diff options
Diffstat (limited to 'mm/migrate.c')
-rw-r--r-- | mm/migrate.c | 515 |
1 files changed, 290 insertions, 225 deletions
diff --git a/mm/migrate.c b/mm/migrate.c index 2cc5a68f6843..df91248755e4 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -20,7 +20,6 @@ #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/mm_inline.h> -#include <linux/nsproxy.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/topology.h> @@ -35,21 +34,16 @@ #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/hugetlb.h> -#include <linux/hugetlb_cgroup.h> #include <linux/gfp.h> #include <linux/pfn_t.h> -#include <linux/memremap.h> -#include <linux/userfaultfd_k.h> -#include <linux/balloon_compaction.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> @@ -177,13 +171,83 @@ void putback_movable_pages(struct list_head *l) } } +/* Must be called with an elevated refcount on the non-hugetlb folio */ +bool isolate_folio_to_list(struct folio *folio, struct list_head *list) +{ + bool isolated, lru; + + if (folio_test_hugetlb(folio)) + return isolate_hugetlb(folio, list); + + lru = !__folio_test_movable(folio); + if (lru) + isolated = folio_isolate_lru(folio); + else + isolated = isolate_movable_page(&folio->page, + ISOLATE_UNEVICTABLE); + + if (!isolated) + return false; + + list_add(&folio->lru, list); + if (lru) + node_stat_add_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio)); + + return true; +} + +static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, + struct folio *folio, + unsigned long idx) +{ + struct page *page = folio_page(folio, idx); + bool contains_data; + pte_t newpte; + void *addr; + + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page); + + 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. + */ + addr = kmap_local_page(page); + contains_data = memchr_inv(addr, 0, PAGE_SIZE); + kunmap_local(addr); + + if (contains_data) + return false; + + newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address), + pvmw->vma->vm_page_prot)); + 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 folio *folio, - struct vm_area_struct *vma, unsigned long addr, void *old) + struct vm_area_struct *vma, unsigned long addr, void *arg) { - DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); + struct rmap_walk_arg *rmap_walk_arg = arg; + DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; @@ -207,6 +271,9 @@ static bool remove_migration_pte(struct folio *folio, continue; } #endif + if (rmap_walk_arg->map_unused_to_zeropage && + try_to_map_unused_to_zeropage(&pvmw, folio, idx)) + continue; folio_get(folio); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); @@ -285,14 +352,21 @@ static bool remove_migration_pte(struct folio *folio, * Get rid of all migration entries and replace them by * references to the indicated page. */ -void remove_migration_ptes(struct folio *src, struct folio *dst, 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 = src, + .arg = &rmap_walk_arg, }; - if (locked) + VM_BUG_ON_FOLIO((flags & RMP_USE_SHARED_ZEROPAGE) && (src != dst), src); + + if (flags & RMP_LOCKED) rmap_walk_locked(dst, &rwc); else rmap_walk(dst, &rwc); @@ -338,14 +412,14 @@ out: * * This function will release the vma lock before returning. */ -void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *ptep) +void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, ptep); pte_t pte; hugetlb_vma_assert_locked(vma); spin_lock(ptl); - pte = huge_ptep_get(ptep); + pte = huge_ptep_get(vma->vm_mm, addr, ptep); if (unlikely(!is_hugetlb_entry_migration(pte))) { spin_unlock(ptl); @@ -393,31 +467,37 @@ static int folio_expected_refs(struct address_space *mapping, } /* - * 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 PagePrivate/PagePrivate2 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)); struct zone *oldzone, *newzone; int dirty; - int expected_count = folio_expected_refs(mapping, folio) + extra_count; long nr = folio_nr_pages(folio); long entries, i; 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_undo_large_rmappable(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); @@ -433,12 +513,17 @@ int folio_migrate_mapping(struct address_space *mapping, return -EAGAIN; } + /* Take off deferred split queue while frozen and memcg set */ + folio_undo_large_rmappable(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)) { __folio_set_swapbacked(newfolio); @@ -452,7 +537,7 @@ int folio_migrate_mapping(struct address_space *mapping, entries = 1; } - /* 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); @@ -466,7 +551,7 @@ int folio_migrate_mapping(struct address_space *mapping, } /* - * 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. */ @@ -477,11 +562,11 @@ int