1 files changed, 156 insertions, 94 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index c8bcdea15f5f..0fb3b89b3967 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -229,6 +229,33 @@ static void reset_cached_positions(struct zone *zone)
 				pageblock_start_pfn(zone_end_pfn(zone) - 1);
 }
 
+#ifdef CONFIG_SPARSEMEM
+/*
+ * If the PFN falls into an offline section, return the start PFN of the
+ * next online section. If the PFN falls into an online section or if
+ * there is no next online section, return 0.
+ */
+static unsigned long skip_offline_sections(unsigned long start_pfn)
+{
+	unsigned long start_nr = pfn_to_section_nr(start_pfn);
+
+	if (online_section_nr(start_nr))
+		return 0;
+
+	while (++start_nr <= __highest_present_section_nr) {
+		if (online_section_nr(start_nr))
+			return section_nr_to_pfn(start_nr);
+	}
+
+	return 0;
+}
+#else
+static unsigned long skip_offline_sections(unsigned long start_pfn)
+{
+	return 0;
+}
+#endif
+
 /*
  * Compound pages of >= pageblock_order should consistently be skipped until
  * released. It is always pointless to compact pages of such order (if they are
@@ -392,18 +419,14 @@ void reset_isolation_suitable(pg_data_t *pgdat)
  * Sets the pageblock skip bit if it was clear. Note that this is a hint as
  * locks are not required for read/writers. Returns true if it was already set.
  */
-static bool test_and_set_skip(struct compact_control *cc, struct page *page,
-							unsigned long pfn)
+static bool test_and_set_skip(struct compact_control *cc, struct page *page)
 {
 	bool skip;
 
-	/* Do no update if skip hint is being ignored */
+	/* Do not update if skip hint is being ignored */
 	if (cc->ignore_skip_hint)
 		return false;
 
-	if (!pageblock_aligned(pfn))
-		return false;
-
 	skip = get_pageblock_skip(page);
 	if (!skip && !cc->no_set_skip_hint)
 		set_pageblock_skip(page);
@@ -440,9 +463,6 @@ static void update_pageblock_skip(struct compact_control *cc,
 	if (cc->no_set_skip_hint)
 		return;
 
-	if (!page)
-		return;
-
 	set_pageblock_skip(page);
 
 	/* Update where async and sync compaction should restart */
@@ -470,8 +490,7 @@ static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
 {
 }
 
-static bool test_and_set_skip(struct compact_control *cc, struct page *page,
-							unsigned long pfn)
+static bool test_and_set_skip(struct compact_control *cc, struct page *page)
 {
 	return false;
 }
@@ -745,8 +764,9 @@ isolate_freepages_range(struct compact_control *cc,
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
-static bool too_many_isolated(pg_data_t *pgdat)
+static bool too_many_isolated(struct compact_control *cc)
 {
+	pg_data_t *pgdat = cc->zone->zone_pgdat;
 	bool too_many;
 
 	unsigned long active, inactive, isolated;
@@ -758,6 +778,17 @@ static bool too_many_isolated(pg_data_t *pgdat)
 	isolated = node_page_state(pgdat, NR_ISOLATED_FILE) +
 			node_page_state(pgdat, NR_ISOLATED_ANON);
 
+	/*
+	 * Allow GFP_NOFS to isolate past the limit set for regular
+	 * compaction runs. This prevents an ABBA deadlock when other
+	 * compactors have already isolated to the limit, but are
+	 * blocked on filesystem locks held by the GFP_NOFS thread.
+	 */
+	if (cc->gfp_mask & __GFP_FS) {
+		inactive >>= 3;
+		active >>= 3;
+	}
+
 	too_many = isolated > (inactive + active) / 2;
 	if (!too_many)
 		wake_throttle_isolated(pgdat);
@@ -806,7 +837,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	 * list by either parallel reclaimers or compaction. If there are,
 	 * delay for some time until fewer pages are isolated
 	 */
-	while (unlikely(too_many_isolated(pgdat))) {
+	while (unlikely(too_many_isolated(cc))) {
 		/* stop isolation if there are still pages not migrated */
 		if (cc->nr_migratepages)
 			return -EAGAIN;
@@ -1074,11 +1105,17 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 			lruvec_memcg_debug(lruvec, page_folio(page));
 
