[RFC PATCH 22/25] memory manage: active/inactive page list manipulation in memcg.

[Zi Yan]

From: Zi Yan <ziy@xxxxxxxxxx>

The syscall allows users to trigger page list scanning to actively
move pages between active/inactive lists according to page
references. This is limited to the memcg which the process belongs
to. It would not impact the global LRU lists, which is the root
memcg.

Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
---
 include/uapi/linux/mempolicy.h |  1 +
 mm/internal.h                  | 93 +++++++++++++++++++++++++++++++++++++++++-
 mm/memory_manage.c             | 76 +++++++++++++++++++++++++++++++++-
 mm/vmscan.c                    | 90 ++++++++--------------------------------
 4 files changed, 184 insertions(+), 76 deletions(-)

diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 4722bb7..dac474a 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -53,6 +53,7 @@ enum {
 #define MPOL_MF_MOVE_MT  (1<<6)	/* Use multi-threaded page copy routine */
 #define MPOL_MF_MOVE_CONCUR  (1<<7)	/* Move pages in a batch */
 #define MPOL_MF_EXCHANGE	(1<<8)	/* Exchange pages */
+#define MPOL_MF_SHRINK_LISTS	(1<<9)	/* Exchange pages */
 
 #define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
 			 MPOL_MF_MOVE     | 	\
diff --git a/mm/internal.h b/mm/internal.h
index 94feb14..eec88de 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -564,7 +564,7 @@ extern int copy_page_lists_mt(struct page **to,
 extern int exchange_page_mthread(struct page *to, struct page *from,
 			int nr_pages);
 extern int exchange_page_lists_mthread(struct page **to,
-						  struct page **from, 
+						  struct page **from,
 						  int nr_pages);
 
 extern int exchange_two_pages(struct page *page1, struct page *page2);
@@ -577,4 +577,95 @@ int expected_page_refs(struct address_space *mapping, struct page *page);
 int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
 		     unsigned long maxnode);
 
+unsigned move_active_pages_to_lru(struct lruvec *lruvec,
+				     struct list_head *list,
+				     struct list_head *pages_to_free,
+				     enum lru_list lru);
+void putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list);
+
+struct scan_control {
+	/* How many pages shrink_list() should reclaim */
+	unsigned long nr_to_reclaim;
+
+	/*
+	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
+	 * are scanned.
+	 */
+	nodemask_t	*nodemask;
+
+	/*
+	 * The memory cgroup that hit its limit and as a result is the
+	 * primary target of this reclaim invocation.
+	 */
+	struct mem_cgroup *target_mem_cgroup;
+
+	/* Writepage batching in laptop mode; RECLAIM_WRITE */
+	unsigned int may_writepage:1;
+
+	/* Can mapped pages be reclaimed? */
+	unsigned int may_unmap:1;
+
+	/* Can pages be swapped as part of reclaim? */
+	unsigned int may_swap:1;
+
+	/* e.g. boosted watermark reclaim leaves slabs alone */
+	unsigned int may_shrinkslab:1;
+
+	/*
+	 * Cgroups are not reclaimed below their configured memory.low,
+	 * unless we threaten to OOM. If any cgroups are skipped due to
+	 * memory.low and nothing was reclaimed, go back for memory.low.
+	 */
+	unsigned int memcg_low_reclaim:1;
+	unsigned int memcg_low_skipped:1;
+
+	unsigned int hibernation_mode:1;
+
+	/* One of the zones is ready for compaction */
+	unsigned int compaction_ready:1;
+
+	unsigned int isolate_only_huge_page:1;
+	unsigned int isolate_only_base_page:1;
+	unsigned int no_reclaim:1;
+
+	/* Allocation order */
+	s8 order;
+
+	/* Scan (total_size >> priority) pages at once */
+	s8 priority;
+
+	/* The highest zone to isolate pages for reclaim from */
+	s8 reclaim_idx;
+
+	/* This context's GFP mask */
+	gfp_t gfp_mask;
+
+	/* Incremented by the number of inactive pages that were scanned */
+	unsigned long nr_scanned;
+
+	/* Number of pages freed so far during a call to shrink_zones() */
+	unsigned long nr_reclaimed;
+
+	struct {
+		unsigned int dirty;
+		unsigned int unqueued_dirty;
+		unsigned int congested;
+		unsigned int writeback;
+		unsigned int immediate;
+		unsigned int file_taken;
+		unsigned int taken;
+	} nr;
+};
+
+unsigned long isolate_lru_pages(unsigned long nr_to_scan,
+		struct lruvec *lruvec, struct list_head *dst,
+		unsigned long *nr_scanned, struct scan_control *sc,
+		enum lru_list lru);
+void shrink_active_list(unsigned long nr_to_scan,
+			       struct lruvec *lruvec,
+			       struct scan_control *sc,
+			       enum lru_list lru);
+unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
+		     struct scan_control *sc, enum lru_list lru);
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/memory_manage.c b/mm/memory_manage.c
index b8f3654..e8dddbf 100644
--- a/mm/memory_manage.c
+++ b/mm/memory_manage.c
@@ -5,13 +5,79 @@
 #include <linux/sched/mm.h>
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
+#include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
 #include <linux/nodemask.h>
+#include <linux/rmap.h>
 #include <linux/security.h>
+#include <linux/swap.h>
 #include <linux/syscalls.h>
 
 #include "internal.h"
 
 
+static unsigned long shrink_lists_node_memcg(pg_data_t *pgdat,
+	struct mem_cgroup *memcg, unsigned long nr_to_scan)
+{
+	struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
+	enum lru_list lru;
+
+	for_each_evictable_lru(lru) {
+		unsigned long nr_to_scan_local = lruvec_size_memcg_node(lru, memcg,
+				pgdat->node_id) / 2;
+		struct scan_control sc = {.may_unmap = 1, .no_reclaim = 1};
+		/*nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, memcg, sc);*/
+		/*
+		 * for slow node, we want active list, we start from the top of
+		 * the active list. For pages in the bottom of
+		 * the inactive list, we can place it to the top of inactive list
+		 */
+		/*
+		 * for fast node, we want inactive list, we start from the bottom of
+		 * the inactive list. For pages in the active list, we just keep them.
+		 */
+		/*
+		 * A key question is how many pages to scan each time, and what criteria
+		 * to use to move pages between active/inactive page lists.
+		 *  */
+		if (is_active_lru(lru))
+			shrink_active_list(nr_to_scan_local, lruvec, &sc, lru);
+		else
+			shrink_inactive_list(nr_to_scan_local, lruvec, &sc, lru);
+	}
+	cond_resched();
+
+	return 0;
+}
+
+static int shrink_lists(struct task_struct *p, struct mm_struct *mm,
+		const nodemask_t *slow, const nodemask_t *fast, unsigned long nr_to_scan)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_task(p);
+	int slow_nid, fast_nid;
+	int err = 0;
+
+	if (!memcg)
+		return 0;
+	/* Let's handle simplest situation first */
+	if (!(nodes_weight(*slow) == 1 && nodes_weight(*fast) == 1))
+		return 0;
+
+	if (memcg == root_mem_cgroup)
+		return 0;
+
+	slow_nid = first_node(*slow);
+	fast_nid = first_node(*fast);
+
+	/* move pages between page lists in slow node */
+	shrink_lists_node_memcg(NODE_DATA(slow_nid), memcg, nr_to_scan);
+
+	/* move pages between page lists in fast node */
+	shrink_lists_node_memcg(NODE_DATA(fast_nid), memcg, nr_to_scan);
+
+	return err;
+}
+
 SYSCALL_DEFINE6(mm_manage, pid_t, pid, unsigned long, nr_pages,
 		unsigned long, maxnode,
 		const unsigned long __user *, slow_nodes,
@@ -42,10 +108,14 @@ SYSCALL_DEFINE6(mm_manage, pid_t, pid, unsigned long, nr_pages,
 		goto out;
 
 	/* Check flags */
-	if (flags & ~(MPOL_MF_MOVE_MT|
+	if (flags & ~(
+				  MPOL_MF_MOVE|
+				  MPOL_MF_MOVE_MT|
 				  MPOL_MF_MOVE_DMA|
 				  MPOL_MF_MOVE_CONCUR|
-				  MPOL_MF_EXCHANGE))
+				  MPOL_MF_EXCHANGE|
+				  MPOL_MF_SHRINK_LISTS|
+				  MPOL_MF_MOVE_ALL))
 		return -EINVAL;
 
 	/* Find the mm_struct */
@@ -94,6 +164,8 @@ SYSCALL_DEFINE6(mm_manage, pid_t, pid, unsigned long, nr_pages,
 		set_bit(MMF_MM_MANAGE, &mm->flags);
 	}
 
