linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Ying Huang <ying.huang@intel.com>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
	linux-mm@kvack.org,  akpm@linux-foundation.org
Cc: Greg Thelen <gthelen@google.com>, Yang Shi <shy828301@gmail.com>,
	 Davidlohr Bueso <dave@stgolabs.net>,
	Tim C Chen <tim.c.chen@intel.com>,
	Brice Goglin <brice.goglin@gmail.com>,
	 Michal Hocko <mhocko@kernel.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Hesham Almatary <hesham.almatary@huawei.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Alistair Popple <apopple@nvidia.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Feng Tang <feng.tang@intel.com>,
	Jagdish Gediya <jvgediya@linux.ibm.com>,
	Baolin Wang <baolin.wang@linux.alibaba.com>,
	David Rientjes <rientjes@google.com>
Subject: Re: [RFC PATCH v4 2/7] mm/demotion: Expose per node memory tier to sysfs
Date: Wed, 08 Jun 2022 15:18:00 +0800	[thread overview]
Message-ID: <e5c311d6c2f97407373aba0895aa6e7c0ce8d377.camel@intel.com> (raw)
In-Reply-To: <20220527122528.129445-3-aneesh.kumar@linux.ibm.com>

On Fri, 2022-05-27 at 17:55 +0530, Aneesh Kumar K.V wrote:
> From: Jagdish Gediya <jvgediya@linux.ibm.com>
> 
> Add support to read/write the memory tierindex for a NUMA node.
> 
> /sys/devices/system/node/nodeN/memtier
> 
> where N = node id
> 
> When read, It list the memory tier that the node belongs to.
> 
> When written, the kernel moves the node into the specified
> memory tier, the tier assignment of all other nodes are not
> affected.
> 
> If the memory tier does not exist, writing to the above file
> create the tier and assign the NUMA node to that tier.
> 
> mutex memory_tier_lock is introduced to protect memory tier
> related chanegs as it can happen from sysfs as well on hot
> plug events.
> 
> Signed-off-by: Jagdish Gediya <jvgediya@linux.ibm.com>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> ---
>  drivers/base/node.c     |  35 ++++++++++++++
>  include/linux/migrate.h |   4 +-
>  mm/migrate.c            | 103 ++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 141 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/base/node.c b/drivers/base/node.c
> index ec8bb24a5a22..cf4a58446d8c 100644
> --- a/drivers/base/node.c
> +++ b/drivers/base/node.c
> @@ -20,6 +20,7 @@
>  #include <linux/pm_runtime.h>
>  #include <linux/swap.h>
>  #include <linux/slab.h>
> +#include <linux/migrate.h>
>  
> 
> 
> 
>  static struct bus_type node_subsys = {
>  	.name = "node",
> @@ -560,11 +561,45 @@ static ssize_t node_read_distance(struct device *dev,
>  }
>  static DEVICE_ATTR(distance, 0444, node_read_distance, NULL);
>  
> 
> 
> 
> +#ifdef CONFIG_TIERED_MEMORY
> +static ssize_t memtier_show(struct device *dev,
> +			    struct device_attribute *attr,
> +			    char *buf)
> +{
> +	int node = dev->id;
> +
> +	return sysfs_emit(buf, "%d\n", node_get_memory_tier(node));
> +}
> +
> +static ssize_t memtier_store(struct device *dev,
> +			     struct device_attribute *attr,
> +			     const char *buf, size_t count)
> +{
> +	unsigned long tier;
> +	int node = dev->id;
> +
> +	int ret = kstrtoul(buf, 10, &tier);
> +	if (ret)
> +		return ret;
> +
> +	ret = node_reset_memory_tier(node, tier);
> +	if (ret)
> +		return ret;
> +
> +	return count;
> +}
> +
> +static DEVICE_ATTR_RW(memtier);
> +#endif
> +
>  static struct attribute *node_dev_attrs[] = {
>  	&dev_attr_meminfo.attr,
>  	&dev_attr_numastat.attr,
>  	&dev_attr_distance.attr,
>  	&dev_attr_vmstat.attr,
> +#ifdef CONFIG_TIERED_MEMORY
> +	&dev_attr_memtier.attr,
> +#endif
>  	NULL
>  };
>  
> 
> 
> 
> diff --git a/include/linux/migrate.h b/include/linux/migrate.h
> index 0ec653623565..d37d1d5dee82 100644
> --- a/include/linux/migrate.h
> +++ b/include/linux/migrate.h
> @@ -177,13 +177,15 @@ enum memory_tier_type {
>  };
>  
> 
> 
> 
>  int next_demotion_node(int node);
> -
>  extern void migrate_on_reclaim_init(void);
>  #ifdef CONFIG_HOTPLUG_CPU
>  extern void set_migration_target_nodes(void);
>  #else
>  static inline void set_migration_target_nodes(void) {}
>  #endif
> +int node_get_memory_tier(int node);
> +int node_set_memory_tier(int node, int tier);
> +int node_reset_memory_tier(int node, int tier);
>  #else
>  #define numa_demotion_enabled	false
>  static inline int next_demotion_node(int node)
> diff --git a/mm/migrate.c b/mm/migrate.c
> index f28ee93fb017..304559ba3372 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -2132,6 +2132,7 @@ static struct bus_type memory_tier_subsys = {
>  	.dev_name = "memtier",
>  };
>  
> 
> 
> 
> +DEFINE_MUTEX(memory_tier_lock);
>  static struct memory_tier *memory_tiers[MAX_MEMORY_TIERS];
>  
> 
> 
> 
>  static ssize_t nodelist_show(struct device *dev,
> @@ -2225,6 +2226,108 @@ static const struct attribute_group *memory_tier_attr_groups[] = {
>  	NULL,
>  };
>  
> 
> 
> 
> +static int __node_get_memory_tier(int node)
> +{
> +	int tier;
> +
> +	for (tier = 0; tier < MAX_MEMORY_TIERS; tier++) {
> +		if (memory_tiers[tier] && node_isset(node, memory_tiers[tier]->nodelist))
> +			return tier;
> +	}
> +
> +	return -1;
> +}
> +
> +int node_get_memory_tier(int node)
> +{
> +	int tier;
> +
> +	/*
> +	 * Make sure memory tier is not unregistered
> +	 * while it is being read.
> +	 */
> +	mutex_lock(&memory_tier_lock);
> +
> +	tier = __node_get_memory_tier(node);
> +
> +	mutex_unlock(&memory_tier_lock);
> +
> +	return tier;
> +}
> +
> +int __node_set_memory_tier(int node, int tier)
> +{
> +	int ret = 0;
> +	/*
> +	 * As register_memory_tier() for new tier can fail,
> +	 * try it before modifying existing tier. register
> +	 * tier makes tier visible in sysfs.
> +	 */
> +	if (!memory_tiers[tier]) {
> +		ret = register_memory_tier(tier);
> +		if (ret) {
> +			goto out;
> +		}
> +	}
> +
> +	node_set(node, memory_tiers[tier]->nodelist);
> +
> +out:
> +	return ret;
> +}
> +
> +int node_reset_memory_tier(int node, int tier)

