@@ -37,15 +37,16 @@ static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
struct dax_kmem_data {
const char *res_name;
+ int mgid;
struct resource *res[];
};
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
+ unsigned long total_len = 0;
struct dax_kmem_data *data;
- int rc = -ENOMEM;
- int i, mapped = 0;
+ int i, rc, mapped = 0;
int numa_node;
/*
@@ -61,24 +62,44 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return -EINVAL;
}
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range range;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc) {
+ dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
+ i, range.start, range.end);
+ continue;
+ }
+ total_len += range_len(&range);
+ }
+
+ if (!total_len) {
+ dev_warn(dev, "rejecting DAX region without any memory after alignment\n");
+ return -EINVAL;
+ }
+
data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
if (!data)
return -ENOMEM;
+ rc = -ENOMEM;
data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
if (!data->res_name)
goto err_res_name;
+ rc = memory_group_register_static(numa_node, total_len);
+ if (rc < 0)
+ 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) {
- dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
- i, range.start, range.end);
+ if (rc)
continue;
- }
/* Region is permanently reserved if hotremove fails. */
res = request_mem_region(range.start, range_len(&range), data->res_name);
@@ -108,8 +129,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
* Ensure that future kexec'd kernels will not treat
* this as RAM automatically.
*/
- rc = add_memory_driver_managed(numa_node, range.start,
- range_len(&range), kmem_name, MHP_NONE);
+ rc = add_memory_driver_managed(data->mgid, range.start,
+ range_len(&range), kmem_name, MHP_NID_IS_MGID);
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
@@ -129,6 +150,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return 0;
err_request_mem:
+ memory_group_unregister(data->mgid);
+err_reg_mgid:
kfree(data->res_name);
err_res_name:
kfree(data);
@@ -171,6 +194,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
}
if (success >= dev_dax->nr_range) {
+ memory_group_unregister(data->mgid);
kfree(data->res_name);
kfree(data);
dev_set_drvdata(dev, NULL);
Although dax/kmem users often disable auto-onlining and instead online memory manually (usually to ZONE_MOVABLE), there is still value in having auto-onlining be aware of the relationship of memory blocks. Let's treat one probed unit as a single static memory device, similar to a single ACPI memory device. Signed-off-by: David Hildenbrand <david@redhat.com> --- drivers/dax/kmem.c | 40 ++++++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-)