nr_failed + nr_thp_failed; + rc_gather += rc; + if (!list_empty(from)) + goto again; out: /* - * Put the permanent failure page back to migration list, they + * Put the permanent failure folio back to migration list, they * will be put back to the right list by the caller. */ - list_splice(&ret_pages, from); - - count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded); - count_vm_events(PGMIGRATE_FAIL, nr_failed_pages); - count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded); - count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed); - count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split); - trace_mm_migrate_pages(nr_succeeded, nr_failed_pages, nr_thp_succeeded, - nr_thp_failed, nr_thp_split, mode, reason); + list_splice(&ret_folios, from); - if (!swapwrite) - current->flags &= ~PF_SWAPWRITE; + /* + * Return 0 in case all split folios of fail-to-migrate large folios + * are migrated successfully. + */ + if (list_empty(from)) + rc_gather = 0; + + count_vm_events(PGMIGRATE_SUCCESS, stats.nr_succeeded); + count_vm_events(PGMIGRATE_FAIL, stats.nr_failed_pages); + count_vm_events(THP_MIGRATION_SUCCESS, stats.nr_thp_succeeded); + count_vm_events(THP_MIGRATION_FAIL, stats.nr_thp_failed); + count_vm_events(THP_MIGRATION_SPLIT, stats.nr_thp_split); + trace_mm_migrate_pages(stats.nr_succeeded, stats.nr_failed_pages, + stats.nr_thp_succeeded, stats.nr_thp_failed, + stats.nr_thp_split, stats.nr_split, mode, + reason); if (ret_succeeded) - *ret_succeeded = nr_succeeded; + *ret_succeeded = stats.nr_succeeded; - return rc; + return rc_gather; } -struct page *alloc_migration_target(struct page *page, unsigned long private) +struct folio *alloc_migration_target(struct folio *src, unsigned long private) { struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; - struct page *new_page = NULL; int nid; - int zidx; + enum zone_type zidx; mtc = (struct migration_target_control *)private; gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) - nid = page_to_nid(page); + nid = folio_nid(src); - if (PageHuge(page)) { - struct hstate *h = page_hstate(compound_head(page)); + if (folio_test_hugetlb(src)) { + struct hstate *h = folio_hstate(src); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); - return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); + return alloc_hugetlb_folio_nodemask(h, nid, + mtc->nmask, gfp_mask, + htlb_allow_alloc_fallback(mtc->reason)); } - if (PageTransHuge(page)) { + if (folio_test_large(src)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; + order = folio_order(src); } - zidx = zone_idx(page_zone(page)); + zidx = folio_zonenum(src); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; - new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); - - return new_page; + return __folio_alloc(gfp_mask, order, nid, mtc->nmask); } #ifdef CONFIG_NUMA @@ -1582,13 +2218,13 @@ static int store_status(int __user *status, int start, int value, int nr) return 0; } -static int do_move_pages_to_node(struct mm_struct *mm, - struct list_head *pagelist, int node) +static int do_move_pages_to_node(struct list_head *pagelist, int node) { int err; struct migration_target_control mtc = { .nid = node, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + .reason = MR_SYSCALL, }; err = migrate_pages(pagelist, alloc_migration_target, NULL, @@ -1598,81 +2234,71 @@ static int do_move_pages_to_node(struct mm_struct *mm, return err; } +static int __add_folio_for_migration(struct folio *folio, int node, + struct list_head *pagelist, bool migrate_all) +{ + if (is_zero_folio(folio) || is_huge_zero_folio(folio)) + return -EFAULT; + + if (folio_is_zone_device(folio)) + return -ENOENT; + + if (folio_nid(folio) == node) + return 0; + + if (folio_maybe_mapped_shared(folio) && !migrate_all) + return -EACCES; + + if (folio_test_hugetlb(folio)) { + if (folio_isolate_hugetlb(folio, pagelist)) + return 1; + } else if (folio_isolate_lru(folio)) { + list_add_tail(&folio->lru, pagelist); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); + return 1; + } + return -EBUSY; +} + /* - * Resolves the given address to a struct page, isolates it from the LRU and + * Resolves the given address to a struct folio, isolates it from the LRU and * puts it to the given pagelist. * Returns: - * errno - if the page cannot be found/isolated + * errno - if the folio cannot be found/isolated * 0 - when it doesn't have to be migrated because it is already on the * target node * 1 - when it has been queued */ -static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, +static int add_folio_for_migration(struct mm_struct *mm, const void __user *p, int node, struct list_head *pagelist, bool migrate_all) { struct vm_area_struct *vma; - struct page *page; - unsigned int follflags; - int err; + struct folio_walk fw; + struct folio *folio; + unsigned long addr; + int err = -EFAULT; mmap_read_lock(mm); - err = -EFAULT; - vma = find_vma(mm, addr); - if (!vma || addr < vma->vm_start || !vma_migratable(vma)) - goto out; - - /* FOLL_DUMP to ignore special (like zero) pages */ - follflags = FOLL_GET | FOLL_DUMP; - page = follow_page(vma, addr, follflags); - - err = PTR_ERR(page); - if (IS_ERR(page)) - goto out; - - err = -ENOENT; - if (!page) - goto out; - - err = 0; - if (page_to_nid(page) == node) - goto out_putpage; - - err = -EACCES; - if (page_mapcount(page) > 1 && !migrate_all) - goto out_putpage; - - if (PageHuge(page)) { - if (PageHead(page)) { - isolate_huge_page(page, pagelist); - err = 1; + addr = (unsigned long)untagged_addr_remote(mm, p); + + vma = vma_lookup(mm, addr); + if (vma && vma_migratable(vma)) { + folio = folio_walk_start(&fw, vma, addr, FW_ZEROPAGE); + if (folio) { + err = __add_folio_for_migration(folio, node, pagelist, + migrate_all); + folio_walk_end(&fw, vma); + } else { + err = -ENOENT; } - } else { - struct page *head; - - head = compound_head(page); - err = isolate_lru_page(head); - if (err) - goto out_putpage; - - err = 1; - list_add_tail(&head->lru, pagelist); - mod_node_page_state(page_pgdat(head), - NR_ISOLATED_ANON + page_is_file_lru(head), - thp_nr_pages(head)); } -out_putpage: - /* - * Either remove the duplicate refcount from - * isolate_lru_page() or drop the page ref if it was - * not isolated. - */ - put_page(page); -out: mmap_read_unlock(mm); return err; } -static int move_pages_and_store_status(struct mm_struct *mm, int node, +static int move_pages_and_store_status(int node, struct list_head *pagelist, int __user *status, int start, int i, unsigned long nr_pages) { @@ -1681,7 +2307,7 @@ static int move_pages_and_store_status(struct mm_struct *mm, int node, if (list_empty(pagelist)) return 0; - err = do_move_pages_to_node(mm, pagelist, node); + err = do_move_pages_to_node(pagelist, node); if (err) { /* * Positive err means the number of failed @@ -1692,7 +2318,7 @@ static int move_pages_and_store_status(struct mm_struct *mm, int node, * well. */ if (err > 0) - err += nr_pages - i - 1; + err += nr_pages - i; return err; } return store_status(status, start, node, i - start); @@ -1708,6 +2334,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, const int __user *nodes, int __user *status, int flags) { + compat_uptr_t __user *compat_pages = (void __user *)pages; int current_node = NUMA_NO_NODE; LIST_HEAD(pagelist); int start, i; @@ -1717,15 +2344,22 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, for (i = start = 0; i < nr_pages; i++) { const void __user *p; - unsigned long addr; int node; err = -EFAULT; - if (get_user(p, pages + i)) - goto out_flush; + if (in_compat_syscall()) { + compat_uptr_t cp; + + if (get_user(cp, compat_pages + i)) + goto out_flush; + + p = compat_ptr(cp); + } else { + if (get_user(p, pages + i)) + goto out_flush; + } if (get_user(node, nodes + i)) goto out_flush; - addr = (unsigned long)untagged_addr(p); err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES) @@ -1741,7 +2375,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, current_node = node; start = i; } else if (node != current_node) { - err = move_pages_and_store_status(mm, current_node, + err = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err) goto out; @@ -1753,8 +2387,8 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, * Errors in the page lookup or isolation are not fatal and we simply * report them via status */ - err = add_page_for_migration(mm, addr, current_node, - &pagelist, flags & MPOL_MF_MOVE_ALL); + err = add_folio_for_migration(mm, p, current_node, &pagelist, + flags & MPOL_MF_MOVE_ALL); if (err > 0) { /* The page is successfully queued for migration */ @@ -1769,15 +2403,19 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, if (err) goto out_flush; - err = move_pages_and_store_status(mm, current_node, &pagelist, + err = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); - if (err) + if (err) { + /* We have accounted for page i */ + if (err > 0) + err--; goto out; + } current_node = NUMA_NO_NODE; } out_flush: /* Make sure we do not overwrite the existing error */ - err1 = move_pages_and_store_status(mm, current_node, &pagelist, + err1 = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err >= 0) err = err1; @@ -1799,21 +2437,26 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, for (i = 0; i < nr_pages; i++) { unsigned long addr = (unsigned long)(*pages); struct vm_area_struct *vma; - struct page *page; + struct folio_walk fw; + struct folio *folio; int err = -EFAULT; vma = vma_lookup(mm, addr); if (!vma) goto set_status; - /* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_DUMP); - - err = PTR_ERR(page); - if (IS_ERR(page)) - goto set_status; - - err = page ? page_to_nid(page) : -ENOENT; + folio = folio_walk_start(&fw, vma, addr, FW_ZEROPAGE); + if (folio) { + if (is_zero_folio(folio) || is_huge_zero_folio(folio)) + err = -EFAULT; + else if (folio_is_zone_device(folio)) + err = -ENOENT; + else + err = folio_nid(folio); + folio_walk_end(&fw, vma); + } else { + err = -ENOENT; + } set_status: *status = err; @@ -1826,6 +2469,7 @@ set_status: static int get_compat_pages_array(const void __user *chunk_pages[], const void __user * __user *pages, + unsigned long chunk_offset, unsigned long chunk_nr) { compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages; @@ -1833,7 +2477,7 @@ static int get_compat_pages_array(const void __user *chunk_pages[], int i; for (i = 0; i < chunk_nr; i++) { - if (get_user(p, pages32 + i)) + if (get_user(p, pages32 + chunk_offset + i)) return -EFAULT; chunk_pages[i] = compat_ptr(p); } @@ -1849,34 +2493,31 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, const void __user * __user *pages, int __user *status) { -#define DO_PAGES_STAT_CHUNK_NR 16 +#define DO_PAGES_STAT_CHUNK_NR 16UL const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; int chunk_status[DO_PAGES_STAT_CHUNK_NR]; + unsigned long chunk_offset = 0; while (nr_pages) { - unsigned long chunk_nr; - - chunk_nr = nr_pages; - if (chunk_nr > DO_PAGES_STAT_CHUNK_NR) - chunk_nr = DO_PAGES_STAT_CHUNK_NR; + unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR); if (in_compat_syscall()) { if (get_compat_pages_array(chunk_pages, pages, - chunk_nr)) + chunk_offset, chunk_nr)) break; } else { - if (copy_from_user(chunk_pages, pages, + if (copy_from_user(chunk_pages, pages + chunk_offset, chunk_nr * sizeof(*chunk_pages))) break; } do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); - if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) + if (copy_to_user(status + chunk_offset, chunk_status, + chunk_nr * sizeof(*status))) break; - pages += chunk_nr; - status += chunk_nr; + chunk_offset += chunk_nr; nr_pages -= chunk_nr; } return nr_pages ? -EFAULT : 0; @@ -1897,25 +2538,19 @@ static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) return current->mm; } - /* Find the mm_struct */ - rcu_read_lock(); - task = find_task_by_vpid(pid); + task = find_get_task_by_vpid(pid); if (!task) { - rcu_read_unlock(); return ERR_PTR(-ESRCH); } - get_task_struct(task); /* * Check if this process has the right to modify the specified * process. Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { - rcu_read_unlock(); mm = ERR_PTR(-EPERM); goto out; } - rcu_read_unlock(); mm = ERR_PTR(security_task_movememory(task)); if (IS_ERR(mm)) @@ -1974,7 +2609,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, #ifdef CONFIG_NUMA_BALANCING /* * Returns true if this is a safe migration target node for misplaced NUMA - * pages. Currently it only checks the watermarks which crude + * pages. Currently it only checks the watermarks which is crude. */ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, unsigned long nr_migrate_pages) @@ -1984,1380 +2619,132 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, for (z = pgdat->nr_zones - 1; z >= 0; z--) { struct zone *zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; /* Avoid waking kswapd by allocating pages_to_migrate pages. */ if (!zone_watermark_ok(zone, 0, high_wmark_pages(zone) + nr_migrate_pages, - ZONE_MOVABLE, 0)) + ZONE_MOVABLE, ALLOC_CMA)) continue; return true; } return false; } -static struct page *alloc_misplaced_dst_page(struct page *page, +static struct folio *alloc_misplaced_dst_folio(struct folio *src, unsigned long data) { int nid = (int) data; - struct page *newpage; - - newpage = __alloc_pages_node(nid, - (GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE | __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_NOWARN) & - ~__GFP_RECLAIM, 0); - - return newpage; -} - -static struct page *alloc_misplaced_dst_page_thp(struct page *page, - unsigned long data) -{ - int nid = (int) data; - struct page *newpage; - - newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!newpage) - goto out; - - prep_transhuge_page(newpage); - -out: - return newpage; -} - -static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) -{ - int page_lru; - int nr_pages = thp_nr_pages(page); - - VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); - - /* Do not migrate THP mapped by multiple processes */ - if (PageTransHuge(page) && total_mapcount(page) > 1) - return 0; - - /* Avoid migrating to a node that is nearly full */ - if (!migrate_balanced_pgdat(pgdat, nr_pages)) - return 0; - - if (isolate_lru_page(page)) - return 0; - - page_lru = page_is_file_lru(page); - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, - nr_pages); - - /* - * Isolating the page has taken another reference, so the - * caller's reference can be safely dropped without the page - * disappearing underneath us during migration. - */ - put_page(page); - return 1; + int order = folio_order(src); + gfp_t gfp = __GFP_THISNODE; + + if (order > 0) + gfp |= GFP_TRANSHUGE_LIGHT; + else { + gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN; + gfp &= ~__GFP_RECLAIM; + } + return __folio_alloc_node(gfp, order, nid); } /* - * Attempt to migrate a misplaced page to the specified destination - * node. Caller is expected to have an elevated reference count on - * the page that will be dropped by this function before returning. + * Prepare for calling migrate_misplaced_folio() by isolating the folio if + * permitted. Must be called with the PTL still held. */ -int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, - int node) +int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node) { + int nr_pages = folio_nr_pages(folio); pg_data_t *pgdat = NODE_DATA(node); - int isolated; - int nr_remaining; - LIST_HEAD(migratepages); - new_page_t *new; - bool compound; - int nr_pages = thp_nr_pages(page); - - /* - * PTE mapped THP or HugeTLB page can't reach here so the page could - * be either base page or THP. And it must be head page if it is - * THP. - */ - compound = PageTransHuge(page); - - if (compound) - new = alloc_misplaced_dst_page_thp; - else - new = alloc_misplaced_dst_page; - - /* - * Don't migrate file pages that are mapped in multiple processes - * with execute permissions as they are probably shared libraries. - */ - if (page_mapcount(page) != 1 && page_is_file_lru(page) && - (vma->vm_flags & VM_EXEC)) - goto out; - - /* - * Also do not migrate dirty pages as not all filesystems can move - * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles. - */ - if (page_is_file_lru(page) && PageDirty(page)) - goto out; - - isolated = numamigrate_isolate_page(pgdat, page); - if (!isolated) - goto out; - - list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL); - if (nr_remaining) { - if (!list_empty(&migratepages)) { - list_del(&page->lru); - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + - page_is_file_lru(page), -nr_pages); - putback_lru_page(page); - } - isolated = 0; - } else - count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages); - BUG_ON(!list_empty(&migratepages)); - return isolated; - -out: - put_page(page); - return 0; -} -#endif /* CONFIG_NUMA_BALANCING */ -#endif /* CONFIG_NUMA */ - -#ifdef CONFIG_DEVICE_PRIVATE -static int migrate_vma_collect_skip(unsigned long start, - unsigned long end, - struct mm_walk *walk) -{ - struct migrate_vma *migrate = walk->private; - unsigned long addr; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->dst[migrate->npages] = 0; - migrate->src[migrate->npages++] = 0; - } - - return 0; -} - -static int migrate_vma_collect_hole(unsigned long start, - unsigned long end, - __always_unused int depth, - struct mm_walk *walk) -{ - struct migrate_vma *migrate = walk->private; - unsigned long addr; - - /* Only allow populating anonymous memory. */ - if (!vma_is_anonymous(walk->vma)) - return migrate_vma_collect_skip(start, end, walk); - - for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; - migrate->dst[migrate->npages] = 0; - migrate->npages++; - migrate->cpages++; - } - - return 0; -} - -static int migrate_vma_collect_pmd(pmd_t *pmdp, - unsigned long start, - unsigned long end, - struct mm_walk *walk) -{ - struct migrate_vma *migrate = walk->private; - struct vm_area_struct *vma = walk->vma; - struct mm_struct *mm = vma->vm_mm; - unsigned long addr = start, unmapped = 0; - spinlock_t *ptl; - pte_t *ptep; - -again: - if (pmd_none(*pmdp)) - return migrate_vma_collect_hole(start, end, -1, walk); - - if (pmd_trans_huge(*pmdp)) { - struct page *page; - - ptl = pmd_lock(mm, pmdp); - if (unlikely(!pmd_trans_huge(*pmdp))) { - spin_unlock(ptl); - goto again; - } - - page = pmd_page(*pmdp); - if (is_huge_zero_page(page)) { - spin_unlock(ptl); - split_huge_pmd(vma, pmdp, addr); - if (pmd_trans_unstable(pmdp)) - return migrate_vma_collect_skip(start, end, - walk); - } else { - int ret; - - get_page(page); - spin_unlock(ptl); - if (unlikely(!trylock_page(page))) - return migrate_vma_collect_skip(start, end, - walk); - ret = split_huge_page(page); - unlock_page(page); - put_page(page); - if (ret) - return migrate_vma_collect_skip(start, end, - walk); - if (pmd_none(*pmdp)) - return migrate_vma_collect_hole(start, end, -1, - walk); - } - } - - if (unlikely(pmd_bad(*pmdp))) - return migrate_vma_collect_skip(start, end, walk); - - ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); - arch_enter_lazy_mmu_mode(); - - for (; addr < end; addr += PAGE_SIZE, ptep++) { - unsigned long mpfn = 0, pfn; - struct page *page; - swp_entry_t entry; - pte_t pte; - - pte = *ptep; - - if (pte_none(pte)) { - if (vma_is_anonymous(vma)) { - mpfn = MIGRATE_PFN_MIGRATE; - migrate->cpages++; - } - goto next; - } - - if (!pte_present(pte)) { - /* - * Only care about unaddressable device page special - * page table entry. Other special swap entries are not - * migratable, and we ignore regular swapped page. - */ - entry = pte_to_swp_entry(pte); - if (!is_device_private_entry(entry)) - goto next; - - page = pfn_swap_entry_to_page(entry); - if (!