dax/kmem: allow kmem to add memory with memmap_on_memory

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.

Link: https://lkml.kernel.org/r/20231107-vv-kmem_memmap-v10-3-1253ec050ed0@intel.com
Signed-off-by: Vishal Verma <vishal.l.verma@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>
Tested-by: Li Zhijian <lizhijian@fujitsu.com>	[cxl.kmem and nvdimm.kmem]
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: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Fan Ni <fan.ni@samsung.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

7 files changed, 15 insertions, 1 deletions

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 1659b787b65f..1ff1ab5fa105 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -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;
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 1ccd23360124..cbbf64443098 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -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);
diff --git a/drivers/dax/cxl.c b/drivers/dax/cxl.c
index 8bc9d04034d6..c696837ab23c 100644
--- a/drivers/dax/cxl.c
+++ b/drivers/dax/cxl.c
@@ -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));
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index 27cf2daaaa79..446617b73aea 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -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;
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index 5d2ddef0f8f5..b9da69f92697 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -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));
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 369c698b7706..42ee360cf4e3 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -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"
 
@@ -93,6 +94,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	struct dax_kmem_data *data;
 	struct memory_dev_type *mtype;
 	int i, rc, mapped = 0;
+	mhp_t mhp_flags;
 	int numa_node;
 	int adist = MEMTIER_DEFAULT_DAX_ADISTANCE;
 
@@ -179,12 +181,16 @@ 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",
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index ae0cb113a5d3..f3c6c67b8412 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -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);