* [PATCH v2 1/5] mm/memory_hotplug: pass online_type to online_memory_block() via arg
2026-01-14 23:50 [PATCH v2 0/5] add runtime hotplug state control Gregory Price
@ 2026-01-14 23:50 ` Gregory Price
2026-01-14 23:50 ` [PATCH v2 2/5] mm/memory_hotplug: add 'online_type' argument to add_memory_driver_managed Gregory Price
` (3 subsequent siblings)
4 siblings, 0 replies; 8+ messages in thread
From: Gregory Price @ 2026-01-14 23:50 UTC (permalink / raw)
To: linux-mm
Cc: linux-cxl, nvdimm, linux-kernel, virtualization, kernel-team,
dan.j.williams, vishal.l.verma, dave.jiang, david, mst, jasowang,
xuanzhuo, eperezma, osalvador, akpm
Modify online_memory_block() to accept the online type through its arg
parameter rather than calling mhp_get_default_online_type() internally.
This prepares for allowing callers to specify explicit online types.
Update the caller in add_memory_resource() to pass the default online
type via a local variable. No functional change.
Acked-by: David Hildenbrand (Red Hat) <david@kernel.org>
Signed-off-by: Gregory Price <gourry@gourry.net>
---
mm/memory_hotplug.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 389989a28abe..5718556121f0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1337,7 +1337,9 @@ static int check_hotplug_memory_range(u64 start, u64 size)
static int online_memory_block(struct memory_block *mem, void *arg)
{
- mem->online_type = mhp_get_default_online_type();
+ int *online_type = arg;
+
+ mem->online_type = *online_type;
return device_online(&mem->dev);
}
@@ -1578,8 +1580,12 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
merge_system_ram_resource(res);
/* online pages if requested */
- if (mhp_get_default_online_type() != MMOP_OFFLINE)
- walk_memory_blocks(start, size, NULL, online_memory_block);
+ if (mhp_get_default_online_type() != MMOP_OFFLINE) {
+ int online_type = mhp_get_default_online_type();
+
+ walk_memory_blocks(start, size, &online_type,
+ online_memory_block);
+ }
return ret;
error:
--
2.52.0
^ permalink raw reply [flat|nested] 8+ messages in thread* [PATCH v2 2/5] mm/memory_hotplug: add 'online_type' argument to add_memory_driver_managed
2026-01-14 23:50 [PATCH v2 0/5] add runtime hotplug state control Gregory Price
2026-01-14 23:50 ` [PATCH v2 1/5] mm/memory_hotplug: pass online_type to online_memory_block() via arg Gregory Price
@ 2026-01-14 23:50 ` Gregory Price
2026-01-14 23:50 ` [PATCH v2 3/5] dax/kmem: extract hotplug/hotremove helper functions Gregory Price
` (2 subsequent siblings)
4 siblings, 0 replies; 8+ messages in thread
From: Gregory Price @ 2026-01-14 23:50 UTC (permalink / raw)
To: linux-mm
Cc: linux-cxl, nvdimm, linux-kernel, virtualization, kernel-team,
dan.j.williams, vishal.l.verma, dave.jiang, david, mst, jasowang,
xuanzhuo, eperezma, osalvador, akpm
Enable external callers to select how to online the memory rather than
implicitly depending on the system defauilt.
Refactor: Extract __add_memory_resource to take an explicit online type,
and update add_memory_resource to pass the system default.
Export mhp_get_default_online_type() and update existing callers of
add_memory_driver_managed to use it explicitly to make it clear what the
behavior of the function is.
dax_kmem and virtio_mem drivers were updated.
Signed-off-by: Gregory Price <gourry@gourry.net>
---
drivers/dax/kmem.c | 3 ++-
drivers/virtio/virtio_mem.c | 3 ++-
include/linux/memory_hotplug.h | 2 +-
mm/memory_hotplug.c | 31 +++++++++++++++++++++++--------
4 files changed, 28 insertions(+), 11 deletions(-)
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index c036e4d0b610..bb13d9ced2e9 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -175,7 +175,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
* this as RAM automatically.
*/
rc = add_memory_driver_managed(data->mgid, range.start,
- range_len(&range), kmem_name, mhp_flags);
+ range_len(&range), kmem_name, mhp_flags,
+ mhp_get_default_online_type());
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 1688ecd69a04..63c0b2b235ab 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -654,7 +654,8 @@ static int virtio_mem_add_memory(struct virtio_mem *vm, uint64_t addr,
/* Memory might get onlined immediately. */
atomic64_add(size, &vm->offline_size);
rc = add_memory_driver_managed(vm->mgid, addr, size, vm->resource_name,
- MHP_MERGE_RESOURCE | MHP_NID_IS_MGID);
+ MHP_MERGE_RESOURCE | MHP_NID_IS_MGID,
+ mhp_get_default_online_type());
if (rc) {
atomic64_sub(size, &vm->offline_size);
dev_warn(&vm->vdev->dev, "adding memory failed: %d\n", rc);
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index f2f16cdd73ee..b68bc410db67 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -295,7 +295,7 @@ extern int add_memory_resource(int nid, struct resource *resource,
mhp_t mhp_flags);
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
const char *resource_name,
- mhp_t mhp_flags);
+ mhp_t mhp_flags, int online_type);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages,
struct vmem_altmap *altmap, int migratetype,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5718556121f0..2b4e31161fc1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -239,6 +239,7 @@ int mhp_get_default_online_type(void)
return mhp_default_online_type;
}
+EXPORT_SYMBOL_GPL(mhp_get_default_online_type);
void mhp_set_default_online_type(int online_type)
{
@@ -1490,7 +1491,8 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
*
* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
*/
-int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
+static int __add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags,
+ int online_type)
{
struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
enum memblock_flags memblock_flags = MEMBLOCK_NONE;
@@ -1580,12 +1582,9 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
merge_system_ram_resource(res);
/* online pages if requested */
- if (mhp_get_default_online_type() != MMOP_OFFLINE) {
- int online_type = mhp_get_default_online_type();
-
+ if (online_type != MMOP_OFFLINE)
walk_memory_blocks(start, size, &online_type,
online_memory_block);
- }
return ret;
error:
@@ -1601,7 +1600,13 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
return ret;
}
-/* requires device_hotplug_lock, see add_memory_resource() */
+int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
+{
+ return __add_memory_resource(nid, res, mhp_flags,
+ mhp_get_default_online_type());
+}
+
+/* requires device_hotplug_lock, see __add_memory_resource() */
int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
{
struct resource *res;
@@ -1649,9 +1654,16 @@ EXPORT_SYMBOL_GPL(add_memory);
*
* The resource_name (visible via /proc/iomem) has to have the format
* "System RAM ($DRIVER)".
+ *
+ * @online_type specifies the online behavior: MMOP_ONLINE, MMOP_ONLINE_KERNEL,
+ * MMOP_ONLINE_MOVABLE to online with that type, MMOP_OFFLINE to leave offline.
+ * Users that want the system default should call mhp_get_default_online_type().
+ *
+ * Returns 0 on success, negative error code on failure.
*/
int add_memory_driver_managed(int nid, u64 start, u64 size,
- const char *resource_name, mhp_t mhp_flags)
+ const char *resource_name, mhp_t mhp_flags,
+ int online_type)
{
struct resource *res;
int rc;
@@ -1661,6 +1673,9 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
resource_name[strlen(resource_name) - 1] != ')')
return -EINVAL;
+ if (online_type < 0 || online_type > MMOP_ONLINE_MOVABLE)
+ return -EINVAL;
+
lock_device_hotplug();
res = register_memory_resource(start, size, resource_name);
@@ -1669,7 +1684,7 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
goto out_unlock;
}
- rc = add_memory_resource(nid, res, mhp_flags);
+ rc = __add_memory_resource(nid, res, mhp_flags, online_type);
if (rc < 0)
release_memory_resource(res);
--
2.52.0
^ permalink raw reply [flat|nested] 8+ messages in thread* [PATCH v2 3/5] dax/kmem: extract hotplug/hotremove helper functions
2026-01-14 23:50 [PATCH v2 0/5] add runtime hotplug state control Gregory Price
2026-01-14 23:50 ` [PATCH v2 1/5] mm/memory_hotplug: pass online_type to online_memory_block() via arg Gregory Price
2026-01-14 23:50 ` [PATCH v2 2/5] mm/memory_hotplug: add 'online_type' argument to add_memory_driver_managed Gregory Price
@ 2026-01-14 23:50 ` Gregory Price
2026-01-14 23:50 ` [PATCH v2 4/5] dax/kmem: add sysfs interface for runtime hotplug state control Gregory Price
2026-01-14 23:50 ` [PATCH v2 5/5] dax/kmem: add memory notifier to block external state changes Gregory Price
4 siblings, 0 replies; 8+ messages in thread
From: Gregory Price @ 2026-01-14 23:50 UTC (permalink / raw)
To: linux-mm
Cc: linux-cxl, nvdimm, linux-kernel, virtualization, kernel-team,
dan.j.williams, vishal.l.verma, dave.jiang, david, mst, jasowang,
xuanzhuo, eperezma, osalvador, akpm
Refactor kmem _probe() _remove() by extracting init, cleanup, hotplug,
and hot-remove logic into separate helper functions:
- dax_kmem_init_resources: inits IO_RESOURCE w/ request_mem_region
- dax_kmem_cleanup_resources: cleans up initialized IO_RESOURCE
- dax_kmem_do_hotplug: handles memory region reservation and adding
- dax_kmem_do_hotremove: handles memory removal and resource cleanup
This is a pure refactoring with no functional change. The helpers will
enable future extensions to support more granular control over memory
hotplug operations.
We need to split hotplug/remove and init/cleanup in order to have the
resources available for hot-add. Otherwise, when probe occurs, the dax
devices are never added to sysfs because the resources are never
registered.
Signed-off-by: Gregory Price <gourry@gourry.net>
---
drivers/dax/kmem.c | 300 +++++++++++++++++++++++++++++++--------------
1 file changed, 206 insertions(+), 94 deletions(-)
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index bb13d9ced2e9..3929cb8576de 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -65,14 +65,185 @@ static void kmem_put_memory_types(void)
mt_put_memory_types(&kmem_memory_types);
}
+/**
+ * dax_kmem_do_hotplug - hotplug memory for dax kmem device
+ * @dev_dax: the dev_dax instance
+ * @data: the dax_kmem_data structure with resource tracking
+ *
+ * Hotplugs all ranges in the dev_dax region as system memory.
+ *
+ * Returns the number of successfully mapped ranges, or negative error.
+ */
+static int dax_kmem_do_hotplug(struct dev_dax *dev_dax,
+ struct dax_kmem_data *data,
+ int online_type)
+{
+ struct device *dev = &dev_dax->dev;
+ int i, rc, onlined = 0;
+ mhp_t mhp_flags;
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range range;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc)
+ continue;
+
+ mhp_flags = MHP_NID_IS_MGID;
+ if (dev_dax->memmap_on_memory)
+ mhp_flags |= MHP_MEMMAP_ON_MEMORY;
+
+ /*
+ * Ensure that future kexec'd kernels will not treat
+ * this as RAM automatically.
+ */
+ rc = add_memory_driver_managed(data->mgid, range.start,
+ range_len(&range), kmem_name, mhp_flags,
+ online_type);
+
+ if (rc) {
+ dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
+ i, range.start, range.end);
+ if (onlined)
+ continue;
+ return rc;
+ }
+ onlined++;
+ }
+
+ return onlined;
+}
+
+/**
+ * dax_kmem_init_resources - create memory regions for dax kmem
+ * @dev_dax: the dev_dax instance
+ * @data: the dax_kmem_data structure with resource tracking
+ *
+ * Initializes all the resources for the DAX
+ *
+ * Returns the number of successfully mapped ranges, or negative error.
