diff options
author | Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> | 2022-08-18 18:40:36 +0530 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2022-09-26 19:46:11 -0700 |
commit | 7b88bda3761b95856cf97822efe8281c8100067b (patch) | |
tree | 4ba51c27eb9585883d9dca4271ecd9b03cb7c7b9 /mm/memory-tiers.c | |
parent | c6123a19c9f040e597f55f856c679651c26b31d1 (diff) | |
download | lwn-7b88bda3761b95856cf97822efe8281c8100067b.tar.gz lwn-7b88bda3761b95856cf97822efe8281c8100067b.zip |
mm/demotion/dax/kmem: set node's abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE
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_DEFAULT_DAX_ADISTANCE. Low-level drivers
like papr_scm or ACPI NFIT can initialize memory device type to a more
accurate value based on device tree details or HMAT. If the kernel
doesn't find the memory type initialized, a default slower memory type is
assigned by the kmem driver.
[aneesh.kumar@linux.ibm.com: assign correct memory type for multiple dax devices with the same node affinity]
Link: https://lkml.kernel.org/r/20220826100224.542312-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20220818131042.113280-5-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Jagdish Gediya <jvgediya.oss@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/memory-tiers.c')
-rw-r--r-- | mm/memory-tiers.c | 114 |
1 files changed, 91 insertions, 23 deletions
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index f74e077533ac..babc10a5cc13 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/types.h> -#include <linux/nodemask.h> #include <linux/slab.h> #include <linux/lockdep.h> #include <linux/sysfs.h> @@ -21,27 +19,15 @@ struct memory_tier { int adistance_start; }; -struct memory_dev_type { - /* list of memory types that are part of same tier as this type */ - struct list_head tier_sibiling; - /* abstract distance for this specific memory type */ - int adistance; - /* Nodes of same abstract distance */ - nodemask_t nodes; - struct memory_tier *memtier; +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]; -/* - * For now we can have 4 faster memory tiers with smaller adistance - * than default DRAM tier. - */ -static struct memory_dev_type default_dram_type = { - .adistance = MEMTIER_ADISTANCE_DRAM, - .tier_sibiling = LIST_HEAD_INIT(default_dram_type.tier_sibiling), -}; +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) { @@ -87,6 +73,24 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty return new_memtier; } +static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype) +{ + 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); + } +} + static struct memory_tier *set_node_memory_tier(int node) { struct memory_tier *memtier; @@ -97,10 +101,9 @@ static struct memory_tier *set_node_memory_tier(int node) if (!node_state(node, N_MEMORY)) return ERR_PTR(-EINVAL); - if (!node_memory_types[node]) - node_memory_types[node] = &default_dram_type; + __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; @@ -131,7 +134,7 @@ static bool clear_node_memory_tier(int node) 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); @@ -144,6 +147,63 @@ static bool clear_node_memory_tier(int node) return cleared; } +static void release_memtype(struct kref *kref) +{ + struct memory_dev_type *memtype; + + memtype = container_of(kref, struct memory_dev_type, kref); + kfree(memtype); +} + +struct memory_dev_type *alloc_memory_type(int adistance) +{ + struct memory_dev_type *memtype; + + memtype = kmalloc(sizeof(*memtype), GFP_KERNEL); + if (!memtype) + return ERR_PTR(-ENOMEM); + + memtype->adistance = adistance; + INIT_LIST_HEAD(&memtype->tier_sibiling); + memtype->nodes = NODE_MASK_NONE; + memtype->memtier = NULL; + kref_init(&memtype->kref); + return memtype; +} +EXPORT_SYMBOL_GPL(alloc_memory_type); + +void destroy_memory_type(struct memory_dev_type *memtype) +{ + kref_put(&memtype->kref, release_memtype); +} +EXPORT_SYMBOL_GPL(destroy_memory_type); + +void init_node_memory_type(int node, struct memory_dev_type *memtype) +{ + + mutex_lock(&memory_tier_lock); + __init_node_memory_type(node, memtype); + mutex_unlock(&memory_tier_lock); +} +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 == 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); +} +EXPORT_SYMBOL_GPL(clear_node_memory_type); + static int __meminit memtier_hotplug_callback(struct notifier_block *self, unsigned long action, void *_arg) { @@ -179,6 +239,14 @@ static int __init memory_tier_init(void) mutex_lock(&memory_tier_lock); /* + * For now we can have 4 faster memory tiers with smaller adistance + * than default DRAM tier. + */ + default_dram_type = alloc_memory_type(MEMTIER_ADISTANCE_DRAM); + if (!default_dram_type) + panic("%s() failed to allocate default DRAM tier\n", __func__); + + /* * Look at all the existing N_MEMORY nodes and add them to * default memory tier or to a tier if we already have memory * types assigned. |