1 files changed, 105 insertions, 35 deletions

diff --git a/kernel/resource.c b/kernel/resource.c
index f1175ce93a1d..833394f9c608 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -320,9 +320,8 @@ int release_resource(struct resource *old)
 EXPORT_SYMBOL(release_resource);
 
 /**
- * Finds the lowest iomem resource that covers part of [@start..@end].  The
- * caller must specify @start, @end, @flags, and @desc (which may be
- * IORES_DESC_NONE).
+ * find_next_iomem_res - Finds the lowest iomem resource that covers part of
+ *			 [@start..@end].
  *
  * If a resource is found, returns 0 and @*res is overwritten with the part
  * of the resource that's within [@start..@end]; if none is found, returns
@@ -337,6 +336,9 @@ EXPORT_SYMBOL(release_resource);
  * @desc:	descriptor the resource must have
  * @first_lvl:	walk only the first level children, if set
  * @res:	return ptr, if resource found
+ *
+ * The caller must specify @start, @end, @flags, and @desc
+ * (which may be IORES_DESC_NONE).
  */
 static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 			       unsigned long flags, unsigned long desc,
@@ -416,11 +418,9 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
 }
 
 /**
- * Walks through iomem resources and calls func() with matching resource
- * ranges. This walks through whole tree and not just first level children.
- * All the memory ranges which overlap start,end and also match flags and
- * desc are valid candidates.
- *
+ * walk_iomem_res_desc - Walks through iomem resources and calls func()
+ *			 with matching resource ranges.
+ * *
  * @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check.
  * @flags: I/O resource flags
  * @start: start addr
@@ -428,6 +428,10 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
  * @arg: function argument for the callback @func
  * @func: callback function that is called for each qualifying resource area
  *
+ * This walks through whole tree and not just first level children.
+ * All the memory ranges which overlap start,end and also match flags and
+ * desc are valid candidates.
+ *
  * NOTE: For a new descriptor search, define a new IORES_DESC in
  * <linux/ioport.h> and set it in 'desc' of a target resource entry.
  */
@@ -557,13 +561,13 @@ int region_intersects(resource_size_t start, size_t size, unsigned long flags,
 	}
 	read_unlock(&resource_lock);
 
-	if (other == 0)
-		return type ? REGION_INTERSECTS : REGION_DISJOINT;
+	if (type == 0)
+		return REGION_DISJOINT;
 
-	if (type)
-		return REGION_MIXED;
+	if (other == 0)
+		return REGION_INTERSECTS;
 
-	return REGION_DISJOINT;
+	return REGION_MIXED;
 }
 EXPORT_SYMBOL_GPL(region_intersects);
 
@@ -1240,7 +1244,6 @@ EXPORT_SYMBOL(__release_region);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /**
  * release_mem_region_adjustable - release a previously reserved memory region
- * @parent: parent resource descriptor
  * @start: resource start address
  * @size: resource region size
  *
@@ -1258,21 +1261,28 @@ EXPORT_SYMBOL(__release_region);
  *   assumes that all children remain in the lower address entry for
  *   simplicity.  Enhance this logic when necessary.
  */
-int release_mem_region_adjustable(struct resource *parent,
-				  resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
 {
+	struct resource *parent = &iomem_resource;
+	struct resource *new_res = NULL;
+	bool alloc_nofail = false;
 	struct resource **p;
 	struct resource *res;
-	struct resource *new_res;
 	resource_size_t end;
-	int ret = -EINVAL;
 
 	end = start + size - 1;
-	if ((start < parent->start) || (end > parent->end))
-		return ret;
+	if (WARN_ON_ONCE((start < parent->start) || (end > parent->end)))
+		return;
 
-	/* The alloc_resource() result gets checked later */
-	new_res = alloc_resource(GFP_KERNEL);
+	/*
+	 * We free up quite a lot of memory on memory hotunplug (esp., memap),
+	 * just before releasing the region. This is highly unlikely to
+	 * fail - let's play save and make it never fail as the caller cannot
+	 * perform any error handling (e.g., trying to re-add memory will fail
+	 * similarly).
+	 */
+retry:
+	new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0));
 
 	p = &parent->child;
 	write_lock(&resource_lock);
@@ -1298,7 +1308,6 @@ int release_mem_region_adjustable(struct resource *parent,
 		 * so if we are dealing with them, let us just back off here.
 		 */
 		if (!(res->flags & IORESOURCE_SYSRAM)) {
-			ret = 0;
 			break;
 		}
 
