#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>
#include <linux/memory.h>
#include <linux/random.h>
#include <linux/sched/sysctl.h>
+#include <linux/memory-tiers.h>
#include <asm/tlbflush.h>
#include "internal.h"
-int isolate_movable_page(struct page *page, isolate_mode_t mode)
+bool isolate_movable_page(struct page *page, isolate_mode_t mode)
{
+ struct folio *folio = folio_get_nontail_page(page);
const struct movable_operations *mops;
/*
* 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;
+ if (unlikely(folio_test_slab(folio)))
+ goto out_putfolio;
+ /* Pairs with smp_wmb() in slab freeing, e.g. SLUB's __free_slab() */
+ smp_rmb();
/*
- * 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 movable flag 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.
*/
- if (unlikely(!__PageMovable(page)))
- goto out_putpage;
+ if (unlikely(!__folio_test_movable(folio)))
+ goto out_putfolio;
+ /* Pairs with smp_wmb() in slab allocation, e.g. SLUB's alloc_slab_page() */
+ smp_rmb();
+ if (unlikely(folio_test_slab(folio)))
+ goto out_putfolio;
+
/*
* As movable pages are not isolated from LRU lists, concurrent
* compaction threads can race against page migration functions
* 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))
+ if (!folio_test_movable(folio) || folio_test_isolated(folio))
goto out_no_isolated;
- mops = page_movable_ops(page);
- VM_BUG_ON_PAGE(!mops, page);
+ mops = folio_movable_ops(folio);
+ VM_BUG_ON_FOLIO(!mops, folio);
- if (!mops->isolate_page(page, mode))
+ if (!mops->isolate_page(&folio->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);
+ WARN_ON_ONCE(folio_test_isolated(folio));
+ folio_set_isolated(folio);
+ 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)
+static void putback_movable_folio(struct folio *folio)
{
- const struct movable_operations *mops = page_movable_ops(page);
+ const struct movable_operations *mops = folio_movable_ops(folio);
- mops->putback_page(page);
- ClearPageIsolated(page);
+ mops->putback_page(&folio->page);
+ folio_clear_isolated(folio);
}
/*
*/
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_active_hugetlb(folio);
continue;
}
- list_del(&page->lru);
+ list_del(&folio->lru);
/*
- * We isolated non-lru movable page so here we can use
- * __PageMovable because LRU page's mapping cannot have
- * PAGE_MAPPING_MOVABLE.
+ * We isolated non-lru movable folio so here we can use
+ * __folio_test_movable because LRU folio'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);
+ if (unlikely(__folio_test_movable(folio))) {
+ VM_BUG_ON_FOLIO(!folio_test_isolated(folio), folio);
+ folio_lock(folio);
+ if (folio_test_movable(folio))
+ putback_movable_folio(folio);
else
- ClearPageIsolated(page);
- unlock_page(page);
- put_page(page);
+ folio_clear_isolated(folio);
+ folio_unlock(folio);
+ folio_put(folio);
} 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);
}
}
}
while (page_vma_mapped_walk(&pvmw)) {
rmap_t rmap_flags = RMAP_NONE;
+ pte_t old_pte;
pte_t pte;
swp_entry_t entry;
struct page *new;
#endif
folio_get(folio);
- pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
- if (pte_swp_soft_dirty(*pvmw.pte))
+ pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
+ old_pte = ptep_get(pvmw.pte);
+
+ entry = pte_to_swp_entry(old_pte);
+ if (!is_migration_entry_young(entry))
+ pte = pte_mkold(pte);
+ if (folio_test_dirty(folio) && is_migration_entry_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))
+ pte = pte_mkwrite(pte, vma);
+ else if (pte_swp_uffd_wp(old_pte))
pte = pte_mkuffd_wp(pte);
if (folio_test_anon(folio) && !is_readable_migration_entry(entry))
entry = make_readable_device_private_entry(
page_to_pfn(new));
pte = swp_entry_to_pte(entry);
- if (pte_swp_soft_dirty(*pvmw.pte))
+ 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 (folio_test_hugetlb(folio)) {