+ */
+static int dax_kmem_init_resources(struct dev_dax *dev_dax,
+ struct dax_kmem_data *data)
+{
+ struct device *dev = &dev_dax->dev;
+ int i, rc, mapped = 0;
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct resource *res;
+ struct range range;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc)
+ continue;
+
+ /* Skip ranges already added */
+ if (data->res[i])
+ continue;
+
+ /* Region is permanently reserved if hotremove fails. */
+ res = request_mem_region(range.start, range_len(&range),
+ data->res_name);
+ if (!res) {
+ dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
+ i, range.start, range.end);
+ /*
+ * Once some memory has been onlined we can't
+ * assume that it can be un-onlined safely.
+ */
+ if (mapped)
+ continue;
+ return -EBUSY;
+ }
+ data->res[i] = res;
+ /*
+ * Set flags appropriate for System RAM. Leave ..._BUSY clear
+ * so that add_memory() can add a child resource. Do not
+ * inherit flags from the parent since it may set new flags
+ * unknown to us that will break add_memory() below.
+ */
+ res->flags = IORESOURCE_SYSTEM_RAM;
+ mapped++;
+ }
+ return mapped;
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/**
+ * dax_kmem_do_hotremove - hot-remove memory for dax kmem device
+ * @dev_dax: the dev_dax instance
+ * @data: the dax_kmem_data structure with resource tracking
+ *
+ * Removes all ranges in the dev_dax region.
+ *
+ * Returns the number of successfully removed ranges.
+ */
+static int dax_kmem_do_hotremove(struct dev_dax *dev_dax,
+ struct dax_kmem_data *data)
+{
+ struct device *dev = &dev_dax->dev;
+ int i, success = 0;
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range range;
+ int rc;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc)
+ continue;
+
+ /* Skip ranges not currently added */
+ if (!data->res[i])
+ continue;
+
+ rc = remove_memory(range.start, range_len(&range));
+ if (rc == 0) {
+ success++;
+ continue;
+ }
+ any_hotremove_failed = true;
+ dev_err(dev, "mapping%d: %#llx-%#llx hotremove failed\n",
+ i, range.start, range.end);
+ }
+
+ return success;
+}
+#else
+static int dax_kmem_do_hotremove(struct dev_dax *dev_dax,
+ struct dax_kmem_data *data)
+{
+ return -ENOSUPP;
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+/**
+ * dax_kmem_cleanup_resources - remove the dax memory resources
+ * @dev_dax: the dev_dax instance
+ * @data: the dax_kmem_data structure with resource tracking
+ *
+ * Removes all resources in the dev_dax region.
+ */
+static void dax_kmem_cleanup_resources(struct dev_dax *dev_dax,
+ struct dax_kmem_data *data)
+{
+ int i;
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ if (!data->res[i])
+ continue;
+ remove_resource(data->res[i]);
+ kfree(data->res[i]);
+ data->res[i] = NULL;
+ }
+}
+
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
unsigned long total_len = 0, orig_len = 0;
struct dax_kmem_data *data;
struct memory_dev_type *mtype;
- int i, rc, mapped = 0;
- mhp_t mhp_flags;
+ int i, rc;
int numa_node;
int adist = MEMTIER_DEFAULT_DAX_ADISTANCE;
@@ -134,68 +305,26 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
goto err_reg_mgid;
data->mgid = rc;
- for (i = 0; i < dev_dax->nr_range; i++) {
- struct resource *res;
- struct range range;
-
- rc = dax_kmem_range(dev_dax, i, &range);
- if (rc)
- continue;
-
- /* Region is permanently reserved if hotremove fails. */
- res = request_mem_region(range.start, range_len(&range), data->res_name);
- if (!res) {
- dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
- i, range.start, range.end);
- /*
- * Once some memory has been onlined we can't
- * assume that it can be un-onlined safely.
- */
- if (mapped)
- continue;
- rc = -EBUSY;
- goto err_request_mem;
- }
- data->res[i] = res;
-
- /*
- * Set flags appropriate for System RAM. Leave ..._BUSY clear
- * so that add_memory() can add a child resource. Do not
- * inherit flags from the parent since it may set new flags
- * unknown to us that will break add_memory() below.
- */
- res->flags = IORESOURCE_SYSTEM_RAM;
-
- mhp_flags = MHP_NID_IS_MGID;
- if (dev_dax->memmap_on_memory)
- mhp_flags |= MHP_MEMMAP_ON_MEMORY;
-
- /*
- * Ensure that future kexec'd kernels will not treat
- * this as RAM automatically.
- */
- rc = add_memory_driver_managed(data->mgid, range.start,
- range_len(&range), kmem_name, mhp_flags,
- mhp_get_default_online_type());
+ dev_set_drvdata(dev, data);
- if (rc) {
- dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
- i, range.start, range.end);
- remove_resource(res);
- kfree(res);
- data->res[i] = NULL;
- if (mapped)
- continue;
- goto err_request_mem;
- }
- mapped++;
- }
+ rc = dax_kmem_init_resources(dev_dax, data);
+ if (rc < 0)
+ goto err_resources;
- dev_set_drvdata(dev, data);
+ /*
+ * Hotplug using the system default policy - this preserves backwards
+ * for existing users who rely on the default auto-online behavior.
+ */
+ rc = dax_kmem_do_hotplug(dev_dax, data, mhp_get_default_online_type());
+ if (rc < 0)
+ goto err_hotplug;
return 0;
-err_request_mem:
+err_hotplug:
+ dax_kmem_cleanup_resources(dev_dax, data);
+err_resources:
+ dev_set_drvdata(dev, NULL);
memory_group_unregister(data->mgid);
err_reg_mgid:
kfree(data->res_name);
@@ -209,7 +338,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
#ifdef CONFIG_MEMORY_HOTREMOVE
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
{
- int i, success = 0;
+ int success;
int node = dev_dax->target_node;
struct device *dev = &dev_dax->dev;
struct dax_kmem_data *data = dev_get_drvdata(dev);
@@ -220,42 +349,25 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
* there is no way to hotremove this memory until reboot because device
* unbind will succeed even if we return failure.
*/
- for (i = 0; i < dev_dax->nr_range; i++) {
- struct range range;
- int rc;
-
- rc = dax_kmem_range(dev_dax, i, &range);
- if (rc)
- continue;
-
- rc = remove_memory(range.start, range_len(&range));
- if (rc == 0) {
- remove_resource(data->res[i]);
- kfree(data->res[i]);
- data->res[i] = NULL;
- success++;
- continue;
- }
- any_hotremove_failed = true;
- dev_err(dev,
- "mapping%d: %#llx-%#llx cannot be hotremoved until the next reboot\n",
- i, range.start, range.end);
+ success = dax_kmem_do_hotremove(dev_dax, data);
+ if (success < dev_dax->nr_range) {
+ dev_err(dev, "Hotplug regions stuck online until reboot\n");
+ return;
}
- if (success >= dev_dax->nr_range) {
- memory_group_unregister(data->mgid);
- kfree(data->res_name);
- kfree(data);
- dev_set_drvdata(dev, NULL);
- /*
- * Clear the memtype association on successful unplug.
- * If not, we have memory blocks left which can be
- * offlined/onlined later. We need to keep memory_dev_type
- * for that. This implies this reference will be around
- * till next reboot.
- */
- clear_node_memory_type(node, NULL);
- }
+ dax_kmem_cleanup_resources(dev_dax, data);
+ memory_group_unregister(data->mgid);
+ kfree(data->res_name);
+ kfree(data);
+ dev_set_drvdata(dev, NULL);
+ /*
+ * Clear the memtype association on successful unplug.
+ * If not, we have memory blocks left which can be
+ * offlined/onlined later. We need to keep memory_dev_type
+ * for that. This implies this reference will be around
+ * till next reboot.
+ */
+ clear_node_memory_type(node, NULL);
}
#else
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
--
2.52.0
^ permalink raw reply [flat|nested] 8+ messages in thread* [PATCH v2 4/5] dax/kmem: add sysfs interface for runtime hotplug state control
2026-01-14 23:50 [PATCH v2 0/5] add runtime hotplug state control Gregory Price
` (2 preceding siblings ...)
2026-01-14 23:50 ` [PATCH v2 3/5] dax/kmem: extract hotplug/hotremove helper functions Gregory Price
@ 2026-01-14 23:50 ` Gregory Price
2026-01-14 23:50 ` [PATCH v2 5/5] dax/kmem: add memory notifier to block external state changes Gregory Price
4 siblings, 0 replies; 8+ messages in thread
From: Gregory Price @ 2026-01-14 23:50 UTC (permalink / raw)
To: linux-mm
Cc: linux-cxl, nvdimm, linux-kernel, virtualization, kernel-team,
dan.j.williams, vishal.l.verma, dave.jiang, david, mst, jasowang,
xuanzhuo, eperezma, osalvador, akpm, Hannes Reinecke
The dax kmem driver currently onlines memory automatically during
probe using the system's default online policy but provides no way
to control or query the entire region state at runtime.
There is no atomic to offline and remove memory blocks together.
Add a new 'hotplug' sysfs attribute that allows userspace to control
and query the entire memory region state.
The interface supports the following states:
- "unplug": memory is offline and blocks are not present
- "online": memory is online as normal system RAM
- "online_movable": memory is online in ZONE_MOVABLE
Valid transitions:
- unplugged -> online
- unplugged -> online_movable
- online -> unplugged
- online_movable -> unplugged
"offline" (memory blocks exist but are offline by default) is not
supported because it's functionally equivalent to "unplugged" and
entices races between offlining and unplugging.
The initial state after probe uses mhp_get_default_online_type() to
preserve backwards compatibility - existing systems with auto-online
policies will continue to work as before.
As with any hot-remove mechanism, the removal can fail and if rollback
fails the system can be left in an inconsistent state.
Unbind Note:
We used to call remove_memory() during unbind, which would fire a
BUG() if any of the memory blocks were online at that time. We lift
this into a WARN in the cleanup routine and don't attempt hotremove
if ->state is not DAX_KMEM_UNPLUGGED.
The resources are still leaked but this prevents deadlock on unbind
if a memory region happens to be impossible to hotremove.
Suggested-by: Hannes Reinecke <hare@suse.de>
Suggested-by: David Hildenbrand <david@kernel.org>
Signed-off-by: Gregory Price <gourry@gourry.net>
---
Documentation/ABI/testing/sysfs-bus-dax | 17 +++
drivers/dax/kmem.c | 159 +++++++++++++++++++++---
2 files changed, 156 insertions(+), 20 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-bus-dax b/Documentation/ABI/testing/sysfs-bus-dax
index b34266bfae49..faf6f63a368c 100644
--- a/Documentation/ABI/testing/sysfs-bus-dax
+++ b/Documentation/ABI/testing/sysfs-bus-dax
@@ -151,3 +151,20 @@ Description:
memmap_on_memory parameter for memory_hotplug. This is
typically set on the kernel command line -
memory_hotplug.memmap_on_memory set to 'true' or 'force'."
+
+What: /sys/bus/dax/devices/daxX.Y/hotplug
+Date: January, 2026
+KernelVersion: v6.21
+Contact: nvdimm@lists.linux.dev
+Description:
+ (RW) Controls what hotplug state of the memory region.
+ Applies to all memory blocks associated with the device.
+ Only applies to dax_kmem devices.
+
+ States: [unplugged, online, online_movable]
+ Arguments:
+ "unplug": memory is offline and blocks are not present
+ "online": memory is online as normal system RAM
+ "online_movable": memory is online in ZONE_MOVABLE
+
+ Devices must unplug to online into a different state.