I think "reset" isn't a good name here.  Maybe something like "change"
or "move"?

Best Regards,
Huang, Ying

> +{
> +	int current_tier, ret = 0;
> +
> +	mutex_lock(&memory_tier_lock);
> +
> +	current_tier = __node_get_memory_tier(node);
> +	if (current_tier == tier)
> +		goto out;
> +
> +	if (current_tier != -1 )
> +		node_clear(node, memory_tiers[current_tier]->nodelist);
> +
> +	ret = __node_set_memory_tier(node, tier);
> +
> +	if (!ret) {
> +		if (nodes_empty(memory_tiers[current_tier]->nodelist))
> +			unregister_memory_tier(current_tier);
> +	} else {
> +		/* reset it back to older tier */
> +		ret = __node_set_memory_tier(node, current_tier);
> +	}
> +out:
> +	mutex_unlock(&memory_tier_lock);
> +
> +	return ret;
> +}
> +
> +int node_set_memory_tier(int node, int tier)
> +{
> +	int current_tier, ret = 0;
> +
> +	if (tier >= MAX_MEMORY_TIERS)
> +		return -EINVAL;
> +
> +	mutex_lock(&memory_tier_lock);
> +	current_tier = __node_get_memory_tier(node);
> +	/*
> +	 * if node is already part of the tier proceed with the
> +	 * current tier value, because we might want to establish
> +	 * new migration paths now. The node might be added to a tier
> +	 * before it was made part of N_MEMORY, hence estabilish_migration_targets
> +	 * will have skipped this node.
> +	 */
> +	if (current_tier != -1)
> +		tier = current_tier;
> +	ret = __node_set_memory_tier(node, tier);
> +	mutex_unlock(&memory_tier_lock);
> +
> +	return ret;
> +}
> +
>  /*
>   * node_demotion[] example:
>   *