@@ -1315,20 +1324,23 @@ int release_mem_region_adjustable(struct resource *parent,
 			/* free the whole entry */
 			*p = res->sibling;
 			free_resource(res);
-			ret = 0;
 		} else if (res->start == start && res->end != end) {
 			/* adjust the start */
-			ret = __adjust_resource(res, end + 1,
-						res->end - end);
+			WARN_ON_ONCE(__adjust_resource(res, end + 1,
+						       res->end - end));
 		} else if (res->start != start && res->end == end) {
 			/* adjust the end */
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
+			WARN_ON_ONCE(__adjust_resource(res, res->start,
+						       start - res->start));
 		} else {
-			/* split into two entries */
+			/* split into two entries - we need a new resource */
 			if (!new_res) {
-				ret = -ENOMEM;
-				break;
+				new_res = alloc_resource(GFP_ATOMIC);
+				if (!new_res) {
+					alloc_nofail = true;
+					write_unlock(&resource_lock);
+					goto retry;
+				}
 			}
 			new_res->name = res->name;
 			new_res->start = end + 1;
@@ -1339,9 +1351,8 @@ int release_mem_region_adjustable(struct resource *parent,
 			new_res->sibling = res->sibling;
 			new_res->child = NULL;
 
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
-			if (ret)
+			if (WARN_ON_ONCE(__adjust_resource(res, res->start,
+							   start - res->start)))
 				break;
 			res->sibling = new_res;
 			new_res = NULL;
@@ -1352,10 +1363,69 @@ int release_mem_region_adjustable(struct resource *parent,
 
 	write_unlock(&resource_lock);
 	free_resource(new_res);
-	return ret;
 }
 #endif	/* CONFIG_MEMORY_HOTREMOVE */
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool system_ram_resources_mergeable(struct resource *r1,
+					   struct resource *r2)
+{
+	/* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */
+	return r1->flags == r2->flags && r1->end + 1 == r2->start &&
+	       r1->name == r2->name && r1->desc == r2->desc &&
+	       !r1->child && !r2->child;
+}
+
+/**
+ * merge_system_ram_resource - mark the System RAM resource mergeable and try to
+ *	merge it with adjacent, mergeable resources
+ * @res: resource descriptor
+ *
+ * This interface is intended for memory hotplug, whereby lots of contiguous
+ * system ram resources are added (e.g., via add_memory*()) by a driver, and
+ * the actual resource boundaries are not of interest (e.g., it might be
+ * relevant for DIMMs). Only resources that are marked mergeable, that have the
+ * same parent, and that don't have any children are considered. All mergeable
+ * resources must be immutable during the request.
+ *
+ * Note:
+ * - The caller has to make sure that no pointers to resources that are
+ *   marked mergeable are used anymore after this call - the resource might
+ *   be freed and the pointer might be stale!
+ * - release_mem_region_adjustable() will split on demand on memory hotunplug
+ */
+void merge_system_ram_resource(struct resource *res)
+{
+	const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	struct resource *cur;
+
+	if (WARN_ON_ONCE((res->flags & flags) != flags))
+		return;
+
+	write_lock(&resource_lock);
+	res->flags |= IORESOURCE_SYSRAM_MERGEABLE;
+
+	/* Try to merge with next item in the list. */
+	cur = res->sibling;
+	if (cur && system_ram_resources_mergeable(res, cur)) {
+		res->end = cur->end;
+		res->sibling = cur->sibling;
+		free_resource(cur);
+	}
+
+	/* Try to merge with previous item in the list. */
+	cur = res->parent->child;
+	while (cur && cur->sibling != res)
+		cur = cur->sibling;
+	if (cur && system_ram_resources_mergeable(cur, res)) {
+		cur->end = res->end;
+		cur->sibling = res->sibling;
+		free_resource(res);
+	}
+	write_unlock(&resource_lock);
+}
+#endif	/* CONFIG_MEMORY_HOTPLUG */
+
 /*
  * Managed region resource
  */