1 files changed, 44 insertions, 30 deletions

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 9ecedc28b928..e6476a8e8b6a 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -172,8 +172,6 @@ EXPORT_SYMBOL(devm_memunmap);
 #ifdef CONFIG_ZONE_DEVICE
 static DEFINE_MUTEX(pgmap_lock);
 static RADIX_TREE(pgmap_radix, GFP_KERNEL);
-#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
-#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
 struct page_map {
 	struct resource res;
@@ -194,18 +192,41 @@ void put_zone_device_page(struct page *page)
 }
 EXPORT_SYMBOL(put_zone_device_page);
 
-static void pgmap_radix_release(struct resource *res)
+static unsigned long order_at(struct resource *res, unsigned long pgoff)
 {
-	resource_size_t key, align_start, align_size, align_end;
+	unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
+	unsigned long nr_pages, mask;
+
+	nr_pages = PHYS_PFN(resource_size(res));
+	if (nr_pages == pgoff)
+		return ULONG_MAX;
+
+	/*
+	 * What is the largest aligned power-of-2 range available from
+	 * this resource pgoff to the end of the resource range,
+	 * considering the alignment of the current pgoff?
+	 */
+	mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
+	if (!mask)
+		return ULONG_MAX;
+
+	return find_first_bit(&mask, BITS_PER_LONG);
+}
 
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
-	align_end = align_start + align_size - 1;
+#define foreach_order_pgoff(res, order, pgoff) \
+	for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
+			pgoff += 1UL << order, order = order_at((res), pgoff))
+
+static void pgmap_radix_release(struct resource *res)
+{
+	unsigned long pgoff, order;
 
 	mutex_lock(&pgmap_lock);
-	for (key = res->start; key <= res->end; key += SECTION_SIZE)
-		radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT);
+	foreach_order_pgoff(res, order, pgoff)
+		radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
 	mutex_unlock(&pgmap_lock);
+
+	synchronize_rcu();
 }
 
 static unsigned long pfn_first(struct page_map *page_map)
@@ -235,7 +256,6 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 {
 	struct page_map *page_map = data;
 	struct resource *res = &page_map->res;
-	resource_size_t align_start, align_size;
 	struct dev_pagemap *pgmap = &page_map->pgmap;
 
 	if (percpu_ref_tryget_live(pgmap->ref)) {
@@ -244,12 +264,10 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	}
 
 	/* pages are dead and unused, undo the arch mapping */
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	mem_hotplug_begin();
-	arch_remove_memory(align_start, align_size);
+	arch_remove_memory(res->start, resource_size(res));
 	mem_hotplug_done();
-	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
 	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
 			"%s: failed to free all reserved pages\n", __func__);
@@ -262,7 +280,7 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT);
+	page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
 	return page_map ? &page_map->pgmap : NULL;
 }
 
@@ -284,17 +302,13 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
-	resource_size_t key, align_start, align_size, align_end;
+	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	int error, nid, is_ram;
-	unsigned long pfn;
 
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
-		- align_start;
-	is_ram = region_intersects(align_start, align_size,
+	is_ram = region_intersects(res->start, resource_size(res),
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
 	if (is_ram == REGION_MIXED) {
@@ -327,12 +341,12 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_end = align_start + align_size - 1;
-	for (key = align_start; key <= align_end; key += SECTION_SIZE) {
+
+	foreach_order_pgoff(res, order, pgoff) {
 		struct dev_pagemap *dup;
 
 		rcu_read_lock();
-		dup = find_dev_pagemap(key);
+		dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff));
 		rcu_read_unlock();
 		if (dup) {
 			dev_err(dev, "%s: %pr collides with mapping for %s\n",
@@ -340,8 +354,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 			error = -EBUSY;
 			break;
 		}
-		error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
-				page_map);
+		error = __radix_tree_insert(&pgmap_radix,
+				PHYS_PFN(res->start) + pgoff, order, page_map);
 		if (error) {
 			dev_err(dev, "%s: failed: %d\n", __func__, error);
 			break;
@@ -355,13 +369,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
-			align_size);
+	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
+			resource_size(res));
 	if (error)
 		goto err_pfn_remap;
 
 	mem_hotplug_begin();
-	error = arch_add_memory(nid, align_start, align_size, true);
+	error = arch_add_memory(nid, res->start, resource_size(res), true);
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
@@ -382,7 +396,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	return __va(res->start);
 
  err_add_memory:
-	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
  err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res);