device-dax: ensure dev_dax->pgmap is valid for dynamic devices

Right now, only static dax regions have a valid @pgmap pointer in its
struct dev_dax.  Dynamic dax case however, do not.

In preparation for device-dax compound devmap support, make sure that
dev_dax pgmap field is set after it has been allocated and initialized.

dynamic dax device have the @pgmap is allocated at probe() and it's
managed by devm (contrast to static dax region which a pgmap is provided
and dax core kfrees it).  So in addition to ensure a valid @pgmap, clear
the pgmap when the dynamic dax device is released to avoid the same
pgmap ranges to be re-requested across multiple region device reconfigs.

Add a static_dev_dax() and use that helper in dev_dax_probe() to ensure
the initialization differences between dynamic and static regions are
more explicit.  While at it, consolidate the ranges initialization when
we allocate the @pgmap for the dynamic dax region case.  Also take the
opportunity to document the differences between static and dynamic da
regions.

Link: https://lkml.kernel.org/r/20211202204422.26777-8-joao.m.martins@oracle.com
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 54 insertions, 8 deletions

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 6cc4da4c713d..a22350e822fa 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -129,11 +129,35 @@ ATTRIBUTE_GROUPS(dax_drv);
 
 static int dax_bus_match(struct device *dev, struct device_driver *drv);
 
+/*
+ * Static dax regions are regions created by an external subsystem
+ * nvdimm where a single range is assigned. Its boundaries are by the external
+ * subsystem and are usually limited to one physical memory range. For example,
+ * for PMEM it is usually defined by NVDIMM Namespace boundaries (i.e. a
+ * single contiguous range)
+ *
+ * On dynamic dax regions, the assigned region can be partitioned by dax core
+ * into multiple subdivisions. A subdivision is represented into one
+ * /dev/daxN.M device composed by one or more potentially discontiguous ranges.
+ *
+ * When allocating a dax region, drivers must set whether it's static
+ * (IORESOURCE_DAX_STATIC).  On static dax devices, the @pgmap is pre-assigned
+ * to dax core when calling devm_create_dev_dax(), whereas in dynamic dax
+ * devices it is NULL but afterwards allocated by dax core on device ->probe().
+ * Care is needed to make sure that dynamic dax devices are torn down with a
+ * cleared @pgmap field (see kill_dev_dax()).
+ */
 static bool is_static(struct dax_region *dax_region)
 {
 	return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0;
 }
 
+bool static_dev_dax(struct dev_dax *dev_dax)
+{
+	return is_static(dev_dax->region);
+}
+EXPORT_SYMBOL_GPL(static_dev_dax);
+
 static u64 dev_dax_size(struct dev_dax *dev_dax)
 {
 	u64 size = 0;
@@ -363,6 +387,14 @@ void kill_dev_dax(struct dev_dax *dev_dax)
 
 	kill_dax(dax_dev);
 	unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+	/*
+	 * Dynamic dax region have the pgmap allocated via dev_kzalloc()
+	 * and thus freed by devm. Clear the pgmap to not have stale pgmap
+	 * ranges on probe() from previous reconfigurations of region devices.
+	 */
+	if (!static_dev_dax(dev_dax))
+		dev_dax->pgmap = NULL;
 }
 EXPORT_SYMBOL_GPL(kill_dev_dax);
 
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 1e946ad7780a..4acdfee7dd59 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -48,6 +48,7 @@ int __dax_driver_register(struct dax_device_driver *dax_drv,
 	__dax_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
 void dax_driver_unregister(struct dax_device_driver *dax_drv);
 void kill_dev_dax(struct dev_dax *dev_dax);
+bool static_dev_dax(struct dev_dax *dev_dax);
 
 #if IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT)
 int dev_dax_probe(struct dev_dax *dev_dax);
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 038816b91af6..630de5a795b0 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -398,18 +398,34 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 	void *addr;
 	int rc, i;
 
-	pgmap = dev_dax->pgmap;
-	if (dev_WARN_ONCE(dev, pgmap && dev_dax->nr_range > 1,
-			"static pgmap / multi-range device conflict\n"))
-		return -EINVAL;
+	if (static_dev_dax(dev_dax))  {
+		if (dev_dax->nr_range > 1) {
+			dev_warn(dev,
+				"static pgmap / multi-range device conflict\n");
+			return -EINVAL;
+		}
+
+		pgmap = dev_dax->pgmap;
+	} else {
+		if (dev_dax->pgmap) {
+			dev_warn(dev,
+				 "dynamic-dax with pre-populated page map\n");
+			return -EINVAL;
+		}
 
-	if (!pgmap) {
 		pgmap = devm_kzalloc(dev,
                        struct_size(pgmap, ranges, dev_dax->nr_range - 1),
                        GFP_KERNEL);
 		if (!pgmap)
 			return -ENOMEM;
+
 		pgmap->nr_range = dev_dax->nr_range;
+		dev_dax->pgmap = pgmap;
+
+		for (i = 0; i < dev_dax->nr_range; i++) {
+			struct range *range = &dev_dax->ranges[i].range;
+			pgmap->ranges[i] = *range;
+		}
 	}
 
 	for (i = 0; i < dev_dax->nr_range; i++) {
@@ -421,9 +437,6 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 					i, range->start, range->end);
 			return -EBUSY;
 		}
-		/* don't update the range for static pgmap */
-		if (!dev_dax->pgmap)
-			pgmap->ranges[i] = *range;
 	}
 
 	pgmap->type = MEMORY_DEVICE_GENERIC;