- unsigned int shift = huge_page_shift(hstate_vma(vma));
+ 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 (folio_test_anon(folio))
- hugepage_add_anon_rmap(new, vma, pvmw.address,
- rmap_flags);
+ hugetlb_add_anon_rmap(folio, vma, pvmw.address,
+ rmap_flags);
else
- page_dup_file_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 (folio_test_anon(folio))
- page_add_anon_rmap(new, vma, pvmw.address,
- rmap_flags);
+ folio_add_anon_rmap_pte(folio, new, vma,
+ pvmw.address, rmap_flags);
else
- page_add_file_rmap(new, vma, 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)
- mlock_page_drain_local();
+ mlock_drain_local();
trace_remove_migration_pte(pvmw.address, pte_val(pte),
compound_order(new));
* 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;
- spin_lock(ptl);
- pte = *ptep;
+ ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (!ptep)
+ return;
+
+ pte = ptep_get(ptep);
+ pte_unmap(ptep);
+
if (!is_swap_pte(pte))
goto out;
if (!is_migration_entry(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);
-}
-
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
- unsigned long address)
-{
- spinlock_t *ptl = pte_lockptr(mm, pmd);
- pte_t *ptep = pte_offset_map(pmd, address);
- __migration_entry_wait(mm, ptep, ptl);
+ spin_unlock(ptl);
}
#ifdef CONFIG_HUGETLB_PAGE
-void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl)
+/*
+ * 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, 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);
- if (unlikely(!is_hugetlb_entry_migration(pte)))
+ if (unlikely(!is_hugetlb_entry_migration(pte))) {
spin_unlock(ptl);
- else
- migration_entry_wait_on_locked(pte_to_swp_entry(pte), NULL, ptl);
-}
-
-void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte)
-{
- spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, pte);
-
- __migration_entry_wait_huge(pte, ptl);
+ hugetlb_vma_unlock_read(vma);
+ } else {
+ /*
+ * 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(pte_to_swp_entry(pte), ptl);
+ }
}
#endif
ptl = pmd_lock(mm, pmd);
if (!is_pmd_migration_entry(*pmd))
goto unlock;
- migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), NULL, ptl);
+ migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), ptl);
return;
unlock:
spin_unlock(ptl);
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 */
folio_set_swapcache(newfolio);
newfolio->private = folio_get_private(folio);
}
+ entries = nr;
} else {
VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
+ entries = 1;
}
/* Move dirty while page refs frozen and newpage not yet exposed */
folio_set_dirty(newfolio);
}
- xas_store(&xas, newfolio);
+ /* Swap cache still stores N entries instead of a high-order entry */
+ for (i = 0; i < entries; i++) {
+ xas_store(&xas, newfolio);
+ xas_next(&xas);
+ }
/*
* Drop cache reference from old page by unfreezing
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);
+
+ 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)) {
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;
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);
* 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);
/*
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);
* Migration functions
***********************************************************/
+int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
+ struct folio *src, enum migrate_mode mode, int extra_count)
+{
+ int rc;
+
+ BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */
+
+ rc = folio_migrate_mapping(mapping, dst, src, extra_count);
+
+ if (rc != MIGRATEPAGE_SUCCESS)
+ return rc;
+
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ folio_migrate_copy(dst, src);
+ else
+ folio_migrate_flags(dst, src);
+ return MIGRATEPAGE_SUCCESS;
+}
+
/**
* migrate_folio() - Simple folio migration.
* @mapping: The address_space containing the folio.
int migrate_folio(struct address_space *mapping, struct folio *dst,
struct folio *src, enum migrate_mode mode)
{
- int rc;
-
- BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */
-
- rc = folio_migrate_mapping(mapping, dst, src, 0);
-
- if (rc != MIGRATEPAGE_SUCCESS)
- return rc;
-
- if (mode != MIGRATE_SYNC_NO_COPY)
- folio_migrate_copy(dst, src);
- else
- folio_migrate_flags(dst, src);
- return MIGRATEPAGE_SUCCESS;
+ return migrate_folio_extra(mapping, dst, src, mode, 0);
}
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_folio(struct address_space *mapping,
recheck_buffers:
busy = false;
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
bh = head;
do {
if (atomic_read(&bh->b_count)) {
rc = -EAGAIN;
goto unlock_buffers;
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
bh = head;
do {
- set_bh_page(bh, &dst->page, bh_offset(bh));
+ folio_set_bh(bh, dst, bh_offset(bh));
bh = bh->b_this_page;
} while (bh != head);
rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
if (check_refs)
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
bh = head;
do {
unlock_buffer(bh);
{
return __buffer_migrate_folio(mapping, dst, src, mode, true);
}
-#endif
+EXPORT_SYMBOL_GPL(buffer_migrate_folio_norefs);
+#endif /* CONFIG_BUFFER_HEAD */
int filemap_migrate_folio(struct address_space *mapping,
struct folio *dst, struct folio *src, enum migrate_mode mode)
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
- if (folio_test_private(src) &&
- !filemap_release_folio(src, GFP_KERNEL))
+ if (!filemap_release_folio(src, GFP_KERNEL))
return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY;
return migrate_folio(mapping, dst, src, mode);
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);
if (!mapping)
rc = migrate_folio(mapping, dst, src, mode);
+ else if (mapping_unmovable(mapping))
+ rc = -EOPNOTSUPP;
else if (mapping->a_ops->migrate_folio)
/*
* Most folios have a mapping and most filesystems
goto out;
}
- mops = page_movable_ops(&src->page);
+ mops = folio_movable_ops(src);
rc = mops->migrate_page(&dst->page, &src->page, mode);
WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
!folio_test_isolated(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);
/*
return rc;
}
-static int __unmap_and_move(struct page *page, struct page *newpage,
- int force, enum migrate_mode mode)
+/*
+ * 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,
+};
+
+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;
+}
+
+static void __migrate_folio_extract(struct folio *dst,
+ int *old_page_state,
+ struct anon_vma **anon_vmap)
+{
+ unsigned long private = (unsigned long)dst->private;
+
+ *anon_vmap = (struct anon_vma *)(private & ~PAGE_OLD_STATES);
+ *old_page_state = private & PAGE_OLD_STATES;
+ dst->private = NULL;
+}
+
+/* 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, false);
+ /* 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)
+{
+ /*
+ * Compaction can migrate also non-LRU pages which are
+ * not accounted to NR_ISOLATED_*. They can be recognized
+ * as __folio_test_movable
+ */
+ if (likely(!__folio_test_movable(src)))
+ 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);
+}
+
+/* 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,
+ enum migrate_reason reason, struct list_head *ret)
{
- struct folio *folio = page_folio(page);
- struct folio *dst = page_folio(newpage);
+ 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 is_lru = !__folio_test_movable(src);
+ bool locked = false;
+ bool dst_locked = false;
+
+ if (folio_ref_count(src) == 1) {
+ /* Folio was freed from under us. So we are done. */
+ folio_clear_active(src);
+ folio_clear_unevictable(src);
+ /* free_pages_prepare() will clear PG_isolated. */
+ list_del(&src->lru);
+ migrate_folio_done(src, reason);
+ return MIGRATEPAGE_SUCCESS;
+ }
- if (!trylock_page(page)) {
- if (!force || mode == MIGRATE_ASYNC)
+ dst = get_new_folio(src, private);
+ if (!dst)
+ return -ENOMEM;
+ *dstp = dst;
+
+ dst->private = NULL;
+
+ if (!folio_trylock(src)) {
+ if (mode == MIGRATE_ASYNC)
goto out;
/*
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,
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_folio(dst, folio, mode);
- goto out_unlock_both;
+ __migrate_folio_record(dst, old_page_state, anon_vma);
+ return MIGRATEPAGE_UNMAP;
}
/*
* 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
* 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(folio);
- 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(folio, 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_folio(dst, folio, 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 (!folio_mapped(src)) {
+ __migrate_folio_record(dst, old_page_state, anon_vma);
+ return MIGRATEPAGE_UNMAP;
}
- if (page_was_mapped)
- remove_migration_ptes(folio,
- rc == MIGRATEPAGE_SUCCESS ? dst : folio, false);
-
-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.
