summaryrefslogtreecommitdiff
path: root/mm/migrate.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/migrate.c')
-rw-r--r--mm/migrate.c225
1 files changed, 117 insertions, 108 deletions
diff --git a/mm/migrate.c b/mm/migrate.c
index 06086dc9da28..35a88334bb3c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -157,8 +157,8 @@ void putback_movable_pages(struct list_head *l)
list_del(&folio->lru);
/*
* We isolated non-lru movable folio so here we can use
- * __PageMovable because LRU folio's mapping cannot have
- * PAGE_MAPPING_MOVABLE.
+ * __folio_test_movable because LRU folio's mapping cannot
+ * have PAGE_MAPPING_MOVABLE.
*/
if (unlikely(__folio_test_movable(folio))) {
VM_BUG_ON_FOLIO(!folio_test_isolated(folio), folio);
@@ -249,7 +249,7 @@ static bool remove_migration_pte(struct folio *folio,
pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
if (folio_test_anon(folio))
- hugepage_add_anon_rmap(new, vma, pvmw.address,
+ hugepage_add_anon_rmap(folio, vma, pvmw.address,
rmap_flags);
else
page_dup_file_rmap(new, true);
@@ -524,7 +524,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
int expected_count;
xas_lock_irq(&xas);
- expected_count = 2 + folio_has_private(src);
+ expected_count = folio_expected_refs(mapping, src);
if (!folio_ref_freeze(src, expected_count)) {
xas_unlock_irq(&xas);
return -EAGAIN;
@@ -533,11 +533,11 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
dst->index = src->index;
dst->mapping = src->mapping;
- folio_get(dst);
+ folio_ref_add(dst, folio_nr_pages(dst));
xas_store(&xas, dst);
- folio_ref_unfreeze(src, expected_count - 1);
+ folio_ref_unfreeze(src, expected_count - folio_nr_pages(src));
xas_unlock_irq(&xas);
@@ -588,20 +588,20 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *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);
+ 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(page_to_nid(&folio->page));
- bool t_toptier = node_is_toptier(page_to_nid(&newfolio->page));
+ 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;
}
- page_cpupid_xchg_last(&newfolio->page, cpupid);
+ folio_xchg_last_cpupid(newfolio, cpupid);
folio_migrate_ksm(newfolio, folio);
/*
@@ -633,8 +633,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
folio_copy_owner(newfolio, folio);
- if (!folio_test_hugetlb(folio))
- mem_cgroup_migrate(folio, newfolio);
+ mem_cgroup_migrate(folio, newfolio);
}
EXPORT_SYMBOL(folio_migrate_flags);
@@ -946,7 +945,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
enum migrate_mode mode)
{
int rc = -EAGAIN;
- bool is_lru = !__PageMovable(&src->page);
+ bool is_lru = !__folio_test_movable(src);
VM_BUG_ON_FOLIO(!folio_test_locked(src), src);
VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst);
@@ -993,7 +992,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
* src is freed; but stats require that PageAnon be left as PageAnon.