(migrate->flags & - MIGRATE_VMA_SELECT_DEVICE_PRIVATE) || - page->pgmap->owner != migrate->pgmap_owner) - goto next; - - mpfn = migrate_pfn(page_to_pfn(page)) | - MIGRATE_PFN_MIGRATE; - if (is_writable_device_private_entry(entry)) - mpfn |= MIGRATE_PFN_WRITE; - } else { - if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) - goto next; - pfn = pte_pfn(pte); - if (is_zero_pfn(pfn)) { - mpfn = MIGRATE_PFN_MIGRATE; - migrate->cpages++; - goto next; - } - page = vm_normal_page(migrate->vma, addr, pte); - mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; - mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; - } - - /* FIXME support THP */ - if (!page || !page->mapping || PageTransCompound(page)) { - mpfn = 0; - goto next; - } + if (folio_is_file_lru(folio)) { /* - * By getting a reference on the page we pin it and that blocks - * any kind of migration. Side effect is that it "freezes" the - * pte. + * Do not migrate file folios that are mapped in multiple + * processes with execute permissions as they are probably + * shared libraries. * - * We drop this reference after isolating the page from the lru - * for non device page (device page are not on the lru and thus - * can't be dropped from it). + * See folio_maybe_mapped_shared() on possible imprecision + * when we cannot easily detect if a folio is shared. */ - get_page(page); + if ((vma->vm_flags & VM_EXEC) && folio_maybe_mapped_shared(folio)) + return -EACCES; /* - * Optimize for the common case where page is only mapped once - * in one process. If we can lock the page, then we can safely - * set up a special migration page table entry now. + * Do not migrate dirty folios as not all filesystems can move + * dirty folios in MIGRATE_ASYNC mode which is a waste of + * cycles. */ - if (trylock_page(page)) { - pte_t swp_pte; - - migrate->cpages++; - ptep_get_and_clear(mm, addr, ptep); - - /* Setup special migration page table entry */ - if (mpfn & MIGRATE_PFN_WRITE) - entry = make_writable_migration_entry( - page_to_pfn(page)); - else - entry = make_readable_migration_entry( - page_to_pfn(page)); - swp_pte = swp_entry_to_pte(entry); - if (pte_present(pte)) { - if (pte_soft_dirty(pte)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - if (pte_uffd_wp(pte)) - swp_pte = pte_swp_mkuffd_wp(swp_pte); - } else { - if (pte_swp_soft_dirty(pte)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - if (pte_swp_uffd_wp(pte)) - swp_pte = pte_swp_mkuffd_wp(swp_pte); - } - set_pte_at(mm, addr, ptep, swp_pte); - - /* - * This is like regular unmap: we remove the rmap and - * drop page refcount. Page won't be freed, as we took - * a reference just above. - */ - page_remove_rmap(page, false); - put_page(page); - - if (pte_present(pte)) - unmapped++; - } else { - put_page(page); - mpfn = 0; - } - -next: - migrate->dst[migrate->npages] = 0; - migrate->src[migrate->npages++] = mpfn; - } - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(ptep - 1, ptl); - - /* Only flush the TLB if we actually modified any entries */ - if (unmapped) - flush_tlb_range(walk->vma, start, end); - - return 0; -} - -static const struct mm_walk_ops migrate_vma_walk_ops = { - .pmd_entry = migrate_vma_collect_pmd, - .pte_hole = migrate_vma_collect_hole, -}; - -/* - * migrate_vma_collect() - collect pages over a range of virtual addresses - * @migrate: migrate struct containing all migration information - * - * This will walk the CPU page table. For each virtual address backed by a - * valid page, it updates the src array and takes a reference on the page, in - * order to pin the page until we lock it and unmap it. - */ -static void migrate_vma_collect(struct migrate_vma *migrate) -{ - struct mmu_notifier_range range; - - /* - * Note that the pgmap_owner is passed to the mmu notifier callback so - * that the registered device driver can skip invalidating device - * private page mappings that won't be migrated. - */ - mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0, - migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end, - migrate->pgmap_owner); - mmu_notifier_invalidate_range_start(&range); - - walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end, - &migrate_vma_walk_ops, migrate); - - mmu_notifier_invalidate_range_end(&range); - migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT); -} - -/* - * migrate_vma_check_page() - check if page is pinned or not - * @page: struct page to check - * - * Pinned pages cannot be migrated. This is the same test as in - * folio_migrate_mapping(), except that here we allow migration of a - * ZONE_DEVICE page. - */ -static bool migrate_vma_check_page(struct page *page) -{ - /* - * One extra ref because caller holds an extra reference, either from - * isolate_lru_page() for a regular page, or migrate_vma_collect() for - * a device page. - */ - int extra = 1; - - /* - * FIXME support THP (transparent huge page), it is bit more complex to - * check them than regular pages, because they can be mapped with a pmd - * or with a pte (split pte mapping). - */ - if (PageCompound(page)) - return false; - - /* Page from ZONE_DEVICE have one extra reference */ - if (is_zone_device_page(page)) - extra++; - - /* For file back page */ - if (page_mapping(page)) - extra += 1 + page_has_private(page); - - if ((page_count(page) - extra) > page_mapcount(page)) - return false; - - return true; -} - -/* - * migrate_vma_unmap() - replace page mapping with special migration pte entry - * @migrate: migrate struct containing all migration information - * - * Isolate pages from the LRU and replace mappings (CPU page table pte) with a - * special migration pte entry and check if it has been pinned. Pinned pages are - * restored because we cannot migrate them. - * - * This is the last step before we call the device driver callback to allocate - * destination memory and copy contents of original page over to new page. - */ -static void migrate_vma_unmap(struct migrate_vma *migrate) -{ - const unsigned long npages = migrate->npages; - unsigned long i, restore = 0; - bool allow_drain = true; - - lru_add_drain(); - - for (i = 0; i < npages; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); - - if (!page) - continue; - - /* ZONE_DEVICE pages are not on LRU */ - if (!is_zone_device_page(page)) { - if (!PageLRU(page) && allow_drain) { - /* Drain CPU's pagevec */ - lru_add_drain_all(); - allow_drain = false; - } - - if (isolate_lru_page(page)) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; - continue; - } - - /* Drop the reference we took in collect */ - put_page(page); - } - - if (page_mapped(page)) - try_to_migrate(page, 0); - - if (page_mapped(page) || !migrate_vma_check_page(page)) { - if (!is_zone_device_page(page)) { - get_page(page); - putback_lru_page(page); - } - - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; - continue; - } - } - - for (i = 0; i < npages && restore; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); - - if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) - continue; - - remove_migration_ptes(page, page, false); - - migrate->src[i] = 