The patch titled
Subject: mm/demotion: assign correct memory type for multiple dax devices with the same node affinity
has been added to the -mm mm-unstable branch. Its filename is
mm-demotion-dax-kmem-set-nodes-abstract-distance-to-memtier_default_dax_adistance-fix.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-demotion-dax-kmem-set-nodes-abstract-distance-to-memtier_default_dax_adistance-fix.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxx>
Subject: mm/demotion: assign correct memory type for multiple dax devices with the same node affinity
Date: Fri, 26 Aug 2022 15:32:24 +0530
With multiple dax devices having the same node affinity, the kernel
wrongly assigned default_dram memory type to some devices after the memory
hotplug operation. Fix this by not clearing node_memory_types on the dax
device remove.
The current kernel cleared node_memory_type on successful removal of a dax
device. But then we can have multiple dax devices with the same node
affinity. Clearing the node_memory_type results in assigning other dax
devices to the default dram type when we bring them online.
Link: https://lkml.kernel.org/r/20220826100224.542312-1-aneesh.kumar@xxxxxxxxxxxxx
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Alistair Popple <apopple@xxxxxxxxxx>
Cc: Bharata B Rao <bharata@xxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: Hesham Almatary <hesham.almatary@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Jagdish Gediya <jvgediya.oss@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: SeongJae Park <sj@xxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxx>
Cc: Wei Xu <weixugc@xxxxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory-tiers.c | 37 +++++++++++++++++++++++++++++--------
1 file changed, 29 insertions(+), 8 deletions(-)
--- a/mm/memory-tiers.c~mm-demotion-dax-kmem-set-nodes-abstract-distance-to-memtier_default_dax_adistance-fix
+++ a/mm/memory-tiers.c
@@ -19,9 +19,14 @@ struct memory_tier {
int adistance_start;
};
+struct node_memory_type_map {
+ struct memory_dev_type *memtype;
+ int map_count;
+};
+
static DEFINE_MUTEX(memory_tier_lock);
static LIST_HEAD(memory_tiers);
-static struct memory_dev_type *node_memory_types[MAX_NUMNODES];
+static struct node_memory_type_map node_memory_types[MAX_NUMNODES];
static struct memory_dev_type *default_dram_type;
static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype)
@@ -70,9 +75,19 @@ static struct memory_tier *find_create_m
static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype)
{
- if (!node_memory_types[node]) {
- node_memory_types[node] = memtype;
- kref_get(&memtype->kref);
+ if (!node_memory_types[node].memtype)
+ node_memory_types[node].memtype = memtype;
+ /*
+ * for each device getting added in the same NUMA node
+ * with this specific memtype, bump the map count. We
+ * Only take memtype device reference once, so that
+ * changing a node memtype can be done by droping the
+ * only reference count taken here.
+ */
+
+ if (node_memory_types[node].memtype == memtype) {
+ if (!node_memory_types[node].map_count++)
+ kref_get(&memtype->kref);
}
}
@@ -88,7 +103,7 @@ static struct memory_tier *set_node_memo
__init_node_memory_type(node, default_dram_type);
- memtype = node_memory_types[node];
+ memtype = node_memory_types[node].memtype;
node_set(node, memtype->nodes);
memtier = find_create_memory_tier(memtype);
return memtier;
@@ -119,7 +134,7 @@ static bool clear_node_memory_tier(int n
if (memtier) {
struct memory_dev_type *memtype;
- memtype = node_memory_types[node];
+ memtype = node_memory_types[node].memtype;
node_clear(node, memtype->nodes);
if (nodes_empty(memtype->nodes)) {
list_del_init(&memtype->tier_sibiling);
@@ -175,8 +190,14 @@ EXPORT_SYMBOL_GPL(init_node_memory_type)
void clear_node_memory_type(int node, struct memory_dev_type *memtype)
{
mutex_lock(&memory_tier_lock);
- if (node_memory_types[node] == memtype) {
- node_memory_types[node] = NULL;
+ if (node_memory_types[node].memtype == memtype)
+ node_memory_types[node].map_count--;
+ /*
+ * If we umapped all the attached devices to this node,
+ * clear the node memory type.
+ */
+ if (!node_memory_types[node].map_count) {
+ node_memory_types[node].memtype = NULL;
kref_put(&memtype->kref, release_memtype);
}
mutex_unlock(&memory_tier_lock);
_
Patches currently in -mm which might be from aneesh.kumar@xxxxxxxxxxxxx are
mm-demotion-add-support-for-explicit-memory-tiers.patch
mm-demotion-move-memory-demotion-related-code.patch
mm-demotion-add-hotplug-callbacks-to-handle-new-numa-node-onlined.patch
mm-demotion-add-hotplug-callbacks-to-handle-new-numa-node-onlined-fix.patch
mm-demotion-dax-kmem-set-nodes-abstract-distance-to-memtier_default_dax_adistance.patch
mm-demotion-dax-kmem-set-nodes-abstract-distance-to-memtier_default_dax_adistance-fix.patch
mm-demotion-build-demotion-targets-based-on-explicit-memory-tiers.patch
mm-demotion-add-pg_data_t-member-to-track-node-memory-tier-details.patch
mm-demotion-drop-memtier-from-memtype.patch
mm-demotion-update-node_is_toptier-to-work-with-memory-tiers.patch
lib-nodemask-optimize-node_random-for-nodemask-with-single-numa-node.patch
a.patch