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 3929cb8576de..c222ae9d675d 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -44,9 +44,15 @@ static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
return 0;
}
+#define DAX_KMEM_UNPLUGGED (-1)
+
struct dax_kmem_data {
const char *res_name;
int mgid;
+ int numa_node;
+ struct dev_dax *dev_dax;
+ int state;
+ struct mutex lock; /* protects hotplug state transitions */
struct resource *res[];
};
@@ -69,8 +75,10 @@ static void kmem_put_memory_types(void)
* dax_kmem_do_hotplug - hotplug memory for dax kmem device
* @dev_dax: the dev_dax instance
* @data: the dax_kmem_data structure with resource tracking
+ * @online_type: MMOP_ONLINE or MMOP_ONLINE_MOVABLE
*
- * Hotplugs all ranges in the dev_dax region as system memory.
+ * Hotplugs all ranges in the dev_dax region as system memory using
+ * the specified online type.
*
* Returns the number of successfully mapped ranges, or negative error.
*/
@@ -82,6 +90,12 @@ static int dax_kmem_do_hotplug(struct dev_dax *dev_dax,
int i, rc, onlined = 0;
mhp_t mhp_flags;
+ if (data->state == MMOP_ONLINE || data->state == MMOP_ONLINE_MOVABLE)
+ return -EINVAL;
+
+ if (online_type != MMOP_ONLINE && online_type != MMOP_ONLINE_MOVABLE)
+ return -EINVAL;
+
for (i = 0; i < dev_dax->nr_range; i++) {
struct range range;
@@ -174,9 +188,9 @@ static int dax_kmem_init_resources(struct dev_dax *dev_dax,
* @dev_dax: the dev_dax instance
* @data: the dax_kmem_data structure with resource tracking
*
- * Removes all ranges in the dev_dax region.
+ * Offlines and removes all ranges in the dev_dax region.
*
- * Returns the number of successfully removed ranges.
+ * Returns the number of successfully removed ranges, or negative error.
*/
static int dax_kmem_do_hotremove(struct dev_dax *dev_dax,
struct dax_kmem_data *data)
@@ -196,7 +210,7 @@ static int dax_kmem_do_hotremove(struct dev_dax *dev_dax,
if (!data->res[i])
continue;
- rc = remove_memory(range.start, range_len(&range));
+ rc = offline_and_remove_memory(range.start, range_len(&range));
if (rc == 0) {
success++;
continue;
@@ -228,6 +242,21 @@ static void dax_kmem_cleanup_resources(struct dev_dax *dev_dax,
{
int i;
+ /*
+ * If the device unbind occurs before memory is hotremoved, we can never
+ * remove the memory (requires reboot). Attempting an offline operation
+ * here may cause deadlock and a failure to finish the unbind.
+ *
+ * This WARN used to be a BUG called by remove_memory().
+ *
+ * Note: This leaks the resources.
+ */
+ if (data->state != DAX_KMEM_UNPLUGGED) {
+ WARN(data->state != DAX_KMEM_UNPLUGGED,
+ "Hotplug memory regions stuck online until reboot");
+ return;
+ }
+
for (i = 0; i < dev_dax->nr_range; i++) {
if (!data->res[i])
continue;
@@ -237,6 +266,91 @@ static void dax_kmem_cleanup_resources(struct dev_dax *dev_dax,
}
}
+static int dax_kmem_parse_state(const char *buf)
+{
+ if (sysfs_streq(buf, "unplug"))
+ return DAX_KMEM_UNPLUGGED;
+ if (sysfs_streq(buf, "online"))
+ return MMOP_ONLINE;
+ if (sysfs_streq(buf, "online_movable"))
+ return MMOP_ONLINE_MOVABLE;
+ return -EINVAL;
+}
+
+static ssize_t hotplug_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dax_kmem_data *data = dev_get_drvdata(dev);
+ const char *state_str;
+
+ if (!data)
+ return -ENXIO;
+
+ switch (data->state) {
+ case DAX_KMEM_UNPLUGGED:
+ state_str = "unplugged";
+ break;
+ case MMOP_ONLINE:
+ state_str = "online";
+ break;
+ case MMOP_ONLINE_MOVABLE:
+ state_str = "online_movable";
+ break;
+ default:
+ state_str = "unknown";
+ break;
+ }
+
+ return sysfs_emit(buf, "%s\n", state_str);
+}
+
+static ssize_t hotplug_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct dev_dax *dev_dax = to_dev_dax(dev);
+ struct dax_kmem_data *data = dev_get_drvdata(dev);
+ int online_type;
+ int rc;
+
+ if (!data)
+ return -ENXIO;
+
+ online_type = dax_kmem_parse_state(buf);
+ if (online_type < DAX_KMEM_UNPLUGGED)
+ return online_type;
+
+ guard(mutex)(&data->lock);
+
+ /* Already in requested state */
+ if (data->state == online_type)
+ return len;
+
+ if (online_type == DAX_KMEM_UNPLUGGED) {
+ rc = dax_kmem_do_hotremove(dev_dax, data);
+ if (rc < 0) {
+ dev_warn(dev, "hotplug state is inconsistent\n");
+ return rc;
+ }
+ data->state = DAX_KMEM_UNPLUGGED;
+ return len;
+ }
+
+ /*
+ * online_type is MMOP_ONLINE or MMOP_ONLINE_MOVABLE
+ * Cannot switch between online types without unplugging first
+ */
+ if (data->state == MMOP_ONLINE || data->state == MMOP_ONLINE_MOVABLE)
+ return -EBUSY;
+
+ rc = dax_kmem_do_hotplug(dev_dax, data, online_type);
+ if (rc < 0)
+ return rc;
+
+ data->state = online_type;
+ return len;
+}
+static DEVICE_ATTR_RW(hotplug);
+
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
@@ -246,6 +360,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
int i, rc;
int numa_node;
int adist = MEMTIER_DEFAULT_DAX_ADISTANCE;
+ int online_type;
/*
* Ensure good NUMA information for the persistent memory.
@@ -304,6 +419,10 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
if (rc < 0)
goto err_reg_mgid;
data->mgid = rc;
+ data->numa_node = numa_node;
+ data->dev_dax = dev_dax;
+ data->state = DAX_KMEM_UNPLUGGED;
+ mutex_init(&data->lock);
dev_set_drvdata(dev, data);
@@ -315,9 +434,17 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
* Hotplug using the system default policy - this preserves backwards
* for existing users who rely on the default auto-online behavior.
*/
- rc = dax_kmem_do_hotplug(dev_dax, data, mhp_get_default_online_type());
- if (rc < 0)
- goto err_hotplug;
+ online_type = mhp_get_default_online_type();
+ if (online_type != MMOP_OFFLINE) {
+ rc = dax_kmem_do_hotplug(dev_dax, data, online_type);
+ if (rc < 0)
+ goto err_hotplug;
+ data->state = online_type;
+ }
+
+ rc = device_create_file(dev, &dev_attr_hotplug);
+ if (rc)
+ dev_warn(dev, "failed to create hotplug sysfs entry\n");
return 0;
@@ -338,23 +465,11 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
#ifdef CONFIG_MEMORY_HOTREMOVE
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
{
- int success;
int node = dev_dax->target_node;
struct device *dev = &dev_dax->dev;
struct dax_kmem_data *data = dev_get_drvdata(dev);
- /*
- * We have one shot for removing memory, if some memory blocks were not
- * offline prior to calling this function remove_memory() will fail, and
- * there is no way to hotremove this memory until reboot because device
- * unbind will succeed even if we return failure.
- */
- success = dax_kmem_do_hotremove(dev_dax, data);
- if (success < dev_dax->nr_range) {
- dev_err(dev, "Hotplug regions stuck online until reboot\n");
- return;
- }
-
+ device_remove_file(dev, &dev_attr_hotplug);
dax_kmem_cleanup_resources(dev_dax, data);
memory_group_unregister(data->mgid);
kfree(data->res_name);
@@ -372,6 +487,10 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
#else
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
{
+ struct device *dev = &dev_dax->dev;
+
+ device_remove_file(dev, &dev_attr_hotplug);
+
/*
* Without hotremove purposely leak the request_mem_region() for the
* device-dax range and return '0' to ->remove() attempts. The removal
--
2.52.0
^ permalink raw reply [flat|nested] 8+ messages in thread* [PATCH v2 5/5] dax/kmem: add memory notifier to block external state changes
2026-01-14 23:50 [PATCH v2 0/5] add runtime hotplug state control Gregory Price
` (3 preceding siblings ...)
2026-01-14 23:50 ` [PATCH v2 4/5] dax/kmem: add sysfs interface for runtime hotplug state control Gregory Price
@ 2026-01-14 23:50 ` Gregory Price
2026-01-15 2:42 ` [PATCH] dax/kmem: add build config for protected dax memory blocks Gregory Price
4 siblings, 1 reply; 8+ messages in thread
From: Gregory Price @ 2026-01-14 23:50 UTC (permalink / raw)
To: linux-mm
Cc: linux-cxl, nvdimm, linux-kernel, virtualization, kernel-team,
dan.j.williams, vishal.l.verma, dave.jiang, david, mst, jasowang,
xuanzhuo, eperezma, osalvador, akpm
Add a memory notifier to prevent external operations from changing the
online/offline state of memory blocks managed by dax_kmem. This ensures
state changes only occur through the driver's hotplug sysfs interface,
providing consistent state tracking and preventing races with auto-online
policies or direct memory block sysfs manipulation.
The goal of this is to prevent `daxN.M/hotplug` from becoming
inconsistent with the state of the memory blocks it owns.
The notifier uses a transition protocol with memory barriers:
- Before initiating a state change, set target_state then in_transition
- Use barrier to ensure target_state is visible before in_transition
- The notifier checks in_transition, then uses barrier before reading
target_state to ensure proper ordering on weakly-ordered architectures
The notifier callback:
- Returns NOTIFY_DONE for non-overlapping memory (not our concern)
- Returns NOTIFY_BAD if in_transition is false (block external ops)
- Validates the memory event matches target_state (MEM_GOING_ONLINE
for online operations, MEM_GOING_OFFLINE for offline/unplug)
- Returns NOTIFY_OK only for driver-initiated operations with matching
target_state
This prevents scenarios where:
- Users manually change memory state via /sys/devices/system/memory/
- Other kernel subsystems interfere with driver-managed memory state
(may be important for regions trying to preserve hot-unpluggability)
Signed-off-by: Gregory Price <gourry@gourry.net>
---
drivers/dax/kmem.c | 157 ++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 154 insertions(+), 3 deletions(-)
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index c222ae9d675d..f3562f65376c 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -53,6 +53,9 @@ struct dax_kmem_data {
struct dev_dax *dev_dax;
int state;
struct mutex lock; /* protects hotplug state transitions */
+ bool in_transition;
+ int target_state;
+ struct notifier_block mem_nb;
struct resource *res[];
};
@@ -71,6 +74,116 @@ static void kmem_put_memory_types(void)
mt_put_memory_types(&kmem_memory_types);
}
+/**
+ * dax_kmem_start_transition - begin a driver-initiated state transition
+ * @data: the dax_kmem_data structure
+ * @target: the target state (MMOP_ONLINE, MMOP_ONLINE_MOVABLE, or MMOP_OFFLINE)
+ *
+ * Sets up state for a driver-initiated memory operation. The memory notifier
+ * will only allow operations that match this target state while in transition.
+ * Uses store-release to ensure target_state is visible before in_transition.
+ */
+static void dax_kmem_start_transition(struct dax_kmem_data *data, int target)
+{
+ data->target_state = target;
+ smp_store_release(&data->in_transition, true);
+}
+
+/**
+ * dax_kmem_end_transition - end a driver-initiated state transition
+ * @data: the dax_kmem_data structure
+ *
+ * Clears the in_transition flag after a state change completes or aborts.
+ */
+static void dax_kmem_end_transition(struct dax_kmem_data *data)
+{
+ WRITE_ONCE(data->in_transition, false);
+}
+
+/**
+ * dax_kmem_overlaps_range - check if a memory range overlaps with this device
+ * @data: the dax_kmem_data structure
+ * @start: start physical address of the range to check
+ * @size: size of the range to check
+ *
+ * Returns true if the range overlaps with any of the device's memory ranges.
+ */
+static bool dax_kmem_overlaps_range(struct dax_kmem_data *data,
+ u64 start, u64 size)
+{
+ struct dev_dax *dev_dax = data->dev_dax;
+ int i;
+
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range range;
+ struct range check = DEFINE_RANGE(start, start + size - 1);
+
+ if (dax_kmem_range(dev_dax, i, &range))
+ continue;
+
+ if (!data->res[i])
+ continue;
+
+ if (range_overlaps(&range, &check))
+ return true;
+ }
+ return false;
+}
+
+/**
+ * dax_kmem_memory_notifier_cb - memory notifier callback for dax kmem
+ * @nb: the notifier block (embedded in dax_kmem_data)
+ * @action: the memory event (MEM_GOING_ONLINE, MEM_GOING_OFFLINE, etc.)
+ * @arg: pointer to memory_notify structure
+ *
+ * This callback prevents external operations (e.g., from sysfs or auto-online
+ * policies) on memory blocks managed by dax_kmem. Only operations initiated
+ * by the driver itself (via the hotplug sysfs interface) are allowed.
+ *
+ * Returns NOTIFY_OK to allow the operation, NOTIFY_BAD to block it,
+ * or NOTIFY_DONE if the memory doesn't belong to this device.
+ */
+static int dax_kmem_memory_notifier_cb(struct notifier_block *nb,
+ unsigned long action, void *arg)
+{
+ struct dax_kmem_data *data = container_of(nb, struct dax_kmem_data,
+ mem_nb);
+ struct memory_notify *mhp = arg;
+ const u64 start = PFN_PHYS(mhp->start_pfn);
+ const u64 size = PFN_PHYS(mhp->nr_pages);
+
+ /* Only interested in going online/offline events */
+ if (action != MEM_GOING_ONLINE && action != MEM_GOING_OFFLINE)
+ return NOTIFY_DONE;
+
+ /* Check if this memory belongs to our device */
+ if (!dax_kmem_overlaps_range(data, start, size))
+ return NOTIFY_DONE;
+
+ /*
+ * Block all operations unless we're in a driver-initiated transition.
+ * When in_transition is set, only allow operations that match our
+ * target_state to prevent races with external operations.
+ *
+ * Use load-acquire to pair with the store-release in
+ * dax_kmem_start_transition(), ensuring target_state is visible.
+ */
+ if (!smp_load_acquire(&data->in_transition))
+ return NOTIFY_BAD;
+
+ /* Online operations expect MEM_GOING_ONLINE */
+ if (action == MEM_GOING_ONLINE &&
+ (data->target_state == MMOP_ONLINE ||
+ data->target_state == MMOP_ONLINE_MOVABLE))
+ return NOTIFY_OK;
+
+ /* Offline/hotremove operations expect MEM_GOING_OFFLINE */
+ if (action == MEM_GOING_OFFLINE && data->target_state == MMOP_OFFLINE)
+ return NOTIFY_OK;
+
+ return NOTIFY_BAD;
+}
+
/**
* dax_kmem_do_hotplug - hotplug memory for dax kmem device
* @dev_dax: the dev_dax instance
@@ -325,11 +438,27 @@ static ssize_t hotplug_store(struct device *dev, struct device_attribute *attr,
if (data->state == online_type)
return len;
+ /*
+ * Start transition with target_state for the notifier.
+ * For unplug, use MMOP_OFFLINE since memory goes offline before removal.
+ */
+ if (online_type == DAX_KMEM_UNPLUGGED || online_type == MMOP_OFFLINE)
+ dax_kmem_start_transition(data, MMOP_OFFLINE);
+ else
+ dax_kmem_start_transition(data, online_type);
+
if (online_type == DAX_KMEM_UNPLUGGED) {
+ int expected = 0;
+
+ for (rc = 0; rc < dev_dax->nr_range; rc++)
+ if (data->res[rc])
+ expected++;
+
rc = dax_kmem_do_hotremove(dev_dax, data);
- if (rc < 0) {
+ dax_kmem_end_transition(data);
+ if (rc < expected) {
dev_warn(dev, "hotplug state is inconsistent\n");
- return rc;
+ return rc == 0 ? -EBUSY : -EIO;
}
data->state = DAX_KMEM_UNPLUGGED;
return len;
@@ -339,10 +468,14 @@ static ssize_t hotplug_store(struct device *dev, struct device_attribute *attr,
* online_type is MMOP_ONLINE or MMOP_ONLINE_MOVABLE
* Cannot switch between online types without unplugging first
*/
- if (data->state == MMOP_ONLINE || data->state == MMOP_ONLINE_MOVABLE)
+ if (data->state == MMOP_ONLINE || data->state == MMOP_ONLINE_MOVABLE) {
+ dax_kmem_end_transition(data);
return -EBUSY;
+ }
rc = dax_kmem_do_hotplug(dev_dax, data, online_type);
+ dax_kmem_end_transition(data);
+
if (rc < 0)
return rc;
@@ -430,13 +563,26 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
if (rc < 0)
goto err_resources;
+ /* Register memory notifier to block external operations */
+ data->mem_nb.notifier_call = dax_kmem_memory_notifier_cb;
+ rc = register_memory_notifier(&data->mem_nb);
+ if (rc) {
+ dev_warn(dev, "failed to register memory notifier\n");
+ goto err_notifier;
+ }
+
/*
* Hotplug using the system default policy - this preserves backwards
* for existing users who rely on the default auto-online behavior.
+ *
+ * Start transition with resolved system default since the notifier
+ * validates the operation type matches.
*/
online_type = mhp_get_default_online_type();
if (online_type != MMOP_OFFLINE) {
+ dax_kmem_start_transition(data, online_type);
rc = dax_kmem_do_hotplug(dev_dax, data, online_type);
+ dax_kmem_end_transition(data);
if (rc < 0)
goto err_hotplug;
data->state = online_type;
@@ -449,6 +595,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return 0;
err_hotplug:
+ unregister_memory_notifier(&data->mem_nb);
+err_notifier:
dax_kmem_cleanup_resources(dev_dax, data);
err_resources:
dev_set_drvdata(dev, NULL);
@@ -471,6 +619,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
device_remove_file(dev, &dev_attr_hotplug);
dax_kmem_cleanup_resources(dev_dax, data);
+ unregister_memory_notifier(&data->mem_nb);
memory_group_unregister(data->mgid);
kfree(data->res_name);
kfree(data);
@@ -488,8 +637,10 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
+ struct dax_kmem_data *data = dev_get_drvdata(dev);
device_remove_file(dev, &dev_attr_hotplug);
+ unregister_memory_notifier(&data->mem_nb);
/*
* Without hotremove purposely leak the request_mem_region() for the
--
2.52.0
^ permalink raw reply [flat|nested] 8+ messages in thread* [PATCH] dax/kmem: add build config for protected dax memory blocks
2026-01-14 23:50 ` [PATCH v2 5/5] dax/kmem: add memory notifier to block external state changes Gregory Price
@ 2026-01-15 2:42 ` Gregory Price
0 siblings, 0 replies; 8+ messages in thread
From: Gregory Price @ 2026-01-15 2:42 UTC (permalink / raw)
To: linux-mm
Cc: linux-cxl, nvdimm, linux-kernel, virtualization, kernel-team,
dan.j.williams, vishal.l.verma, dave.jiang, david, mst, jasowang,
xuanzhuo, eperezma, osalvador, akpm
Since this protection may break userspace tools, it should
be an opt-in until those tools have time to update to the
new daxN.M/hotplug interface instead of memory blocks.
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Gregory Price <gourry@gourry.net>
---
drivers/dax/Kconfig | 18 ++++++++++++++++++
drivers/dax/kmem.c | 29 ++++++++++++++++++++---------
2 files changed, 38 insertions(+), 9 deletions(-)
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index d656e4c0eb84..cc13c22eb8f8 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -78,4 +78,22 @@ config DEV_DAX_KMEM
Say N if unsure.
+config DEV_DAX_KMEM_PROTECTED
+ bool "Protect DAX_KMEM memory blocks being changed"
+ depends on DEV_DAX_KMEM
+ default n
+ help
+ Prevents actions from outside the KMEM DAX driver from changing
+ DAX KMEM memory block states. For example, the memory block
+ sysfs functions (online, state) will return -EBUSY, and normal
+ calls to memory_hotplug functions from other drivers and kernel
+ sources will fail.
+
+ This may break existing memory block management patterns that
+ depend on offlining DAX KMEM blocks from userland before unbinding
+ the driver. Use this only if your tools have been updated to use
+ the daxN.M/hotplug interface.
+
+ Say N if unsure.
+
endif
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index f3562f65376c..094b8a51099e 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -184,6 +184,21 @@ static int dax_kmem_memory_notifier_cb(struct notifier_block *nb,
return NOTIFY_BAD;
}
+static int dax_kmem_register_notifier(struct dax_kmem_data *data)
+{
+ if (!IS_ENABLED(DEV_DAX_KMEM_PROTECTED))
+ return 0;
+ data->mem_nb.notifier_call = dax_kmem_memory_notifier_cb;
+ return register_memory_notifier(&data->mem_nb);
+}
+
+static void dax_kmem_unregister_notifier(struct dax_kmem_data *data)
+{
+ if (!IS_ENABLED(DEV_DAX_KMEM_PROTECTED))
+ return;
+ unregister_memory_notifier(&data->mem_nb);
+}
+
/**
* dax_kmem_do_hotplug - hotplug memory for dax kmem device
* @dev_dax: the dev_dax instance
@@ -563,13 +578,9 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
if (rc < 0)
goto err_resources;
- /* Register memory notifier to block external operations */
- data->mem_nb.notifier_call = dax_kmem_memory_notifier_cb;
- rc = register_memory_notifier(&data->mem_nb);
- if (rc) {
- dev_warn(dev, "failed to register memory notifier\n");
+ rc = dax_kmem_register_notifier(data);
+ if (rc)
goto err_notifier;
- }
/*
* Hotplug using the system default policy - this preserves backwards
@@ -595,7 +606,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return 0;
err_hotplug:
- unregister_memory_notifier(&data->mem_nb);
+ dax_kmem_unregister_notifier(data);
err_notifier:
dax_kmem_cleanup_resources(dev_dax, data);
err_resources:
@@ -619,7 +630,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
device_remove_file(dev, &dev_attr_hotplug);
dax_kmem_cleanup_resources(dev_dax, data);
- unregister_memory_notifier(&data->mem_nb);
+ dax_kmem_unregister_notifier(data);
memory_group_unregister(data->mgid);
kfree(data->res_name);
kfree(data);
@@ -640,7 +651,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
struct dax_kmem_data *data = dev_get_drvdata(dev);
device_remove_file(dev, &dev_attr_hotplug);
- unregister_memory_notifier(&data->mem_nb);
+ dax_kmem_unregister_notifier(data);
/*
* Without hotremove purposely leak the request_mem_region() for the
--
2.52.0
^ permalink raw reply [flat|nested] 8+ messages in thread