0; - unlock_page(page); - put_page(page); - restore--; - } -} - -/** - * migrate_vma_setup() - prepare to migrate a range of memory - * @args: contains the vma, start, and pfns arrays for the migration - * - * Returns: negative errno on failures, 0 when 0 or more pages were migrated - * without an error. - * - * Prepare to migrate a range of memory virtual address range by collecting all - * the pages backing each virtual address in the range, saving them inside the - * src array. Then lock those pages and unmap them. Once the pages are locked - * and unmapped, check whether each page is pinned or not. Pages that aren't - * pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) in the - * corresponding src array entry. Then restores any pages that are pinned, by - * remapping and unlocking those pages. - * - * The caller should then allocate destination memory and copy source memory to - * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE - * flag set). Once these are allocated and copied, the caller must update each - * corresponding entry in the dst array with the pfn value of the destination - * page and with MIGRATE_PFN_VALID. Destination pages must be locked via - * lock_page(). - * - * Note that the caller does not have to migrate all the pages that are marked - * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from - * device memory to system memory. If the caller cannot migrate a device page - * back to system memory, then it must return VM_FAULT_SIGBUS, which has severe - * consequences for the userspace process, so it must be avoided if at all - * possible. - * - * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we - * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus - * allowing the caller to allocate device memory for those unbacked virtual - * addresses. For this the caller simply has to allocate device memory and - * properly set the destination entry like for regular migration. Note that - * this can still fail, and thus inside the device driver you must check if the - * migration was successful for those entries after calling migrate_vma_pages(), - * just like for regular migration. - * - * After that, the callers must call migrate_vma_pages() to go over each entry - * in the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag - * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set, - * then migrate_vma_pages() to migrate struct page information from the source - * struct page to the destination struct page. If it fails to migrate the - * struct page information, then it clears the MIGRATE_PFN_MIGRATE flag in the - * src array. - * - * At this point all successfully migrated pages have an entry in the src - * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst - * array entry with MIGRATE_PFN_VALID flag set. - * - * Once migrate_vma_pages() returns the caller may inspect which pages were - * successfully migrated, and which were not. Successfully migrated pages will - * have the MIGRATE_PFN_MIGRATE flag set for their src array entry. - * - * It is safe to update device page table after migrate_vma_pages() because - * both destination and source page are still locked, and the mmap_lock is held - * in read mode (hence no one can unmap the range being migrated). - * - * Once the caller is done cleaning up things and updating its page table (if it - * chose to do so, this is not an obligation) it finally calls - * migrate_vma_finalize() to update the CPU page table to point to new pages - * for successfully migrated pages or otherwise restore the CPU page table to - * point to the original source pages. - */ -int migrate_vma_setup(struct migrate_vma *args) -{ - long nr_pages = (args->end - args->start) >> PAGE_SHIFT; - - args->start &= PAGE_MASK; - args->end &= PAGE_MASK; - if (!args->vma || is_vm_hugetlb_page(args->vma) || - (args->vma->vm_flags & VM_SPECIAL) || vma_is_dax(args->vma)) - return -EINVAL; - if (nr_pages <= 0) - return -EINVAL; - if (args->start < args->vma->vm_start || - args->start >= args->vma->vm_end) - return -EINVAL; - if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end) - return -EINVAL; - if (!args->src || !args->dst) - return -EINVAL; - - memset(args->src, 0, sizeof(*args->src) * nr_pages); - args->cpages = 0; - args->npages = 0; - - migrate_vma_collect(args); - - if (args->cpages) - migrate_vma_unmap(args); - - /* - * At this point pages are locked and unmapped, and thus they have - * stable content and can safely be copied to destination memory that - * is allocated by the drivers. - */ - return 0; - -} -EXPORT_SYMBOL(migrate_vma_setup); - -/* - * This code closely matches the code in: - * __handle_mm_fault() - * handle_pte_fault() - * do_anonymous_page() - * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE - * private page. - */ -static void migrate_vma_insert_page(struct migrate_vma *migrate, - unsigned long addr, - struct page *page, - unsigned long *src) -{ - struct vm_area_struct *vma = migrate->vma; - struct mm_struct *mm = vma->vm_mm; - bool flush = false; - spinlock_t *ptl; - pte_t entry; - pgd_t *pgdp; - p4d_t *p4dp; - pud_t *pudp; - pmd_t *pmdp; - pte_t *ptep; - - /* Only allow populating anonymous memory */ - if (!vma_is_anonymous(vma)) - goto abort; - - pgdp = pgd_offset(mm, addr); - p4dp = p4d_alloc(mm, pgdp, addr); - if (!p4dp) - goto abort; - pudp = pud_alloc(mm, p4dp, addr); - if (!pudp) - goto abort; - pmdp = pmd_alloc(mm, pudp, addr); - if (!pmdp) - goto abort; - - if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp)) - goto abort; - - /* - * Use pte_alloc() instead of pte_alloc_map(). We can't run - * pte_offset_map() on pmds where a huge pmd might be created - * from a different thread. - * - * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when - * parallel threads are excluded by other means. - * - * Here we only have mmap_read_lock(mm). - */ - if (pte_alloc(mm, pmdp)) - goto abort; - - /* See the comment in pte_alloc_one_map() */ - if (unlikely(pmd_trans_unstable(pmdp))) - goto abort; - - if (unlikely(anon_vma_prepare(vma))) - goto abort; - if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) - goto abort; - - /* - * The memory barrier inside __SetPageUptodate makes sure that - * preceding stores to the page contents become visible before - * the set_pte_at() write. - */ - __SetPageUptodate(page); - - if (is_zone_device_page(page)) { - if (is_device_private_page(page)) { - swp_entry_t swp_entry; - - if (vma->vm_flags & VM_WRITE) - swp_entry = make_writable_device_private_entry( - page_to_pfn(page)); - else - swp_entry = make_readable_device_private_entry( - page_to_pfn(page)); - entry = swp_entry_to_pte(swp_entry); - } else { - /* - * For now we only support migrating to un-addressable - * device memory. - */ - pr_warn_once("Unsupported ZONE_DEVICE page type.