From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> To: Joonsoo Kim <iamjoonsoo.kim@lge.com>, Andrew Morton <akpm@linux-foundation.org> Cc: Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>, Michal Hocko <mhocko@suse.cz>, KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>, Hugh Dickins <hughd@google.com>, Davidlohr Bueso <davidlohr.bueso@hp.com>, David Gibson <david@gibson.dropbear.id.au>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Joonsoo Kim <js1304@gmail.com>, Joonsoo Kim <iamjoonsoo.kim@lge.com> Subject: Re: [PATCH 6/9] mm, hugetlb: do not use a page in page cache for cow optimization Date: Mon, 15 Jul 2013 19:25:40 +0530 [thread overview] Message-ID: <87d2qkj5b7.fsf@linux.vnet.ibm.com> (raw) In-Reply-To: <1373881967-16153-7-git-send-email-iamjoonsoo.kim@lge.com> Joonsoo Kim <iamjoonsoo.kim@lge.com> writes: > Currently, we use a page with mapped count 1 in page cache for cow > optimization. If we find this condition, we don't allocate a new > page and copy contents. Instead, we map this page directly. > This may introduce a problem that writting to private mapping overwrite > hugetlb file directly. You can find this situation with following code. > > size = 20 * MB; > flag = MAP_SHARED; > p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); > if (p == MAP_FAILED) { > fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); > return -1; > } > p[0] = 's'; > fprintf(stdout, "BEFORE STEAL PRIVATE WRITE: %c\n", p[0]); > munmap(p, size); > > flag = MAP_PRIVATE; > p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); > if (p == MAP_FAILED) { > fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); > } > p[0] = 'c'; > munmap(p, size); > > flag = MAP_SHARED; > p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); > if (p == MAP_FAILED) { > fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); > return -1; > } > fprintf(stdout, "AFTER STEAL PRIVATE WRITE: %c\n", p[0]); > munmap(p, size); > > We can see that "AFTER STEAL PRIVATE WRITE: c", not "AFTER STEAL > PRIVATE WRITE: s". If we turn off this optimization to a page > in page cache, the problem is disappeared. Do we need to trun of the optimization for page cache completely ? Can't we check for MAP_PRIVATE case ? Also, we may want to add the above test into libhugetlbfs > > Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> > > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index d4a1695..6c1eb9b 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -2512,7 +2512,6 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > { > struct hstate *h = hstate_vma(vma); > struct page *old_page, *new_page; > - int avoidcopy; > int outside_reserve = 0; > unsigned long mmun_start; /* For mmu_notifiers */ > unsigned long mmun_end; /* For mmu_notifiers */ > @@ -2522,10 +2521,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > retry_avoidcopy: > /* If no-one else is actually using this page, avoid the copy > * and just make the page writable */ > - avoidcopy = (page_mapcount(old_page) == 1); > - if (avoidcopy) { > - if (PageAnon(old_page)) > - page_move_anon_rmap(old_page, vma, address); > + if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { > + page_move_anon_rmap(old_page, vma, address); > set_huge_ptep_writable(vma, address, ptep); > return 0; > } -aneesh
WARNING: multiple messages have this Message-ID (diff)
