Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752108AbdFTGWI (ORCPT ); Tue, 20 Jun 2017 02:22:08 -0400 Received: from mx0b-001b2d01.pphosted.com ([148.163.158.5]:53684 "EHLO mx0a-001b2d01.pphosted.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751136AbdFTGVK (ORCPT ); Tue, 20 Jun 2017 02:21:10 -0400 From: Mike Rapoport To: Andrew Morton Cc: Andrea Arcangeli , Hugh Dickins , "Kirill A. Shutemov" , Hillf Danton , Pavel Emelyanov , linux mm , lkml , Mike Rapoport Subject: [PATCH 3/7] userfaultfd: shmem: add shmem_mfill_zeropage_pte for userfaultfd support Date: Tue, 20 Jun 2017 09:20:48 +0300 X-Mailer: git-send-email 2.7.4 In-Reply-To: <1497939652-16528-1-git-send-email-rppt@linux.vnet.ibm.com> References: <1497939652-16528-1-git-send-email-rppt@linux.vnet.ibm.com> X-TM-AS-GCONF: 00 x-cbid: 17062006-0016-0000-0000-000004C11661 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 17062006-0017-0000-0000-000027F2EB33 Message-Id: <1497939652-16528-4-git-send-email-rppt@linux.vnet.ibm.com> X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-06-20_03:,, signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 spamscore=0 suspectscore=2 malwarescore=0 phishscore=0 adultscore=0 bulkscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.0.1-1703280000 definitions=main-1706200115 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3852 Lines: 120 shmem_mfill_zeropage_pte is the low level routine that implements the userfaultfd UFFDIO_ZEROPAGE command. Since for shmem mappings zero pages are always allocated and accounted, the new method is a slight extension of the existing shmem_mcopy_atomic_pte. Signed-off-by: Mike Rapoport --- include/linux/shmem_fs.h | 6 +++++ mm/shmem.c | 62 +++++++++++++++++++++++++++++++++++------------- 2 files changed, 51 insertions(+), 17 deletions(-) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a7d6bd2..b6c3540 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -137,9 +137,15 @@ extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); +extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr); #else #define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) +#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ + dst_addr) ({ BUG(); 0; }) #endif #endif diff --git a/mm/shmem.c b/mm/shmem.c index a92e3d7..e775a49 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2197,12 +2197,13 @@ bool shmem_mapping(struct address_space *mapping) return mapping->a_ops == &shmem_aops; } -int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep) +static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + bool zeropage, + struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); @@ -2225,17 +2226,22 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, if (!page) goto out_unacct_blocks; - page_kaddr = kmap_atomic(page); - ret = copy_from_user(page_kaddr, (const void __user *)src_addr, - PAGE_SIZE); - kunmap_atomic(page_kaddr); - - /* fallback to copy_from_user outside mmap_sem */ - if (unlikely(ret)) { - *pagep = page; - shmem_inode_unacct_blocks(inode, 1); - /* don't free the page */ - return -EFAULT; + if (!zeropage) { /* mcopy_atomic */ + page_kaddr = kmap_atomic(page); + ret = copy_from_user(page_kaddr, + (const void __user *)src_addr, + PAGE_SIZE); + kunmap_atomic(page_kaddr); + + /* fallback to copy_from_user outside mmap_sem */ + if (unlikely(ret)) { + *pagep = page; + shmem_inode_unacct_blocks(inode, 1); + /* don't free the page */ + return -EFAULT; + } + } else { /* mfill_zeropage_atomic */ + clear_highpage(page); } } else { page = *pagep; @@ -2301,6 +2307,28 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, goto out; } +int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, false, pagep); +} + +int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) +{ + struct page *page = NULL; + + return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, 0, true, &page); +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; -- 2.7.4