Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-11-06 Thread Anshuman Khandual
On 11/06/2018 06:05 AM, Will Deacon wrote: > On Fri, Nov 02, 2018 at 11:45:00AM +0530, Anshuman Khandual wrote: >> On 10/17/2018 07:39 AM, Andrea Arcangeli wrote: >>> What we need to do during split is an invalidate of the huge TLB. >>> There's no pmd_trans_splitting anymore, so we only clear th

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-11-05 Thread Will Deacon
On Fri, Nov 02, 2018 at 11:45:00AM +0530, Anshuman Khandual wrote: > On 10/17/2018 07:39 AM, Andrea Arcangeli wrote: > > What we need to do during split is an invalidate of the huge TLB. > > There's no pmd_trans_splitting anymore, so we only clear the present > > bit in the PTE despite pmd_present

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-11-01 Thread Anshuman Khandual
On 10/17/2018 07:39 AM, Andrea Arcangeli wrote: > Hello Zi, > > On Sun, Oct 14, 2018 at 08:53:55PM -0400, Zi Yan wrote: >> Hi Andrea, what is the purpose/benefit of making x86’s pmd_present() returns >> true >> for a THP under splitting? Does it cause problems when ARM64’s pmd_present() >> ret

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-11-01 Thread Anshuman Khandual
On 10/18/2018 07:47 AM, Naoya Horiguchi wrote: > On Tue, Oct 16, 2018 at 10:31:50AM -0400, Zi Yan wrote: >> On 15 Oct 2018, at 0:06, Anshuman Khandual wrote: >> >>> On 10/15/2018 06:23 AM, Zi Yan wrote: On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: > On 10/10/2018 06:13 PM, Zi

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-25 Thread Anshuman Khandual
On 10/26/2018 12:15 AM, Zi Yan wrote: > On 25 Oct 2018, at 4:10, Anshuman Khandual wrote: > >> On 10/16/2018 08:01 PM, Zi Yan wrote: >>> On 15 Oct 2018, at 0:06, Anshuman Khandual wrote: >>> On 10/15/2018 06:23 AM, Zi Yan wrote: > On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: >

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-25 Thread Zi Yan
On 25 Oct 2018, at 4:10, Anshuman Khandual wrote: > On 10/16/2018 08:01 PM, Zi Yan wrote: >> On 15 Oct 2018, at 0:06, Anshuman Khandual wrote: >> >>> On 10/15/2018 06:23 AM, Zi Yan wrote: On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: > On 10/10/2018 06:13 PM, Zi Yan wrote: >>

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-25 Thread Anshuman Khandual
On 10/16/2018 08:01 PM, Zi Yan wrote: > On 15 Oct 2018, at 0:06, Anshuman Khandual wrote: > >> On 10/15/2018 06:23 AM, Zi Yan wrote: >>> On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: >>> On 10/10/2018 06:13 PM, Zi Yan wrote: > On 10 Oct 2018, at 0:05, Anshuman Khandual wrote: >

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-22 Thread Zi Yan
Hi Andrea, On 16 Oct 2018, at 22:09, Andrea Arcangeli wrote: > Hello Zi, > > On Sun, Oct 14, 2018 at 08:53:55PM -0400, Zi Yan wrote: >> Hi Andrea, what is the purpose/benefit of making x86’s pmd_present() returns >> true >> for a THP under splitting? Does it cause problems when ARM64’s pmd_prese

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-17 Thread Naoya Horiguchi
On Tue, Oct 16, 2018 at 10:31:50AM -0400, Zi Yan wrote: > On 15 Oct 2018, at 0:06, Anshuman Khandual wrote: > > > On 10/15/2018 06:23 AM, Zi Yan wrote: > >> On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: > >> > >>> On 10/10/2018 06:13 PM, Zi Yan wrote: > On 10 Oct 2018, at 0:05, Anshuman K

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-16 Thread Andrea Arcangeli
Hello Zi, On Sun, Oct 14, 2018 at 08:53:55PM -0400, Zi Yan wrote: > Hi Andrea, what is the purpose/benefit of making x86’s pmd_present() returns > true > for a THP under splitting? Does it cause problems when ARM64’s pmd_present() > returns false in the same situation? !pmd_present means it's a

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-16 Thread Zi Yan
On 15 Oct 2018, at 0:06, Anshuman Khandual wrote: > On 10/15/2018 06:23 AM, Zi Yan wrote: >> On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: >> >>> On 10/10/2018 06:13 PM, Zi Yan wrote: On 10 Oct 2018, at 0:05, Anshuman Khandual wrote: > On 10/09/2018 07:28 PM, Zi Yan wrote: >>

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-16 Thread Anshuman Khandual
On 10/15/2018 02:02 PM, Aneesh Kumar K.V wrote: > On 10/12/18 1:32 PM, Anshuman Khandual wrote: >> >> >> On 10/09/2018 06:48 PM, Will Deacon wrote: >>> On Tue, Oct 09, 2018 at 04:04:21PM +0300, Kirill A. Shutemov wrote: On Tue, Oct 09, 2018 at 09:28:58AM +0530, Anshuman Khandual wrote:

