Re: [RFC] mm:fix zero_page huge_zero_page rss/pss statistic

2014-12-12 Thread Kirill A. Shutemov
'Konstantin Khlebnikov'; 'linux- > > ker...@vger.kernel.org'; 'linux...@kvack.org'; 'linux-arm- > > ker...@lists.infradead.org'; 'n-horigu...@ah.jp.nec.com'; 'o...@redhat.com'; > > 'gorcu...@openvz.org'; 'pfei...@google.

RE: [RFC] mm:fix zero_page huge_zero_page rss/pss statistic

2014-12-11 Thread Wang, Yalin
@kvack.org'; 'linux-arm- > ker...@lists.infradead.org'; 'n-horigu...@ah.jp.nec.com'; 'o...@redhat.com'; > 'gorcu...@openvz.org'; 'pfei...@google.com' > Subject: Re: [RFC] mm:fix zero_page huge_zero_page rss/pss statistic > > On W

Re: [RFC] mm:fix zero_page huge_zero_page rss/pss statistic

2014-12-10 Thread Kirill A. Shutemov
On Wed, Dec 10, 2014 at 03:22:21PM +0800, Wang, Yalin wrote: > smaps_pte_entry() doesn't ignore zero_huge_page, > but it ignore zero_page, because vm_normal_page() will > ignore it. We remove vm_normal_page() call, because walk_page_range() > have ignore VM_PFNMAP vma maps, it's safe to just use pf

[RFC] mm:fix zero_page huge_zero_page rss/pss statistic

2014-12-09 Thread Wang, Yalin
smaps_pte_entry() doesn't ignore zero_huge_page, but it ignore zero_page, because vm_normal_page() will ignore it. We remove vm_normal_page() call, because walk_page_range() have ignore VM_PFNMAP vma maps, it's safe to just use pfn_valid(), so that we can also consider zero_page to be a valid page.