-			/* Try get exclusive access under lock */
-			if (!skip_updated) {
+			/*
+			 * Try get exclusive access under lock. If marked for
+			 * skip, the scan is aborted unless the current context
+			 * is a rescan to reach the end of the pageblock.
+			 */
+			if (!skip_updated && valid_page) {
 				skip_updated = true;
-				if (test_and_set_skip(cc, page, low_pfn))
+				if (test_and_set_skip(cc, valid_page) &&
+				    !cc->finish_pageblock) {
 					goto isolate_abort;
+				}
 			}
 
 			/*
@@ -1191,7 +1228,7 @@ isolate_abort:
 	 * rescanned twice in a row.
 	 */
 	if (low_pfn == end_pfn && (!nr_isolated || cc->finish_pageblock)) {
-		if (valid_page && !skip_updated)
+		if (!cc->no_set_skip_hint && valid_page && !skip_updated)
 			set_pageblock_skip(valid_page);
 		update_cached_migrate(cc, low_pfn);
 	}
@@ -1379,7 +1416,7 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn)
 	isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false);
 
 	/* Skip this pageblock in the future as it's full or nearly full */
-	if (cc->nr_freepages < cc->nr_migratepages)
+	if (start_pfn == end_pfn)
 		set_pageblock_skip(page);
 
 	return;
@@ -1403,11 +1440,10 @@ static int next_search_order(struct compact_control *cc, int order)
 	return order;
 }
 
-static unsigned long
-fast_isolate_freepages(struct compact_control *cc)
+static void fast_isolate_freepages(struct compact_control *cc)
 {
 	unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1);
-	unsigned int nr_scanned = 0;
+	unsigned int nr_scanned = 0, total_isolated = 0;
 	unsigned long low_pfn, min_pfn, highest = 0;
 	unsigned long nr_isolated = 0;
 	unsigned long distance;
@@ -1417,7 +1453,7 @@ fast_isolate_freepages(struct compact_control *cc)
 
 	/* Full compaction passes in a negative order */
 	if (cc->order <= 0)
-		return cc->free_pfn;
+		return;
 
 	/*
 	 * If starting the scan, use a deeper search and use the highest
@@ -1506,6 +1542,7 @@ fast_isolate_freepages(struct compact_control *cc)
 				set_page_private(page, order);
 				nr_isolated = 1 << order;
 				nr_scanned += nr_isolated - 1;
+				total_isolated += nr_isolated;
 				cc->nr_freepages += nr_isolated;
 				list_add_tail(&page->lru, &cc->freepages);
 				count_compact_events(COMPACTISOLATED, nr_isolated);
@@ -1518,6 +1555,10 @@ fast_isolate_freepages(struct compact_control *cc)
 
 		spin_unlock_irqrestore(&cc->zone->lock, flags);
 
+		/* Skip fast search if enough freepages isolated */
+		if (cc->nr_freepages >= cc->nr_migratepages)
+			break;
+
 		/*
 		 * Smaller scan on next order so the total scan is related
 		 * to freelist_scan_limit.
@@ -1526,6 +1567,9 @@ fast_isolate_freepages(struct compact_control *cc)
 			limit = max(1U, limit >> 1);
 	}
 
