Re: [PATCH v2 2/3] mm/hugetlb: use get_page_unless_zero() in hugetlb_fault()

2014-08-12 Thread Naoya Horiguchi
On Sat, Aug 09, 2014 at 04:11:06PM -0700, Hugh Dickins wrote: > On Fri, 1 Aug 2014, Naoya Horiguchi wrote: > > > After fixing locking in follow_page(FOLL_GET) for hugepages, I start to > > observe the BUG of "get_page() on refcount 0 page" in hugetlb_fault() in > > the same test. > > > > I'm not

Re: [PATCH v2 2/3] mm/hugetlb: use get_page_unless_zero() in hugetlb_fault()

2014-08-12 Thread Naoya Horiguchi
On Sat, Aug 09, 2014 at 04:11:06PM -0700, Hugh Dickins wrote: On Fri, 1 Aug 2014, Naoya Horiguchi wrote: After fixing locking in follow_page(FOLL_GET) for hugepages, I start to observe the BUG of get_page() on refcount 0 page in hugetlb_fault() in the same test. I'm not exactly sure

Re: [PATCH v2 2/3] mm/hugetlb: use get_page_unless_zero() in hugetlb_fault()

2014-08-09 Thread Hugh Dickins
On Fri, 1 Aug 2014, Naoya Horiguchi wrote: > After fixing locking in follow_page(FOLL_GET) for hugepages, I start to > observe the BUG of "get_page() on refcount 0 page" in hugetlb_fault() in > the same test. > > I'm not exactly sure about how this race is triggered, but hugetlb_fault() > calls

Re: [PATCH v2 2/3] mm/hugetlb: use get_page_unless_zero() in hugetlb_fault()

2014-08-09 Thread Hugh Dickins
On Fri, 1 Aug 2014, Naoya Horiguchi wrote: After fixing locking in follow_page(FOLL_GET) for hugepages, I start to observe the BUG of get_page() on refcount 0 page in hugetlb_fault() in the same test. I'm not exactly sure about how this race is triggered, but hugetlb_fault() calls

[PATCH v2 2/3] mm/hugetlb: use get_page_unless_zero() in hugetlb_fault()

2014-08-01 Thread Naoya Horiguchi
After fixing locking in follow_page(FOLL_GET) for hugepages, I start to observe the BUG of "get_page() on refcount 0 page" in hugetlb_fault() in the same test. I'm not exactly sure about how this race is triggered, but hugetlb_fault() calls pte_page() and get_page() outside page table lock, so

[PATCH v2 2/3] mm/hugetlb: use get_page_unless_zero() in hugetlb_fault()

2014-08-01 Thread Naoya Horiguchi
After fixing locking in follow_page(FOLL_GET) for hugepages, I start to observe the BUG of get_page() on refcount 0 page in hugetlb_fault() in the same test. I'm not exactly sure about how this race is triggered, but hugetlb_fault() calls pte_page() and get_page() outside page table lock, so it's