From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1034741AbeEXW2O (ORCPT ); Thu, 24 May 2018 18:28:14 -0400 Received: from userp2130.oracle.com ([156.151.31.86]:37646 "EHLO userp2130.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1033218AbeEXW2N (ORCPT ); Thu, 24 May 2018 18:28:13 -0400 Subject: Re: [PATCH -V2 -mm 4/4] mm, hugetlbfs: Pass fault address to cow handler To: "Huang, Ying" , Andrew Morton Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Michal Hocko , David Rientjes , Andrea Arcangeli , "Kirill A. Shutemov" , Andi Kleen , Jan Kara , Matthew Wilcox , Hugh Dickins , Minchan Kim , Shaohua Li , Christopher Lameter , "Aneesh Kumar K.V" , Punit Agrawal , Anshuman Khandual References: <20180524005851.4079-1-ying.huang@intel.com> <20180524005851.4079-5-ying.huang@intel.com> From: Mike Kravetz Message-ID: Date: Thu, 24 May 2018 15:27:32 -0700 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.5.2 MIME-Version: 1.0 In-Reply-To: <20180524005851.4079-5-ying.huang@intel.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit X-Proofpoint-Virus-Version: vendor=nai engine=5900 definitions=8903 signatures=668700 X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 suspectscore=0 malwarescore=0 phishscore=0 bulkscore=0 spamscore=0 mlxscore=0 mlxlogscore=999 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1711220000 definitions=main-1805240253 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/23/2018 05:58 PM, Huang, Ying wrote: > From: Huang Ying > > This is to take better advantage of the general huge page copying > optimization. Where, the target subpage will be copied last to avoid > the cache lines of target subpage to be evicted when copying other > subpages. This works better if the address of the target subpage is > available when copying huge page. So hugetlbfs page fault handlers > are changed to pass that information to hugetlb_cow(). This will > benefit workloads which don't access the begin of the hugetlbfs huge > page after the page fault under heavy cache contention. > > Signed-off-by: "Huang, Ying" Reviewed-by: Mike Kravetz -- Mike Kravetz > Cc: Mike Kravetz > Cc: Michal Hocko > Cc: David Rientjes > Cc: Andrea Arcangeli > Cc: "Kirill A. Shutemov" > Cc: Andi Kleen > Cc: Jan Kara > Cc: Matthew Wilcox > Cc: Hugh Dickins > Cc: Minchan Kim > Cc: Shaohua Li > Cc: Christopher Lameter > Cc: "Aneesh Kumar K.V" > Cc: Punit Agrawal > Cc: Anshuman Khandual > --- > mm/hugetlb.c | 9 +++++---- > 1 file changed, 5 insertions(+), 4 deletions(-) > > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index ad3bec2ed269..1df974af34c1 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -3500,7 +3500,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, > * Keep the pte_same checks anyway to make transition from the mutex easier. > */ > static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > - unsigned long haddr, pte_t *ptep, > + unsigned long address, pte_t *ptep, > struct page *pagecache_page, spinlock_t *ptl) > { > pte_t pte; > @@ -3509,6 +3509,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > int ret = 0, outside_reserve = 0; > unsigned long mmun_start; /* For mmu_notifiers */ > unsigned long mmun_end; /* For mmu_notifiers */ > + unsigned long haddr = address & huge_page_mask(h); > > pte = huge_ptep_get(ptep); > old_page = pte_page(pte); > @@ -3583,7 +3584,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > goto out_release_all; > } > > - copy_user_huge_page(new_page, old_page, haddr, vma, > + copy_user_huge_page(new_page, old_page, address, vma, > pages_per_huge_page(h)); > __SetPageUptodate(new_page); > set_page_huge_active(new_page); > @@ -3817,7 +3818,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, > hugetlb_count_add(pages_per_huge_page(h), mm); > if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { > /* Optimization, do the COW without a second fault */ > - ret = hugetlb_cow(mm, vma, haddr, ptep, page, ptl); > + ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); > } > > spin_unlock(ptl); > @@ -3971,7 +3972,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, > > if (flags & FAULT_FLAG_WRITE) { > if (!huge_pte_write(entry)) { > - ret = hugetlb_cow(mm, vma, haddr, ptep, > + ret = hugetlb_cow(mm, vma, address, ptep, > pagecache_page, ptl); > goto out_put_page; > } >