From: Vlastimil Babka <vbabka@suse.cz> To: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>, Andrew Morton <akpm@linux-foundation.org>, Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com>, Dave Hansen <dave.hansen@intel.com>, Johannes Weiner <hannes@cmpxchg.org>, Michal Hocko <mhocko@suse.cz>, David Rientjes <rientjes@google.com>, "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCHv10 37/36, RFC] thp: allow mlocked THP again Date: Fri, 11 Sep 2015 15:22:14 +0200 [thread overview] Message-ID: <55F2D586.3040204@suse.cz> (raw) In-Reply-To: <1441293388-137552-1-git-send-email-kirill.shutemov@linux.intel.com> On 09/03/2015 05:16 PM, Kirill A. Shutemov wrote: > This patch brings back mlocked THP. Instead of forbidding mlocked pages > altogether, we just avoid mlocking PTE-mapped THPs and munlock THPs on > split_huge_pmd(). > > This means PTE-mapped THPs will be on normal lru lists and will be > split under memory pressure by vmscan. After the split vmscan will > detect unevictable small pages and mlock them. Yeah that sounds like a compromise that should work. > This way we can void leaking mlocked pages into non-VM_LOCKED VMAs. avoid But mlocked page in non-mlocked VMA's is a normal thing for shared pages when only one of the sharing mm's did mlock(), right? So this description doesn't explain the whole issue. I admit I forgot the exact details already :( > > Not-Yet-Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > --- > > I'm not yet 100% certain that this approch is correct. Review would be appriciated. > More testing is required. > > --- > mm/gup.c | 6 ++++-- > mm/huge_memory.c | 33 +++++++++++++++++++++++------- > mm/memory.c | 3 +-- > mm/mlock.c | 61 +++++++++++++++++++++++++++++++++++++------------------- > 4 files changed, 71 insertions(+), 32 deletions(-) > > diff --git a/mm/gup.c b/mm/gup.c > index 70d65e4015a4..e95b0cb6ed81 100644 > --- a/mm/gup.c > +++ b/mm/gup.c > @@ -143,6 +143,10 @@ retry: > mark_page_accessed(page); > } > if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { > + /* Do not mlock pte-mapped THP */ > + if (PageTransCompound(page)) > + goto out; > + > /* > * The preliminary mapping check is mainly to avoid the > * pointless overhead of lock_page on the ZERO_PAGE > @@ -920,8 +924,6 @@ long populate_vma_page_range(struct vm_area_struct *vma, > gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; > if (vma->vm_flags & VM_LOCKONFAULT) > gup_flags &= ~FOLL_POPULATE; > - if (vma->vm_flags & VM_LOCKED) > - gup_flags |= FOLL_SPLIT; > /* > * We want to touch writable mappings with a write fault in order > * to break COW, except for shared mappings because these don't COW > diff --git a/mm/huge_memory.c b/mm/huge_memory.c > index 2cc99f9096a8..d714de02473b 100644 > --- a/mm/huge_memory.c > +++ b/mm/huge_memory.c > @@ -846,8 +846,6 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, > > if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) > return VM_FAULT_FALLBACK; > - if (vma->vm_flags & VM_LOCKED) > - return VM_FAULT_FALLBACK; > if (unlikely(anon_vma_prepare(vma))) > return VM_FAULT_OOM; > if (unlikely(khugepaged_enter(vma, vma->vm_flags))) > @@ -1316,7 +1314,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, > update_mmu_cache_pmd(vma, addr, pmd); > } > if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { > - if (page->mapping && trylock_page(page)) { > + /* > + * We don't mlock() pte-mapped THPs. This way we can avoid > + * leaking mlocked pages into non-VM_LOCKED VMAs. > + * In most cases the pmd is the only mapping of the page: we > + * break COW for the mlock(). The only scenario when we have I don't understand what's meant by "we break COW for the mlock()"? > + * the page shared here is if we mlocking read-only mapping > + * shared over fork(). We skip mlocking such pages. Why do we skip them? There's no PTE mapping involved, just multiple PMD mappings? Why are those a problem?
