[PATCH AUTOSEL 4.19 41/81] mm: fix inactive list balancing between NUMA nodes and cgroups

[PATCH AUTOSEL 4.19 41/81] mm: fix inactive list balancing between NUMA nodes and cgroups

[Sasha Levin]

From: Johannes Weiner <hannes@cmpxchg.org>

[ Upstream commit 3b991208b897f52507168374033771a984b947b1 ]

During !CONFIG_CGROUP reclaim, we expand the inactive list size if it's
thrashing on the node that is about to be reclaimed.  But when cgroups
are enabled, we suddenly ignore the node scope and use the cgroup scope
only.  The result is that pressure bleeds between NUMA nodes depending
on whether cgroups are merely compiled into Linux.  This behavioral
difference is unexpected and undesirable.

When the refault adaptivity of the inactive list was first introduced,
there were no statistics at the lruvec level - the intersection of node
and memcg - so it was better than nothing.

But now that we have that infrastructure, use lruvec_page_state() to
make the list balancing decision always NUMA aware.

[hannes@cmpxchg.org: fix bisection hole]
  Link: http://lkml.kernel.org/r/20190417155241.GB23013@cmpxchg.org
Link: http://lkml.kernel.org/r/20190412144438.2645-1-hannes@cmpxchg.org
Fixes: 2a2e48854d70 ("mm: vmscan: fix IO/refault regression in cache workingset transition")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 mm/vmscan.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3830066018c1..ee545d1e9894 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2190,7 +2190,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-				 struct mem_cgroup *memcg,
 				 struct scan_control *sc, bool actual_reclaim)
 {
 	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
@@ -2211,16 +2210,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
 	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
-	if (memcg)
-		refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-	else
-		refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 	/*
 	 * When refaults are being observed, it means a new workingset
 	 * is being established. Disable active list protection to get
 	 * rid of the stale workingset quickly.
 	 */
+	refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 	if (file && actual_reclaim && lruvec->refaults != refaults) {
 		inactive_ratio = 0;
 	} else {
@@ -2241,12 +2236,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 }
 
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
-				 struct lruvec *lruvec, struct mem_cgroup *memcg,
-				 struct scan_control *sc)
+				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru),
-					 memcg, sc, true))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -2346,7 +2339,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			 * anonymous pages on the LRU in eligible zones.
 			 * Otherwise, the small LRU gets thrashed.
 			 */
-			if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
+			if (!inactive_list_is_low(lruvec, false, sc, false) &&
 			    lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
 					>> sc->priority) {
 				scan_balance = SCAN_ANON;
@@ -2364,7 +2357,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
+	if (!inactive_list_is_low(lruvec, true, sc, false) &&
 	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
@@ -2517,7 +2510,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 				nr[lru] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(lru, nr_to_scan,
-							    lruvec, memcg, sc);
+							    lruvec, sc);
 			}
 		}
 
@@ -2584,7 +2577,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+	if (inactive_list_is_low(lruvec, false, sc, true))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2982,12 +2975,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
 		unsigned long refaults;
 		struct lruvec *lruvec;
 
-		if (memcg)
-			refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-		else
-			refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 		lruvec->refaults = refaults;
 	} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
 }
@@ -3344,7 +3333,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 63/81] mm/memory_hotplug.c: drop memory device reference after find_memory_block()

[Sasha Levin]

From: David Hildenbrand <david@redhat.com>

[ Upstream commit 89c02e69fc5245f8a2f34b58b42d43a737af1a5e ]

Right now we are using find_memory_block() to get the node id for the
pfn range to online.  We are missing to drop a reference to the memory
block device.  While the device still gets unregistered via
device_unregister(), resulting in no user visible problem, the device is
never released via device_release(), resulting in a memory leak.  Fix
that by properly using a put_device().

Link: http://lkml.kernel.org/r/20190411110955.1430-1-david@redhat.com
Fixes: d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Pankaj Gupta <pagupta@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Arun KS <arunks@codeaurora.org>
Cc: Mathieu Malaterre <malat@debian.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 mm/memory_hotplug.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 156991edec2a..af6735562215 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -901,6 +901,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	 */
 	mem = find_memory_block(__pfn_to_section(pfn));
 	nid = mem->nid;
+	put_device(&mem->dev);
 
 	/* associate pfn range with the zone */
 	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
-- 
2.20.1

[PATCH AUTOSEL 4.19 67/81] mm/memory.c: fix modifying of page protection by insert_pfn()

[Sasha Levin]

From: Jan Kara <jack@suse.cz>

[ Upstream commit cae85cb8add35f678cf487139d05e083ce2f570a ]

Aneesh has reported that PPC triggers the following warning when
excercising DAX code:

  IP set_pte_at+0x3c/0x190
  LR insert_pfn+0x208/0x280
  Call Trace:
     insert_pfn+0x68/0x280
     dax_iomap_pte_fault.isra.7+0x734/0xa40
     __xfs_filemap_fault+0x280/0x2d0
     do_wp_page+0x48c/0xa40
     __handle_mm_fault+0x8d0/0x1fd0
     handle_mm_fault+0x140/0x250
     __do_page_fault+0x300/0xd60
     handle_page_fault+0x18

Now that is WARN_ON in set_pte_at which is

        VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));

The problem is that on some architectures set_pte_at() cannot cope with
a situation where there is already some (different) valid entry present.

Use ptep_set_access_flags() instead to modify the pfn which is built to
deal with modifying existing PTE.

Link: http://lkml.kernel.org/r/20190311084537.16029-1-jack@suse.cz
Fixes: b2770da64254 "mm: add vm_insert_mixed_mkwrite()"
Signed-off-by: Jan Kara <jack@suse.cz>
Reported-by: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: Chandan Rajendra <chandan@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 mm/memory.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 9c69278173b7..e0010cb870e0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1796,10 +1796,12 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 				WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
 				goto out_unlock;
 			}
-			entry = *pte;
-			goto out_mkwrite;
-		} else
-			goto out_unlock;
+			entry = pte_mkyoung(*pte);
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+			if (ptep_set_access_flags(vma, addr, pte, entry, 1))
+				update_mmu_cache(vma, addr, pte);
+		}
+		goto out_unlock;
 	}
 
 	/* Ok, finally just insert the thing.. */
@@ -1808,7 +1810,6 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 	else
 		entry = pte_mkspecial(pfn_t_pte(pfn, prot));
 
-out_mkwrite:
 	if (mkwrite) {
 		entry = pte_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-- 
2.20.1