mm: merge populate and nopage into fault (fixes nonlinear)

Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes
the virtual address -> file offset differently from linear mappings.

->populate is a layering violation because the filesystem/pagecache code
should need to know anything about the virtual memory mapping.  The hitch here
is that the ->nopage handler didn't pass down enough information (ie.  pgoff).
 But it is more logical to pass pgoff rather than have the ->nopage function
calculate it itself anyway (because that's a similar layering violation).

Having the populate handler install the pte itself is likewise a nasty thing
to be doing.

This patch introduces a new fault handler that replaces ->nopage and
->populate and (later) ->nopfn.  Most of the old mechanism is still in place
so there is a lot of duplication and nice cleanups that can be removed if
everyone switches over.

The rationale for doing this in the first place is that nonlinear mappings are
subject to the pagefault vs invalidate/truncate race too, and it seemed stupid
to duplicate the synchronisation logic rather than just consolidate the two.

After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in
pagecache.  Seems like a fringe functionality anyway.

NOPAGE_REFAULT is removed.  This should be implemented with ->fault, and no
users have hit mainline yet.

[akpm@linux-foundation.org: cleanup]
[randy.dunlap@oracle.com: doc. fixes for readahead]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 30 insertions, 24 deletions

diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 65ffc321f0c0..82f4b8e9834e 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -205,62 +205,67 @@ __xip_unmap (struct address_space * mapping,
 }
 
 /*
- * xip_nopage() is invoked via the vma operations vector for a
+ * xip_fault() is invoked via the vma operations vector for a
  * mapped memory region to read in file data during a page fault.
  *
- * This function is derived from filemap_nopage, but used for execute in place
+ * This function is derived from filemap_fault, but used for execute in place
  */
-static struct page *
-xip_file_nopage(struct vm_area_struct * area,
-                   unsigned long address,
-                   int *type)
+static struct page *xip_file_fault(struct vm_area_struct *area,
+                                        struct fault_data *fdata)
 {
         struct file *file = area->vm_file;
         struct address_space *mapping = file->f_mapping;
         struct inode *inode = mapping->host;
         struct page *page;
-        unsigned long size, pgoff, endoff;
+        pgoff_t size;
 
-        pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT)
-                + area->vm_pgoff;
-        endoff = ((area->vm_end - area->vm_start) >> PAGE_CACHE_SHIFT)
-                + area->vm_pgoff;
+        /* XXX: are VM_FAULT_ codes OK? */
 
         size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-        if (pgoff >= size)
-                return NOPAGE_SIGBUS;
+        if (fdata->pgoff >= size) {
+                fdata->type = VM_FAULT_SIGBUS;
+                return NULL;
+        }
 
-        page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
+        page = mapping->a_ops->get_xip_page(mapping,
+                                        fdata->pgoff*(PAGE_SIZE/512), 0);
         if (!IS_ERR(page))
                 goto out;
-        if (PTR_ERR(page) != -ENODATA)
-                return NOPAGE_SIGBUS;
+        if (PTR_ERR(page) != -ENODATA) {
+                fdata->type = VM_FAULT_OOM;
+                return NULL;
+        }
 
         /* sparse block */
         if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
             (area->vm_flags & (VM_SHARED| VM_MAYSHARE)) &&
             (!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
                 /* maybe shared writable, allocate new block */
-                page = mapping->a_ops->get_xip_page (mapping,
-                        pgoff*(PAGE_SIZE/512), 1);
-                if (IS_ERR(page))
-                        return NOPAGE_SIGBUS;
+                page = mapping->a_ops->get_xip_page(mapping,
+                                        fdata->pgoff*(PAGE_SIZE/512), 1);
+                if (IS_ERR(page)) {
+                        fdata->type = VM_FAULT_SIGBUS;
+                        return NULL;
+                }
                 /* unmap page at pgoff from all other vmas */
-                __xip_unmap(mapping, pgoff);
+                __xip_unmap(mapping, fdata->pgoff);
         } else {
                 /* not shared and writable, use xip_sparse_page() */
                 page = xip_sparse_page();
-                if (!page)
-                        return NOPAGE_OOM;
+                if (!page) {
+                        fdata->type = VM_FAULT_OOM;
+                        return NULL;
+                }
         }
 
 out:
+        fdata->type = VM_FAULT_MINOR;
         page_cache_get(page);
         return page;
 }
 
 static struct vm_operations_struct xip_file_vm_ops = {
-        .nopage         = xip_file_nopage,
+        .fault  = xip_file_fault,
 };
 
 int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
@@ -269,6 +274,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
 
         file_accessed(file);
         vma->vm_ops = &xip_file_vm_ops;
+        vma->vm_flags |= VM_CAN_NONLINEAR;
         return 0;
 }
 EXPORT_SYMBOL_GPL(xip_file_mmap);