mm: make GUP handle pfn mapping unless FOLL_GET is requested

With DAX, pfn mapping becoming more common.  The patch adjusts GUP code to
cover pfn mapping for cases when we don't need struct page to proceed.

To make it possible, let's change follow_page() code to return -EEXIST
error code if proper page table entry exists, but no corresponding struct
page.  __get_user_page() would ignore the error code and move to the next
page frame.

The immediate effect of the change is working MAP_POPULATE and mlock() on
DAX mappings.

[akpm@linux-foundation.org: fix arm64 build]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Toshi Kani <toshi.kani@hp.com>
Acked-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/gup.c b/mm/gup.c
index 6297f6bccfb1e42bedde7d69479eefbd52317b23..a798293fc6486bac215ecb58ed071263a5f775f0 100644 (file)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -12,7 +12,9 @@
 #include <linux/sched.h>
 #include <linux/rwsem.h>
 #include <linux/hugetlb.h>
+
 #include <asm/pgtable.h>
+#include <asm/tlbflush.h>
 
 #include "internal.h"
 
@@ -32,6 +34,30 @@ static struct page *no_page_table(struct vm_area_struct *vma,
        return NULL;
 }
 
+static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
+               pte_t *pte, unsigned int flags)
+{
+       /* No page to get reference */
+       if (flags & FOLL_GET)
+               return -EFAULT;
+
+       if (flags & FOLL_TOUCH) {
+               pte_t entry = *pte;
+
+               if (flags & FOLL_WRITE)
+                       entry = pte_mkdirty(entry);
+               entry = pte_mkyoung(entry);
+
+               if (!pte_same(*pte, entry)) {
+                       set_pte_at(vma->vm_mm, address, pte, entry);
+                       update_mmu_cache(vma, address, pte);
+               }
+       }
+
+       /* Proper page table entry exists, but no corresponding struct page */
+       return -EEXIST;
+}
+
 static struct page *follow_page_pte(struct vm_area_struct *vma,
                unsigned long address, pmd_t *pmd, unsigned int flags)
 {
@@ -73,10 +99,21 @@ retry:
 
        page = vm_normal_page(vma, address, pte);
        if (unlikely(!page)) {
-               if ((flags & FOLL_DUMP) ||
-                   !is_zero_pfn(pte_pfn(pte)))
-                       goto bad_page;
-               page = pte_page(pte);
+               if (flags & FOLL_DUMP) {
+                       /* Avoid special (like zero) pages in core dumps */
+                       page = ERR_PTR(-EFAULT);
+                       goto out;
+               }
+
+               if (is_zero_pfn(pte_pfn(pte))) {
+                       page = pte_page(pte);
+               } else {
+                       int ret;
+
+                       ret = follow_pfn_pte(vma, address, ptep, flags);
+                       page = ERR_PTR(ret);
+                       goto out;
+               }
        }
 
        if (flags & FOLL_GET)
@@ -114,12 +151,9 @@ retry:
                        unlock_page(page);
                }
        }
+out:
        pte_unmap_unlock(ptep, ptl);
        return page;
-bad_page:
-       pte_unmap_unlock(ptep, ptl);
-       return ERR_PTR(-EFAULT);
-
 no_page:
        pte_unmap_unlock(ptep, ptl);
        if (!pte_none(pte))
@@ -489,9 +523,15 @@ retry:
                                goto next_page;
                        }
                        BUG();
-               }
-               if (IS_ERR(page))
+               } else if (PTR_ERR(page) == -EEXIST) {
+                       /*
+                        * Proper page table entry exists, but no corresponding
+                        * struct page.
+                        */
+                       goto next_page;
+               } else if (IS_ERR(page)) {
                        return i ? i : PTR_ERR(page);
+               }
                if (pages) {
                        pages[i] = page;
                        flush_anon_page(vma, page, start);