3 files changed, 50 insertions, 4 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index f91926f2f482..8bb8a7ee0f99 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -525,6 +525,7 @@ prototypes:
         void (*close)(struct vm_area_struct*);
         int (*fault)(struct vm_area_struct*, struct vm_fault *);
         int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
+        int (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
         int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
@@ -534,6 +535,7 @@ close:		yes
 fault:          yes             can return with page locked
 map_pages:      yes
 page_mkwrite:   yes             can return with page locked
+pfn_mkwrite:    yes
 access:         yes
 
         ->fault() is called when a previously not present pte is about
@@ -560,6 +562,12 @@ the page has been truncated, the filesystem should not look up a new page
 like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
 will cause the VM to retry the fault.
 
+        ->pfn_mkwrite() is the same as page_mkwrite but when the pte is
+VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
+VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
+after this call is to make the pte read-write, unless pfn_mkwrite returns
+an error.
+
         ->access() is called when get_user_pages() fails in
 access_process_vm(), typically used to debug a process through
 /proc/pid/mem or ptrace.  This function is needed only for
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0e7bb2194da5..8b086070c3a5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -251,6 +251,9 @@ struct vm_operations_struct {
          * writable, if an error is returned it will cause a SIGBUS */
         int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
+        /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
+        int (*pfn_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);
+
         /* called by access_process_vm when get_user_pages() fails, typically
          * for use by special VMAs that can switch between memory and hardware
          */
diff --git a/mm/memory.c b/mm/memory.c
index f9628e568c58..22e037e3364e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2180,6 +2180,42 @@ oom:
         return VM_FAULT_OOM;
 }
 
+/*
+ * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED
+ * mapping
+ */
+static int wp_pfn_shared(struct mm_struct *mm,
+                        struct vm_area_struct *vma, unsigned long address,
+                        pte_t *page_table, spinlock_t *ptl, pte_t orig_pte,
+                        pmd_t *pmd)
+{
+        if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) {
+                struct vm_fault vmf = {
+                        .page = NULL,
+                        .pgoff = linear_page_index(vma, address),
+                        .virtual_address = (void __user *)(address & PAGE_MASK),
+                        .flags = FAULT_FLAG_WRITE | FAULT_FLAG_MKWRITE,
+                };
+                int ret;
+
+                pte_unmap_unlock(page_table, ptl);
+                ret = vma->vm_ops->pfn_mkwrite(vma, &vmf);
+                if (ret & VM_FAULT_ERROR)
+                        return ret;
+                page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+                /*
+                 * We might have raced with another page fault while we
+                 * released the pte_offset_map_lock.
+                 */
+                if (!pte_same(*page_table, orig_pte)) {
+                        pte_unmap_unlock(page_table, ptl);
+                        return 0;
+                }
+        }
+        return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte,
+                             NULL, 0, 0);
+}
+
 static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma,
                           unsigned long address, pte_t *page_table,
                           pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte,
@@ -2258,13 +2294,12 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                  * VM_PFNMAP VMA.
                  *
                  * We should not cow pages in a shared writeable mapping.
-                 * Just mark the pages writable as we can't do any dirty
-                 * accounting on raw pfn maps.
+                 * Just mark the pages writable and/or call ops->pfn_mkwrite.
                  */
                 if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
                                      (VM_WRITE|VM_SHARED))
-                        return wp_page_reuse(mm, vma, address, page_table, ptl,
-                                             orig_pte, old_page, 0, 0);
+                        return wp_pfn_shared(mm, vma, address, page_table, ptl,
+                                             orig_pte, pmd);
 
                 pte_unmap_unlock(page_table, ptl);
                 return wp_page_copy(mm, vma, address, page_table, pmd,