diff options
Diffstat (limited to 'mm/migrate.c')
| -rw-r--r-- | mm/migrate.c | 988 |
1 files changed, 112 insertions, 876 deletions
diff --git a/mm/migrate.c b/mm/migrate.c index c7da064b4781..3d60823afd2d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -38,12 +38,10 @@ #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> @@ -51,10 +49,10 @@ #include <linux/oom.h> #include <linux/memory.h> #include <linux/random.h> +#include <linux/sched/sysctl.h> #include <asm/tlbflush.h> -#define CREATE_TRACE_POINTS #include <trace/events/migrate.h> #include "internal.h" @@ -107,7 +105,7 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) /* Driver shouldn't use PG_isolated bit of page->flags */ WARN_ON_ONCE(PageIsolated(page)); - __SetPageIsolated(page); + SetPageIsolated(page); unlock_page(page); return 0; @@ -126,7 +124,7 @@ static void putback_movable_page(struct page *page) mapping = page_mapping(page); mapping->a_ops->putback_page(page); - __ClearPageIsolated(page); + ClearPageIsolated(page); } /* @@ -159,7 +157,7 @@ void putback_movable_pages(struct list_head *l) if (PageMovable(page)) putback_movable_page(page); else - __ClearPageIsolated(page); + ClearPageIsolated(page); unlock_page(page); put_page(page); } else { @@ -173,37 +171,33 @@ void putback_movable_pages(struct list_head *l) /* * 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 *old) { - 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; + DEFINE_FOLIO_VMA_WALK(pvmw, old, 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); + pte_t pte; + swp_entry_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 - get_page(new); + folio_get(folio); pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); if (pte_swp_soft_dirty(*pvmw.pte)) pte = pte_mksoft_dirty(pte); @@ -232,12 +226,12 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, } #ifdef CONFIG_HUGETLB_PAGE - if (PageHuge(new)) { + if (folio_test_hugetlb(folio)) { unsigned int shift = huge_page_shift(hstate_vma(vma)); pte = pte_mkhuge(pte); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); - if (PageAnon(new)) + if (folio_test_anon(folio)) hugepage_add_anon_rmap(new, vma, pvmw.address); else page_dup_rmap(new, true); @@ -245,17 +239,17 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, } else #endif { - if (PageAnon(new)) + if (folio_test_anon(folio)) page_add_anon_rmap(new, vma, pvmw.address, false); else - page_add_file_rmap(new, false); + page_add_file_rmap(new, vma, false); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } - if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) - mlock_vma_page(new); + if (vma->vm_flags & VM_LOCKED) + mlock_page_drain(smp_processor_id()); - 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 +262,17 @@ 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, bool locked) { struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, - .arg = old, + .arg = src, }; if (locked) - rmap_walk_locked(new, &rwc); + rmap_walk_locked(dst, &rwc); else - rmap_walk(new, &rwc); + rmap_walk(dst, &rwc); } /* @@ -341,14 +335,8 @@ 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; } @@ -771,6 +759,7 @@ int buffer_migrate_page_norefs(struct address_space *mapping, */ static int writeout(struct address_space *mapping, struct page *page) { + struct folio *folio = page_folio(page); struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = 1, @@ -796,7 +785,7 @@ static int writeout(struct address_space *mapping, struct page *page) * At this point we know that the migration attempt cannot * be successful. */ - remove_migration_ptes(page, page, false); + remove_migration_ptes(folio, folio, false); rc = mapping->a_ops->writepage(page, &wbc); @@ -883,7 +872,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, VM_BUG_ON_PAGE(!PageIsolated(page), page); if (!PageMovable(page)) { rc = MIGRATEPAGE_SUCCESS; - __ClearPageIsolated(page); + ClearPageIsolated(page); goto out; } @@ -905,7 +894,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, * We clear PG_movable under page_lock so any compactor * cannot try to migrate this page. */ - __ClearPageIsolated(page); + ClearPageIsolated(page); } /* @@ -917,8 +906,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, page->mapping = NULL; if (likely(!is_zone_device_page(newpage))) - flush_dcache_page(newpage); - + flush_dcache_folio(page_folio(newpage)); } out: return rc; @@ -927,6 +915,8 @@ out: static int __unmap_and_move(struct page *page, struct page *newpage, int force, enum migrate_mode mode) { + struct folio *folio = page_folio(page); + struct folio *dst = page_folio(newpage); int rc = -EAGAIN; bool page_was_mapped = false; struct anon_vma *anon_vma = NULL; @@ -1030,16 +1020,31 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes */ VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma, page); - try_to_migrate(page, 0); + try_to_migrate(folio, 0); page_was_mapped = true; } if (!page_mapped(page)) rc = move_to_new_page(newpage, page, mode); + /* + * When successful, push newpage to LRU immediately: so that if it + * turns out to be an mlocked page, remove_migration_ptes() will + * automatically build up the correct newpage->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. + */ + if (rc == MIGRATEPAGE_SUCCESS) { + lru_cache_add(newpage); + if (page_was_mapped) + lru_add_drain(); + } + if (page_was_mapped) - remove_migration_ptes(page, - rc == MIGRATEPAGE_SUCCESS ? newpage : page, false); + remove_migration_ptes(folio, + rc == MIGRATEPAGE_SUCCESS ? dst : folio, false); out_unlock_both: unlock_page(newpage); @@ -1050,20 +1055,12 @@ out_unlock: unlock_page(page); out: /* - * If migration is successful, decrease refcount of the newpage + * 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. + * refcounter. */ - if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(!is_lru)) - put_page(newpage); - else - putback_lru_page(newpage); - } + if (rc == MIGRATEPAGE_SUCCESS) + put_page(newpage); return rc; } @@ -1092,7 +1089,7 @@ static int unmap_and_move(new_page_t get_new_page, if (unlikely(__PageMovable(page))) { lock_page(page); if (!PageMovable(page)) - __ClearPageIsolated(page); + ClearPageIsolated(page); unlock_page(page); } goto out; @@ -1173,6 +1170,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, enum migrate_mode mode, int reason, struct list_head *ret) { + struct folio *dst, *src = page_folio(hpage); int rc = -EAGAIN; int page_was_mapped = 0; struct page *new_hpage; @@ -1200,6 +1198,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, new_hpage = get_new_page(hpage, private); if (!new_hpage) return -ENOMEM; + dst = page_folio(new_hpage); if (!trylock_page(hpage)) { if (!force) @@ -1249,7 +1248,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, ttu |= TTU_RMAP_LOCKED; } - try_to_migrate(hpage, ttu); + try_to_migrate(src, ttu); page_was_mapped = 1; if (mapping_locked) @@ -1260,8 +1259,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, rc = move_to_new_page(new_hpage, hpage, mode); if (page_was_mapped) - remove_migration_ptes(hpage, - rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); + remove_migration_ptes(src, + rc == MIGRATEPAGE_SUCCESS ? dst : src, false); unlock_put_anon: unlock_page(new_hpage); @@ -1351,7 +1350,6 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, 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); @@ -1360,9 +1358,6 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, trace_mm_migrate_pages_start(mode, reason); - if (!swapwrite) - current->flags |= PF_SWAPWRITE; - thp_subpage_migration: for (pass = 0; pass < 10 && (retry || thp_retry); pass++) { retry = 0; @@ -1517,9 +1512,6 @@ out: trace_mm_migrate_pages(nr_succeeded, nr_failed_pages, nr_thp_succeeded, nr_thp_failed, nr_thp_split, mode, reason); - if (!swapwrite) - current->flags &= ~PF_SWAPWRITE; - if (ret_succeeded) *ret_succeeded = nr_succeeded; @@ -1612,7 +1604,6 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, { struct vm_area_struct *vma; struct page *page; - unsigned int follflags; int err; mmap_read_lock(mm); @@ -1622,8 +1613,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, goto out; /* FOLL_DUMP to ignore special (like zero) pages */ - follflags = FOLL_GET | FOLL_DUMP; - page = follow_page(vma, addr, follflags); + page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); err = PTR_ERR(page); if (IS_ERR(page)) @@ -1762,6 +1752,13 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, } /* + * The move_pages() man page does not have an -EEXIST choice, so + * use -EFAULT instead. + */ + if (err == -EEXIST) + err = -EFAULT; + + /* * If the page is already on the target node (!err), store the * node, otherwise, store the err. */ @@ -2034,16 +2031,27 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; int nr_pages = thp_nr_pages(page); + int order = compound_order(page); - VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + VM_BUG_ON_PAGE(order && !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)) + if (!migrate_balanced_pgdat(pgdat, nr_pages)) { + int z; + + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) + return 0; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + if (populated_zone(pgdat->node_zones + z)) + break; + } + wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); return 0; + } if (isolate_lru_page(page)) return 0; @@ -2072,6 +2080,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, pg_data_t *pgdat = NODE_DATA(node); int isolated; int nr_remaining; + unsigned int nr_succeeded; LIST_HEAD(migratepages); new_page_t *new; bool compound; @@ -2110,7 +2119,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, list_add(&page->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, NULL); + MIGRATE_ASYNC, MR_NUMA_MISPLACED, + &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); @@ -2119,8 +2129,13 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, putback_lru_page(page); } isolated = 0; - } else - count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages); + } + if (nr_succeeded) { + count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); + if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node)) + mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, + nr_succeeded); + } BUG_ON(!list_empty(&migratepages)); return isolated; @@ -2131,761 +2146,6 @@ out: #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; - } - - /* - * 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. - * - * 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). - */ - get_page(page); - - /* - * 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. - */ - 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; - } - - /* - * 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); - - if (newpage != page) { - unlock_page(newpage); - if (is_zone_device_page(newpage)) - put_page(newpage); - else - putback_lru_page(newpage); - } - } -} -EXPORT_SYMBOL(migrate_vma_finalize); -#endif /* CONFIG_DEVICE_PRIVATE */ - /* * node_demotion[] example: * @@ -3082,18 +2342,21 @@ static int establish_migrate_target(int node, nodemask_t *used, if (best_distance != -1) { val = node_distance(node, migration_target); if (val > best_distance) - return NUMA_NO_NODE; + goto out_clear; } index = nd->nr; if (WARN_ONCE(index >= DEMOTION_TARGET_NODES, "Exceeds maximum demotion target nodes\n")) - return NUMA_NO_NODE; + goto out_clear; nd->nodes[index] = migration_target; nd->nr++; return migration_target; +out_clear: + node_clear(migration_target, *used); + return NUMA_NO_NODE; } /* @@ -3190,7 +2453,7 @@ again: /* * For callers that do not hold get_online_mems() already. */ -static void set_migration_target_nodes(void) +void set_migration_target_nodes(void) { get_online_mems(); __set_migration_target_nodes(); @@ -3254,51 +2517,24 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self, return notifier_from_errno(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. - */ -static int migration_online_cpu(unsigned int cpu) -{ - set_migration_target_nodes(); - return 0; -} - -static int migration_offline_cpu(unsigned int cpu) +void __init migrate_on_reclaim_init(void) { - 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); + hotplug_memory_notifier(migrate_on_reclaim_callback, 100); /* - * 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. + * At this point, all numa nodes with memory/CPus have their state + * properly set, so we can build the demotion order now. + * Let us hold the cpu_hotplug lock just, as we could possibily have + * CPU hotplug events during boot. */ - 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; + cpus_read_lock(); + set_migration_target_nodes(); + cpus_read_unlock(); } -late_initcall(migrate_on_reclaim_init); #endif /* CONFIG_HOTPLUG_CPU */ bool numa_demotion_enabled = false; |