Large amounts of memory managed by the kmem driver may come in via CXL,
and it is often desirable to have the memmap for this memory on the new
memory itself.
Enroll kmem-managed memory for memmap_on_memory semantics if the dax
region originates via CXL. For non-CXL dax regions, retain the existing
default behavior of hot adding without memmap_on_memory semantics.
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
drivers/dax/bus.h | 1 +
drivers/dax/dax-private.h | 1 +
drivers/dax/bus.c | 3 +++
drivers/dax/cxl.c | 1 +
drivers/dax/hmem/hmem.c | 1 +
drivers/dax/kmem.c | 8 +++++++-
drivers/dax/pmem.c | 1 +
7 files changed, 15 insertions(+), 1 deletion(-)
@@ -23,6 +23,7 @@ struct dev_dax_data {
struct dev_pagemap *pgmap;
resource_size_t size;
int id;
+ bool memmap_on_memory;
};
struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
@@ -70,6 +70,7 @@ struct dev_dax {
struct ida ida;
struct device dev;
struct dev_pagemap *pgmap;
+ bool memmap_on_memory;
int nr_range;
struct dev_dax_range {
unsigned long pgoff;
@@ -367,6 +367,7 @@ static ssize_t create_store(struct device *dev, struct device_attribute *attr,
.dax_region = dax_region,
.size = 0,
.id = -1,
+ .memmap_on_memory = false,
};
struct dev_dax *dev_dax = devm_create_dev_dax(&data);
@@ -1400,6 +1401,8 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
dev_dax->align = dax_region->align;
ida_init(&dev_dax->ida);
+ dev_dax->memmap_on_memory = data->memmap_on_memory;
+
inode = dax_inode(dax_dev);
dev->devt = inode->i_rdev;
dev->bus = &dax_bus_type;
@@ -26,6 +26,7 @@ static int cxl_dax_region_probe(struct device *dev)
.dax_region = dax_region,
.id = -1,
.size = range_len(&cxlr_dax->hpa_range),
+ .memmap_on_memory = true,
};
return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
@@ -36,6 +36,7 @@ static int dax_hmem_probe(struct platform_device *pdev)
.dax_region = dax_region,
.id = -1,
.size = region_idle ? 0 : range_len(&mri->range),
+ .memmap_on_memory = false,
};
return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
@@ -12,6 +12,7 @@
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/memory-tiers.h>
+#include <linux/memory_hotplug.h>
#include "dax-private.h"
#include "bus.h"
@@ -56,6 +57,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
unsigned long total_len = 0;
struct dax_kmem_data *data;
int i, rc, mapped = 0;
+ mhp_t mhp_flags;
int numa_node;
/*
@@ -136,12 +138,16 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
*/
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_NID_IS_MGID);
+ range_len(&range), kmem_name, mhp_flags);
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
@@ -63,6 +63,7 @@ static struct dev_dax *__dax_pmem_probe(struct device *dev)
.id = id,
.pgmap = &pgmap,
.size = range_len(&range),
+ .memmap_on_memory = false,
};
return devm_create_dev_dax(&data);