+ * A folio that has not been unmapped will be restored to
+ * right list unless we want to retry.
*/
- if (rc == MIGRATEPAGE_SUCCESS)
- put_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;
+ bool is_lru = !__folio_test_movable(src);
+ 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);
- /* free_pages_prepare() will clear PG_isolated. */
+ rc = move_to_new_folio(dst, src, mode);
+ if (rc)
goto out;
- }
- newpage = get_new_page(page, private);
- if (!newpage)
- return -ENOMEM;
+ if (unlikely(!is_lru))
+ goto out_unlock_both;
- newpage->private = 0;
- 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, false);
+out_unlock_both:
+ folio_unlock(dst);
+ set_page_owner_migrate_reason(&dst->page, 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;
}
* 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, *src = page_folio(hpage);
+ 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);
+ folio_putback_active_hugetlb(src);
return MIGRATEPAGE_SUCCESS;
}
- new_hpage = get_new_page(hpage, private);
- if (!new_hpage)
+ dst = get_new_folio(src, private);
+ if (!dst)
return -ENOMEM;
- dst = page_folio(new_hpage);
- if (!trylock_page(hpage)) {
+ if (!folio_trylock(src)) {
if (!force)
goto out;
switch (mode) {
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)) {
+ 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_page_mapping_lock_write(&src->page);
if (unlikely(!mapping))
goto unlock_put_anon;
i_mmap_unlock_write(mapping);
}
- if (!page_mapped(hpage))
+ if (!folio_mapped(src))
rc = move_to_new_folio(dst, src, mode);
if (page_was_mapped)
rc == MIGRATEPAGE_SUCCESS ? dst : src, false);
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;
+ 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);
+ folio_putback_active_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 (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_putback_active_hugetlb(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)
{
- int rc = 0;
+ int rc;
- lock_page(page);
- rc = split_huge_page_to_list(page, from);
- unlock_page(page);
+ 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 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);
-
-thp_subpage_migration:
- for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
+ for (pass = 0; pass < NR_MAX_MIGRATE_PAGES_RETRY && retry; pass++) {
retry = 0;
- thp_retry = 0;
+ nr_retry_pages = 0;
+
+ list_for_each_entry_safe(folio, folio2, from, lru) {
+ if (!folio_test_hugetlb(folio))
+ continue;
+
+ 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
+ * Success: 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) {
- /*
- * 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.
- *
- * 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.
- */
- 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;
- }
- /* Hugetlb migration is unsupported */
- } else if (!no_subpage_counting) {
- nr_failed++;
- }
-
- nr_failed_pages += nr_subpages;
- break;
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.
- */
- if (is_thp && !nosplit) {
- nr_thp_failed++;
- if (!try_split_thp(page, &page2, &thp_split_pages)) {
- nr_thp_split++;
- goto retry;
- }
- } else if (!no_subpage_counting) {
- nr_failed++;
- }
-
- nr_failed_pages += nr_subpages;
- /*
- * There might be some subpages of fail-to-migrate THPs
- * left in thp_split_pages list. Move them back to migration
- * list so that they could be put back to the right list by
- * the caller otherwise the page refcnt will be leaked.
+ * other folios, just exit.
*/
- list_splice_init(&thp_split_pages, from);
- nr_thp_failed += thp_retry;
- goto out;
+ stats->nr_failed_pages += nr_pages + nr_retry_pages;
+ return -ENOMEM;
case -EAGAIN:
- if (is_thp)
- thp_retry++;
- else
- retry++;
+ retry++;
+ nr_retry_pages += nr_pages;
break;
case MIGRATEPAGE_SUCCESS:
- nr_succeeded += nr_subpages;
- if (is_thp)
- nr_thp_succeeded++;
+ stats->nr_succeeded += nr_pages;
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++;
- else if (!no_subpage_counting)
- nr_failed++;
-
- nr_failed_pages += nr_subpages;
+ nr_failed++;
+ stats->nr_failed_pages += nr_pages;
break;
}
}
}
- nr_failed += retry;
- nr_thp_failed += thp_retry;
/*
- * 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.
+ * 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.
