mm: enable thp migration for shmem thp

My testing for the latest kernel supporting thp migration showed an
infinite loop in offlining the memory block that is filled with shmem
thps.  We can get out of the loop with a signal, but kernel should return
with failure in this case.

What happens in the loop is that scan_movable_pages() repeats returning
the same pfn without any progress.  That's because page migration always
fails for shmem thps.

In memory offline code, memory blocks containing unmovable pages should be
prevented from being offline targets by has_unmovable_pages() inside
start_isolate_page_range().  So it's possible to change migratability for
non-anonymous thps to avoid the issue, but it introduces more complex and
thp-specific handling in migration code, so it might not good.

So this patch is suggesting to fix the issue by enabling thp migration for
shmem thp.  Both of anon/shmem thp are migratable so we don't need
precheck about the type of thps.

Link: http://lkml.kernel.org/r/20180406030706.GA2434@hori1.linux.bs1.fc.nec.co.jp
Fixes: commit 72b39cfc4d75 ("mm, memory_hotplug: do not fail offlining too early")
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Zi Yan <zi.yan@sent.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 14ed6ee..a3a1815 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2925,7 +2925,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
                pmde = maybe_pmd_mkwrite(pmde, vma);
 
        flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
-       page_add_anon_rmap(new, vma, mmun_start, true);
+       if (PageAnon(new))
+               page_add_anon_rmap(new, vma, mmun_start, true);
+       else
+               page_add_file_rmap(new, true);
        set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
        if (vma->vm_flags & VM_LOCKED)
                mlock_vma_page(new);

diff --git a/mm/migrate.c b/mm/migrate.c
index 70ef794..5684330 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -472,7 +472,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
        pslot = radix_tree_lookup_slot(&mapping->i_pages,
                                        page_index(page));
 
-       expected_count += 1 + page_has_private(page);
+       expected_count += hpage_nr_pages(page) + page_has_private(page);
        if (page_count(page) != expected_count ||
                radix_tree_deref_slot_protected(pslot,
                                        &mapping->i_pages.xa_lock) != page) {
@@ -505,7 +505,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
         */
        newpage->index = page->index;
        newpage->mapping = page->mapping;
-       get_page(newpage);      /* add cache reference */
+       page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
        if (PageSwapBacked(page)) {
                __SetPageSwapBacked(newpage);
                if (PageSwapCache(page)) {
@@ -524,13 +524,26 @@ int migrate_page_move_mapping(struct address_space *mapping,
        }
 
        radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+       if (PageTransHuge(page)) {
+               int i;
+               int index = page_index(page);
+
+               for (i = 0; i < HPAGE_PMD_NR; i++) {
+                       pslot = radix_tree_lookup_slot(&mapping->i_pages,
+                                                      index + i);
+                       radix_tree_replace_slot(&mapping->i_pages, pslot,
+                                               newpage + i);
+               }
+       } else {
+               radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+       }
 
        /*
         * Drop cache reference from old page by unfreezing
         * to one less reference.
         * We know this isn't the last reference.
         */
-       page_ref_unfreeze(page, expected_count - 1);
+       page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
 
        xa_unlock(&mapping->i_pages);
        /* Leave irq disabled to prevent preemption while updating stats */

diff --git a/mm/rmap.c b/mm/rmap.c
index f0dd4e4..8d5337f 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1374,9 +1374,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                if (!pvmw.pte && (flags & TTU_MIGRATION)) {
                        VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
 
-                       if (!PageAnon(page))
-                               continue;
-
                        set_pmd_migration_entry(&pvmw, page);
                        continue;
                }