When faulting in pages for mlock(), we want to break COW for anonymous
or file pages within VM_WRITABLE, non-VM_SHARED vmas. However, there is
no need to write-fault into VM_SHARED vmas since shared file pages can
be mlocked first and dirtied later, when/if they actually get written to.
Skipping the write fault is desirable, as we don't want to unnecessarily
cause these pages to be dirtied and queued for writeback.
Signed-off-by: Michel Lespinasse <walken@google.com>
---
mm/memory.c | 7 ++++++-
mm/mlock.c | 7 ++++++-
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index d4c0c2e..7f45085 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3291,7 +3291,12 @@ int make_pages_present(unsigned long addr, unsigned long end)
vma = find_vma(current->mm, addr);
if (!vma)
return -ENOMEM;
- write = (vma->vm_flags & VM_WRITE) != 0;
+ /*
+ * We want to touch writable mappings with a write fault in order
+ * to break COW, except for shared mappings because these don't COW
+ * and we would not want to dirty them for nothing.
+ */
+ write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
BUG_ON(addr >= end);
BUG_ON(end > vma->vm_end);
len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
diff --git a/mm/mlock.c b/mm/mlock.c
index b70919c..4f31864 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -171,7 +171,12 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
gup_flags = FOLL_TOUCH | FOLL_GET;
- if (vma->vm_flags & VM_WRITE)
+ /*
+ * We want to touch writable mappings with a write fault in order
+ * to break COW, except for shared mappings because these don't COW
+ * and we would not want to dirty them for nothing.
+ */
+ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
gup_flags |= FOLL_WRITE;
/* We don't try to access the guard page of a stack vma */
--
1.7.3.1
--
