@@ -341,8 +341,8 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
vm_flags_t vm_flags);
bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins);
-int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
- unsigned int new_order);
+int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order, bool isolated);
int min_order_for_split(struct folio *folio);
int split_folio_to_list(struct folio *folio, struct list_head *list);
bool uniform_split_supported(struct folio *folio, unsigned int new_order,
@@ -351,6 +351,13 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order,
bool warns);
int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
struct list_head *list);
+
+static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order)
+{
+ return __split_huge_page_to_list_to_order(page, list, new_order, false);
+}
+
/*
* try_folio_split - try to split a @folio at @page using non uniform split.
* @folio: folio to be split
@@ -3544,7 +3544,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
struct page *split_at, struct page *lock_at,
struct list_head *list, pgoff_t end,
struct xa_state *xas, struct address_space *mapping,
- bool uniform_split)
+ bool uniform_split, bool isolated)
{
struct lruvec *lruvec;
struct address_space *swap_cache = NULL;
@@ -3586,6 +3586,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
int old_order = folio_order(folio);
struct folio *release;
struct folio *end_folio = folio_next(folio);
+ int extra_count = 1;
/* order-1 anonymous folio is not supported */
if (folio_test_anon(folio) && split_order == 1)
@@ -3629,6 +3630,14 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
__split_folio_to_order(folio, old_order, split_order);
after_split:
+ /*
+ * When a folio is isolated, the split folios will
+ * not go through unmap/remap, so add the extra
+ * count here
+ */
+ if (isolated)
+ extra_count++;
+
/*
* Iterate through after-split folios and perform related
* operations. But in buddy allocator like split, the folio
@@ -3665,7 +3674,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
* page cache.
*/
folio_ref_unfreeze(release,
- 1 + ((!folio_test_anon(origin_folio) ||
+ extra_count + ((!folio_test_anon(origin_folio) ||
folio_test_swapcache(origin_folio)) ?
folio_nr_pages(release) : 0));
@@ -3676,7 +3685,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
if (release == origin_folio)
continue;
- if (!folio_is_device_private(origin_folio))
+ if (!isolated && !folio_is_device_private(origin_folio))
lru_add_page_tail(origin_folio, &release->page,
lruvec, list);
@@ -3714,6 +3723,12 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
if (nr_dropped)
shmem_uncharge(mapping->host, nr_dropped);
+ /*
+ * Don't remap and unlock isolated folios
+ */
+ if (isolated)
+ return ret;
+
remap_page(origin_folio, 1 << order,
folio_test_anon(origin_folio) ?
RMP_USE_SHARED_ZEROPAGE : 0);
@@ -3808,6 +3823,7 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order,
* @lock_at: a page within @folio to be left locked to caller
* @list: after-split folios will be put on it if non NULL
* @uniform_split: perform uniform split or not (non-uniform split)
+ * @isolated: The pages are already unmapped
*
* It calls __split_unmapped_folio() to perform uniform and non-uniform split.
* It is in charge of checking whether the split is supported or not and
@@ -3818,7 +3834,7 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order,
*/
static int __folio_split(struct folio *folio, unsigned int new_order,
struct page *split_at, struct page *lock_at,
- struct list_head *list, bool uniform_split)
+ struct list_head *list, bool uniform_split, bool isolated)
{
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
XA_STATE(xas, &folio->mapping->i_pages, folio->index);
@@ -3864,14 +3880,16 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
* is taken to serialise against parallel split or collapse
* operations.
*/
- anon_vma = folio_get_anon_vma(folio);
- if (!anon_vma) {
- ret = -EBUSY;
- goto out;
+ if (!isolated) {
+ anon_vma = folio_get_anon_vma(folio);
+ if (!anon_vma) {
+ ret = -EBUSY;
+ goto out;
+ }
+ anon_vma_lock_write(anon_vma);
}
end = -1;
mapping = NULL;
- anon_vma_lock_write(anon_vma);
} else {
unsigned int min_order;
gfp_t gfp;
@@ -3933,7 +3951,8 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
goto out_unlock;
}
- unmap_folio(folio);
+ if (!isolated)
+ unmap_folio(folio);
/* block interrupt reentry in xa_lock and spinlock */
local_irq_disable();
@@ -3986,14 +4005,15 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
ret = __split_unmapped_folio(folio, new_order,
split_at, lock_at, list, end, &xas, mapping,
- uniform_split);
+ uniform_split, isolated);
} else {
spin_unlock(&ds_queue->split_queue_lock);
fail:
if (mapping)
xas_unlock(&xas);
local_irq_enable();
- remap_page(folio, folio_nr_pages(folio), 0);
+ if (!isolated)
+ remap_page(folio, folio_nr_pages(folio), 0);
ret = -EAGAIN;
}
@@ -4059,12 +4079,13 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
* Returns -EINVAL when trying to split to an order that is incompatible
* with the folio. Splitting to order 0 is compatible with all folios.
