Re: put_page on transparent huge page leaks?

2014-02-22 Thread Jay Cornwall
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

Re: put_page on transparent huge page leaks?

2014-02-22 Thread Jay Cornwall
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: npages = get_user_pages(fault->state->task, fault->state

Re: put_page on transparent huge page leaks?

2014-02-21 Thread Kirill A. Shutemov
On Fri, Feb 21, 2014 at 11:23:39AM -0600, Jay Cornwall wrote: > Hi, > > 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: > > npages = get_user_pages(fault->state->task, fault->state->mm, > fa

put_page on transparent huge page leaks?

2014-02-21 Thread Jay Cornwall
Hi, 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: npages = get_user_pages(fault->state->task, fault->state->mm, fault->address, 1, write, 0, &page, NULL); if (npages == 1) put_pa