+	trace_mm_compaction_fast_isolate_freepages(min_pfn, cc->free_pfn,
+						   nr_scanned, total_isolated);
+
 	if (!page) {
 		cc->fast_search_fail++;
 		if (scan_start) {
@@ -1556,11 +1600,10 @@ fast_isolate_freepages(struct compact_control *cc)
 
 	cc->total_free_scanned += nr_scanned;
 	if (!page)
-		return cc->free_pfn;
+		return;
 
 	low_pfn = page_to_pfn(page);
 	fast_isolate_around(cc, low_pfn);
-	return low_pfn;
 }
 
 /*
@@ -1684,11 +1727,10 @@ splitmap:
  * This is a migrate-callback that "allocates" freepages by taking pages
  * from the isolated freelists in the block we are migrating to.
  */
-static struct page *compaction_alloc(struct page *migratepage,
-					unsigned long data)
+static struct folio *compaction_alloc(struct folio *src, unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
-	struct page *freepage;
+	struct folio *dst;
 
 	if (list_empty(&cc->freepages)) {
 		isolate_freepages(cc);
@@ -1697,11 +1739,11 @@ static struct page *compaction_alloc(struct page *migratepage,
 			return NULL;
 	}
 
-	freepage = list_entry(cc->freepages.next, struct page, lru);
-	list_del(&freepage->lru);
+	dst = list_entry(cc->freepages.next, struct folio, lru);
+	list_del(&dst->lru);
 	cc->nr_freepages--;
 
-	return freepage;
+	return dst;
 }
 
 /*
@@ -1709,11 +1751,11 @@ static struct page *compaction_alloc(struct page *migratepage,
  * freelist.  All pages on the freelist are from the same zone, so there is no
  * special handling needed for NUMA.
  */
-static void compaction_free(struct page *page, unsigned long data)
+static void compaction_free(struct folio *dst, unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
 
-	list_add(&page->lru, &cc->freepages);
+	list_add(&dst->lru, &cc->freepages);
 	cc->nr_freepages++;
 }
 
@@ -1736,6 +1778,7 @@ static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNE
  */
 static unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
 static int sysctl_extfrag_threshold = 500;
+static int __read_mostly sysctl_compact_memory;
 
 static inline void
 update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)
@@ -1864,7 +1907,6 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 					pfn = cc->zone->zone_start_pfn;
 				cc->fast_search_fail = 0;
 				found_block = true;
-				set_pageblock_skip(freepage);
 				break;
 			}
 		}
@@ -1940,8 +1982,14 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc)
 
 		page = pageblock_pfn_to_page(block_start_pfn,
 						block_end_pfn, cc->zone);
-		if (!page)
+		if (!page) {
+			unsigned long next_pfn;
+
+			next_pfn = skip_offline_sections(block_start_pfn);
+			if (next_pfn)
+				block_end_pfn = min(next_pfn, cc->free_pfn);
 			continue;
+		}
 
 		/*
 		 * If isolation recently failed, do not retry. Only check the
@@ -2193,25 +2241,11 @@ static enum compact_result compact_finished(struct compact_control *cc)
 	return ret;
 }
 
-static enum compact_result __compaction_suitable(struct zone *zone, int order,
-					unsigned int alloc_flags,
-					int highest_zoneidx,
-					unsigned long wmark_target)
+static bool __compaction_suitable(struct zone *zone, int order,
+				  int highest_zoneidx,
+				  unsigned long wmark_target)
 {
 	unsigned long watermark;
-
-	if (is_via_compact_memory(order))
-		return COMPACT_CONTINUE;
-
-	watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
-	/*
-	 * If watermarks for high-order allocation are already met, there
-	 * should be no need for compaction at all.
-	 */
-	if (zone_watermark_ok(zone, order, watermark, highest_zoneidx,
-								alloc_flags))
-		return COMPACT_SUCCESS;
-
 	/*
 	 * Watermarks for order-0 must be met for compaction to be able to
 	 * isolate free pages for migration targets. This means that the
@@ -2229,29 +2263,20 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
 	watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
 				low_wmark_pages(zone) : min_wmark_pages(zone);
 	watermark += compact_gap(order);
-	if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx,
-						ALLOC_CMA, wmark_target))
-		return COMPACT_SKIPPED;
-
-	return COMPACT_CONTINUE;
+	return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx,
+				   ALLOC_CMA, wmark_target);
 }
 
 /*
  * compaction_suitable: Is this suitable to run compaction on this zone now?
- * Returns
- *   COMPACT_SKIPPED  - If there are too few free pages for compaction
- *   COMPACT_SUCCESS  - If the allocation would succeed without compaction
- *   COMPACT_CONTINUE - If compaction should run now
  */
-enum compact_result compaction_suitable(struct zone *zone, int order,
-					unsigned int alloc_flags,
-					int highest_zoneidx)
+bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx)
 {
-	enum compact_result ret;
-	int fragindex;
+	enum compact_result compact_result;
+	bool suitable;
 
-	ret = __compaction_suitable(zone, order, alloc_flags, highest_zoneidx,
-				    zone_page_state(zone, NR_FREE_PAGES));
+	suitable = __compaction_suitable(zone, order, highest_zoneidx,
+					 zone_page_state(zone, NR_FREE_PAGES));
 	/*
 	 * fragmentation index determines if allocation failures are due to
 	 * low memory or external fragmentation
@@ -2268,17 +2293,24 @@ enum compact_result compaction_suitable(struct zone *zone, int order,
 	 * excessive compaction for costly orders, but it should not be at the
 	 * expense of system stability.
 	 */
-	if (ret == COMPACT_CONTINUE && (order > PAGE_ALLOC_COSTLY_ORDER)) {
-		fragindex = fragmentation_index(zone, order);
-		if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
-			ret = COMPACT_NOT_SUITABLE_ZONE;
+	if (suitable) {
+		compact_result = COMPACT_CONTINUE;
+		if (order > PAGE_ALLOC_COSTLY_ORDER) {
+			int fragindex = fragmentation_index(zone, order);
+
+			if (fragindex >= 0 &&
+			    fragindex <= sysctl_extfrag_threshold) {
+				suitable = false;
+				compact_result = COMPACT_NOT_SUITABLE_ZONE;
+			}
+		}
+	} else {
+		compact_result = COMPACT_SKIPPED;
 	}
 
-	trace_mm_compaction_suitable(zone, order, ret);
-	if (ret == COMPACT_NOT_SUITABLE_ZONE)
-		ret = COMPACT_SKIPPED;
+	trace_mm_compaction_suitable(zone, order, compact_result);
 
-	return ret;
+	return suitable;
 }
 
 bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
@@ -2294,7 +2326,6 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
 				ac->highest_zoneidx, ac->nodemask) {
 		unsigned long available;
-		enum compact_result compact_result;
 
 		/*
 		 * Do not consider all the reclaimable memory because we do not
@@ -2304,9 +2335,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 		 */
 		available = zone_reclaimable_pages(zone) / order;
 		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
-		compact_result = __compaction_suitable(zone, order, alloc_flags,
-				ac->highest_zoneidx, available);
-		if (compact_result == COMPACT_CONTINUE)
+		if (__compaction_suitable(zone, order, ac->highest_zoneidx,
+					  available))
 			return true;
 	}
 
@@ -2336,11 +2366,22 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 	INIT_LIST_HEAD(&cc->migratepages);
 
 	cc->migratetype = gfp_migratetype(cc->gfp_mask);
-	ret = compaction_suitable(cc->zone, cc->order, cc->alloc_flags,
-							cc->highest_zoneidx);
-	/* Compaction is likely to fail */
-	if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED)
-		return ret;
+
+	if (!is_via_compact_memory(cc->order)) {
+		unsigned long watermark;
+
+		/* Allocation can already succeed, nothing to do */
+		watermark = wmark_pages(cc->zone,
+					cc->alloc_flags & ALLOC_WMARK_MASK);
+		if (zone_watermark_ok(cc->zone, cc->order, watermark,
+				      cc->highest_zoneidx, cc->alloc_flags))
+			return COMPACT_SUCCESS;
+
+		/* Compaction is likely to fail */
+		if (!compaction_suitable(cc->zone, cc->order,
+					 cc->highest_zoneidx))
+			return COMPACT_SKIPPED;
+	}
 