*/
- if (!list_empty(&thp_split_pages)) {
- /*
- * Move non-migrated pages (after 10 retries) to ret_pages
- * to avoid migrating them again.
- */
- list_splice_init(from, &ret_pages);
- list_splice_init(&thp_split_pages, from);
- no_subpage_counting = true;
- retry = 1;
- goto thp_subpage_migration;
- }
+ nr_failed += retry;
+ stats->nr_failed_pages += nr_retry_pages;
- rc = nr_failed + nr_thp_failed;
-out:
- /*
- * Put the permanent failure page back to migration list, they
+ return nr_failed;
+}
+
+/*
+ * 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, *dst2;
+ 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 = is_large && folio_test_pmd_mappable(folio);
+ nr_pages = folio_nr_pages(folio);
+
+ cond_resched();
+
+ /*
+ * 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)) {
+ stats->nr_thp_split++;
+ stats->nr_split++;
+ continue;
+ }
+ stats->nr_failed_pages += nr_pages;
+ list_move_tail(&folio->lru, ret_folios);
+ continue;
+ }
+
+ rc = migrate_folio_unmap(get_new_folio, put_new_folio,
+ private, folio, &dst, mode, reason,
+ ret_folios);
+ /*
+ * The rules are:
+ * Success: folio will be freed
+ * Unmap: 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 folios, move unmapped folios, then exit.
+ */
+ 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);
+
+ 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;
+ }
+ }
+
+ 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:
+ retry++;
+ thp_retry += is_thp;
+ nr_retry_pages += nr_pages;
+ break;
+ case MIGRATEPAGE_SUCCESS:
+ stats->nr_succeeded += nr_pages;
+ stats->nr_thp_succeeded += is_thp;
+ break;
+ case MIGRATEPAGE_UNMAP:
+ 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 folio is
+ * removed from migration folio list and not
+ * retried in the next outer loop.
+ */
+ nr_failed++;
+ stats->nr_thp_failed += is_thp;
+ stats->nr_failed_pages += nr_pages;
+ break;
+ }
+ }
+ }
+ nr_failed += 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;
+
+ 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) {
+ 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:
+ * Success: folio will be freed
+ * -EAGAIN: stay on the unmap_folios list
+ * Other errno: put on ret_folios list
+ */
+ switch(rc) {
+ case -EAGAIN:
+ retry++;
+ thp_retry += is_thp;
+ nr_retry_pages += nr_pages;
+ break;
+ case MIGRATEPAGE_SUCCESS:
+ stats->nr_succeeded += nr_pages;
+ stats->nr_thp_succeeded += is_thp;
+ break;
+ default:
+ nr_failed++;
+ stats->nr_thp_failed += is_thp;
+ stats->nr_failed_pages += nr_pages;
+ break;
+ }
+ dst = dst2;
+ dst2 = list_next_entry(dst, lru);
+ }
+ }
+ 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 */
+ 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 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);
+ }
+
+ 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;
+ /*
+ * 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
+ */
+ 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)) {
+ /*
+ * 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.
+ */
+ 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_gather += rc;
+ if (!list_empty(from))
+ goto again;
+out:
+ /*
+ * 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);
+ list_splice(&ret_folios, 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);
+ /*
+ * 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 folio *folio = page_folio(page);
struct migration_target_control *mtc;
gfp_t gfp_mask;
unsigned int order = 0;
- struct folio *new_folio = NULL;
int nid;
int zidx;
gfp_mask = mtc->gfp_mask;
nid = mtc->nid;
if (nid == NUMA_NO_NODE)
- nid = folio_nid(folio);
+ nid = folio_nid(src);
- if (folio_test_hugetlb(folio)) {
- struct hstate *h = page_hstate(&folio->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);
}
- if (folio_test_large(folio)) {
+ 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 = folio_order(folio);
+ order = folio_order(src);
}
- zidx = zone_idx(folio_zone(folio));
+ zidx = zone_idx(folio_zone(src));
if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
gfp_mask |= __GFP_HIGHMEM;
- new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask);
-
- return &new_folio->page;
+ return __folio_alloc(gfp_mask, order, nid, mtc->nmask);
}
#ifdef CONFIG_NUMA
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 = {
* target node
* 1 - when it has been queued
*/
-static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
+static int add_page_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 *folio;
int err;
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;
err = -ENOENT;
- if (!page || is_zone_device_page(page))
+ if (!page)
goto out;
+ 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)) {
- err = isolate_hugetlb(page, pagelist);
- if (!err)
- err = 1;
- }
+ err = -EBUSY;
+ if (folio_test_hugetlb(folio)) {
+ if (isolate_hugetlb(folio, pagelist))
+ err = 1;
} else {
- struct page *head;
-
- head = compound_head(page);
- err = isolate_lru_page(head);
- if (err)
- 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)
{
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
* well.