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> To: Joonsoo Kim <iamjoonsoo.kim@lge.com>, Andrew Morton <akpm@linux-foundation.org> Cc: Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>, Michal Hocko <mhocko@suse.cz>, KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>, Hugh Dickins <hughd@google.com>, Davidlohr Bueso <davidlohr.bueso@hp.com>, David Gibson <david@gibson.dropbear.id.au>, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Joonsoo Kim <js1304@gmail.com> Subject: Re: [PATCH 6/9] mm, hugetlb: do not use a page in page cache for cow optimization Date: Mon, 15 Jul 2013 19:25:40 +0530 [thread overview] Message-ID: <87d2qkj5b7.fsf@linux.vnet.ibm.com> (raw) In-Reply-To: <1373881967-16153-7-git-send-email-iamjoonsoo.kim@lge.com> Joonsoo Kim <iamjoonsoo.kim@lge.com> writes: > Currently, we use a page with mapped count 1 in page cache for cow > optimization. If we find this condition, we don't allocate a new > page and copy contents. Instead, we map this page directly. > This may introduce a problem that writting to private mapping overwrite > hugetlb file directly. You can find this situation with following code. > > size = 20 * MB; > flag = MAP_SHARED; > p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); > if (p == MAP_FAILED) { > fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); > return -1; > } > p[0] = 's'; > fprintf(stdout, "BEFORE STEAL PRIVATE WRITE: %c\n", p[0]); > munmap(p, size); > > flag = MAP_PRIVATE; > p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); > if (p == MAP_FAILED) { > fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); > } > p[0] = 'c'; > munmap(p, size); > > flag = MAP_SHARED; > p = mmap(NULL, size, PROT_READ|PROT_WRITE, flag, fd, 0); > if (p == MAP_FAILED) { > fprintf(stderr, "mmap() failed: %s\n", strerror(errno)); > return -1; > } > fprintf(stdout, "AFTER STEAL PRIVATE WRITE: %c\n", p[0]); > munmap(p, size); > > We can see that "AFTER STEAL PRIVATE WRITE: c", not "AFTER STEAL > PRIVATE WRITE: s". If we turn off this optimization to a page > in page cache, the problem is disappeared. Do we need to trun of the optimization for page cache completely ? Can't we check for MAP_PRIVATE case ? Also, we may want to add the above test into libhugetlbfs > > Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> > > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index d4a1695..6c1eb9b 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -2512,7 +2512,6 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > { > struct hstate *h = hstate_vma(vma); > struct page *old_page, *new_page; > - int avoidcopy; > int outside_reserve = 0; > unsigned long mmun_start; /* For mmu_notifiers */ > unsigned long mmun_end; /* For mmu_notifiers */ > @@ -2522,10 +2521,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, > retry_avoidcopy: > /* If no-one else is actually using this page, avoid the copy > * and just make the page writable */ > - avoidcopy = (page_mapcount(old_page) == 1); > - if (avoidcopy) { > - if (PageAnon(old_page)) > - page_move_anon_rmap(old_page, vma, address); > + if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { > + page_move_anon_rmap(old_page, vma, address); > set_huge_ptep_writable(vma, address, ptep); > return 0; > } -aneesh -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2013-07-15 13:55 UTC|newest] Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top 2013-07-15 9:52 [PATCH 0/9] mm, hugetlb: clean-up and possible bug fix Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 9:52 ` [PATCH 1/9] mm, hugetlb: move up the code which check availability of free huge page Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 14:01 ` Aneesh Kumar K.V 2013-07-15 14:01 ` Aneesh Kumar K.V 2013-07-16 1:16 ` Joonsoo Kim 2013-07-16 1:16 ` Joonsoo Kim 2013-07-16 3:36 ` Aneesh Kumar K.V 2013-07-16 3:36 ` Aneesh Kumar K.V 2013-07-16 5:10 ` Joonsoo Kim 2013-07-16 5:10 ` Joonsoo Kim 