NOMMU: Fix MAP_PRIVATE mmap() of objects where the data can be mapped directly

Fix MAP_PRIVATE mmap() of files and devices where the data in the backing store
might be mapped directly.  Use the BDI_CAP_MAP_DIRECT capability flag to govern
whether or not we should be trying to map a file directly.  This can be used to
determine whether or not a region has been filled in at the point where we call
do_mmap_shared() or do_mmap_private().

The BDI_CAP_MAP_DIRECT capability flag is cleared by validate_mmap_request() if
there's any reason we can't use it.  It's also cleared in do_mmap_pgoff() if
f_op->get_unmapped_area() fails.

Without this fix, attempting to run a program from a RomFS image on a
non-mappable MTD partition results in a BUG as the kernel attempts XIP, and
this can be caught in gdb:

Program received signal SIGABRT, Aborted.
0xc005dce8 in add_nommu_region (region=<value optimized out>) at mm/nommu.c:547
(gdb) bt
#0  0xc005dce8 in add_nommu_region (region=<value optimized out>) at mm/nommu.c:547
#1  0xc005f168 in do_mmap_pgoff (file=0xc31a6620, addr=<value optimized out>, len=3808, prot=3, flags=6146, pgoff=0) at mm/nommu.c:1373
#2  0xc00a96b8 in elf_fdpic_map_file (params=0xc33fbbec, file=0xc31a6620, mm=0xc31bef60, what=0xc0213144 "executable") at mm.h:1145
#3  0xc00aa8b4 in load_elf_fdpic_binary (bprm=0xc316cb00, regs=<value optimized out>) at fs/binfmt_elf_fdpic.c:343
#4  0xc006b588 in search_binary_handler (bprm=0x6, regs=0xc33fbce0) at fs/exec.c:1234
#5  0xc006c648 in do_execve (filename=<value optimized out>, argv=0xc3ad14cc, envp=0xc3ad1460, regs=0xc33fbce0) at fs/exec.c:1356
#6  0xc0008cf0 in sys_execve (name=<value optimized out>, argv=0xc3ad14cc, envp=0xc3ad1460) at arch/frv/kernel/process.c:263
#7  0xc00075dc in __syscall_call () at arch/frv/kernel/entry.S:897

Note that this fix does the following commit differently:

	commit a190887b58c32d19c2eee007c5eb8faa970a69ba
	Author: David Howells <dhowells@redhat.com>
	Date:   Sat Sep 5 11:17:07 2009 -0700
	nommu: fix error handling in do_mmap_pgoff()

Reported-by: Graff Yang <graff.yang@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Greg Ungerer <gerg@snapgear.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/nommu.c b/mm/nommu.c
index 56a446f059716ccb95736fa7670dd1f07e6b30b5..6a002abcb58fb2271c07d001529a64607cb03172 100644 (file)
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1034,7 +1034,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma)
        ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
        if (ret == 0) {
                vma->vm_region->vm_top = vma->vm_region->vm_end;
-               return ret;
+               return 0;
        }
        if (ret != -ENOSYS)
                return ret;
@@ -1051,7 +1051,8 @@ static int do_mmap_shared_file(struct vm_area_struct *vma)
  */
 static int do_mmap_private(struct vm_area_struct *vma,
                           struct vm_region *region,
-                          unsigned long len)
+                          unsigned long len,
+                          unsigned long capabilities)
 {
        struct page *pages;
        unsigned long total, point, n, rlen;
@@ -1062,13 +1063,13 @@ static int do_mmap_private(struct vm_area_struct *vma,
         * shared mappings on devices or memory
         * - VM_MAYSHARE will be set if it may attempt to share
         */
-       if (vma->vm_file) {
+       if (capabilities & BDI_CAP_MAP_DIRECT) {
                ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
                if (ret == 0) {
                        /* shouldn't return success if we're not sharing */
                        BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
                        vma->vm_region->vm_top = vma->vm_region->vm_end;
-                       return ret;
+                       return 0;
                }
                if (ret != -ENOSYS)
                        return ret;
@@ -1306,7 +1307,7 @@ unsigned long do_mmap_pgoff(struct file *file,
                 * - this is the hook for quasi-memory character devices to
                 *   tell us the location of a shared mapping
                 */
-               if (file && file->f_op->get_unmapped_area) {
+               if (capabilities & BDI_CAP_MAP_DIRECT) {
                        addr = file->f_op->get_unmapped_area(file, addr, len,
                                                             pgoff, flags);
                        if (IS_ERR((void *) addr)) {
@@ -1330,15 +1331,17 @@ unsigned long do_mmap_pgoff(struct file *file,
        }
 
        vma->vm_region = region;
-       add_nommu_region(region);
 
-       /* set up the mapping */
+       /* set up the mapping
+        * - the region is filled in if BDI_CAP_MAP_DIRECT is still set
+        */
        if (file && vma->vm_flags & VM_SHARED)
                ret = do_mmap_shared_file(vma);
        else
-               ret = do_mmap_private(vma, region, len);
+               ret = do_mmap_private(vma, region, len, capabilities);
        if (ret < 0)
-               goto error_put_region;
+               goto error_just_free;
+       add_nommu_region(region);
 
        /* okay... we have a mapping; now we have to register it */
        result = vma->vm_start;
@@ -1356,19 +1359,6 @@ share:
        kleave(" = %lx", result);
        return result;
 
-error_put_region:
-       __put_nommu_region(region);
-       if (vma) {
-               if (vma->vm_file) {
-                       fput(vma->vm_file);
-                       if (vma->vm_flags & VM_EXECUTABLE)
-                               removed_exe_file_vma(vma->vm_mm);
-               }
-               kmem_cache_free(vm_area_cachep, vma);
-       }
-       kleave(" = %d [pr]", ret);
-       return ret;
-
 error_just_free:
        up_write(&nommu_region_sem);
 error: