mm/compaction: enable compacting >0 order folios.

migrate_pages() supports >0 order folio migration and during compaction,
even if compaction_alloc() cannot provide >0 order free pages,
migrate_pages() can split the source page and try to migrate the base
pages from the split.  It can be a baseline and start point for adding
support for compacting >0 order folios.

Link: https://lkml.kernel.org/r/20240220183220.1451315-3-zi.yan@sent.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Suggested-by: Huang Ying <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Adam Manzanares <a.manzanares@samsung.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/compaction.c b/mm/compaction.c
index 52ff6b9344c707a5716d40d9508d7bf73379e145..2ba9ba49b0e9ff0acb4c65b1bf77ff2f49264753 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -40,9 +40,22 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 {
        count_vm_events(item, delta);
 }
+
+/*
+ * order == -1 is expected when compacting proactively via
+ * 1. /proc/sys/vm/compact_memory
+ * 2. /sys/devices/system/node/nodex/compact
+ * 3. /proc/sys/vm/compaction_proactiveness
+ */
+static inline bool is_via_compact_memory(int order)
+{
+       return order == -1;
+}
+
 #else
 #define count_compact_event(item) do { } while (0)
 #define count_compact_events(item, delta) do { } while (0)
+static inline bool is_via_compact_memory(int order) { return false; }
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
@@ -816,6 +829,32 @@ static bool too_many_isolated(struct compact_control *cc)
        return too_many;
 }
 
+/**
+ * skip_isolation_on_order() - determine when to skip folio isolation based on
+ *                            folio order and compaction target order
+ * @order:             to-be-isolated folio order
+ * @target_order:      compaction target order
+ *
+ * This avoids unnecessary folio isolations during compaction.
+ */
+static bool skip_isolation_on_order(int order, int target_order)
+{
+       /*
+        * Unless we are performing global compaction (i.e.,
+        * is_via_compact_memory), skip any folios that are larger than the
+        * target order: we wouldn't be here if we'd have a free folio with
+        * the desired target_order, so migrating this folio would likely fail
+        * later.
+        */
+       if (!is_via_compact_memory(target_order) && order >= target_order)
+               return true;
+       /*
+        * We limit memory compaction to pageblocks and won't try
+        * creating free blocks of memory that are larger than that.
+        */
+       return order >= pageblock_order;
+}
+
 /**
  * isolate_migratepages_block() - isolate all migrate-able pages within
  *                               a single pageblock
@@ -947,7 +986,22 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
                        valid_page = page;
                }
 
-               if (PageHuge(page) && cc->alloc_contig) {
+               if (PageHuge(page)) {
+                       /*
+                        * skip hugetlbfs if we are not compacting for pages
+                        * bigger than its order. THPs and other compound pages
+                        * are handled below.
+                        */
+                       if (!cc->alloc_contig) {
+                               const unsigned int order = compound_order(page);
+
+                               if (order <= MAX_PAGE_ORDER) {
+                                       low_pfn += (1UL << order) - 1;
+                                       nr_scanned += (1UL << order) - 1;
+                               }
+                               goto isolate_fail;
+                       }
+                       /* for alloc_contig case */
                        if (locked) {
                                unlock_page_lruvec_irqrestore(locked, flags);
                                locked = NULL;
@@ -1008,21 +1062,24 @@ 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 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.
+                * Regardless of being on LRU, compound pages such as THP
+                * (hugetlbfs is handled above) are not to be compacted unless
+                * we are attempting an allocation larger than the compound
+                * page size. 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) && !cc->alloc_contig) {
                        const unsigned int order = compound_order(page);
 
-                       if (likely(order <= MAX_PAGE_ORDER)) {
-                               low_pfn += (1UL << order) - 1;
-                               nr_scanned += (1UL << order) - 1;
+                       /* Skip based on page order and compaction target order. */
+                       if (skip_isolation_on_order(order, cc->order)) {
+                               if (order <= MAX_PAGE_ORDER) {
+                                       low_pfn += (1UL << order) - 1;
+                                       nr_scanned += (1UL << order) - 1;
+                               }
+                               goto isolate_fail;
                        }
-                       goto isolate_fail;
                }
 
                /*
@@ -1165,10 +1222,11 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
                        }
 
                        /*
-                        * folio become large since the non-locked check,
-                        * and it's on LRU.
+                        * Check LRU folio order under the lock
                         */
-                       if (unlikely(folio_test_large(folio) && !cc->alloc_contig)) {
+                       if (unlikely(skip_isolation_on_order(folio_order(folio),
+                                                            cc->order) &&
+                                    !cc->alloc_contig)) {
                                low_pfn += folio_nr_pages(folio) - 1;
                                nr_scanned += folio_nr_pages(folio) - 1;
                                folio_set_lru(folio);
@@ -1788,6 +1846,10 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
        struct compact_control *cc = (struct compact_control *)data;
        struct folio *dst;
 
+       /* this makes migrate_pages() split the source page and retry */
+       if (folio_test_large(src))
+               return NULL;
+
        if (list_empty(&cc->freepages)) {
                isolate_freepages(cc);
 
@@ -2090,17 +2152,6 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
        return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
 
-/*
- * order == -1 is expected when compacting proactively via
- * 1. /proc/sys/vm/compact_memory
- * 2. /sys/devices/system/node/nodex/compact
- * 3. /proc/sys/vm/compaction_proactiveness
- */
-static inline bool is_via_compact_memory(int order)
-{
-       return order == -1;
-}
-
 /*
  * Determine whether kswapd is (or recently was!) running on this node.
  *