resource: provide new functions to walk through resources

I have added two more functions to walk through resources.

Currently walk_system_ram_range() deals with pfn and /proc/iomem can
contain partial pages.  By dealing in pfn, callback function loses the
info that last page of a memory range is a partial page and not the full
page.  So I implemented walk_system_ram_res() which returns u64 values to
callback functions and now it properly return start and end address.

walk_system_ram_range() uses find_next_system_ram() to find the next ram
resource.  This in turn only travels through siblings of top level child
and does not travers through all the nodes of the resoruce tree.  I also
need another function where I can walk through all the resources, for
example figure out where "GART" aperture is.  Figure out where ACPI memory
is.

So I wrote another function walk_iomem_res() which walks through all
/proc/iomem resources and returns matches as asked by caller.  Caller can
specify "name" of resource, start and end and flags.

Got rid of find_next_system_ram_res() and instead implemented more generic
find_next_iomem_res() which can be used to traverse top level children
only based on an argument.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Cc: Greg Kroah-Hartman <greg@kroah.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: WANG Chao <chaowang@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 92 insertions, 9 deletions

diff --git a/kernel/resource.c b/kernel/resource.c
index 3c2237ac32db..da14b8d09296 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -59,10 +59,12 @@ static DEFINE_RWLOCK(resource_lock);
 static struct resource *bootmem_resource_free;
 static DEFINE_SPINLOCK(bootmem_resource_lock);
 
-static void *r_next(struct seq_file *m, void *v, loff_t *pos)
+static struct resource *next_resource(struct resource *p, bool sibling_only)
 {
-        struct resource *p = v;
-        (*pos)++;
+        /* Caller wants to traverse through siblings only */
+        if (sibling_only)
+                return p->sibling;
+
         if (p->child)
                 return p->child;
         while (!p->sibling && p->parent)
@@ -70,6 +72,13 @@ static void *r_next(struct seq_file *m, void *v, loff_t *pos)
         return p->sibling;
 }
 
+static void *r_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        struct resource *p = v;
+        (*pos)++;
+        return (void *)next_resource(p, false);
+}
+
 #ifdef CONFIG_PROC_FS
 
 enum { MAX_IORES_LEVEL = 5 };
@@ -322,16 +331,19 @@ int release_resource(struct resource *old)
 
 EXPORT_SYMBOL(release_resource);
 
-#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
 /*
- * Finds the lowest memory reosurce exists within [res->start.res->end)
+ * Finds the lowest iomem reosurce exists with-in [res->start.res->end)
  * the caller must specify res->start, res->end, res->flags and "name".
  * If found, returns 0, res is overwritten, if not found, returns -1.
+ * This walks through whole tree and not just first level children
+ * until and unless first_level_children_only is true.
  */
-static int find_next_system_ram(struct resource *res, char *name)
+static int find_next_iomem_res(struct resource *res, char *name,
+                               bool first_level_children_only)
 {
         resource_size_t start, end;
         struct resource *p;
+        bool sibling_only = false;
 
         BUG_ON(!res);
 
@@ -340,8 +352,14 @@ static int find_next_system_ram(struct resource *res, char *name)
         BUG_ON(start >= end);
 
         read_lock(&resource_lock);
-        for (p = iomem_resource.child; p ; p = p->sibling) {
-                /* system ram is just marked as IORESOURCE_MEM */
+
+        if (first_level_children_only) {
+                p = iomem_resource.child;
+                sibling_only = true;
+        } else
+                p = &iomem_resource;
+
+        while ((p = next_resource(p, sibling_only))) {
                 if (p->flags != res->flags)
                         continue;
                 if (name && strcmp(p->name, name))
@@ -353,6 +371,7 @@ static int find_next_system_ram(struct resource *res, char *name)
                 if ((p->end >= start) && (p->start < end))
                         break;
         }
+
         read_unlock(&resource_lock);
         if (!p)
                 return -1;
@@ -365,6 +384,70 @@ static int find_next_system_ram(struct resource *res, char *name)
 }
 
 /*
+ * 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
+ * name are valid candidates.
+ *
+ * @name: name of resource
+ * @flags: resource flags
+ * @start: start addr
+ * @end: end addr
+ */
+int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end,
+                void *arg, int (*func)(u64, u64, void *))
+{
+        struct resource res;
+        u64 orig_end;
+        int ret = -1;
+
+        res.start = start;
+        res.end = end;
+        res.flags = flags;
+        orig_end = res.end;
+        while ((res.start < res.end) &&
+                (!find_next_iomem_res(&res, name, false))) {
+                ret = (*func)(res.start, res.end, arg);
+                if (ret)
+                        break;
+                res.start = res.end + 1;
+                res.end = orig_end;
+        }
+        return ret;
+}
+
+/*
+ * This function calls callback against all memory range of "System RAM"
+ * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
+ * Now, this function is only for "System RAM". This function deals with
+ * full ranges and not pfn. If resources are not pfn aligned, dealing
+ * with pfn can truncate ranges.
+ */
+int walk_system_ram_res(u64 start, u64 end, void *arg,
+                                int (*func)(u64, u64, void *))
+{
+        struct resource res;
+        u64 orig_end;
+        int ret = -1;
+
+        res.start = start;
+        res.end = end;
+        res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+        orig_end = res.end;
+        while ((res.start < res.end) &&
+                (!find_next_iomem_res(&res, "System RAM", true))) {
+                ret = (*func)(res.start, res.end, arg);
+                if (ret)
+                        break;
+                res.start = res.end + 1;
+                res.end = orig_end;
+        }
+        return ret;
+}
+
+#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
+
+/*
  * This function calls callback against all memory range of "System RAM"
  * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
  * Now, this function is only for "System RAM".
@@ -382,7 +465,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
         res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
         orig_end = res.end;
         while ((res.start < res.end) &&
-                (find_next_system_ram(&res, "System RAM") >= 0)) {
+                (find_next_iomem_res(&res, "System RAM", true) >= 0)) {
                 pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
                 end_pfn = (res.end + 1) >> PAGE_SHIFT;
                 if (end_pfn > pfn)