From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qt0-f199.google.com (mail-qt0-f199.google.com [209.85.216.199]) by kanga.kvack.org (Postfix) with ESMTP id 2D0A2280391 for ; Wed, 28 Jun 2017 14:01:24 -0400 (EDT) Received: by mail-qt0-f199.google.com with SMTP id w12so29284181qta.8 for ; Wed, 28 Jun 2017 11:01:24 -0700 (PDT) Received: from mx1.redhat.com (mx1.redhat.com. [209.132.183.28]) by mx.google.com with ESMTPS id 55si2628869qtq.162.2017.06.28.11.01.22 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Wed, 28 Jun 2017 11:01:23 -0700 (PDT) From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Subject: [PATCH 13/15] mm/migrate: migrate_vma() unmap page from vma while collecting pages Date: Wed, 28 Jun 2017 14:00:45 -0400 Message-Id: <20170628180047.5386-14-jglisse@redhat.com> In-Reply-To: <20170628180047.5386-1-jglisse@redhat.com> References: <20170628180047.5386-1-jglisse@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: owner-linux-mm@kvack.org List-ID: To: akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: John Hubbard , Dan Williams , David Nellans , =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= , Evgeny Baskakov , Mark Hairgrove , Sherry Cheung , Subhash Gutti Common case for migration of virtual address range is page are map only once inside the vma in which migration is taking place. Because we already walk the CPU page table for that range we can directly do the unmap there and setup special migration swap entry. Signed-off-by: JA(C)rA'me Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti --- mm/migrate.c | 114 ++++++++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 98 insertions(+), 16 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index c2080658b905..d11fb4c8d785 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2110,7 +2110,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, { struct migrate_vma *migrate = walk->private; struct mm_struct *mm = walk->vma->vm_mm; - unsigned long addr = start; + unsigned long addr = start, unmapped = 0; spinlock_t *ptl; pte_t *ptep; @@ -2120,9 +2120,12 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, } ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + arch_enter_lazy_mmu_mode(); + for (; addr < end; addr += PAGE_SIZE, ptep++) { unsigned long mpfn, pfn; struct page *page; + swp_entry_t entry; pte_t pte; pte = *ptep; @@ -2154,11 +2157,44 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; + /* + * Optimize for the common case where page is only mapped once + * in one process. If we can lock the page, then we can safely + * set up a special migration page table entry now. + */ + if (trylock_page(page)) { + pte_t swp_pte; + + mpfn |= MIGRATE_PFN_LOCKED; + ptep_get_and_clear(mm, addr, ptep); + + /* Setup special migration page table entry */ + entry = make_migration_entry(page, pte_write(pte)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pte)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(mm, addr, ptep, swp_pte); + + /* + * This is like regular unmap: we remove the rmap and + * drop page refcount. Page won't be freed, as we took + * a reference just above. + */ + page_remove_rmap(page, false); + put_page(page); + unmapped++; + } + next: migrate->src[migrate->npages++] = mpfn; } + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(ptep - 1, ptl); + /* Only flush the TLB if we actually modified any entries */ + if (unmapped) + flush_tlb_range(walk->vma, start, end); + return 0; } @@ -2183,7 +2219,13 @@ static void migrate_vma_collect(struct migrate_vma *migrate) mm_walk.mm = migrate->vma->vm_mm; mm_walk.private = migrate; + mmu_notifier_invalidate_range_start(mm_walk.mm, + migrate->start, + migrate->end); walk_page_range(migrate->start, migrate->end, &mm_walk); + mmu_notifier_invalidate_range_end(mm_walk.mm, + migrate->start, + migrate->end); migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT); } @@ -2239,12 +2281,16 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) for (i = 0; i < npages; i++) { struct page *page = migrate_pfn_to_page(migrate->src[i]); + bool remap = true; if (!page) continue; - lock_page(page); - migrate->src[i] |= MIGRATE_PFN_LOCKED; + if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) { + remap = false; + lock_page(page); + migrate->src[i] |= MIGRATE_PFN_LOCKED; + } if (!PageLRU(page) && allow_drain) { /* Drain CPU's pagevec */ @@ -2253,21 +2299,50 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) } if (isolate_lru_page(page)) { - migrate->src[i] = 0; - unlock_page(page); - migrate->cpages--; - put_page(page); + if (remap) { + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; + } else { + migrate->src[i] = 0; + unlock_page(page); + migrate->cpages--; + put_page(page); + } continue; } if (!migrate_vma_check_page(page)) { - migrate->src[i] = 0; - unlock_page(page); - migrate->cpages--; + if (remap) { + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; - putback_lru_page(page); + get_page(page); + putback_lru_page(page); + } else { + migrate->src[i] = 0; + unlock_page(page); + migrate->cpages--; + + putback_lru_page(page); + } } } + + for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) { + struct page *page = migrate_pfn_to_page(migrate->src[i]); + + if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) + continue; + + remove_migration_pte(page, migrate->vma, addr, page); + + migrate->src[i] = 0; + unlock_page(page); + put_page(page); + restore--; + } } /* @@ -2294,12 +2369,19 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE)) continue; - try_to_unmap(page, flags); - if (page_mapped(page) || !migrate_vma_check_page(page)) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; + if (page_mapped(page)) { + try_to_unmap(page, flags); + if (page_mapped(page)) + goto restore; } + + if (migrate_vma_check_page(page)) + continue; + +restore: + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; } for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) { -- 2.13.0 -- 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: email@kvack.org