On Thu, Jan 19, 2012 at 12:21 AM, Arun Sharma [off-list ref] 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

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>