dax: add a sysfs knob to control memmap_on_memory behavior

Add a sysfs knob for dax devices to control the memmap_on_memory setting
if the dax device were to be hotplugged as system memory.

The default memmap_on_memory setting for dax devices originating via pmem
or hmem is set to 'false' - i.e.  no memmap_on_memory semantics, to
preserve legacy behavior.  For dax devices via CXL, the default is on. 
The sysfs control allows the administrator to override the above defaults
if needed.

Link: https://lkml.kernel.org/r/20240124-vv-dax_abi-v7-5-20d16cb8d23d@intel.com
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Tested-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Huang, Ying <ying.huang@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 60 insertions, 0 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-dax b/Documentation/ABI/testing/sysfs-bus-dax
index 6359f7bc9bf4..b34266bfae49 100644
--- a/Documentation/ABI/testing/sysfs-bus-dax
+++ b/Documentation/ABI/testing/sysfs-bus-dax
@@ -134,3 +134,20 @@ KernelVersion:	v5.1
 Contact:	nvdimm@lists.linux.dev
 Description:
 		(RO) The id attribute indicates the region id of a dax region.
+
+What:		/sys/bus/dax/devices/daxX.Y/memmap_on_memory
+Date:		January, 2024
+KernelVersion:	v6.8
+Contact:	nvdimm@lists.linux.dev
+Description:
+		(RW) Control the memmap_on_memory setting if the dax device
+		were to be hotplugged as system memory. This determines whether
+		the 'altmap' for the hotplugged memory will be placed on the
+		device being hotplugged (memmap_on_memory=1) or if it will be
+		placed on regular memory (memmap_on_memory=0). This attribute
+		must be set before the device is handed over to the 'kmem'
+		driver (i.e.  hotplugged into system-ram). Additionally, this
+		depends on CONFIG_MHP_MEMMAP_ON_MEMORY, and a globally enabled
+		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'."
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 0fd948a4443e..27c86d0ca711 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1349,6 +1349,48 @@ static ssize_t numa_node_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(numa_node);
 
+static ssize_t memmap_on_memory_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+
+	return sysfs_emit(buf, "%d\n", dev_dax->memmap_on_memory);
+}
+
+static ssize_t memmap_on_memory_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t len)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	bool val;
+	int rc;
+
+	rc = kstrtobool(buf, &val);
+	if (rc)
+		return rc;
+
+	if (val == true && !mhp_supports_memmap_on_memory()) {
+		dev_dbg(dev, "memmap_on_memory is not available\n");
+		return -EOPNOTSUPP;
+	}
+
+	rc = down_write_killable(&dax_dev_rwsem);
+	if (rc)
+		return rc;
+
+	if (dev_dax->memmap_on_memory != val && dev->driver &&
+	    to_dax_drv(dev->driver)->type == DAXDRV_KMEM_TYPE) {
+		up_write(&dax_dev_rwsem);
+		return -EBUSY;
+	}
+
+	dev_dax->memmap_on_memory = val;
+	up_write(&dax_dev_rwsem);
+
+	return len;
+}
+static DEVICE_ATTR_RW(memmap_on_memory);
+
 static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -1375,6 +1417,7 @@ static struct attribute *dev_dax_attributes[] = {
 	&dev_attr_align.attr,
 	&dev_attr_resource.attr,
 	&dev_attr_numa_node.attr,
+	&dev_attr_memmap_on_memory.attr,
 	NULL,
 };