memremap: provide an optional internal refcount in struct dev_pagemap

Provide an internal refcounting logic if no ->ref field is provided
in the pagemap passed into devm_memremap_pages so that callers don't
have to reinvent it poorly.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

include/linux/memremap.h

@@ -95,6 +95,8 @@ struct dev_pagemap_ops {
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @res: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
+ * @internal_ref: internal reference if @ref is not provided by the caller
+ * @done: completion for @internal_ref
  * @dev: host device of the mapping for debug
  * @data: private data pointer for page_free()
  * @type: memory type: see MEMORY_* in memory_hotplug.h
@@ -105,6 +107,8 @@ struct dev_pagemap {
 	struct vmem_altmap altmap;
 	struct resource res;
 	struct percpu_ref *ref;
+	struct percpu_ref internal_ref;
+	struct completion done;
 	struct device *dev;
 	enum memory_type type;
 	unsigned int flags;

kernel/memremap.c

@@ -29,7 +29,7 @@ static void devmap_managed_enable_put(void *data)
 
 static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
 {
-	if (!pgmap->ops->page_free) {
+	if (!pgmap->ops || !pgmap->ops->page_free) {
 		WARN(1, "Missing page_free method\n");
 		return -EINVAL;
 	}
@@ -75,6 +75,24 @@ static unsigned long pfn_next(unsigned long pfn)
 #define for_each_device_pfn(pfn, map) \
 	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
 
+static void dev_pagemap_kill(struct dev_pagemap *pgmap)
+{
+	if (pgmap->ops && pgmap->ops->kill)
+		pgmap->ops->kill(pgmap);
+	else
+		percpu_ref_kill(pgmap->ref);
+}
+
+static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
+{
+	if (pgmap->ops && pgmap->ops->cleanup) {
+		pgmap->ops->cleanup(pgmap);
+	} else {
+		wait_for_completion(&pgmap->done);
+		percpu_ref_exit(pgmap->ref);
+	}
+}
+
 static void devm_memremap_pages_release(void *data)
 {
 	struct dev_pagemap *pgmap = data;
@@ -84,10 +102,10 @@ static void devm_memremap_pages_release(void *data)
 	unsigned long pfn;
 	int nid;
 
-	pgmap->ops->kill(pgmap);
+	dev_pagemap_kill(pgmap);
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
-	pgmap->ops->cleanup(pgmap);
+	dev_pagemap_cleanup(pgmap);
 
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
@@ -114,20 +132,29 @@ static void devm_memremap_pages_release(void *data)
 		      "%s: failed to free all reserved pages\n", __func__);
 }
 
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+	struct dev_pagemap *pgmap =
+		container_of(ref, struct dev_pagemap, internal_ref);
+
+	complete(&pgmap->done);
+}
+
 /**
  * devm_memremap_pages - remap and provide memmap backing for the given resource
  * @dev: hosting device for @res
  * @pgmap: pointer to a struct dev_pagemap
  *
  * Notes:
- * 1/ At a minimum the res, ref and type and ops members of @pgmap must be
- *    initialized by the caller before passing it to this function
+ * 1/ At a minimum the res and type members of @pgmap must be initialized
+ *    by the caller before passing it to this function
  *
  * 2/ The altmap field may optionally be initialized, in which case
  *    PGMAP_ALTMAP_VALID must be set in pgmap->flags.
  *
- * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped
- *    at devm_memremap_pages_release() time, or if this routine fails.
+ * 3/ The ref field may optionally be provided, in which pgmap->ref must be
+ *    'live' on entry and will be killed and reaped at
+ *    devm_memremap_pages_release() time, or if this routine fails.
  *
  * 4/ res is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
@@ -175,11 +202,22 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		break;
 	}
 
-	if (!pgmap->ref || !pgmap->ops || !pgmap->ops->kill ||
-	    !pgmap->ops->cleanup) {
+	if (!pgmap->ref) {
+		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+			return ERR_PTR(-EINVAL);
+
+		init_completion(&pgmap->done);
+		error = percpu_ref_init(&pgmap->internal_ref,
+				dev_pagemap_percpu_release, 0, GFP_KERNEL);
+		if (error)
+			return ERR_PTR(error);
+		pgmap->ref = &pgmap->internal_ref;
+	} else {
+		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
 			WARN(1, "Missing reference count teardown definition\n");
 			return ERR_PTR(-EINVAL);
 		}
+	}
 
 	if (need_devmap_managed) {
 		error = devmap_managed_enable_get(dev, pgmap);
@@ -296,8 +334,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
  err_pfn_remap:
 	pgmap_array_delete(res);
  err_array:
-	pgmap->ops->kill(pgmap);
-	pgmap->ops->cleanup(pgmap);
+	dev_pagemap_kill(pgmap);
+	dev_pagemap_cleanup(pgmap);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(devm_memremap_pages);

tools/testing/nvdimm/test/iomap.c

@@ -100,26 +100,60 @@ static void nfit_test_kill(void *_pgmap)
 {
 	struct dev_pagemap *pgmap = _pgmap;
 
-	WARN_ON(!pgmap || !pgmap->ref || !pgmap->ops || !pgmap->ops->kill ||
-		!pgmap->ops->cleanup);
+	WARN_ON(!pgmap || !pgmap->ref);
+
+	if (pgmap->ops && pgmap->ops->kill)
 		pgmap->ops->kill(pgmap);
+	else
+		percpu_ref_kill(pgmap->ref);
+
+	if (pgmap->ops && pgmap->ops->cleanup) {
 		pgmap->ops->cleanup(pgmap);
+	} else {
+		wait_for_completion(&pgmap->done);
+		percpu_ref_exit(pgmap->ref);
+	}
+}
+
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+	struct dev_pagemap *pgmap =
+		container_of(ref, struct dev_pagemap, internal_ref);
+
+	complete(&pgmap->done);
 }
 
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
+	int error;
 	resource_size_t offset = pgmap->res.start;
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-	if (nfit_res) {
-		int rc;
+	if (!nfit_res)
+		return devm_memremap_pages(dev, pgmap);
 
-		rc = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
-		if (rc)
-			return ERR_PTR(rc);
-		return nfit_res->buf + offset - nfit_res->res.start;
+	pgmap->dev = dev;
+	if (!pgmap->ref) {
+		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+			return ERR_PTR(-EINVAL);
+
+		init_completion(&pgmap->done);
+		error = percpu_ref_init(&pgmap->internal_ref,
+				dev_pagemap_percpu_release, 0, GFP_KERNEL);
+		if (error)
+			return ERR_PTR(error);
+		pgmap->ref = &pgmap->internal_ref;
+	} else {
+		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+			WARN(1, "Missing reference count teardown definition\n");
+			return ERR_PTR(-EINVAL);
 		}
-	return devm_memremap_pages(dev, pgmap);
+	}
+
+	error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
+	if (error)
+		return ERR_PTR(error);
+	return nfit_res->buf + offset - nfit_res->res.start;
 }
 EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);