mm: introduce VM_POPULATE flag to better deal with racy userspace programs
The vm_populate() code populates user mappings without constantly
holding the mmap_sem. This makes it susceptible to racy userspace
programs: the user mappings may change while vm_populate() is running,
and in this case vm_populate() may end up populating the new mapping
instead of the old one.
In order to reduce the possibility of userspace getting surprised by
this behavior, this change introduces the VM_POPULATE vma flag which
gets set on vmas we want vm_populate() to work on. This way
vm_populate() may still end up populating the new mapping after such a
race, but only if the new mapping is also one that the user has
requested (using MAP_SHARED, MAP_LOCKED or mlock) to be populated.
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/fremap.c b/mm/fremap.c
index 503a723..0cd4c1148 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -204,8 +204,10 @@
unsigned long addr;
struct file *file = get_file(vma->vm_file);
- addr = mmap_region(file, start, size,
- vma->vm_flags, pgoff);
+ vm_flags = vma->vm_flags;
+ if (!(flags & MAP_NONBLOCK))
+ vm_flags |= VM_POPULATE;
+ addr = mmap_region(file, start, size, vm_flags, pgoff);
fput(file);
if (IS_ERR_VALUE(addr)) {
err = addr;
@@ -224,6 +226,12 @@
mutex_unlock(&mapping->i_mmap_mutex);
}
+ if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) {
+ if (!has_write_lock)
+ goto get_write_lock;
+ vma->vm_flags |= VM_POPULATE;
+ }
+
if (vma->vm_flags & VM_LOCKED) {
/*
* drop PG_Mlocked flag for over-mapped range
diff --git a/mm/mlock.c b/mm/mlock.c
index 569400a..d6378fe 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -340,9 +340,9 @@
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
- newflags = vma->vm_flags | VM_LOCKED;
- if (!on)
- newflags &= ~VM_LOCKED;
+ newflags = vma->vm_flags & ~VM_LOCKED;
+ if (on)
+ newflags |= VM_LOCKED | VM_POPULATE;
tmp = vma->vm_end;
if (tmp > end)
@@ -402,7 +402,8 @@
* range with the first VMA. Also, skip undesirable VMA types.
*/
nend = min(end, vma->vm_end);
- if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ if ((vma->vm_flags & (VM_IO | VM_PFNMAP | VM_POPULATE)) !=
+ VM_POPULATE)
continue;
if (nstart < vma->vm_start)
nstart = vma->vm_start;
@@ -475,18 +476,18 @@
struct vm_area_struct * vma, * prev = NULL;
if (flags & MCL_FUTURE)
- current->mm->def_flags |= VM_LOCKED;
+ current->mm->def_flags |= VM_LOCKED | VM_POPULATE;
else
- current->mm->def_flags &= ~VM_LOCKED;
+ current->mm->def_flags &= ~(VM_LOCKED | VM_POPULATE);
if (flags == MCL_FUTURE)
goto out;
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
vm_flags_t newflags;
- newflags = vma->vm_flags | VM_LOCKED;
- if (!(flags & MCL_CURRENT))
- newflags &= ~VM_LOCKED;
+ newflags = vma->vm_flags & ~VM_LOCKED;
+ if (flags & MCL_CURRENT)
+ newflags |= VM_LOCKED | VM_POPULATE;
/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
diff --git a/mm/mmap.c b/mm/mmap.c
index 8826c77..39a3944 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1306,9 +1306,7 @@
}
addr = mmap_region(file, addr, len, vm_flags, pgoff);
- if (!IS_ERR_VALUE(addr) &&
- ((vm_flags & VM_LOCKED) ||
- (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
+ if (!IS_ERR_VALUE(addr) && (vm_flags & VM_POPULATE))
*populate = true;
return addr;
}