mm,thp,compaction,cma: allow THP migration for CMA allocations

The code to implement THP migrations already exists, and the code for CMA
to clear out a region of memory already exists.

Only a few small tweaks are needed to allow CMA to move THP memory when
attempting an allocation from alloc_contig_range.

With these changes, migrating THPs from a CMA area works when allocating a
1GB hugepage from CMA memory.

[riel@surriel.com: fix hugetlbfs pages per Mike, cleanup per Vlastimil]
Link: http://lkml.kernel.org/r/20200228104700.0af2f18d@imladris.surriel.com
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Link: http://lkml.kernel.org/r/20200227213238.1298752-2-riel@surriel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/compaction.c b/mm/compaction.c
index 672d3c7..000ade0 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -894,12 +894,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
                /*
                 * Regardless of being on LRU, compound pages such as THP and
-                * hugetlbfs are not to be compacted. We can potentially save
-                * a lot of iterations if we skip them at once. The check is
-                * racy, but we can consider only valid values and the only
-                * danger is skipping too much.
+                * hugetlbfs are not to be compacted unless we are attempting
+                * an allocation much larger than the huge page size (eg CMA).
+                * We can potentially save a lot of iterations if we skip them
+                * at once. The check is racy, but we can consider only valid
+                * values and the only danger is skipping too much.
                 */
-               if (PageCompound(page)) {
+               if (PageCompound(page) && !cc->alloc_contig) {
                        const unsigned int order = compound_order(page);
 
                        if (likely(order < MAX_ORDER))
@@ -969,7 +970,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
                         * and it's on LRU. It can only be a THP so the order
                         * is safe to read and it's 0 for tail pages.
                         */
-                       if (unlikely(PageCompound(page))) {
+                       if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
                                low_pfn += compound_nr(page) - 1;
                                goto isolate_fail;
                        }
@@ -981,12 +982,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
                if (__isolate_lru_page(page, isolate_mode) != 0)
                        goto isolate_fail;
 
-               VM_BUG_ON_PAGE(PageCompound(page), page);
+               /* The whole page is taken off the LRU; skip the tail pages. */
+               if (PageCompound(page))
+                       low_pfn += compound_nr(page) - 1;
 
                /* Successfully isolated */
                del_page_from_lru_list(page, lruvec, page_lru(page));
-               inc_node_page_state(page,
-                               NR_ISOLATED_ANON + page_is_file_cache(page));
+               mod_node_page_state(page_pgdat(page),
+                               NR_ISOLATED_ANON + page_is_file_cache(page),
+                               hpage_nr_pages(page));
 
 isolate_success:
                list_add(&page->lru, &cc->migratepages);

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f2cf666..e5f76da 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8251,15 +8251,20 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 
                /*
                 * Hugepages are not in LRU lists, but they're movable.
+                * THPs are on the LRU, but need to be counted as #small pages.
                 * We need not scan over tail pages because we don't
                 * handle each tail page individually in migration.
                 */
-               if (PageHuge(page)) {
+               if (PageHuge(page) || PageTransCompound(page)) {
                        struct page *head = compound_head(page);
                        unsigned int skip_pages;
 
-                       if (!hugepage_migration_supported(page_hstate(head)))
+                       if (PageHuge(page)) {
+                               if (!hugepage_migration_supported(page_hstate(head)))
+                                       return page;
+                       } else if (!PageLRU(head) && !__PageMovable(head)) {
                                return page;
+                       }
 
                        skip_pages = compound_nr(head) - (page - head);
                        iter += skip_pages - 1;