Messages in this thread | | | Date | Thu, 23 Feb 2012 13:15:30 +0530 | Subject | Re: [PATCH] mm: Enable MAP_UNINITIALIZED for archs with mmu | From | Balbir Singh <> |
| |
On Thu, Jan 19, 2012 at 12:21 AM, Arun Sharma <asharma@fb.com> wrote: > > This enables malloc optimizations where we might > madvise(..,MADV_DONTNEED) a page only to fault it > back at a different virtual address. > > To ensure that we don't leak sensitive data to > unprivileged processes, we enable this optimization > only for pages that are reused within a memory > cgroup. >
So the assumption is that only apps that have access to each others VMA's will run in this cgroup?
> The idea is to make this opt-in both at the mmap() > level and cgroup level so the default behavior is > unchanged after the patch. >
Sorry, I am not convinced we need to do this
1. I know that zeroing out memory is expensive, but building a potential loop hole is not a good idea 2. How do we ensure that tasks in a cgroup should be allowed to reuse memory uninitialized, how does the cgroup admin know what she is getting into?
So I am going to NACK this.
Balbir
| |