[v7 3/3] device-dax: "Hotremove" persistent memory that is used like normal RAM

[Pavel Tatashin <pasha.tatashin@soleen.com>]

It is now allowed to use persistent memory like a regular RAM, but
currently there is no way to remove this memory until machine is
rebooted.

This work expands the functionality to also allows hotremoving
previously hotplugged persistent memory, and recover the device for use
for other purposes.

To hotremove persistent memory, the management software must first
offline all memory blocks of dax region, and than unbind it from
device-dax/kmem driver. So, operations should look like this:

echo offline > /sys/devices/system/memory/memoryN/state
...
echo dax0.0 > /sys/bus/dax/drivers/kmem/unbind

Note: if unbind is done without offlining memory beforehand, it won't be
possible to do dax0.0 hotremove, and dax's memory is going to be part of
System RAM until reboot.

Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/dax-private.h |  2 ++
 drivers/dax/kmem.c        | 41 +++++++++++++++++++++++++++++++++++----
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index b4177aafbbd1..9ee659ed5566 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -45,6 +45,7 @@ struct dax_region {
  * @pgmap - pgmap for memmap setup / lifetime (driver owned)
  * @ref: pgmap reference count (driver owned)
  * @cmp: @ref final put completion (driver owned)
+ * @dax_mem_res: physical address range of hotadded DAX memory
  */
 struct dev_dax {
 	struct dax_region *region;
@@ -54,6 +55,7 @@ struct dev_dax {
 	struct dev_pagemap pgmap;
 	struct percpu_ref ref;
 	struct completion cmp;
+	struct resource *dax_kmem_res;
 };
 
 static inline struct dev_dax *to_dev_dax(struct device *dev)
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 4c0131857133..c52a8e5f2345 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -71,21 +71,54 @@ int dev_dax_kmem_probe(struct device *dev)
 		kfree(new_res);
 		return rc;
 	}
+	dev_dax->dax_kmem_res = new_res;
 
 	return 0;
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static int dev_dax_kmem_remove(struct device *dev)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct resource *res = dev_dax->dax_kmem_res;
+	resource_size_t kmem_start = res->start;
+	resource_size_t kmem_size = resource_size(res);
+	int rc;
+
+	/*
+	 * 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.
+	 */
+	rc = remove_memory(dev_dax->target_node, kmem_start, kmem_size);
+	if (rc) {
+		dev_err(dev,
+			"region %pR cannot be hotremoved, error (%d)\n",
+			res, rc);
+		return rc;
+	}
+
+	/* Release and free dax resources */
+	release_resource(res);
+	kfree(res);
+	dev_dax->dax_kmem_res = NULL;
+
+	return 0;
+}
+#else
 static int dev_dax_kmem_remove(struct device *dev)
 {
 	/*
-	 * Purposely leak the request_mem_region() for the device-dax
-	 * range and return '0' to ->remove() attempts. The removal of
-	 * the device from the driver always succeeds, but the region
-	 * is permanently pinned as reserved by the unreleased
+	 * Without hotremove purposely leak the request_mem_region() for the
+	 * device-dax range and return '0' to ->remove() attempts. The removal
+	 * of the device from the driver always succeeds, but the region is
+	 * permanently pinned as reserved by the unreleased
 	 * request_mem_region().
 	 */
 	return 0;
 }
+#endif /* CONFIG_MEMORY_HOTREMOVE */
 
 static struct dax_device_driver device_dax_kmem_driver = {
 	.drv = {
-- 
2.22.0

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm