resources: support allocating space within a region from the top down

Allocate space from the top of a region first, then work downward,
if an architecture desires this.

When we allocate space from a resource, we look for gaps between children
of the resource.  Previously, we always looked at gaps from the bottom up.
For example, given this:

    [mem 0xbff00000-0xf7ffffff] PCI Bus 0000:00
      [mem 0xbff00000-0xbfffffff] gap -- available
      [mem 0xc0000000-0xdfffffff] PCI Bus 0000:02
      [mem 0xe0000000-0xf7ffffff] gap -- available

we attempted to allocate from the [mem 0xbff00000-0xbfffffff] gap first,
then the [mem 0xe0000000-0xf7ffffff] gap.

With this patch an architecture can choose to allocate from the top gap
[mem 0xe0000000-0xf7ffffff] first.

We can't do this across the board because iomem_resource.end is initialized
to 0xffffffff_ffffffff on 64-bit architectures, and most machines can't
address the entire 64-bit physical address space.  Therefore, we only
allocate top-down if the arch requests it by clearing
"resource_alloc_from_bottom".

Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

3 files changed, 100 insertions, 4 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8dd7248508a9..fe50cbd315b0 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2156,6 +2156,11 @@ and is between 256 and 4096 characters. It is defined in the file
 	reset_devices	[KNL] Force drivers to reset the underlying device
 			during initialization.
 
+	resource_alloc_from_bottom
+			Allocate new resources from the beginning of available
+			space, not the end.  If you need to use this, please
+			report a bug.
+
 	resume=		[SWSUSP]
 			Specify the partition device for software suspend
 
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index b22790268b64..d377ea815d45 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -112,6 +112,7 @@ struct resource_list {
 /* PC/ISA/whatever - the normal PC address spaces: IO and memory */
 extern struct resource ioport_resource;
 extern struct resource iomem_resource;
+extern int resource_alloc_from_bottom;
 
 extern struct resource *request_resource_conflict(struct resource *root, struct resource *new);
 extern int request_resource(struct resource *root, struct resource *new);
diff --git a/kernel/resource.c b/kernel/resource.c
index e15b922d4ba4..716b6804077e 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -40,6 +40,23 @@ EXPORT_SYMBOL(iomem_resource);
 
 static DEFINE_RWLOCK(resource_lock);
 
+/*
+ * By default, we allocate free space bottom-up.  The architecture can request
+ * top-down by clearing this flag.  The user can override the architecture's
+ * choice with the "resource_alloc_from_bottom" kernel boot option, but that
+ * should only be a debugging tool.
+ */
+int resource_alloc_from_bottom = 1;
+
+static __init int setup_alloc_from_bottom(char *s)
+{
+	printk(KERN_INFO
+	       "resource: allocating from bottom-up; please report a bug\n");
+	resource_alloc_from_bottom = 1;
+	return 0;
+}
+early_param("resource_alloc_from_bottom", setup_alloc_from_bottom);
+
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
@@ -380,7 +397,74 @@ static bool resource_contains(struct resource *res1, struct resource *res2)
 }
 
 /*
+ * Find the resource before "child" in the sibling list of "root" children.
+ */
+static struct resource *find_sibling_prev(struct resource *root, struct resource *child)
+{
+	struct resource *this;
+
+	for (this = root->child; this; this = this->sibling)
+		if (this->sibling == child)
+			return this;
+
+	return NULL;
+}
+
+/*
+ * Find empty slot in the resource tree given range and alignment.
+ * This version allocates from the end of the root resource first.
+ */
+static int find_resource_from_top(struct resource *root, struct resource *new,
+				  resource_size_t size, resource_size_t min,
+				  resource_size_t max, resource_size_t align,
+				  resource_size_t (*alignf)(void *,
+						   const struct resource *,
+						   resource_size_t,
+						   resource_size_t),
+				  void *alignf_data)
+{
+	struct resource *this;
+	struct resource tmp, avail, alloc;
+
+	tmp.start = root->end;
+	tmp.end = root->end;
+
+	this = find_sibling_prev(root, NULL);
+	for (;;) {
+		if (this) {
+			if (this->end < root->end)
+				tmp.start = this->end + 1;
+		} else
+			tmp.start = root->start;
+
+		resource_clip(&tmp, min, max);
+
+		/* Check for overflow after ALIGN() */
+		avail = *new;
+		avail.start = ALIGN(tmp.start, align);
+		avail.end = tmp.end;
+		if (avail.start >= tmp.start) {
+			alloc.start = alignf(alignf_data, &avail, size, align);
+			alloc.end = alloc.start + size - 1;
+			if (resource_contains(&avail, &alloc)) {
+				new->start = alloc.start;
+				new->end = alloc.end;
+				return 0;
+			}
+		}
+
+		if (!this || this->start == root->start)
+			break;
+
+		tmp.end = this->start - 1;
+		this = find_sibling_prev(root, this);
+	}
+	return -EBUSY;
+}
+
+/*
  * Find empty slot in the resource tree given range and alignment.
+ * This version allocates from the beginning of the root resource first.
  */
 static int find_resource(struct resource *root, struct resource *new,
 			 resource_size_t size, resource_size_t min,
@@ -396,14 +480,15 @@ static int find_resource(struct resource *root, struct resource *new,
 
 	tmp.start = root->start;
 	/*
-	 * Skip past an allocated resource that starts at 0, since the assignment
-	 * of this->start - 1 to tmp->end below would cause an underflow.
+	 * Skip past an allocated resource that starts at 0, since the
+	 * assignment of this->start - 1 to tmp->end below would cause an
+	 * underflow.
 	 */
 	if (this && this->start == 0) {
 		tmp.start = this->end + 1;
 		this = this->sibling;
 	}
-	for(;;) {
+	for (;;) {
 		if (this)
 			tmp.end = this->start - 1;
 		else
@@ -424,8 +509,10 @@ static int find_resource(struct resource *root, struct resource *new,
 				return 0;
 			}
 		}
+
 		if (!this)
 			break;
+
 		tmp.start = this->end + 1;
 		this = this->sibling;
 	}
@@ -458,7 +545,10 @@ int allocate_resource(struct resource *root, struct resource *new,
 		alignf = simple_align_resource;
 
 	write_lock(&resource_lock);
-	err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
+	if (resource_alloc_from_bottom)
+		err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
+	else
+		err = find_resource_from_top(root, new, size, min, max, align, alignf, alignf_data);
 	if (err >= 0 && __request_resource(root, new))
 		err = -EBUSY;
 	write_unlock(&resource_lock);