The patch titled
Subject: memory tier: dax/kmem: introduce an abstract layer for finding, allocating, and putting memory types
has been added to the -mm mm-unstable branch. Its filename is
memory-tier-dax-kmem-introduce-an-abstract-layer-for-finding-allocating-and-putting-memory-types.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/memory-tier-dax-kmem-introduce-an-abstract-layer-for-finding-allocating-and-putting-memory-types.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: "Ho-Ren (Jack) Chuang" <horenchuang@xxxxxxxxxxxxx>
Subject: memory tier: dax/kmem: introduce an abstract layer for finding, allocating, and putting memory types
Date: Fri, 5 Apr 2024 00:07:05 +0000
Patch series "Improved Memory Tier Creation for CPUless NUMA Nodes", v11.
When a memory device, such as CXL1.1 type3 memory, is emulated as normal
memory (E820_TYPE_RAM), the memory device is indistinguishable from normal
DRAM in terms of memory tiering with the current implementation. The
current memory tiering assigns all detected normal memory nodes to the
same DRAM tier. This results in normal memory devices with different
attributions being unable to be assigned to the correct memory tier,
leading to the inability to migrate pages between different types of
memory.
https://lore.kernel.org/linux-mm/PH0PR08MB7955E9F08CCB64F23963B5C3A860A@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/T/
This patchset automatically resolves the issues. It delays the
initialization of memory tiers for CPUless NUMA nodes until they obtain
HMAT information and after all devices are initialized at boot time,
eliminating the need for user intervention. If no HMAT is specified, it
falls back to using `default_dram_type`.
Example usecase:
We have CXL memory on the host, and we create VMs with a new system memory
device backed by host CXL memory. We inject CXL memory performance
attributes through QEMU, and the guest now sees memory nodes with
performance attributes in HMAT. With this change, we enable the guest
kernel to construct the correct memory tiering for the memory nodes.
This patch (of 2):
Since different memory devices require finding, allocating, and putting
memory types, these common steps are abstracted in this patch, enhancing
the scalability and conciseness of the code.
Link: https://lkml.kernel.org/r/20240405000707.2670063-1-horenchuang@xxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/20240405000707.2670063-2-horenchuang@xxxxxxxxxxxxx
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@xxxxxxxxxxxxx>
Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Cc: Alistair Popple <apopple@xxxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: Gregory Price <gourry.memverge@xxxxxxxxx>
Cc: Hao Xiang <hao.xiang@xxxxxxxxxxxxx>
Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Ravi Jonnalagadda <ravis.opensrc@xxxxxxxxxx>
Cc: SeongJae Park <sj@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/dax/kmem.c | 30 ++++--------------------------
include/linux/memory-tiers.h | 13 +++++++++++++
mm/memory-tiers.c | 29 +++++++++++++++++++++++++++++
3 files changed, 46 insertions(+), 26 deletions(-)
--- a/drivers/dax/kmem.c~memory-tier-dax-kmem-introduce-an-abstract-layer-for-finding-allocating-and-putting-memory-types
+++ a/drivers/dax/kmem.c
@@ -55,36 +55,14 @@ static LIST_HEAD(kmem_memory_types);
static struct memory_dev_type *kmem_find_alloc_memory_type(int adist)
{
- bool found = false;
- struct memory_dev_type *mtype;
-
- mutex_lock(&kmem_memory_type_lock);
- list_for_each_entry(mtype, &kmem_memory_types, list) {
- if (mtype->adistance == adist) {
- found = true;
- break;
- }
- }
- if (!found) {
- mtype = alloc_memory_type(adist);
- if (!IS_ERR(mtype))
- list_add(&mtype->list, &kmem_memory_types);
- }
- mutex_unlock(&kmem_memory_type_lock);
-
- return mtype;
+ guard(mutex)(&kmem_memory_type_lock);
+ return mt_find_alloc_memory_type(adist, &kmem_memory_types);
}
static void kmem_put_memory_types(void)
{
- struct memory_dev_type *mtype, *mtn;
-
- mutex_lock(&kmem_memory_type_lock);
- list_for_each_entry_safe(mtype, mtn, &kmem_memory_types, list) {
- list_del(&mtype->list);
- put_memory_type(mtype);
- }
- mutex_unlock(&kmem_memory_type_lock);
+ guard(mutex)(&kmem_memory_type_lock);
+ mt_put_memory_types(&kmem_memory_types);
}
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
--- a/include/linux/memory-tiers.h~memory-tier-dax-kmem-introduce-an-abstract-layer-for-finding-allocating-and-putting-memory-types
+++ a/include/linux/memory-tiers.h
@@ -48,6 +48,9 @@ int mt_calc_adistance(int node, int *adi
int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
const char *source);
int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
+struct memory_dev_type *mt_find_alloc_memory_type(int adist,
+ struct list_head *memory_types);
+void mt_put_memory_types(struct list_head *memory_types);
#ifdef CONFIG_MIGRATION
int next_demotion_node(int node);
void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -136,5 +139,15 @@ static inline int mt_perf_to_adistance(s
{
return -EIO;
}
+
+static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist,
+ struct list_head *memory_types)
+{
+ return NULL;
+}
+
+static inline void mt_put_memory_types(struct list_head *memory_types)
+{
+}
#endif /* CONFIG_NUMA */
#endif /* _LINUX_MEMORY_TIERS_H */
--- a/mm/memory-tiers.c~memory-tier-dax-kmem-introduce-an-abstract-layer-for-finding-allocating-and-putting-memory-types
+++ a/mm/memory-tiers.c
@@ -623,6 +623,35 @@ void clear_node_memory_type(int node, st
}
EXPORT_SYMBOL_GPL(clear_node_memory_type);
+struct memory_dev_type *mt_find_alloc_memory_type(int adist, struct list_head *memory_types)
+{
+ struct memory_dev_type *mtype;
+
+ list_for_each_entry(mtype, memory_types, list)
+ if (mtype->adistance == adist)
+ return mtype;
+
+ mtype = alloc_memory_type(adist);
+ if (IS_ERR(mtype))
+ return mtype;
+
+ list_add(&mtype->list, memory_types);
+
+ return mtype;
+}
+EXPORT_SYMBOL_GPL(mt_find_alloc_memory_type);
+
+void mt_put_memory_types(struct list_head *memory_types)
+{
+ struct memory_dev_type *mtype, *mtn;
+
+ list_for_each_entry_safe(mtype, mtn, memory_types, list) {
+ list_del(&mtype->list);
+ put_memory_type(mtype);
+ }
+}
+EXPORT_SYMBOL_GPL(mt_put_memory_types);
+
static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix)
{
pr_info(
_
Patches currently in -mm which might be from horenchuang@xxxxxxxxxxxxx are
memory-tier-dax-kmem-introduce-an-abstract-layer-for-finding-allocating-and-putting-memory-types.patch
memory-tier-create-cpuless-memory-tiers-after-obtaining-hmat-info.patch