 	/*
 	 * Clear pageblock skip if there were failures recently and compaction
@@ -2456,7 +2497,8 @@ rescan:
 			}
 			/*
 			 * If an ASYNC or SYNC_LIGHT fails to migrate a page
-			 * within the current order-aligned block, scan the
+			 * within the current order-aligned block and
+			 * fast_find_migrateblock may be used then scan the
 			 * remainder of the pageblock. This will mark the
 			 * pageblock "skip" to avoid rescanning in the near
 			 * future. This will isolate more pages than necessary
@@ -2464,8 +2506,9 @@ rescan:
 			 * fast_find_migrateblock revisiting blocks that were
 			 * recently partially scanned.
 			 */
-			if (cc->direct_compaction && !cc->finish_pageblock &&
-						(cc->mode < MIGRATE_SYNC)) {
+			if (!pageblock_aligned(cc->migrate_pfn) &&
+			    !cc->ignore_skip_hint && !cc->finish_pageblock &&
+			    (cc->mode < MIGRATE_SYNC)) {
 				cc->finish_pageblock = true;
 
 				/*
@@ -2780,6 +2823,15 @@ static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int
 static int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos)
 {
+	int ret;
+
+	ret = proc_dointvec(table, write, buffer, length, ppos);
+	if (ret)
+		return ret;
+
+	if (sysctl_compact_memory != 1)
+		return -EINVAL;
+
 	if (write)
 		compact_nodes();
 
@@ -2833,8 +2885,14 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat)
 		if (!populated_zone(zone))
 			continue;
 
-		if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0,
-					highest_zoneidx) == COMPACT_CONTINUE)
+		/* Allocation can already succeed, check other zones */
+		if (zone_watermark_ok(zone, pgdat->kcompactd_max_order,
+				      min_wmark_pages(zone),
+				      highest_zoneidx, 0))
+			continue;
+
+		if (compaction_suitable(zone, pgdat->kcompactd_max_order,
+					highest_zoneidx))
 			return true;
 	}
 
@@ -2871,8 +2929,12 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 		if (compaction_deferred(zone, cc.order))
 			continue;
 
-		if (compaction_suitable(zone, cc.order, 0, zoneid) !=
-							COMPACT_CONTINUE)
+		/* Allocation can already succeed, nothing to do */
+		if (zone_watermark_ok(zone, cc.order,
+				      min_wmark_pages(zone), zoneid, 0))
+			continue;
+
+		if (!compaction_suitable(zone, cc.order, zoneid))
 			continue;
 
 		if (kthread_should_stop())
@@ -3021,7 +3083,7 @@ static int kcompactd(void *p)
  * This kcompactd start function will be called by init and node-hot-add.
  * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added.
  */
-void kcompactd_run(int nid)
+void __meminit kcompactd_run(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
 
@@ -3039,7 +3101,7 @@ void kcompactd_run(int nid)
  * Called by memory hotplug when all memory in a node is offlined. Caller must
  * be holding mem_hotplug_begin/done().
  */
-void kcompactd_stop(int nid)
+void __meminit kcompactd_stop(int nid)
 {
 	struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd;
 
@@ -3095,7 +3157,7 @@ static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
 static struct ctl_table vm_compaction[] = {
 	{
 		.procname	= "compact_memory",
-		.data		= NULL,
+		.data		= &sysctl_compact_memory,
 		.maxlen		= sizeof(int),
 		.mode		= 0200,
 		.proc_handler	= sysctl_compaction_handler,