\n"); - goto abort; - } - } else { - entry = mk_pte(page, vma->vm_page_prot); - if (vma->vm_flags & VM_WRITE) - entry = pte_mkwrite(pte_mkdirty(entry)); - } - - ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); - - if (check_stable_address_space(mm)) - goto unlock_abort; - - if (pte_present(*ptep)) { - unsigned long pfn = pte_pfn(*ptep); - - if (!is_zero_pfn(pfn)) - goto unlock_abort; - flush = true; - } else if (!pte_none(*ptep)) - goto unlock_abort; - - /* - * Check for userfaultfd but do not deliver the fault. Instead, - * just back off. - */ - if (userfaultfd_missing(vma)) - goto unlock_abort; - - inc_mm_counter(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); - if (!is_zone_device_page(page)) - lru_cache_add_inactive_or_unevictable(page, vma); - get_page(page); - - if (flush) { - flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush_notify(vma, addr, ptep); - set_pte_at_notify(mm, addr, ptep, entry); - update_mmu_cache(vma, addr, ptep); - } else { - /* No need to invalidate - it was non-present before */ - set_pte_at(mm, addr, ptep, entry); - update_mmu_cache(vma, addr, ptep); - } - - pte_unmap_unlock(ptep, ptl); - *src = MIGRATE_PFN_MIGRATE; - return; - -unlock_abort: - pte_unmap_unlock(ptep, ptl); -abort: - *src &= ~MIGRATE_PFN_MIGRATE; -} - -/** - * migrate_vma_pages() - migrate meta-data from src page to dst page - * @migrate: migrate struct containing all migration information - * - * This migrates struct page meta-data from source struct page to destination - * struct page. This effectively finishes the migration from source page to the - * destination page. - */ -void migrate_vma_pages(struct migrate_vma *migrate) -{ - const unsigned long npages = migrate->npages; - const unsigned long start = migrate->start; - struct mmu_notifier_range range; - unsigned long addr, i; - bool notified = false; - - for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) { - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); - struct address_space *mapping; - int r; - - if (!newpage) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - continue; - } - - if (!page) { - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) - continue; - if (!notified) { - notified = true; - - mmu_notifier_range_init_owner(&range, - MMU_NOTIFY_MIGRATE, 0, migrate->vma, - migrate->vma->vm_mm, addr, migrate->end, - migrate->pgmap_owner); - mmu_notifier_invalidate_range_start(&range); - } - migrate_vma_insert_page(migrate, addr, newpage, - &migrate->src[i]); - continue; - } - - mapping = page_mapping(page); - - if (is_zone_device_page(newpage)) { - if (is_device_private_page(newpage)) { - /* - * For now only support private anonymous when - * migrating to un-addressable device memory. - */ - if (mapping) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - continue; - } - } else { - /* - * Other types of ZONE_DEVICE page are not - * supported. - */ - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - continue; - } - } - - r = migrate_page(mapping, newpage, page, MIGRATE_SYNC_NO_COPY); - if (r != MIGRATEPAGE_SUCCESS) - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + if (folio_test_dirty(folio)) + return -EAGAIN; } - /* - * No need to double call mmu_notifier->invalidate_range() callback as - * the above ptep_clear_flush_notify() inside migrate_vma_insert_page() - * did already call it. - */ - if (notified) - mmu_notifier_invalidate_range_only_end(&range); -} -EXPORT_SYMBOL(migrate_vma_pages); - -/** - * migrate_vma_finalize() - restore CPU page table entry - * @migrate: migrate struct containing all migration information - * - * This replaces the special migration pte entry with either a mapping to the - * new page if migration was successful for that page, or to the original page - * otherwise. - * - * This also unlocks the pages and puts them back on the lru, or drops the extra - * refcount, for device pages. - */ -void migrate_vma_finalize(struct migrate_vma *migrate) -{ - const unsigned long npages = migrate->npages; - unsigned long i; - - for (i = 0; i < npages; i++) { - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); - - if (!page) { - if (newpage) { - unlock_page(newpage); - put_page(newpage); - } - continue; - } - - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) { - if (newpage) { - unlock_page(newpage); - put_page(newpage); - } - newpage = page; - } - - remove_migration_ptes(page, newpage, false); - unlock_page(page); - - if (is_zone_device_page(page)) - put_page(page); - else - putback_lru_page(page); + /* Avoid migrating to a node that is nearly full */ + if (!migrate_balanced_pgdat(pgdat, nr_pages)) { + int z; - if (newpage != page) { - unlock_page(newpage); - if (is_zone_device_page(newpage)) - put_page(newpage); - else - putback_lru_page(newpage); + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) + return -EAGAIN; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + if (managed_zone(pgdat->node_zones + z)) + break; } - } -} -EXPORT_SYMBOL(migrate_vma_finalize); -#endif /* CONFIG_DEVICE_PRIVATE */ - -/* - * node_demotion[] example: - * - * Consider a system with two sockets. Each socket has - * three classes of memory attached: fast, medium and slow. - * Each memory class is placed in its own NUMA node. The - * CPUs are placed in the node with the "fast" memory. The - * 6 NUMA nodes (0-5) might be split among the sockets like - * this: - * - * Socket A: 0, 1, 2 - * Socket B: 3, 4, 5 - * - * When Node 0 fills up, its memory should be migrated to - * Node 1. When Node 1 fills up, it should be migrated to - * Node 2. The migration path start on the nodes with the - * processors (since allocations default to this node) and - * fast memory, progress through medium and end with the - * slow memory: - * - * 0 -> 1 -> 2 -> stop - * 3 -> 4 -> 5 -> stop - * - * This is represented in the node_demotion[] like this: - * - * { nr=1, nodes[0]=1 }, // Node 0 migrates to 1 - * { nr=1, nodes[0]=2 }, // Node 1 migrates to 2 - * { nr=0, nodes[0]=-1 }, // Node 2 does not migrate - * { nr=1, nodes[0]=4 }, // Node 3 migrates to 4 - * { nr=1, nodes[0]=5 }, // Node 4 migrates to 5 - * { nr=0, nodes[0]=-1 }, // Node 5 does not migrate - * - * Moreover some systems may have multiple slow memory nodes. - * Suppose a system has one socket with 3 memory nodes, node 0 - * is fast memory type, and node 1/2 both are slow memory - * type, and the distance between fast memory node and slow - * memory node is same. So the migration path should be: - * - * 0 -> 1/2 -> stop - * - * This is represented in the node_demotion[] like