WARNING: multiple messages have this Message-ID (diff)
From: Vlastimil Babka <vbabka@suse.cz> To: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>, Andrew Morton <akpm@linux-foundation.org>, Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com>, Dave Hansen <dave.hansen@intel.com>, Johannes Weiner <hannes@cmpxchg.org>, Michal Hocko <mhocko@suse.cz>, David Rientjes <rientjes@google.com>, "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>, linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: Re: [PATCHv10 37/36, RFC] thp: allow mlocked THP again Date: Fri, 11 Sep 2015 15:22:14 +0200 [thread overview] Message-ID: <55F2D586.3040204@suse.cz> (raw) In-Reply-To: <1441293388-137552-1-git-send-email-kirill.shutemov@linux.intel.com> On 09/03/2015 05:16 PM, Kirill A. Shutemov wrote: > This patch brings back mlocked THP. Instead of forbidding mlocked pages > altogether, we just avoid mlocking PTE-mapped THPs and munlock THPs on > split_huge_pmd(). > > This means PTE-mapped THPs will be on normal lru lists and will be > split under memory pressure by vmscan. After the split vmscan will > detect unevictable small pages and mlock them. Yeah that sounds like a compromise that should work. > This way we can void leaking mlocked pages into non-VM_LOCKED VMAs. avoid But mlocked page in non-mlocked VMA's is a normal thing for shared pages when only one of the sharing mm's did mlock(), right? So this description doesn't explain the whole issue. I admit I forgot the exact details already :( > > Not-Yet-Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> > --- > > I'm not yet 100% certain that this approch is correct. Review would be appriciated. > More testing is required. > > --- > mm/gup.c | 6 ++++-- > mm/huge_memory.c | 33 +++++++++++++++++++++++------- > mm/memory.c | 3 +-- > mm/mlock.c | 61 +++++++++++++++++++++++++++++++++++++------------------- > 4 files changed, 71 insertions(+), 32 deletions(-) > > diff --git a/mm/gup.c b/mm/gup.c > index 70d65e4015a4..e95b0cb6ed81 100644 > --- a/mm/gup.c > +++ b/mm/gup.c > @@ -143,6 +143,10 @@ retry: > mark_page_accessed(page); > } > if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { > + /* Do not mlock pte-mapped THP */ > + if (PageTransCompound(page)) > + goto out; > + > /* > * The preliminary mapping check is mainly to avoid the > * pointless overhead of lock_page on the ZERO_PAGE > @@ -920,8 +924,6 @@ long populate_vma_page_range(struct vm_area_struct *vma, > gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; > if (vma->vm_flags & VM_LOCKONFAULT) > gup_flags &= ~FOLL_POPULATE; > - if (vma->vm_flags & VM_LOCKED) > - gup_flags |= FOLL_SPLIT; > /* > * We want to touch writable mappings with a write fault in order > * to break COW, except for shared mappings because these don't COW > diff --git a/mm/huge_memory.c b/mm/huge_memory.c > index 2cc99f9096a8..d714de02473b 100644 > --- a/mm/huge_memory.c > +++ b/mm/huge_memory.c > @@ -846,8 +846,6 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, > > if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) > return VM_FAULT_FALLBACK; > - if (vma->vm_flags & VM_LOCKED) > - return VM_FAULT_FALLBACK; > if (unlikely(anon_vma_prepare(vma))) > return VM_FAULT_OOM; > if (unlikely(khugepaged_enter(vma, vma->vm_flags))) > @@ -1316,7 +1314,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, > update_mmu_cache_pmd(vma, addr, pmd); > } > if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { > - if (page->mapping && trylock_page(page)) { > + /* > + * We don't mlock() pte-mapped THPs. This way we can avoid > + * leaking mlocked pages into non-VM_LOCKED VMAs. > + * In most cases the pmd is the only mapping of the page: we > + * break COW for the mlock(). The only scenario when we have I don't understand what's meant by "we break COW for the mlock()"? > + * the page shared here is if we mlocking read-only mapping > + * shared over fork(). We skip mlocking such pages. Why do we skip them? There's no PTE mapping involved, just multiple PMD mappings? Why are those a problem? -- 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:[~2015-09-11 13:22 UTC|newest] Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top 2015-09-03 15:12 [PATCHv10 00/36] THP refcounting redesign Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 01/36] mm, proc: adjust PSS calculation Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 02/36] rmap: add argument to charge compound page Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 03/36] memcg: adjust to support new THP refcounting Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 04/36] mm, thp: adjust conditions when we can reuse the page on WP fault Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 05/36] mm: adjust FOLL_SPLIT for new refcounting Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 06/36] mm: handle PTE-mapped tail pages in gerneric fast gup implementaiton Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 07/36] thp, mlock: do not allow huge pages in mlocked area Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 08/36] khugepaged: ignore pmd tables with THP mapped with ptes Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 09/36] thp: rename split_huge_page_pmd() to split_huge_pmd() Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 10/36] mm, vmstats: new THP splitting event Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 11/36] mm: temporally mark THP broken Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 12/36] thp: drop all split_huge_page()-related code Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:12 ` [PATCHv10 13/36] mm: drop tail page refcounting Kirill A. Shutemov 2015-09-03 15:12 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 14/36] futex, thp: remove special case for THP in get_futex_key Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 15/36] ksm: prepare to new THP semantics Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 16/36] mm, thp: remove compound_lock Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 17/36] arm64, thp: remove infrastructure for handling splitting PMDs Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 18/36] arm, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 19/36] mips, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 20/36] powerpc, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 21/36] s390, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 22/36] sparc, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 23/36] tile, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 24/36] x86, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 25/36] mm, " Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 26/36] mm: rework mapcount accounting to enable 4k mapping of THPs Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 27/36] mm: differentiate page_mapped() from page_mapcount() for compound pages Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 28/36] mm, numa: skip PTE-mapped THP on numa fault Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 29/36] thp: implement split_huge_pmd() Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 30/36] thp: add option to setup migration entries during PMD split Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 31/36] thp, mm: split_huge_page(): caller need to lock page Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 32/36] thp: reintroduce split_huge_page() Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 33/36] migrate_pages: try to split pages on qeueuing Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 34/36] thp: introduce deferred_split_huge_page() Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 35/36] mm: re-enable THP Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:13 ` [PATCHv10 36/36] thp: update documentation Kirill A. Shutemov 2015-09-03 15:13 ` Kirill A. Shutemov 2015-09-03 15:16 ` [PATCHv10 37/36, RFC] thp: allow mlocked THP again Kirill A. Shutemov 2015-09-03 15:16 ` Kirill A. Shutemov 2015-09-11 13:22 ` Vlastimil Babka [this message] 2015-09-11 13:22 ` Vlastimil Babka 2015-09-14 11:05 ` Kirill A. Shutemov 2015-09-14 11:05 ` Kirill A. Shutemov
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=55F2D586.3040204@suse.cz \ --to=vbabka@suse.cz \ --cc=aarcange@redhat.com \ --cc=akpm@linux-foundation.org \ --cc=aneesh.kumar@linux.vnet.ibm.com \ --cc=dave.hansen@intel.com \ --cc=hannes@cmpxchg.org \ --cc=hughd@google.com \ --cc=kirill.shutemov@linux.intel.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=mhocko@suse.cz \ --cc=rientjes@google.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.