*/
if (rc == MIGRATEPAGE_SUCCESS) {
- if (__PageMovable(&src->page)) {
+ if (__folio_test_movable(src)) {
VM_BUG_ON_FOLIO(!folio_test_isolated(src), src);
/*
@@ -1028,22 +1027,28 @@ union migration_ptr {
struct anon_vma *anon_vma;
struct address_space *mapping;
};
+
+enum {
+ PAGE_WAS_MAPPED = BIT(0),
+ PAGE_WAS_MLOCKED = BIT(1),
+};
+
static void __migrate_folio_record(struct folio *dst,
- unsigned long page_was_mapped,
+ unsigned long old_page_state,
struct anon_vma *anon_vma)
{
union migration_ptr ptr = { .anon_vma = anon_vma };
dst->mapping = ptr.mapping;
- dst->private = (void *)page_was_mapped;
+ dst->private = (void *)old_page_state;
}
static void __migrate_folio_extract(struct folio *dst,
- int *page_was_mappedp,
+ int *old_page_state,
struct anon_vma **anon_vmap)
{
union migration_ptr ptr = { .mapping = dst->mapping };
*anon_vmap = ptr.anon_vma;
- *page_was_mappedp = (unsigned long)dst->private;
+ *old_page_state = (unsigned long)dst->private;
dst->mapping = NULL;
dst->private = NULL;
}
@@ -1085,7 +1090,7 @@ static void migrate_folio_done(struct folio *src,
/*
* Compaction can migrate also non-LRU pages which are
* not accounted to NR_ISOLATED_*. They can be recognized
- * as __PageMovable
+ * as __folio_test_movable
*/
if (likely(!__folio_test_movable(src)))
mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON +
@@ -1104,9 +1109,9 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
{
struct folio *dst;
int rc = -EAGAIN;
- int page_was_mapped = 0;
+ int old_page_state = 0;
struct anon_vma *anon_vma = NULL;
- bool is_lru = !__PageMovable(&src->page);
+ bool is_lru = !__folio_test_movable(src);
bool locked = false;
bool dst_locked = false;
@@ -1158,6 +1163,8 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
folio_lock(src);
}
locked = true;
+ if (folio_test_mlocked(src))
+ old_page_state |= PAGE_WAS_MLOCKED;
if (folio_test_writeback(src)) {
/*
@@ -1207,7 +1214,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
dst_locked = true;
if (unlikely(!is_lru)) {
- __migrate_folio_record(dst, page_was_mapped, anon_vma);
+ __migrate_folio_record(dst, old_page_state, anon_vma);
return MIGRATEPAGE_UNMAP;
}
@@ -1233,11 +1240,11 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
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);
- page_was_mapped = 1;
+ old_page_state |= PAGE_WAS_MAPPED;
}
if (!folio_mapped(src)) {
- __migrate_folio_record(dst, page_was_mapped, anon_vma);
+ __migrate_folio_record(dst, old_page_state, anon_vma);
return MIGRATEPAGE_UNMAP;
}
@@ -1249,7 +1256,8 @@ out:
if (rc == -EAGAIN)
ret = NULL;
- migrate_folio_undo_src(src, page_was_mapped, anon_vma, locked, ret);
+ 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;
@@ -1262,12 +1270,12 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
struct list_head *ret)
{
int rc;
- int page_was_mapped = 0;
+ int old_page_state = 0;
struct anon_vma *anon_vma = NULL;
- bool is_lru = !__PageMovable(&src->page);
+ bool is_lru = !__folio_test_movable(src);
struct list_head *prev;
- __migrate_folio_extract(dst, &page_was_mapped, &anon_vma);
+ __migrate_folio_extract(dst, &old_page_state, &anon_vma);
prev = dst->lru.prev;
list_del(&dst->lru);
@@ -1288,10 +1296,10 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
* isolated from the unevictable LRU: but this case is the easiest.
