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, 34 insertions, 7 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca9536a348c..f28a1b3e63a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -173,6 +173,7 @@ extern unsigned int kobjsize(const void *objp);
                                          * In this case, do_no_page must
                                          * return with the page locked.
                                          */
+#define VM_CAN_NONLINEAR 0x10000000     /* Has ->fault & does nonlinear pages */
 
 #ifndef VM_STACK_DEFAULT_FLAGS          /* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -196,6 +197,25 @@ extern unsigned int kobjsize(const void *objp);
  */
 extern pgprot_t protection_map[16];
 
+#define FAULT_FLAG_WRITE        0x01
+#define FAULT_FLAG_NONLINEAR    0x02
+
+/*
+ * fault_data is filled in the the pagefault handler and passed to the
+ * vma's ->fault function. That function is responsible for filling in
+ * 'type', which is the type of fault if a page is returned, or the type
+ * of error if NULL is returned.
+ *
+ * pgoff should be used in favour of address, if possible. If pgoff is
+ * used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get
+ * nonlinear mapping support.
+ */
+struct fault_data {
+        unsigned long address;
+        pgoff_t pgoff;
+        unsigned int flags;
+        int type;
+};
 
 /*
  * These are the virtual MM functions - opening of an area, closing and
@@ -205,9 +225,15 @@ extern pgprot_t protection_map[16];
 struct vm_operations_struct {
         void (*open)(struct vm_area_struct * area);
         void (*close)(struct vm_area_struct * area);
-        struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
-        unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address);
-        int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
+        struct page *(*fault)(struct vm_area_struct *vma,
+                        struct fault_data *fdata);
+        struct page *(*nopage)(struct vm_area_struct *area,
+                        unsigned long address, int *type);
+        unsigned long (*nopfn)(struct vm_area_struct *area,
+                        unsigned long address);
+        int (*populate)(struct vm_area_struct *area, unsigned long address,
+                        unsigned long len, pgprot_t prot, unsigned long pgoff,
+                        int nonblock);
 
         /* notification that a previously read-only page is about to become
          * writable, if an error is returned it will cause a SIGBUS */
@@ -661,7 +687,6 @@ static inline int page_mapped(struct page *page)
  */
 #define NOPAGE_SIGBUS   (NULL)
 #define NOPAGE_OOM      ((struct page *) (-1))
-#define NOPAGE_REFAULT  ((struct page *) (-2))  /* Return to userspace, rerun */
 
 /*
  * Error return values for the *_nopfn functions
@@ -1110,9 +1135,11 @@ extern void truncate_inode_pages_range(struct address_space *,
                                        loff_t lstart, loff_t lend);
 
 /* generic vm_area_ops exported for stackable file systems */
-extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
-extern int filemap_populate(struct vm_area_struct *, unsigned long,
-                unsigned long, pgprot_t, unsigned long, int);
+extern struct page *filemap_fault(struct vm_area_struct *, struct fault_data *);
+extern struct page * __deprecated_for_modules
+filemap_nopage(struct vm_area_struct *, unsigned long, int *);
+extern int __deprecated_for_modules filemap_populate(struct vm_area_struct *,
+                unsigned long, unsigned long, pgprot_t, unsigned long, int);
 
 /* mm/page-writeback.c */
 int write_one_page(struct page *page, int wait);