From patchwork Thu Oct 1 07:46:34 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dave Chinner X-Patchwork-Id: 7305811 Return-Path: X-Original-To: patchwork-linux-nvdimm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 224B69F314 for ; Thu, 1 Oct 2015 07:47:59 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 0B46520807 for ; Thu, 1 Oct 2015 07:47:58 +0000 (UTC) Received: from ml01.01.org (ml01.01.org [198.145.21.10]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id DD02120803 for ; Thu, 1 Oct 2015 07:47:56 +0000 (UTC) Received: from ml01.vlan14.01.org (localhost [IPv6:::1]) by ml01.01.org (Postfix) with ESMTP id BCDBA615A0; Thu, 1 Oct 2015 00:47:56 -0700 (PDT) X-Original-To: linux-nvdimm@lists.01.org Delivered-To: linux-nvdimm@lists.01.org Received: from ipmail04.adl6.internode.on.net (ipmail04.adl6.internode.on.net [150.101.137.141]) by ml01.01.org (Postfix) with ESMTP id 806DB61588 for ; Thu, 1 Oct 2015 00:47:54 -0700 (PDT) X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: A2AACQCY5AxWPEcOLHleGQGDDYgcokkDBpAfiU2EBk0BAQEBAQEHAQEBAUE/hCUBBScvIxAISTkDBxSIRswMhiyPBQWHNo5DjmSHWZIqgi0BRh2BZiyKKwEBAQ Received: from ppp121-44-14-71.lns20.syd4.internode.on.net (HELO dastard) ([121.44.14.71]) by ipmail04.adl6.internode.on.net with ESMTP; 01 Oct 2015 17:16:46 +0930 Received: from disappointment.disaster.area ([192.168.1.110] helo=disappointment) by dastard with esmtp (Exim 4.80) (envelope-from ) id 1ZhYZh-0005ht-Pv; Thu, 01 Oct 2015 17:46:45 +1000 Received: from dave by disappointment with local (Exim 4.86) (envelope-from ) id 1ZhYZh-0001lk-Oz; Thu, 01 Oct 2015 17:46:45 +1000 From: Dave Chinner To: xfs@oss.sgi.com Subject: [PATCH 2/7] Revert "dax: fix race between simultaneous faults" Date: Thu, 1 Oct 2015 17:46:34 +1000 Message-Id: <1443685599-4843-3-git-send-email-david@fromorbit.com> X-Mailer: git-send-email 2.5.0 In-Reply-To: <1443685599-4843-1-git-send-email-david@fromorbit.com> References: <1443685599-4843-1-git-send-email-david@fromorbit.com> Cc: jack@suse.cz, linux-nvdimm@lists.01.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, kirill.shutemov@linux.intel.com X-BeenThere: linux-nvdimm@lists.01.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: "Linux-nvdimm developer list." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Errors-To: linux-nvdimm-bounces@lists.01.org Sender: "Linux-nvdimm" X-Spam-Status: No, score=-2.6 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_LOW, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP This reverts commit 843172978bb92997310d2f7fbc172ece423cfc02. --- fs/dax.c | 33 ++++++++++++++++----------------- mm/memory.c | 11 +++-------- 2 files changed, 19 insertions(+), 25 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index 400fe95..3994a2b 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -285,6 +285,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh, static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { + struct address_space *mapping = inode->i_mapping; sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; void __pmem *addr; @@ -292,6 +293,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, pgoff_t size; int error; + i_mmap_lock_read(mapping); + /* * Check truncate didn't happen while we were allocating a block. * If it did, this block may or may not be still allocated to the @@ -321,6 +324,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, error = vm_insert_mixed(vma, vaddr, pfn); out: + i_mmap_unlock_read(mapping); + return error; } @@ -382,17 +387,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * from a read fault and we've raced with a truncate */ error = -EIO; - goto unlock; + goto unlock_page; } - } else { - i_mmap_lock_write(mapping); } error = get_block(inode, block, &bh, 0); if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; /* fs corruption? */ if (error) - goto unlock; + goto unlock_page; if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) { if (vmf->flags & FAULT_FLAG_WRITE) { @@ -403,9 +406,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; if (error) - goto unlock; + goto unlock_page; } else { - i_mmap_unlock_write(mapping); return dax_load_hole(mapping, page, vmf); } } @@ -417,15 +419,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, else clear_user_highpage(new_page, vaddr); if (error) - goto unlock; + goto unlock_page; vmf->page = page; if (!page) { + i_mmap_lock_read(mapping); /* Check we didn't race with truncate */ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) { + i_mmap_unlock_read(mapping); error = -EIO; - goto unlock; + goto out; } } return VM_FAULT_LOCKED; @@ -461,8 +465,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); } - if (!page) - i_mmap_unlock_write(mapping); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; @@ -471,14 +473,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; - unlock: + unlock_page: if (page) { unlock_page(page); page_cache_release(page); - } else { - i_mmap_unlock_write(mapping); } - goto out; } EXPORT_SYMBOL(__dax_fault); @@ -556,10 +555,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - i_mmap_lock_write(mapping); length = get_block(inode, block, &bh, write); if (length) return VM_FAULT_SIGBUS; + i_mmap_lock_read(mapping); /* * If the filesystem isn't willing to tell us the length of a hole, @@ -633,11 +632,11 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, } out: + i_mmap_unlock_read(mapping); + if (buffer_unwritten(&bh)) complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); - i_mmap_unlock_write(mapping); - return result; fallback: diff --git a/mm/memory.c b/mm/memory.c index 5ec066f..deb679c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2427,16 +2427,11 @@ void unmap_mapping_range(struct address_space *mapping, details.last_index = ULONG_MAX; - /* - * DAX already holds i_mmap_lock to serialise file truncate vs - * page fault and page fault vs page fault. - */ - if (!IS_DAX(mapping->host)) - i_mmap_lock_write(mapping); + /* DAX uses i_mmap_lock to serialise file truncate vs page fault */ + i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); - if (!IS_DAX(mapping->host)) - i_mmap_unlock_write(mapping); + i_mmap_unlock_write(mapping); } EXPORT_SYMBOL(unmap_mapping_range);