*/
folio_add_lru(dst);
- if (page_was_mapped)
+ if (old_page_state & PAGE_WAS_MLOCKED)
lru_add_drain();
- if (page_was_mapped)
+ if (old_page_state & PAGE_WAS_MAPPED)
remove_migration_ptes(src, dst, false);
out_unlock_both:
@@ -1323,11 +1331,12 @@ out:
*/
if (rc == -EAGAIN) {
list_add(&dst->lru, prev);
- __migrate_folio_record(dst, page_was_mapped, anon_vma);
+ __migrate_folio_record(dst, old_page_state, anon_vma);
return rc;
}
- migrate_folio_undo_src(src, page_was_mapped, anon_vma, true, ret);
+ 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;
@@ -1496,6 +1505,7 @@ struct migrate_pages_stats {
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 */
};
/*
@@ -1615,6 +1625,7 @@ static int migrate_pages_batch(struct list_head *from,
int nr_retry_pages = 0;
int pass = 0;
bool is_thp = false;
+ bool is_large = false;
struct folio *folio, *folio2, *dst = NULL, *dst2;
int rc, rc_saved = 0, nr_pages;
LIST_HEAD(unmap_folios);
@@ -1630,7 +1641,8 @@ static int migrate_pages_batch(struct list_head *from,
nr_retry_pages = 0;
list_for_each_entry_safe(folio, folio2, from, lru) {
- is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio);
+ is_large = folio_test_large(folio);
+ is_thp = is_large && folio_test_pmd_mappable(folio);
nr_pages = folio_nr_pages(folio);
cond_resched();
@@ -1650,6 +1662,7 @@ static int migrate_pages_batch(struct list_head *from,
stats->nr_thp_failed++;
if (!try_split_folio(folio, split_folios)) {
stats->nr_thp_split++;
+ stats->nr_split++;
continue;
}
stats->nr_failed_pages += nr_pages;
@@ -1678,11 +1691,12 @@ static int migrate_pages_batch(struct list_head *from,
nr_failed++;
stats->nr_thp_failed += is_thp;
/* Large folio NUMA faulting doesn't split to retry. */
- if (folio_test_large(folio) && !nosplit) {
+ if (is_large && !nosplit) {
int ret = try_split_folio(folio, split_folios);
if (!ret) {
stats->nr_thp_split += is_thp;
+ stats->nr_split++;
break;
} else if (reason == MR_LONGTERM_PIN &&
ret == -EAGAIN) {
@@ -1795,12 +1809,12 @@ out:
dst = list_first_entry(&dst_folios, struct folio, lru);
dst2 = list_next_entry(dst, lru);
list_for_each_entry_safe(folio, folio2, &unmap_folios, lru) {
- int page_was_mapped = 0;
+ int old_page_state = 0;
struct anon_vma *anon_vma = NULL;
- __migrate_folio_extract(dst, &page_was_mapped, &anon_vma);
- migrate_folio_undo_src(folio, page_was_mapped, anon_vma,
- true, ret_folios);
+ __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;
@@ -1828,6 +1842,7 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio,
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;
@@ -1835,7 +1850,11 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio,
return rc;
}
stats->nr_thp_failed += astats.nr_thp_split;
- nr_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;
/*
* Fall back to migrate all failed folios one by one synchronously. All
* failed folios except split THPs will be retried, so their failure
@@ -1970,7 +1989,8 @@ out:
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, mode, reason);
+ stats.nr_thp_split, stats.nr_split, mode,
+ reason);
if (ret_succeeded)
*ret_succeeded = stats.nr_succeeded;
@@ -2029,8 +2049,7 @@ 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 = {
@@ -2060,8 +2079,8 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p,
struct vm_area_struct *vma;
unsigned long addr;
struct page *page;
+ struct folio *folio;
int err;
- bool isolated;
mmap_read_lock(mm);
addr = (unsigned long)untagged_addr_remote(mm, p);
@@ -2082,51 +2101,44 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p,
if (!page)
goto out;
- if (is_zone_device_page(page))
- goto out_putpage;
+ folio = page_folio(page);
+ if (folio_is_zone_device(folio))
+ goto out_putfolio;
err = 0;
- if (page_to_nid(page) == node)
- goto out_putpage;
+ if (folio_nid(folio) == node)
+ goto out_putfolio;
err = -EACCES;
if (page_mapcount(page) > 1 && !migrate_all)
- goto out_putpage;
+ goto out_putfolio;
- if (PageHuge(page)) {
- if (PageHead(page)) {
- isolated = isolate_hugetlb(page_folio(page), pagelist);
- err = isolated ? 1 : -EBUSY;
- }
+ err = -EBUSY;
+ if (folio_test_hugetlb(folio)) {
+ if (isolate_hugetlb(folio, pagelist))
+ err = 1;
} else {
- struct page *head;
-
- head = compound_head(page);
- isolated = isolate_lru_page(head);
- if (!isolated) {
- err = -EBUSY;
- goto out_putpage;
- }
+ if (!folio_isolate_lru(folio))
+ goto out_putfolio;
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));
+ list_add_tail(&folio->lru, pagelist);
+ node_stat_mod_folio(folio,
+ NR_ISOLATED_ANON + folio_is_file_lru(folio),
+ folio_nr_pages(folio));
}
-out_putpage:
+out_putfolio:
/*
- * Either remove the duplicate refcount from
- * isolate_lru_page() or drop the page ref if it was
- * not isolated.
+ * Either remove the duplicate refcount from folio_isolate_lru()
+ * or drop the folio ref if it was not isolated.
*/
- put_page(page);
+ folio_put(folio);
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)
{
@@ -2135,7 +2147,7 @@ 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
@@ -2203,7 +2215,7 @@ 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;
@@ -2238,7 +2250,7 @@ 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) {
/* We have accounted for page i */
@@ -2250,7 +2262,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
}
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;
@@ -2491,16 +2503,9 @@ static struct folio *alloc_misplaced_dst_folio(struct folio *src,
return __folio_alloc_node(gfp, order, nid);
}
-static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
+static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
{
- int nr_pages = thp_nr_pages(page);
- int order = compound_order(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;
+ int nr_pages = folio_nr_pages(folio);
/* Avoid migrating to a node that is nearly full */
if (!migrate_balanced_pgdat(pgdat, nr_pages)) {
@@ -2512,75 +2517,79 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
if (managed_zone(pgdat->node_zones + z))
break;
}
- wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
+ wakeup_kswapd(pgdat->node_zones + z, 0,
+ folio_order(folio), ZONE_MOVABLE);
return 0;
}
- if (!isolate_lru_page(page))
+ if (!folio_isolate_lru(folio))
return 0;
- mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page),
+ node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio),
nr_pages);
/*
- * Isolating the page has taken another reference, so the
- * caller's reference can be safely dropped without the page
+ * Isolating the folio has taken another reference, so the
+ * caller's reference can be safely dropped without the folio
* disappearing underneath us during migration.
*/
- put_page(page);
+ folio_put(folio);
return 1;
}
/*
- * Attempt to migrate a misplaced page to the specified destination
+ * Attempt to migrate a misplaced folio 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.
+ * the folio that will be dropped by this function before returning.
*/
-int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
- int node)
+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 = thp_nr_pages(page);
+ int nr_pages = folio_nr_pages(folio);
/*
- * Don't migrate file pages that are mapped in multiple processes
+ * Don't migrate file folios that are mapped in multiple processes
* with execute permissions as they are probably shared libraries.
+ * To check if the folio is shared, ideally we want to make sure
+ * every page is mapped to the same process. Doing that is very
+ * expensive, so check the estimated mapcount of the folio instead.
*/
- if (page_mapcount(page) != 1 && page_is_file_lru(page) &&
+ if (folio_estimated_sharers(folio) != 1 && folio_is_file_lru(folio) &&
(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.
+ * 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 (page_is_file_lru(page) && PageDirty(page))
+ if (folio_is_file_lru(folio) && folio_test_dirty(folio))
goto out;
- isolated = numamigrate_isolate_page(pgdat, page);
+ isolated = numamigrate_isolate_folio(pgdat, folio);
if (!isolated)
goto out;
- list_add(&page->lru, &migratepages);
+ 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(&page->lru);
- mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
- page_is_file_lru(page), -nr_pages);
- putback_lru_page(page);
+ 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_succeeded) {
count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
- if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node))
+ if (!node_is_toptier(folio_nid(folio)) && node_is_toptier(node))
mod_node_page_state(pgdat, PGPROMOTE_SUCCESS,
nr_succeeded);
}
@@ -2588,7 +2597,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
return isolated;
out:
- put_page(page);
+ folio_put(folio);
return 0;
}
#endif /* CONFIG_NUMA_BALANCING */
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-11-23 02:54:24 +0000