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-16 Thread Anshuman Khandual
On 10/15/2018 06:23 AM, Zi Yan wrote: > On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: > >> On 10/10/2018 06:13 PM, Zi Yan wrote: >>> On 10 Oct 2018, at 0:05, Anshuman Khandual wrote: >>> On 10/09/2018 07:28 PM, Zi Yan wrote: > cc: Naoya Horiguchi (who proposed to use !_PAGE_PRESENT

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-15 Thread Aneesh Kumar K.V
On 10/12/18 1:32 PM, Anshuman Khandual wrote: On 10/09/2018 06:48 PM, Will Deacon wrote: On Tue, Oct 09, 2018 at 04:04:21PM +0300, Kirill A. Shutemov wrote: On Tue, Oct 09, 2018 at 09:28:58AM +0530, Anshuman Khandual wrote: A normal mapped THP page at PMD level should be correctly differenti

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-14 Thread Zi Yan
On 12 Oct 2018, at 4:00, Anshuman Khandual wrote: > On 10/10/2018 06:13 PM, Zi Yan wrote: >> On 10 Oct 2018, at 0:05, Anshuman Khandual wrote: >> >>> On 10/09/2018 07:28 PM, Zi Yan wrote: cc: Naoya Horiguchi (who proposed to use !_PAGE_PRESENT && !_PAGE_PSE for x86 PMD migration en

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-12 Thread Anshuman Khandual
On 10/09/2018 06:48 PM, Will Deacon wrote: > On Tue, Oct 09, 2018 at 04:04:21PM +0300, Kirill A. Shutemov wrote: >> On Tue, Oct 09, 2018 at 09:28:58AM +0530, Anshuman Khandual wrote: >>> A normal mapped THP page at PMD level should be correctly differentiated >>> from a PMD migration entry while

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-12 Thread Anshuman Khandual
On 10/10/2018 06:13 PM, Zi Yan wrote: > On 10 Oct 2018, at 0:05, Anshuman Khandual wrote: > >> On 10/09/2018 07:28 PM, Zi Yan wrote: >>> cc: Naoya Horiguchi (who proposed to use !_PAGE_PRESENT && !_PAGE_PSE for >>> x86 >>> PMD migration entry check) >>> >>> On 8 Oct 2018, at 23:58, Anshuman Kh

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-10 Thread Zi Yan
On 10 Oct 2018, at 0:05, Anshuman Khandual wrote: > On 10/09/2018 07:28 PM, Zi Yan wrote: >> cc: Naoya Horiguchi (who proposed to use !_PAGE_PRESENT && !_PAGE_PSE for x86 >> PMD migration entry check) >> >> On 8 Oct 2018, at 23:58, Anshuman Khandual wrote: >> >>> A normal mapped THP page at PMD le

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-09 Thread Anshuman Khandual
On 10/09/2018 07:28 PM, Zi Yan wrote: > cc: Naoya Horiguchi (who proposed to use !_PAGE_PRESENT && !_PAGE_PSE for x86 > PMD migration entry check) > > On 8 Oct 2018, at 23:58, Anshuman Khandual wrote: > >> A normal mapped THP page at PMD level should be correctly differentiated >> from a PMD m

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-09 Thread Zi Yan
cc: Naoya Horiguchi (who proposed to use !_PAGE_PRESENT && !_PAGE_PSE for x86 PMD migration entry check) On 8 Oct 2018, at 23:58, Anshuman Khandual wrote: > A normal mapped THP page at PMD level should be correctly differentiated > from a PMD migration entry while walking the page table. A mapped

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-09 Thread Anshuman Khandual
On 10/09/2018 06:34 PM, Kirill A. Shutemov wrote: > On Tue, Oct 09, 2018 at 09:28:58AM +0530, Anshuman Khandual wrote: >> A normal mapped THP page at PMD level should be correctly differentiated >> from a PMD migration entry while walking the page table. A mapped THP would >> additionally check

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-09 Thread Will Deacon
On Tue, Oct 09, 2018 at 04:04:21PM +0300, Kirill A. Shutemov wrote: > On Tue, Oct 09, 2018 at 09:28:58AM +0530, Anshuman Khandual wrote: > > A normal mapped THP page at PMD level should be correctly differentiated > > from a PMD migration entry while walking the page table. A mapped THP would > > a

Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-09 Thread Kirill A. Shutemov
On Tue, Oct 09, 2018 at 09:28:58AM +0530, Anshuman Khandual wrote: > A normal mapped THP page at PMD level should be correctly differentiated > from a PMD migration entry while walking the page table. A mapped THP would > additionally check positive for pmd_present() along with pmd_trans_huge() > a

[PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry

2018-10-08 Thread Anshuman Khandual
A normal mapped THP page at PMD level should be correctly differentiated from a PMD migration entry while walking the page table. A mapped THP would additionally check positive for pmd_present() along with pmd_trans_huge() as compared to a PMD migration entry. This just adds a new conditional test