*/
-int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
- unsigned int new_order)
+int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+ unsigned int new_order, bool isolated)
{
struct folio *folio = page_folio(page);
- return __folio_split(folio, new_order, &folio->page, page, list, true);
+ return __folio_split(folio, new_order, &folio->page, page, list, true,
+ isolated);
}
/*
@@ -4093,7 +4114,7 @@ int folio_split(struct folio *folio, unsigned int new_order,
struct page *split_at, struct list_head *list)
{
return __folio_split(folio, new_order, split_at, &folio->page, list,
- false);
+ false, false);
}
int min_order_for_split(struct folio *folio)
@@ -804,6 +804,24 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
src[i] &= ~MIGRATE_PFN_MIGRATE;
return 0;
}
+
+static void migrate_vma_split_pages(struct migrate_vma *migrate,
+ unsigned long idx, unsigned long addr,
+ struct folio *folio)
+{
+ unsigned long i;
+ unsigned long pfn;
+ unsigned long flags;
+
+ folio_get(folio);
+ split_huge_pmd_address(migrate->vma, addr, true, folio);
+ __split_huge_page_to_list_to_order(folio_page(folio, 0), NULL, 0, true);
+ migrate->src[idx] &= ~MIGRATE_PFN_COMPOUND;
+ flags = migrate->src[idx] & ((1UL << MIGRATE_PFN_SHIFT) - 1);
+ pfn = migrate->src[idx] >> MIGRATE_PFN_SHIFT;
+ for (i = 1; i < HPAGE_PMD_NR; i++)
+ migrate->src[i+idx] = migrate_pfn(pfn + i) | flags;
+}
#else /* !CONFIG_ARCH_ENABLE_THP_MIGRATION */
static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
unsigned long addr,
@@ -813,6 +831,11 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate,
{
return 0;
}
+
+static void migrate_vma_split_pages(struct migrate_vma *migrate,
+ unsigned long idx, unsigned long addr,
+ struct folio *folio)
+{}
#endif
/*
@@ -962,8 +985,9 @@ static void __migrate_device_pages(unsigned long *src_pfns,
struct migrate_vma *migrate)
{
struct mmu_notifier_range range;
- unsigned long i;
+ unsigned long i, j;
bool notified = false;
+ unsigned long addr;
for (i = 0; i < npages; ) {
struct page *newpage = migrate_pfn_to_page(dst_pfns[i]);
@@ -1005,12 +1029,16 @@ static void __migrate_device_pages(unsigned long *src_pfns,
(!(dst_pfns[i] & MIGRATE_PFN_COMPOUND))) {
nr = HPAGE_PMD_NR;
src_pfns[i] &= ~MIGRATE_PFN_COMPOUND;
- src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
- goto next;
+ } else {
+ nr = 1;
}
- migrate_vma_insert_page(migrate, addr, &dst_pfns[i],
- &src_pfns[i]);
+ for (j = 0; j < nr && i + j < npages; j++) {
+ src_pfns[i+j] |= MIGRATE_PFN_MIGRATE;
+ migrate_vma_insert_page(migrate,
+ addr + j * PAGE_SIZE,
+ &dst_pfns[i+j], &src_pfns[i+j]);
+ }
goto next;
}
@@ -1032,7 +1060,10 @@ static void __migrate_device_pages(unsigned long *src_pfns,
MIGRATE_PFN_COMPOUND);
goto next;
}
- src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
+ nr = 1 << folio_order(folio);
+ addr = migrate->start + i * PAGE_SIZE;
+ migrate_vma_split_pages(migrate, i, addr, folio);
+ extra_cnt++;
} else if ((src_pfns[i] & MIGRATE_PFN_MIGRATE) &&
(dst_pfns[i] & MIGRATE_PFN_COMPOUND) &&
!(src_pfns[i] & MIGRATE_PFN_COMPOUND)) {
@@ -1067,12 +1098,17 @@ static void __migrate_device_pages(unsigned long *src_pfns,
BUG_ON(folio_test_writeback(folio));
if (migrate && migrate->fault_page == page)
- extra_cnt = 1;
- r = folio_migrate_mapping(mapping, newfolio, folio, extra_cnt);
- if (r != MIGRATEPAGE_SUCCESS)
- src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
- else
- folio_migrate_flags(newfolio, folio);
+ extra_cnt++;
+ for (j = 0; j < nr && i + j < npages; j++) {
+ folio = page_folio(migrate_pfn_to_page(src_pfns[i+j]));
+ newfolio = page_folio(migrate_pfn_to_page(dst_pfns[i+j]));
+
+ r = folio_migrate_mapping(mapping, newfolio, folio, extra_cnt);
+ if (r != MIGRATEPAGE_SUCCESS)
+ src_pfns[i+j] &= ~MIGRATE_PFN_MIGRATE;
+ else
+ folio_migrate_flags(newfolio, folio);
+ }
next:
i += nr;
}
Support splitting pages during THP zone device migration as needed. The common case that arises is that after setup, during migrate the destination might not be able to allocate MIGRATE_PFN_COMPOUND pages. Add a new routine migrate_vma_split_pages() to support the splitting of already isolated pages. The pages being migrated are already unmapped and marked for migration during setup (via unmap). folio_split() and __split_unmapped_folio() take additional isolated arguments, to avoid unmapping and remaping these pages and unlocking/putting the folio. Since unmap/remap is avoided in these code paths, an extra reference count is added to the split folio pages, which will be dropped in the finalize phase. Signed-off-by: Balbir Singh <balbirs@nvidia.com> --- include/linux/huge_mm.h | 11 ++++++-- mm/huge_memory.c | 53 +++++++++++++++++++++++++----------- mm/migrate_device.c | 60 ++++++++++++++++++++++++++++++++--------- 3 files changed, 94 insertions(+), 30 deletions(-)