+	if (flags & MPOL_MF_SHRINK_LISTS)
+		shrink_lists(task, mm, slow, fast, nr_pages);
 
 	clear_bit(MMF_MM_MANAGE, &mm->flags);
 	mmput(mm);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1d539d6..3693550 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -63,75 +63,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/vmscan.h>
 
-struct scan_control {
-	/* How many pages shrink_list() should reclaim */
-	unsigned long nr_to_reclaim;
-
-	/*
-	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
-	 * are scanned.
-	 */
-	nodemask_t	*nodemask;
-
-	/*
-	 * The memory cgroup that hit its limit and as a result is the
-	 * primary target of this reclaim invocation.
-	 */
-	struct mem_cgroup *target_mem_cgroup;
-
-	/* Writepage batching in laptop mode; RECLAIM_WRITE */
-	unsigned int may_writepage:1;
-
-	/* Can mapped pages be reclaimed? */
-	unsigned int may_unmap:1;
-
-	/* Can pages be swapped as part of reclaim? */
-	unsigned int may_swap:1;
-
-	/* e.g. boosted watermark reclaim leaves slabs alone */
-	unsigned int may_shrinkslab:1;
-
-	/*
-	 * Cgroups are not reclaimed below their configured memory.low,
-	 * unless we threaten to OOM. If any cgroups are skipped due to
-	 * memory.low and nothing was reclaimed, go back for memory.low.
-	 */
-	unsigned int memcg_low_reclaim:1;
-	unsigned int memcg_low_skipped:1;
-
-	unsigned int hibernation_mode:1;
-
-	/* One of the zones is ready for compaction */
-	unsigned int compaction_ready:1;
-
-	/* Allocation order */
-	s8 order;
-
-	/* Scan (total_size >> priority) pages at once */
-	s8 priority;
-
-	/* The highest zone to isolate pages for reclaim from */
-	s8 reclaim_idx;
-
-	/* This context's GFP mask */
-	gfp_t gfp_mask;
-
-	/* Incremented by the number of inactive pages that were scanned */
-	unsigned long nr_scanned;
-
-	/* Number of pages freed so far during a call to shrink_zones() */
-	unsigned long nr_reclaimed;
-
-	struct {
-		unsigned int dirty;
-		unsigned int unqueued_dirty;
-		unsigned int congested;
-		unsigned int writeback;
-		unsigned int immediate;
-		unsigned int file_taken;
-		unsigned int taken;
-	} nr;
-};
 
 #ifdef ARCH_HAS_PREFETCH
 #define prefetch_prev_lru_page(_page, _base, _field)			\
@@ -1261,6 +1192,13 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			; /* try to reclaim the page below */
 		}
 
+		/* We keep the page in inactive list for migration in the next
+		 * step */
+		if (sc->no_reclaim) {
+			stat->nr_ref_keep++;
+			goto keep_locked;
+		}
+
 		/*
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
@@ -1613,7 +1551,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
  *
  * returns how many pages were moved onto *@dst.
  */
-static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
+unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct lruvec *lruvec, struct list_head *dst,
 		unsigned long *nr_scanned, struct scan_control *sc,
 		enum lru_list lru)
@@ -1634,6 +1572,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct page *page;
 
 		page = lru_to_page(src);
+		nr_pages = hpage_nr_pages(page);
+
+		if (sc->isolate_only_base_page && nr_pages != 1)
+			continue;
+		if (sc->isolate_only_huge_page && nr_pages == 1)
+			continue;
+
 		prefetchw_prev_lru_page(page, src, flags);
 
 		VM_BUG_ON_PAGE(!PageLRU(page), page);
@@ -1653,7 +1598,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		scan++;
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
-			nr_pages = hpage_nr_pages(page);
 			nr_taken += nr_pages;
 			nr_zone_taken[page_zonenum(page)] += nr_pages;
 			list_move(&page->lru, dst);
@@ -1855,7 +1799,7 @@ static int current_may_throttle(void)
  * shrink_inactive_list() is a helper for shrink_node().  It returns the number
  * of reclaimed pages
  */
-static noinline_for_stack unsigned long
+noinline_for_stack unsigned long
 shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		     struct scan_control *sc, enum lru_list lru)
 {
@@ -2029,7 +1973,7 @@ unsigned move_active_pages_to_lru(struct lruvec *lruvec,
 	return nr_moved;
 }
 
-static void shrink_active_list(unsigned long nr_to_scan,
+void shrink_active_list(unsigned long nr_to_scan,
 			       struct lruvec *lruvec,
 			       struct scan_control *sc,
 			       enum lru_list lru)
-- 
2.7.4