2013-07-22 14:45 ` Michal Hocko 2013-07-22 14:45 ` Michal Hocko 2013-07-15 9:52 ` [PATCH 2/9] mm, hugetlb: trivial commenting fix Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 13:12 ` Hillf Danton 2013-07-15 13:12 ` Hillf Danton 2013-07-15 14:02 ` Aneesh Kumar K.V 2013-07-15 14:02 ` Aneesh Kumar K.V 2013-07-22 14:46 ` Michal Hocko 2013-07-22 14:46 ` Michal Hocko 2013-07-15 9:52 ` [PATCH 3/9] mm, hugetlb: clean-up alloc_huge_page() Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-22 14:51 ` Michal Hocko 2013-07-22 14:51 ` Michal Hocko 2013-07-23 7:29 ` Joonsoo Kim 2013-07-23 7:29 ` Joonsoo Kim 2013-07-15 9:52 ` [PATCH 4/9] mm, hugetlb: fix and clean-up node iteration code to alloc or free Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 14:27 ` Aneesh Kumar K.V 2013-07-15 14:27 ` Aneesh Kumar K.V 2013-07-16 1:41 ` Joonsoo Kim 2013-07-16 1:41 ` Joonsoo Kim 2013-07-17 2:00 ` Jianguo Wu 2013-07-17 2:00 ` Jianguo Wu 2013-07-18 6:46 ` Joonsoo Kim 2013-07-18 6:46 ` Joonsoo Kim 2013-07-15 9:52 ` [PATCH 5/9] mm, hugetlb: remove redundant list_empty check in gather_surplus_pages() Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 14:31 ` Aneesh Kumar K.V 2013-07-15 14:31 ` Aneesh Kumar K.V 2013-07-16 1:42 ` Joonsoo Kim 2013-07-16 1:42 ` Joonsoo Kim 2013-07-22 14:55 ` Michal Hocko 2013-07-22 14:55 ` Michal Hocko 2013-07-15 9:52 ` [PATCH 6/9] mm, hugetlb: do not use a page in page cache for cow optimization Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 13:55 ` Aneesh Kumar K.V [this message] 2013-07-15 13:55 ` Aneesh Kumar K.V 2013-07-16 1:56 ` Joonsoo Kim 2013-07-16 1:56 ` Joonsoo Kim 2013-07-17 8:55 ` Wanpeng Li 2013-07-17 8:55 ` Wanpeng Li 2013-07-15 9:52 ` [PATCH 7/9] mm, hugetlb: add VM_NORESERVE check in vma_has_reserves() Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 14:48 ` Aneesh Kumar K.V 2013-07-15 14:48 ` Aneesh Kumar K.V 2013-07-15 15:11 ` Aneesh Kumar K.V 2013-07-15 15:11 ` Aneesh Kumar K.V 2013-07-16 2:12 ` Joonsoo Kim 2013-07-16 2:12 ` Joonsoo Kim 2013-07-16 5:47 ` Aneesh Kumar K.V 2013-07-16 5:47 ` Aneesh Kumar K.V 2013-07-16 7:12 ` Joonsoo Kim 2013-07-16 7:12 ` Joonsoo Kim 2013-07-18 2:03 ` Wanpeng Li 2013-07-18 2:03 ` Wanpeng Li 2013-07-15 9:52 ` [PATCH 8/9] mm, hugetlb: remove decrement_hugepage_resv_vma() Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 14:50 ` Aneesh Kumar K.V 2013-07-15 14:50 ` Aneesh Kumar K.V 2013-07-17 9:31 ` Wanpeng Li 2013-07-17 9:31 ` Wanpeng Li 2013-07-15 9:52 ` [PATCH 9/9] mm, hugetlb: decrement reserve count if VM_NORESERVE alloc page cache Joonsoo Kim 2013-07-15 9:52 ` Joonsoo Kim 2013-07-15 15:11 ` Aneesh Kumar K.V 2013-07-15 15:11 ` Aneesh Kumar K.V 2013-07-18 2:02 ` Wanpeng Li 2013-07-18 2:02 ` Wanpeng Li 2013-07-15 14:10 ` [PATCH 0/9] mm, hugetlb: clean-up and possible bug fix Aneesh Kumar K.V 2013-07-15 14:10 ` Aneesh Kumar K.V 2013-07-16 1:10 ` Joonsoo Kim 2013-07-16 1:10 ` Joonsoo Kim 2013-07-16 1:27 ` Sam Ben 2013-07-16 1:27 ` Sam Ben 2013-07-16 1:45 ` Joonsoo Kim 2013-07-16 1:45 ` Joonsoo Kim 2013-07-16 1:55 ` Sam Ben 2013-07-16 1:55 ` Sam Ben 2013-07-16 2:14 ` Joonsoo Kim 2013-07-16 2:14 ` Joonsoo Kim
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=87d2qkj5b7.fsf@linux.vnet.ibm.com \ --to=aneesh.kumar@linux.vnet.ibm.com \ --cc=akpm@linux-foundation.org \ --cc=david@gibson.dropbear.id.au \ --cc=davidlohr.bueso@hp.com \ --cc=hughd@google.com \ --cc=iamjoonsoo.kim@lge.com \ --cc=js1304@gmail.com \ --cc=kamezawa.hiroyu@jp.fujitsu.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mgorman@suse.de \ --cc=mhocko@suse.cz \ --cc=riel@redhat.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.