this: - * { nr=2, {nodes[0]=1, nodes[1]=2} }, // Node 0 migrates to node 1 and node 2 - * { nr=0, nodes[0]=-1, }, // Node 1 dose not migrate - * { nr=0, nodes[0]=-1, }, // Node 2 does not migrate - */ - -/* - * Writes to this array occur without locking. Cycles are - * not allowed: Node X demotes to Y which demotes to X... - * - * If multiple reads are performed, a single rcu_read_lock() - * must be held over all reads to ensure that no cycles are - * observed. - */ -#define DEFAULT_DEMOTION_TARGET_NODES 15 - -#if MAX_NUMNODES < DEFAULT_DEMOTION_TARGET_NODES -#define DEMOTION_TARGET_NODES (MAX_NUMNODES - 1) -#else -#define DEMOTION_TARGET_NODES DEFAULT_DEMOTION_TARGET_NODES -#endif - -struct demotion_nodes { - unsigned short nr; - short nodes[DEMOTION_TARGET_NODES]; -}; - -static struct demotion_nodes *node_demotion __read_mostly; - -/** - * next_demotion_node() - Get the next node in the demotion path - * @node: The starting node to lookup the next node - * - * Return: node id for next memory node in the demotion path hierarchy - * from @node; NUMA_NO_NODE if @node is terminal. This does not keep - * @node online or guarantee that it *continues* to be the next demotion - * target. - */ -int next_demotion_node(int node) -{ - struct demotion_nodes *nd; - unsigned short target_nr, index; - int target; - - if (!node_demotion) - return NUMA_NO_NODE; - nd = &node_demotion[node]; - - /* - * node_demotion[] is updated without excluding this - * function from running. RCU doesn't provide any - * compiler barriers, so the READ_ONCE() is required - * to avoid compiler reordering or read merging. - * - * Make sure to use RCU over entire code blocks if - * node_demotion[] reads need to be consistent. - */ - rcu_read_lock(); - target_nr = READ_ONCE(nd->nr); - - switch (target_nr) { - case 0: - target = NUMA_NO_NODE; - goto out; - case 1: - index = 0; - break; - default: /* - * If there are multiple target nodes, just select one - * target node randomly. - * - * In addition, we can also use round-robin to select - * target node, but we should introduce another variable - * for node_demotion[] to record last selected target node, - * that may cause cache ping-pong due to the changing of - * last target node. Or introducing per-cpu data to avoid - * caching issue, which seems more complicated. So selecting - * target node randomly seems better until now. + * If there are no managed zones, it should not proceed + * further. */ - index = get_random_int() % target_nr; - break; - } - - target = READ_ONCE(nd->nodes[index]); - -out: - rcu_read_unlock(); - return target; -} - -#if defined(CONFIG_HOTPLUG_CPU) -/* Disable reclaim-based migration. */ -static void __disable_all_migrate_targets(void) -{ - int node, i; - - if (!node_demotion) - return; - - for_each_online_node(node) { - node_demotion[node].nr = 0; - for (i = 0; i < DEMOTION_TARGET_NODES; i++) - node_demotion[node].nodes[i] = NUMA_NO_NODE; - } -} - -static void disable_all_migrate_targets(void) -{ - __disable_all_migrate_targets(); - - /* - * Ensure that the "disable" is visible across the system. - * Readers will see either a combination of before+disable - * state or disable+after. They will never see before and - * after state together. - * - * The before+after state together might have cycles and - * could cause readers to do things like loop until this - * function finishes. This ensures they can only see a - * single "bad" read and would, for instance, only loop - * once. - */ - synchronize_rcu(); -} - -/* - * Find an automatic demotion target for 'node'. - * Failing here is OK. It might just indicate - * being at the end of a chain. - */ -static int establish_migrate_target(int node, nodemask_t *used, - int best_distance) -{ - int migration_target, index, val; - struct demotion_nodes *nd; - - if (!node_demotion) - return NUMA_NO_NODE; - - nd = &node_demotion[node]; - - migration_target = find_next_best_node(node, used); - if (migration_target == NUMA_NO_NODE) - return NUMA_NO_NODE; - - /* - * If the node has been set a migration target node before, - * which means it's the best distance between them. Still - * check if this node can be demoted to other target nodes - * if they have a same best distance. - */ - if (best_distance != -1) { - val = node_distance(node, migration_target); - if (val > best_distance) - return NUMA_NO_NODE; - } - - index = nd->nr; - if (WARN_ONCE(index >= DEMOTION_TARGET_NODES, - "Exceeds maximum demotion target nodes\n")) - return NUMA_NO_NODE; - - nd->nodes[index] = migration_target; - nd->nr++; - - return migration_target; -} - -/* - * When memory fills up on a node, memory contents can be - * automatically migrated to another node instead of - * discarded at reclaim. - * - * Establish a "migration path" which will start at nodes - * with CPUs and will follow the priorities used to build the - * page allocator zonelists. - * - * The difference here is that cycles must be avoided. If - * node0 migrates to node1, then neither node1, nor anything - * node1 migrates to can migrate to node0. Also one node can - * be migrated to multiple nodes if the target nodes all have - * a same best-distance against the source node. - * - * This function can run simultaneously with readers of - * node_demotion[]. However, it can not run simultaneously - * with itself. Exclusion is provided by memory hotplug events - * being single-threaded. - */ -static void __set_migration_target_nodes(void) -{ - nodemask_t next_pass = NODE_MASK_NONE; - nodemask_t this_pass = NODE_MASK_NONE; - nodemask_t used_targets = NODE_MASK_NONE; - int node, best_distance; - - /* - * Avoid any oddities like cycles that could occur - * from changes in the topology. This will leave - * a momentary gap when migration is disabled. - */ - disable_all_migrate_targets(); - - /* - * Allocations go close to CPUs, first. Assume that - * the migration path starts at the nodes with CPUs. - */ - next_pass = node_states[N_CPU]; -again: - this_pass = next_pass; - next_pass = NODE_MASK_NONE; - /* - * To avoid cycles in the migration "graph", ensure - * that migration sources are not future targets by - * setting them in 'used_targets'. Do this only - * once per pass so that multiple source nodes can - * share a target node. - * - * 'used_targets' will become unavailable in future - * passes. This limits some opportunities for - * multiple source nodes to share a destination. - */ - nodes_or(used_targets, used_targets, this_pass); - - for_each_node_mask(node, this_pass) { - best_distance = -1; - - /* - * Try to set up the migration path for the node, and the target - * migration nodes can be multiple, so doing a loop to find all - * the