mm: optimize dev_pagemap reference counting around get_dev_pagemap

Change the calling convention so that get_dev_pagemap always consumes the
previous reference instead of doing this using an explicit earlier call to
put_dev_pagemap in the callers.

The callers will still need to put the final reference after finishing the
loop over the pages.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 3df6cd4ffb40647ac739fd187e34c1bf7918c659..891c77487a6aa09941a878024a40d28350f5de04 100644 (file)
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -507,22 +507,23 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
  * @pfn: page frame number to lookup page_map
  * @pgmap: optional known pgmap that already has a reference
  *
- * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the
- * same mapping.
+ * If @pgmap is non-NULL and covers @pfn it will be returned as-is.  If @pgmap
+ * is non-NULL but does not cover @pfn the reference to it will be released.
  */
 struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
                struct dev_pagemap *pgmap)
 {
-       const struct resource *res = pgmap ? pgmap->res : NULL;
        resource_size_t phys = PFN_PHYS(pfn);
 
        /*
-        * In the cached case we're already holding a live reference so
-        * we can simply do a blind increment
+        * In the cached case we're already holding a live reference.
         */
-       if (res && phys >= res->start && phys <= res->end) {
-               percpu_ref_get(pgmap->ref);
-               return pgmap;
+       if (pgmap) {
+               const struct resource *res = pgmap ? pgmap->res : NULL;
+
+               if (res && phys >= res->start && phys <= res->end)
+                       return pgmap;
+               put_dev_pagemap(pgmap);
        }
 
        /* fall back to slow path lookup */

diff --git a/mm/gup.c b/mm/gup.c
index e0d82b6706d72d82637bca5eaef1e35e15a1abdf..3affe7544b0c49fc7e5c80dcd54b8ecbfcbfe6de 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1410,7 +1410,6 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
                VM_BUG_ON_PAGE(compound_head(page) != head, page);
 
-               put_dev_pagemap(pgmap);
                SetPageReferenced(page);
                pages[*nr] = page;
                (*nr)++;
@@ -1420,6 +1419,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
        ret = 1;
 
 pte_unmap:
+       if (pgmap)
+               put_dev_pagemap(pgmap);
        pte_unmap(ptem);
        return ret;
 }
@@ -1459,10 +1460,12 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
                SetPageReferenced(page);
                pages[*nr] = page;
                get_page(page);
-               put_dev_pagemap(pgmap);
                (*nr)++;
                pfn++;
        } while (addr += PAGE_SIZE, addr != end);
+
+       if (pgmap)
+               put_dev_pagemap(pgmap);
        return 1;
 }