*/
if (err > 0)
- err += nr_pages - i - 1;
+ err += nr_pages - i;
return err;
}
return store_status(status, start, node, i - start);
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;
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)
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;
* 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_page_for_migration(mm, p, current_node, &pagelist,
+ flags & MPOL_MF_MOVE_ALL);
if (err > 0) {
/* The page is successfully queued for migration */
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;
if (IS_ERR(page))
goto set_status;
- if (page && !is_zone_device_page(page)) {
+ err = -ENOENT;
+ if (!page)
+ goto set_status;
+
+ if (!is_zone_device_page(page))
err = page_to_nid(page);
- put_page(page);
- } else {
- err = -ENOENT;
- }
+
+ put_page(page);
set_status:
*status = err;
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;
- int order = compound_order(page);
+ int order = folio_order(src);
gfp_t gfp = __GFP_THISNODE;
- struct folio *new;
if (order > 0)
gfp |= GFP_TRANSHUGE_LIGHT;
__GFP_NOWARN;
gfp &= ~__GFP_RECLAIM;
}
- new = __folio_alloc_node(gfp, order, nid);
-
- return &new->page;
+ 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)) {
if (managed_zone(pgdat->node_zones + z))
break;
}
- wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE);
+
+ /*
+ * If there are no managed zones, it should not proceed
+ * further.
+ */
+ if (z < 0)
+ return 0;
+
+ 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);
- nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
+ 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);
}
return isolated;
out:
- put_page(page);
+ folio_put(folio);
return 0;
}
#endif /* CONFIG_NUMA_BALANCING */
-
-/*
- * 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.
- */
- index = get_random_int() % target_nr;
- break;
- }
-
- target = READ_ONCE(nd->nodes[index]);
-
-out:
- rcu_read_unlock();
- return target;
-}
-
-/* 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)
- goto out_clear;
- }
-
- index = nd->nr;
- if (WARN_ONCE(index >= DEMOTION_TARGET_NODES,
- "Exceeds maximum demotion target nodes\n"))
- goto out_clear;
-
- nd->nodes[index] = migration_target;
- nd->nr++;
-
- return migration_target;
-out_clear:
- node_clear(migration_target, *used);
- return NUMA_NO_NODE;
-}
-
-/*
- * 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;
- nodemask_t this_pass;
- 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);
-
- /*
- * 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);
- }
- /*
- * '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.
- */
-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().
- */
-#ifdef CONFIG_MEMORY_HOTPLUG
-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;
- }
-
- return notifier_from_errno(0);
-}
-#endif
-
-void __init migrate_on_reclaim_init(void)
-{
- node_demotion = kcalloc(nr_node_ids,
- sizeof(struct demotion_nodes),
- GFP_KERNEL);
- WARN_ON(!node_demotion);
-#ifdef CONFIG_MEMORY_HOTPLUG
- hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
-#endif
- /*
- * 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.
- */
- cpus_read_lock();
- set_migration_target_nodes();
- cpus_read_unlock();
-}
-
-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)
-{
- ssize_t ret;
-
- ret = kstrtobool(buf, &numa_demotion_enabled);
- if (ret)
- return ret;
-
- 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;
- }
- return 0;
-
-delete_obj:
- kobject_put(numa_kobj);
- return err;
-}
-subsys_initcall(numa_init_sysfs);
-#endif /* CONFIG_SYSFS */
#endif /* CONFIG_NUMA */