target nodes if they all have a best node distance. - */ - do { - int target_node = - establish_migrate_target(node, &used_targets, - best_distance); - - if (target_node == NUMA_NO_NODE) - break; - - if (best_distance == -1) - best_distance = node_distance(node, target_node); + if (z < 0) + return -EAGAIN; - /* - * Visit targets from this pass in the next pass. - * Eventually, every node will have been part of - * a pass, and will become set in 'used_targets'. - */ - node_set(target_node, next_pass); - } while (1); + wakeup_kswapd(pgdat->node_zones + z, 0, + folio_order(folio), ZONE_MOVABLE); + return -EAGAIN; } - /* - * 'next_pass' contains nodes which became migration - * targets in this pass. Make additional passes until - * no more migrations targets are available. - */ - if (!nodes_empty(next_pass)) - goto again; -} -/* - * For callers that do not hold get_online_mems() already. - */ -static void set_migration_target_nodes(void) -{ - get_online_mems(); - __set_migration_target_nodes(); - put_online_mems(); -} - -/* - * This leaves migrate-on-reclaim transiently disabled between - * the MEM_GOING_OFFLINE and MEM_OFFLINE events. This runs - * whether reclaim-based migration is enabled or not, which - * ensures that the user can turn reclaim-based migration at - * any time without needing to recalculate migration targets. - * - * These callbacks already hold get_online_mems(). That is why - * __set_migration_target_nodes() can be used as opposed to - * set_migration_target_nodes(). - */ -static int __meminit migrate_on_reclaim_callback(struct notifier_block *self, - unsigned long action, void *_arg) -{ - struct memory_notify *arg = _arg; - - /* - * Only update the node migration order when a node is - * changing status, like online->offline. This avoids - * the overhead of synchronize_rcu() in most cases. - */ - if (arg->status_change_nid < 0) - return notifier_from_errno(0); - - switch (action) { - case MEM_GOING_OFFLINE: - /* - * Make sure there are not transient states where - * an offline node is a migration target. This - * will leave migration disabled until the offline - * completes and the MEM_OFFLINE case below runs. - */ - disable_all_migrate_targets(); - break; - case MEM_OFFLINE: - case MEM_ONLINE: - /* - * Recalculate the target nodes once the node - * reaches its final state (online or offline). - */ - __set_migration_target_nodes(); - break; - case MEM_CANCEL_OFFLINE: - /* - * MEM_GOING_OFFLINE disabled all the migration - * targets. Reenable them. - */ - __set_migration_target_nodes(); - break; - case MEM_GOING_ONLINE: - case MEM_CANCEL_ONLINE: - break; - } + if (!folio_isolate_lru(folio)) + return -EAGAIN; - return notifier_from_errno(0); + node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), + nr_pages); + return 0; } /* - * React to hotplug events that might affect the migration targets - * like events that online or offline NUMA nodes. - * - * The ordering is also currently dependent on which nodes have - * CPUs. That means we need CPU on/offline notification too. + * Attempt to migrate a misplaced folio to the specified destination + * node. Caller is expected to have isolated the folio by calling + * migrate_misplaced_folio_prepare(), which will result in an + * elevated reference count on the folio. This function will un-isolate the + * folio, dereferencing the folio before returning. */ -static int migration_online_cpu(unsigned int cpu) +int migrate_misplaced_folio(struct folio *folio, int node) { - set_migration_target_nodes(); - return 0; -} - -static int migration_offline_cpu(unsigned int cpu) -{ - set_migration_target_nodes(); - return 0; -} - -static int __init migrate_on_reclaim_init(void) -{ - int ret; - - node_demotion = kmalloc_array(nr_node_ids, - sizeof(struct demotion_nodes), - GFP_KERNEL); - WARN_ON(!node_demotion); - - ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline", - NULL, migration_offline_cpu); - /* - * In the unlikely case that this fails, the automatic - * migration targets may become suboptimal for nodes - * where N_CPU changes. With such a small impact in a - * rare case, do not bother trying to do anything special. - */ - WARN_ON(ret < 0); - ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online", - migration_online_cpu, NULL); - WARN_ON(ret < 0); - - hotplug_memory_notifier(migrate_on_reclaim_callback, 100); - return 0; -} -late_initcall(migrate_on_reclaim_init); -#endif /* CONFIG_HOTPLUG_CPU */ - -bool numa_demotion_enabled = false; - -#ifdef CONFIG_SYSFS -static ssize_t numa_demotion_enabled_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "%s\n", - numa_demotion_enabled ? "true" : "false"); -} - -static ssize_t numa_demotion_enabled_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) - numa_demotion_enabled = true; - else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) - numa_demotion_enabled = false; - else - return -EINVAL; - - return count; -} - -static struct kobj_attribute numa_demotion_enabled_attr = - __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, - numa_demotion_enabled_store); - -static struct attribute *numa_attrs[] = { - &numa_demotion_enabled_attr.attr, - NULL, -}; - -static const struct attribute_group numa_attr_group = { - .attrs = numa_attrs, -}; - -static int __init numa_init_sysfs(void) -{ - int err; - struct kobject *numa_kobj; - - numa_kobj = kobject_create_and_add("numa", mm_kobj); - if (!numa_kobj) { - pr_err("failed to create numa kobject\n"); - return -ENOMEM; - } - err = sysfs_create_group(numa_kobj, &numa_attr_group); - if (err) { - pr_err("failed to register numa group\n"); - goto delete_obj; + pg_data_t *pgdat = NODE_DATA(node); + int nr_remaining; + unsigned int nr_succeeded; + LIST_HEAD(migratepages); + struct mem_cgroup *memcg = get_mem_cgroup_from_folio(folio); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); + + list_add(&folio->lru, &migratepages); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED, &nr_succeeded); + if (nr_remaining && !list_empty(&migratepages)) + putback_movable_pages(&migratepages); + if (nr_succeeded) { + count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); + count_memcg_events(memcg, NUMA_PAGE_MIGRATE, nr_succeeded); + if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) + && !node_is_toptier(folio_nid(folio)) + && node_is_toptier(node)) + mod_lruvec_state(lruvec, PGPROMOTE_SUCCESS, nr_succeeded); } - return 0; - -delete_obj: - kobject_put(numa_kobj); - return err; + mem_cgroup_put(memcg); + BUG_ON(!list_empty(&migratepages)); + return nr_remaining ? -EAGAIN : 0; } -subsys_initcall(numa_init_sysfs); -#endif +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_NUMA */ |