  parent reply	other threads:[~2022-06-08  7:18 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-05-26 21:22 RFC: Memory Tiering Kernel Interfaces (v3) Wei Xu
2022-05-27  2:58 ` Ying Huang
2022-05-27 14:05   ` Hesham Almatary
2022-05-27 16:25     ` Wei Xu
2022-05-27 12:25 ` [RFC PATCH v4 0/7] mm/demotion: Memory tiers and demotion Aneesh Kumar K.V
2022-05-27 12:25   ` [RFC PATCH v4 1/7] mm/demotion: Add support for explicit memory tiers Aneesh Kumar K.V
2022-05-27 13:59     ` Jonathan Cameron
2022-06-02  6:07     ` Ying Huang
2022-06-06  2:49       ` Ying Huang
2022-06-06  3:56         ` Aneesh Kumar K V
2022-06-06  5:33           ` Ying Huang
2022-06-06  6:01             ` Aneesh Kumar K V
2022-06-06  6:27               ` Aneesh Kumar K.V
2022-06-06  7:53                 ` Ying Huang
2022-06-06  8:01                   ` Aneesh Kumar K V
2022-06-06  8:52                     ` Ying Huang
2022-06-06  9:02                       ` Aneesh Kumar K V
2022-06-08  1:24                         ` Ying Huang
2022-06-08  7:16     ` Ying Huang
2022-06-08  8:24       ` Aneesh Kumar K V
2022-06-08  8:27         ` Ying Huang
2022-05-27 12:25   ` [RFC PATCH v4 2/7] mm/demotion: Expose per node memory tier to sysfs Aneesh Kumar K.V
2022-05-27 14:15     ` Jonathan Cameron
2022-06-03  8:40       ` Aneesh Kumar K V
2022-06-06 14:59         ` Jonathan Cameron
2022-06-06 16:01           ` Aneesh Kumar K V
2022-06-06 16:16             ` Jonathan Cameron
2022-06-06 16:39               ` Aneesh Kumar K V
2022-06-06 17:46                 ` Aneesh Kumar K.V
2022-06-07 14:32                   ` Jonathan Cameron
2022-06-08  7:18     ` Ying Huang [this message]
2022-06-08  8:25       ` Aneesh Kumar K V
2022-06-08  8:29         ` Ying Huang
2022-05-27 12:25   ` [RFC PATCH v4 3/7] mm/demotion: Build demotion targets based on explicit memory tiers Aneesh Kumar K.V
2022-05-27 14:31     ` Jonathan Cameron
2022-05-30  3:35     ` [mm/demotion] 8ebccd60c2: BUG:sleeping_function_called_from_invalid_context_at_mm/compaction.c kernel test robot
2022-05-27 12:25   ` [RFC PATCH v4 4/7] mm/demotion/dax/kmem: Set node's memory tier to MEMORY_TIER_PMEM Aneesh Kumar K.V
2022-06-01  6:29     ` Bharata B Rao
2022-06-01 13:49       ` Aneesh Kumar K V
2022-06-02  6:36         ` Bharata B Rao
2022-06-03  9:04           ` Aneesh Kumar K V
2022-06-06 10:11             ` Bharata B Rao
2022-06-06 10:16               ` Aneesh Kumar K V
2022-06-06 11:54                 ` Aneesh Kumar K.V
2022-06-06 12:09                   ` Bharata B Rao
2022-06-06 13:00                     ` Aneesh Kumar K V
2022-05-27 12:25   ` [RFC PATCH v4 5/7] mm/demotion: Add support to associate rank with memory tier Aneesh Kumar K.V
2022-05-27 14:45     ` Jonathan Cameron
2022-05-27 15:45       ` Aneesh Kumar K V
2022-05-30 12:36         ` Jonathan Cameron
2022-06-02  6:41     ` Ying Huang
2022-05-27 12:25   ` [RFC PATCH v4 6/7] mm/demotion: Add support for removing node from demotion memory tiers Aneesh Kumar K.V
2022-06-02  6:43     ` Ying Huang
2022-05-27 12:25   ` [RFC PATCH v4 7/7] mm/demotion: Demote pages according to allocation fallback order Aneesh Kumar K.V
2022-05-27 15:03     ` Jonathan Cameron
2022-06-02  7:35     ` Ying Huang
2022-06-03 15:09       ` Aneesh Kumar K V
2022-06-06  0:43         ` Ying Huang
2022-06-06  4:07           ` Aneesh Kumar K V
2022-06-06  5:26             ` Ying Huang
2022-06-06  6:21               ` Aneesh Kumar K.V
2022-06-06  7:42                 ` Ying Huang
2022-06-06  8:02                   ` Aneesh Kumar K V
2022-06-06  8:06                     ` Ying Huang
2022-06-06 17:07               ` Yang Shi
2022-05-27 13:40 ` RFC: Memory Tiering Kernel Interfaces (v3) Aneesh Kumar K V
2022-05-27 16:30   ` Wei Xu
2022-05-29  4:31     ` Ying Huang
2022-05-30 12:50       ` Jonathan Cameron
2022-05-31  1:57         ` Ying Huang
2022-06-07 19:25         ` Tim Chen
2022-06-08  4:41           ` Aneesh Kumar K V

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e5c311d6c2f97407373aba0895aa6e7c0ce8d377.camel@intel.com \
    --to=ying.huang@intel.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=apopple@nvidia.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=brice.goglin@gmail.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=dave@stgolabs.net \
    --cc=feng.tang@intel.com \
    --cc=gthelen@google.com \
    --cc=hesham.almatary@huawei.com \
    --cc=jvgediya@linux.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=rientjes@google.com \
    --cc=shy828301@gmail.com \
    --cc=tim.c.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox