Messages in this thread | | | Date | Sat, 22 Feb 2014 13:31:19 -0600 | From | Jay Cornwall <> | Subject | Re: put page on transparent huge page leaks ? |
| |
On 2014-02-22 11:44, Jay Cornwall wrote: > On 2014-02-21 20:31, Kirill A. Shutemov wrote: >> On Fri, Feb 21, 2014 at 11:23:39AM -0600, Jay Cornwall wrote: >>> I'm tracking a possible memory leak in iommu/amd. The driver uses >>> this logic >>> to fault a page in response to a PRI from a device: > > The head page appears to be leaking a reference. There is *no leak* if > the driver faults the head page directly.
My apologies, this was fixed somewhere in the patch series: "mm: tail page refcounting optimization for slab and hugetlbfs" (Jan 22nd).
Our merge was slightly older than I'd thought.
| |