Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964791AbbEUTgN (ORCPT ); Thu, 21 May 2015 15:36:13 -0400 Received: from mail-qg0-f51.google.com ([209.85.192.51]:35799 "EHLO mail-qg0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756584AbbEUTeF (ORCPT ); Thu, 21 May 2015 15:34:05 -0400 From: j.glisse@gmail.com To: akpm@linux-foundation.org Cc: , linux-mm@kvack.org, Linus Torvalds , , Mel Gorman , "H. Peter Anvin" , Peter Zijlstra , Andrea Arcangeli , Johannes Weiner , Larry Woodman , Rik van Riel , Dave Airlie , Brendan Conoboy , Joe Donohue , Duncan Poole , Sherry Cheung , Subhash Gutti , John Hubbard , Mark Hairgrove , Lucien Dunning , Cameron Buschardt , Arvind Gopalakrishnan , Haggai Eran , Shachar Raindel , Liran Liss , Roland Dreier , Ben Sander , Greg Stoner , John Bridgman , Michael Mantor , Paul Blinzer , Laurent Morichetti , Alexander Deucher , Oded Gabbay , =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Subject: [PATCH 14/36] fork: pass the dst vma to copy_page_range() and its sub-functions. Date: Thu, 21 May 2015 15:31:23 -0400 Message-Id: <1432236705-4209-15-git-send-email-j.glisse@gmail.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1432236705-4209-1-git-send-email-j.glisse@gmail.com> References: <1432236705-4209-1-git-send-email-j.glisse@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5247 Lines: 142 From: Jérôme Glisse For HMM we will need to resort to the old way of allocating new page for anonymous memory when that anonymous memory have been migrated to device memory. This does not impact any process that do not use HMM through some device driver. Only process that migrate anonymous memory to device memory with HMM will have to copy migrated page on fork. We do not expect this to be a common or adviced thing to do so we resort to the simpler solution of allocating new page. If this kind of usage turns out to be important we will revisit way to achieve COW even for remote memory. Signed-off-by: Jérôme Glisse --- include/linux/mm.h | 5 +++-- kernel/fork.c | 2 +- mm/memory.c | 33 +++++++++++++++++++++------------ 3 files changed, 25 insertions(+), 15 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index cf642d9..8923532 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1083,8 +1083,9 @@ int walk_page_range(unsigned long addr, unsigned long end, int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk); void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma); +int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + struct vm_area_struct *dst_vma, + struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); int follow_pfn(struct vm_area_struct *vma, unsigned long address, diff --git a/kernel/fork.c b/kernel/fork.c index 4083be7..0bd5b59 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -492,7 +492,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) rb_parent = &tmp->vm_rb; mm->map_count++; - retval = copy_page_range(mm, oldmm, mpnt); + retval = copy_page_range(mm, oldmm, tmp, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); diff --git a/mm/memory.c b/mm/memory.c index 5a1131f..6497009 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -885,8 +885,10 @@ out_set_pte: } static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) + pmd_t *dst_pmd, pmd_t *src_pmd, + struct vm_area_struct *dst_vma, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; @@ -947,9 +949,12 @@ again: return 0; } -static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline int copy_pmd_range(struct mm_struct *dst_mm, + struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, + struct vm_area_struct *dst_vma, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { pmd_t *src_pmd, *dst_pmd; unsigned long next; @@ -974,15 +979,18 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, - vma, addr, next)) + dst_vma, vma, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } -static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline int copy_pud_range(struct mm_struct *dst_mm, + struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, + struct vm_area_struct *dst_vma, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; unsigned long next; @@ -996,14 +1004,15 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, - vma, addr, next)) + dst_vma, vma, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - struct vm_area_struct *vma) + struct vm_area_struct *dst_vma, + struct vm_area_struct *vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; @@ -1057,7 +1066,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next))) { + dst_vma, vma, addr, next))) { ret = -ENOMEM; break; } -- 1.9.3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/