folio_migrate_mapping(struct address_space *mapping, /* * 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. */ @@ -521,6 +606,17 @@ int folio_migrate_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } + +int folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int extra_count) +{ + int expected_count = folio_expected_refs(mapping, folio) + extra_count; + + if (folio_ref_count(folio) != expected_count) + return -EAGAIN; + + return __folio_migrate_mapping(mapping, newfolio, folio, expected_count); +} EXPORT_SYMBOL(folio_migrate_mapping); /* @@ -531,10 +627,16 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src) { XA_STATE(xas, &mapping->i_pages, folio_index(src)); - int expected_count; + int rc, expected_count = folio_expected_refs(mapping, src); + + if (folio_ref_count(src) != expected_count) + return -EAGAIN; + + rc = folio_mc_copy(dst, src); + if (unlikely(rc)) + return rc; xas_lock_irq(&xas); - expected_count = folio_expected_refs(mapping, src); if (!folio_ref_freeze(src, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; @@ -561,8 +663,6 @@ 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)) @@ -616,7 +716,8 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's - * ksm_get_folio() 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); @@ -642,38 +743,38 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_readahead(newfolio); folio_copy_owner(newfolio, folio); + pgalloc_tag_copy(newfolio, folio); 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 ***********************************************************/ -int migrate_folio_extra(struct address_space *mapping, struct folio *dst, - struct folio *src, enum migrate_mode mode, int extra_count) +static int __migrate_folio(struct address_space *mapping, struct folio *dst, + struct folio *src, void *src_private, + enum migrate_mode mode) { - int rc; + int rc, expected_count = folio_expected_refs(mapping, src); - BUG_ON(folio_test_writeback(src)); /* 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, dst, src, extra_count); + rc = folio_mc_copy(dst, src); + if (unlikely(rc)) + return rc; + rc = __folio_migrate_mapping(mapping, dst, src, expected_count); if (rc != MIGRATEPAGE_SUCCESS) return rc; - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(dst, src); - else - folio_migrate_flags(dst, src); + if (src_private) + folio_attach_private(dst, folio_detach_private(src)); + + folio_migrate_flags(dst, src); return MIGRATEPAGE_SUCCESS; } @@ -690,9 +791,10 @@ int migrate_folio_extra(struct address_space *mapping, struct folio *dst, * Folios are locked upon entry and exit. */ int migrate_folio(struct address_space *mapping, struct folio *dst, - struct folio *src, enum migrate_mode mode) + struct folio *src, enum migrate_mode mode) { - return migrate_folio_extra(mapping, dst, src, mode, 0); + BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ + return __migrate_folio(mapping, dst, src, NULL, mode); } EXPORT_SYMBOL(migrate_folio); @@ -777,24 +879,16 @@ recheck_buffers: } } - rc = folio_migrate_mapping(mapping, dst, src, 0); + rc = filemap_migrate_folio(mapping, dst, src, mode); if (rc != MIGRATEPAGE_SUCCESS) goto unlock_buffers; - folio_attach_private(dst, folio_detach_private(src)); - bh = head; do { folio_set_bh(bh, dst, bh_offset(bh)); bh = bh->b_this_page; } while (bh != head); - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(dst, src); - else - folio_migrate_flags(dst, src); - - rc = MIGRATEPAGE_SUCCESS; unlock_buffers: if (check_refs) spin_unlock(&mapping->i_private_lock); @@ -854,20 +948,7 @@ EXPORT_SYMBOL_GPL(buffer_migrate_folio_norefs); int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { - int ret; - - ret = folio_migrate_mapping(mapping, dst, src, 0); - if (ret != MIGRATEPAGE_SUCCESS) - return ret; - - if (folio_get_private(src)) - folio_attach_private(dst, folio_detach_private(src)); - - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(dst, src); - else - folio_migrate_flags(dst, src); - return MIGRATEPAGE_SUCCESS; + return __migrate_folio(mapping, dst, src, folio_get_private(src), mode); } EXPORT_SYMBOL_GPL(filemap_migrate_folio); @@ -901,7 +982,7 @@ static int writeout(struct address_space *mapping, struct folio *folio) * At this point we know that the migration attempt cannot * be successful. */ - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, 0); rc = mapping->a_ops->writepage(&folio->page, &wbc); @@ -922,7 +1003,6 @@ static int fallback_migrate_folio(struct address_space *mapping, /* Only writeback folios in full synchronous migration */ switch (mode) { case MIGRATE_SYNC: - case MIGRATE_SYNC_NO_COPY: break; default: return -EBUSY; @@ -965,7 +1045,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, if (!mapping) rc = migrate_folio(mapping, dst, src, mode); - else if (mapping_unmovable(mapping)) + else if (mapping_inaccessible(mapping)) rc = -EOPNOTSUPP; else if (mapping->a_ops->migrate_folio) /* @@ -1066,7 +1146,7 @@ static void migrate_folio_undo_src(struct folio *src, struct list_head *ret) { if (page_was_mapped) - remove_migration_ptes(src, src, false); + remove_migration_ptes(src, src, 0); /* Drop an anon_vma reference if we took one */ if (anon_vma) put_anon_vma(anon_vma); @@ -1116,7 +1196,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio, int rc = -EAGAIN; int old_page_state = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__folio_test_movable(src); + bool is_lru = data_race(!__folio_test_movable(src)); bool locked = false; bool dst_locked = false; @@ -1180,7 +1260,6 @@ static int migrate_folio_unmap(new_folio_t get_new_folio, */ switch (mode) { case MIGRATE_SYNC: - case MIGRATE_SYNC_NO_COPY: break; default: rc = -EBUSY; @@ -1305,7 +1384,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, lru_add_drain(); if (old_page_state & PAGE_WAS_MAPPED) - remove_migration_ptes(src, dst, false); + remove_migration_ptes(src, dst, 0); out_unlock_both: folio_unlock(dst); @@ -1391,7 +1470,6 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, goto out; switch (mode) { case MIGRATE_SYNC: - case MIGRATE_SYNC_NO_COPY: break; default: goto out; @@ -1444,7 +1522,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, if (page_was_mapped) remove_migration_ptes(src, - rc == MIGRATEPAGE_SUCCESS ? dst : src, false); + rc == MIGRATEPAGE_SUCCESS ? dst : src, 0); unlock_put_anon: folio_unlock(dst); @@ -1479,11 +1557,17 @@ out: return rc; } -static inline int try_split_folio(struct folio *folio, struct list_head *split_folios) +static inline int try_split_folio(struct folio *folio, struct list_head *split_folios, + enum migrate_mode mode) { int rc; - folio_lock(folio); + 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) @@ -1659,6 +1743,10 @@ static int migrate_pages_batch(struct list_head *from, * 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. * * Only check it without removing it from the list. * Since the folio can be on deferred_split_scan() @@ -1672,9 +1760,11 @@ static int migrate_pages_batch(struct list_head *from, * use _deferred_list. */ if (nr_pages > 2 && - !list_empty(&folio->_deferred_list)) { - if (try_split_folio(folio, split_folios) == 0) { + !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; @@ -1694,7 +1784,7 @@ static int migrate_pages_batch(struct list_head *from, if (!thp_migration_supported() && is_thp) { nr_failed++; stats->nr_thp_failed++; - if (!try_split_folio(folio, split_folios)) { + if (!try_split_folio(folio, split_folios, mode)) { stats->nr_thp_split++; stats->nr_split++; continue; @@ -1726,7 +1816,7 @@ static int migrate_pages_batch(struct list_head *from, 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); + int ret = try_split_folio(folio, split_folios, mode); if (!ret) { stats->nr_thp_split += is_thp; @@ -2100,76 +2190,66 @@ static int do_move_pages_to_node(struct list_head *pagelist, int node) 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_likely_mapped_shared(folio) && !migrate_all) + return -EACCES; + + if (folio_test_hugetlb(folio)) { + if (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, const void __user *p, +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; - unsigned long addr; - struct page *page; + struct folio_walk fw; struct folio *folio; - int err; + unsigned long addr; + int err = -EFAULT; mmap_read_lock(mm); addr = (unsigned long)untagged_addr_remote(mm, p); - err = -EFAULT; vma = vma_lookup(mm, addr); - if (!vma || !vma_migratable(vma)) - goto out; - - /* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); - - err = PTR_ERR(page); - if (IS_ERR(page)) - goto out; - - err = -ENOENT; - if (!page) - goto out; - - folio = page_folio(page); - if (folio_is_zone_device(folio)) - goto out_putfolio; - - err = 0; - if (folio_nid(folio) == node) - goto out_putfolio; - - err = -EACCES; - if (folio_likely_mapped_shared(folio) && !migrate_all) - goto out_putfolio; - - err = -EBUSY; - if (folio_test_hugetlb(folio)) { - if (isolate_hugetlb(folio, pagelist)) - err = 1; - } else { - if (!folio_isolate_lru(folio)) - goto out_putfolio; - - err = 1; - list_add_tail(&folio->lru, pagelist); - node_stat_mod_folio(folio, - NR_ISOLATED_ANON + folio_is_file_lru(folio), - folio_nr_pages(folio)); + 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; + } } -out_putfolio: - /* - * Either remove the duplicate refcount from folio_isolate_lru() - * or drop the folio ref if it was not isolated. - */ - folio_put(folio); -out: mmap_read_unlock(mm); return err; } @@ -2263,8 +2343,8 @@ 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, p, 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 */ @@ -2320,28 +2400,26 @@ 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_GET | FOLL_DUMP); - - err = PTR_ERR(page); - if (IS_ERR(page)) - goto set_status; - - err = -ENOENT; - if (!page) - goto set_status; - - if (!is_zone_device_page(page)) - err = page_to_nid(page); - - put_page(page); + 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; @@ -2421,25 +2499,19 @@ 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)) @@ -2515,7 +2587,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, if (!zone_watermark_ok(zone, 0, high_wmark_pages(zone) + nr_migrate_pages, - ZONE_MOVABLE, 0)) + ZONE_MOVABLE, ALLOC_CMA)) continue; return true; } @@ -2539,16 +2611,44 @@ static struct folio *alloc_misplaced_dst_folio(struct folio *src, return __folio_alloc_node(gfp, order, nid); } -static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio) +/* + * Prepare for calling migrate_misplaced_folio() by isolating the folio if + * permitted. Must be called with the PTL still held. + */ +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); + + if (folio_is_file_lru(folio)) { + /* + * Do not migrate file folios that are mapped in multiple + * processes with execute permissions as they are probably + * shared libraries. + * + * See folio_likely_mapped_shared() on possible imprecision + * when we cannot easily detect if a folio is shared. + */ + if ((vma->vm_flags & VM_EXEC) && + folio_likely_mapped_shared(folio)) + return -EACCES; + + /* + * Do not migrate dirty folios as not all filesystems can move + * dirty folios in MIGRATE_ASYNC mode which is a waste of + * cycles. + */ + if (folio_test_dirty(folio)) + return -EAGAIN; + } /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, nr_pages)) { int z; if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) - return 0; + return -EAGAIN; for (z = pgdat->nr_zones - 1; z >= 0; z--) { if (managed_zone(pgdat->node_zones + z)) break; @@ -2559,90 +2659,55 @@ static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio) * further. */ if (z < 0) - return 0; + return -EAGAIN; wakeup_kswapd(pgdat->node_zones + z, 0, folio_order(folio), ZONE_MOVABLE); - return 0; + return -EAGAIN; } if (!folio_isolate_lru(folio)) - return 0; + return -EAGAIN; node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), nr_pages); - - /* - * Isolating the folio has taken another reference, so the - * caller's reference can be safely dropped without the folio - * disappearing underneath us during migration. - */ - folio_put(folio); - return 1; + return 0; } /* * Attempt to migrate a misplaced folio to the specified destination - * node. Caller is expected to have an elevated reference count on - * the folio that will be dropped by this function before returning. + * 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. */ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node) { pg_data_t *pgdat = NODE_DATA(node); - int isolated; int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - int nr_pages = folio_nr_pages(folio); - - /* - * Don't migrate file folios that are mapped in multiple processes - * with execute permissions as they are probably shared libraries. - * - * See folio_likely_mapped_shared() on possible imprecision when we - * cannot easily detect if a folio is shared. - */ - if (folio_likely_mapped_shared(folio) && folio_is_file_lru(folio) && - (vma->vm_flags & VM_EXEC)) - goto out; - - /* - * Also do not migrate dirty folios as not all filesystems can move - * dirty folios in MIGRATE_ASYNC mode which is a waste of cycles. - */ - if (folio_is_file_lru(folio) && folio_test_dirty(folio)) - goto out; - - isolated = numamigrate_isolate_folio(pgdat, folio); - if (!isolated) - goto out; + 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) { - if (!list_empty(&migratepages)) { - list_del(&folio->lru); - node_stat_mod_folio(folio, NR_ISOLATED_ANON + - folio_is_file_lru(folio), -nr_pages); - folio_putback_lru(folio); - } - isolated = 0; - } + if (nr_remaining && !list_empty(&migratepages)) + putback_movable_pages(&migratepages); if (nr_succeeded) { count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); - if (!node_is_toptier(folio_nid(folio)) && node_is_toptier(node)) - mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, - 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); } + mem_cgroup_put(memcg); BUG_ON(!list_empty(&migratepages)); - return isolated; - -out: - folio_put(folio); - return 0; + return nr_remaining ? -EAGAIN : 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_NUMA */ |