memremap: provide a not device managed memremap_pages

The kvmppc ultravisor code wants a device private memory pool that is
system wide and not attached to a device.  Instead of faking up one
provide a low-level memremap_pages for it.

Link: https://lore.kernel.org/r/20190818090557.17853-5-hch@lst.de
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: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 52 insertions, 32 deletions

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 09a087ca30ff..77a77704eb28 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -96,9 +96,8 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 	}
 }
 
-static void devm_memremap_pages_release(void *data)
+void memunmap_pages(struct dev_pagemap *pgmap)
 {
-	struct dev_pagemap *pgmap = data;
 	struct resource *res = &pgmap->res;
 	unsigned long pfn;
 	int nid;
@@ -128,6 +127,12 @@ static void devm_memremap_pages_release(void *data)
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
 	devmap_managed_enable_put();
 }
+EXPORT_SYMBOL_GPL(memunmap_pages);
+
+static void devm_memremap_pages_release(void *data)
+{
+	memunmap_pages(data);
+}
 
 static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 {
@@ -137,27 +142,12 @@ static void dev_pagemap_percpu_release(struct percpu_ref *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 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/ 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
- *    this is not enforced.
+/*
+ * Not device managed version of dev_memremap_pages, undone by
+ * memunmap_pages().  Please use dev_memremap_pages if you have a struct
+ * device available.
  */
-void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
+void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 {
 	struct resource *res = &pgmap->res;
 	struct dev_pagemap *conflict_pgmap;
@@ -168,7 +158,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		.altmap = pgmap_altmap(pgmap),
 	};
 	pgprot_t pgprot = PAGE_KERNEL;
-	int error, nid, is_ram;
+	int error, is_ram;
 	bool need_devmap_managed = true;
 
 	switch (pgmap->type) {
@@ -223,7 +213,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
 	if (conflict_pgmap) {
-		dev_WARN(dev, "Conflicting mapping in same section\n");
+		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
 		error = -ENOMEM;
 		goto err_array;
@@ -231,7 +221,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
 	if (conflict_pgmap) {
-		dev_WARN(dev, "Conflicting mapping in same section\n");
+		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
 		error = -ENOMEM;
 		goto err_array;
@@ -252,7 +242,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	if (error)
 		goto err_array;
 
-	nid = dev_to_node(dev);
 	if (nid < 0)
 		nid = numa_mem_id();
 
@@ -308,12 +297,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 				PHYS_PFN(res->start),
 				PHYS_PFN(resource_size(res)), pgmap);
 	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-
-	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
-			pgmap);
-	if (error)
-		return ERR_PTR(error);
-
 	return __va(res->start);
 
  err_add_memory:
@@ -328,6 +311,43 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	devmap_managed_enable_put();
 	return ERR_PTR(error);
 }
+EXPORT_SYMBOL_GPL(memremap_pages);
+
+/**
+ * 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 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/ 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
+ *    this is not enforced.
+ */
+void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
+{
+	int error;
+	void *ret;
+
+	ret = memremap_pages(pgmap, dev_to_node(dev));
+	if (IS_ERR(ret))
+		return ret;
+
+	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+			pgmap);
+	if (error)
+		return ERR_PTR(error);
+	return ret;
+}
 EXPORT_SYMBOL_GPL(devm_memremap_pages);
 
 void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)