Date:   Fri, 29 Jul 2022 12:49:34 +0530
From:   "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>
To:     "Huang, Ying" <ying.huang@...el.com>
Cc:     linux-mm@...ck.org, akpm@...ux-foundation.org,
        Wei Xu <weixugc@...gle.com>, Yang Shi <shy828301@...il.com>,
        Davidlohr Bueso <dave@...olabs.net>,
        Tim C Chen <tim.c.chen@...el.com>,
        Michal Hocko <mhocko@...nel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Hesham Almatary <hesham.almatary@...wei.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Jonathan Cameron <Jonathan.Cameron@...wei.com>,
        Alistair Popple <apopple@...dia.com>,
        Dan Williams <dan.j.williams@...el.com>,
        Johannes Weiner <hannes@...xchg.org>, jvgediya.oss@...il.com
Subject: Re: [PATCH v11 4/8] mm/demotion/dax/kmem: Set node's abstract
 distance to MEMTIER_ADISTANCE_PMEM

"Huang, Ying" <ying.huang@...el.com> writes:

> "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com> writes:
>
>> By default, all nodes are assigned to the default memory tier which
>> is the memory tier designated for nodes with DRAM
>>
>> Set dax kmem device node's tier to slower memory tier by assigning
>> abstract distance to MEMTIER_ADISTANCE_PMEM. PMEM tier
>> appears below the default memory tier in demotion order.
>>
>> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@...ux.ibm.com>
>> ---
>>  drivers/dax/kmem.c           |  9 +++++++++
>>  include/linux/memory-tiers.h | 19 ++++++++++++++++++-
>>  mm/memory-tiers.c            | 28 ++++++++++++++++------------
>>  3 files changed, 43 insertions(+), 13 deletions(-)
>>
>> diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
>> index a37622060fff..6b0d5de9a3e9 100644
>> --- a/drivers/dax/kmem.c
>> +++ b/drivers/dax/kmem.c
>> @@ -11,6 +11,7 @@
>>  #include <linux/fs.h>
>>  #include <linux/mm.h>
>>  #include <linux/mman.h>
>> +#include <linux/memory-tiers.h>
>>  #include "dax-private.h"
>>  #include "bus.h"
>>  
>> @@ -41,6 +42,12 @@ struct dax_kmem_data {
>>  	struct resource *res[];
>>  };
>>  
>> +static struct memory_dev_type default_pmem_type  = {
>
> Why is this named as default_pmem_type?  We will not change the memory
> type of a node usually.
>

Any other suggestion? pmem_dev_type? 


>> +	.adistance = MEMTIER_ADISTANCE_PMEM,
>> +	.tier_sibiling = LIST_HEAD_INIT(default_pmem_type.tier_sibiling),
>> +	.nodes  = NODE_MASK_NONE,
>> +};
>> +
>>  static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
>>  {
>>  	struct device *dev = &dev_dax->dev;
>> @@ -62,6 +69,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
>>  		return -EINVAL;
>>  	}
>>  
>> +	init_node_memory_type(numa_node, &default_pmem_type);
>> +
>
> The memory hot-add below may fail.  So the error handling needs to be
> added.
>
> And, it appears that the memory type and memory tier of a node may be
> fully initialized here before NUMA hot-adding started.  So I suggest to
> set node_memory_types[] here only.  And set memory_dev_type->nodes in
> node hot-add callback.  I think there is the proper place to complete
> the initialization.
>
> And, in theory dax/kmem.c can be unloaded.  So we need to clear
> node_memory_types[] for nodes somewhere.
>

I guess by module exit we can be sure that all the memory managed
by dax/kmem is hotplugged out. How about something like below?

diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 6b0d5de9a3e9..eb4e158012a9 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -248,6 +248,7 @@ static void __exit dax_kmem_exit(void)
 	dax_driver_unregister(&device_dax_kmem_driver);
 	if (!any_hotremove_failed)
 		kfree_const(kmem_name);
+	unregister_memory_type(&default_pmem_type);
 }
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index fc6b7a14da51..8355baf5b8b4 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -31,6 +31,7 @@ struct memory_dev_type {
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
 void init_node_memory_type(int node, struct memory_dev_type *default_type);
+void unregister_memory_type(struct memory_dev_type *memtype);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -57,6 +58,10 @@ static inline bool node_is_toptier(int node)
 #define numa_demotion_enabled	false
 static inline void init_node_memory_type(int node, struct memory_dev_type *default_type)
 {
+}
+
+static inline void unregister_memory_type(struct memory_dev_type *memtype)
+{
 
 }
 
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 064e0f932795..4d29ebd4c4f3 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -500,6 +500,28 @@ void init_node_memory_type(int node, struct memory_dev_type *default_type)
 	mutex_unlock(&memory_tier_lock);
 }
 
+void unregister_memory_type(struct memory_dev_type *memtype)
+{
+	int node;
+	struct memory_tier *memtier = memtype->memtier;
+
+	mutex_lock(&memory_tier_lock);
+	for(node = 0; node < MAX_NUMNODES; node++) {
+		if (node_memory_types[node] == memtype) {
+			if (!nodes_empty(memtype->nodes))
+				WARN_ON(1);
+			node_memory_types[node] = NULL;
+		}
+	}
+
+	list_del(&memtype->tier_sibiling);
+	memtype->memtier = NULL;
+	if (list_empty(&memtier->memory_types))
+		destroy_memory_tier(memtier);
+
+	mutex_unlock(&memory_tier_lock);
+}
+
 void update_node_adistance(int node, struct memory_dev_type *memtype)
 {
 	pg_data_t *pgdat;

Powered by blists - more mailing lists