summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
authorPeter Feiner <pfeiner@google.com>2014-10-13 15:55:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-10-14 02:18:28 +0200
commit64e455079e1bd7787cc47be30b7f601ce682a5f6 (patch)
tree05193bd91be3ffc0d33ddd3ffb654ef4c23778f9 /fs/proc
parent63a12d9d01831208a47f5c0fbbf93f503d1fb162 (diff)
mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared
For VMAs that don't want write notifications, PTEs created for read faults have their write bit set. If the read fault happens after VM_SOFTDIRTY is cleared, then the PTE's softdirty bit will remain clear after subsequent writes. Here's a simple code snippet to demonstrate the bug: char* m = mmap(NULL, getpagesize(), PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_SHARED, -1, 0); system("echo 4 > /proc/$PPID/clear_refs"); /* clear VM_SOFTDIRTY */ assert(*m == '\0'); /* new PTE allows write access */ assert(!soft_dirty(x)); *m = 'x'; /* should dirty the page */ assert(soft_dirty(x)); /* fails */ With this patch, write notifications are enabled when VM_SOFTDIRTY is cleared. Furthermore, to avoid unnecessary faults, write notifications are disabled when VM_SOFTDIRTY is set. As a side effect of enabling and disabling write notifications with care, this patch fixes a bug in mprotect where vm_page_prot bits set by drivers were zapped on mprotect. An analogous bug was fixed in mmap by commit c9d0bf241451 ("mm: uncached vma support with writenotify"). Signed-off-by: Peter Feiner <pfeiner@google.com> Reported-by: Peter Feiner <pfeiner@google.com> Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Jamie Liu <jamieliu@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/task_mmu.c19
1 files changed, 14 insertions, 5 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b7a7dc963a35..4e0388cffe3d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -827,8 +827,21 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
.private = &cp,
};
down_read(&mm->mmap_sem);
- if (type == CLEAR_REFS_SOFT_DIRTY)
+ if (type == CLEAR_REFS_SOFT_DIRTY) {
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (!(vma->vm_flags & VM_SOFTDIRTY))
+ continue;
+ up_read(&mm->mmap_sem);
+ down_write(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
+ }
+ downgrade_write(&mm->mmap_sem);
+ break;
+ }
mmu_notifier_invalidate_range_start(mm, 0, -1);
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cp.vma = vma;
if (is_vm_hugetlb_page(vma))
@@ -848,10 +861,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
continue;
if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
continue;
- if (type == CLEAR_REFS_SOFT_DIRTY) {
- if (vma->vm_flags & VM_SOFTDIRTY)
- vma->vm_flags &= ~VM_SOFTDIRTY;
- }
walk_page_range(vma->vm_start, vma->vm_end,
&clear_refs_walk);
}