Re: [PATCH v2 0/2] arm64: fix the bugs found in the hugetlb test

2016-11-08 Thread Huang Shijie
Hi Will & Catalin, On Tue, Nov 08, 2016 at 04:36:43PM +, Will Deacon wrote: > On Tue, Nov 08, 2016 at 02:09:09PM +, Catalin Marinas wrote: > > On Tue, Nov 08, 2016 at 01:44:37PM +0800, Huang Shijie wrote: > > > (3) The test result in the Softiron and Juno-r1 boards: > > > > > >This de

[PATCH v2 0/2] arm64: fix the bugs found in the hugetlb test

2016-11-08 Thread Huang Shijie
(1) Backgroud For the arm64, the hugetlb page size can be 32M (PMD + Contiguous bit). In the 4K page environment, the max page order is 10 (max_order - 1), so 32M page is the gigantic page. The arm64 MMU supports a Contiguous bit which is a hint that the PTE is one of a set of c

Re: [PATCH v2 0/2] arm64: fix the bugs found in the hugetlb test

2016-11-08 Thread Will Deacon
On Tue, Nov 08, 2016 at 02:09:09PM +, Catalin Marinas wrote: > On Tue, Nov 08, 2016 at 01:44:37PM +0800, Huang Shijie wrote: > > (3) The test result in the Softiron and Juno-r1 boards: > > > >This detail test result shows below (both the "make func" & "make > > stress"): > > > > 4KB

Re: [PATCH v2 0/2] arm64: fix the bugs found in the hugetlb test

2016-11-08 Thread Catalin Marinas
On Tue, Nov 08, 2016 at 01:44:37PM +0800, Huang Shijie wrote: > (3) The test result in the Softiron and Juno-r1 boards: > >This detail test result shows below (both the "make func" & "make stress"): > > 4KB granule: > > 1.1) PTE + Contiguous bit : 4K x 16 = 64K (per huge page siz