From patchwork Fri Jan 8 19:49:51 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Wilcox, Matthew R" X-Patchwork-Id: 7989761 Return-Path: X-Original-To: patchwork-linux-fsdevel@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 B78629F1CC for ; Fri, 8 Jan 2016 19:50:50 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id B159E20211 for ; Fri, 8 Jan 2016 19:50:49 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 9E653201EC for ; Fri, 8 Jan 2016 19:50:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933146AbcAHTuE (ORCPT ); Fri, 8 Jan 2016 14:50:04 -0500 Received: from mga04.intel.com ([192.55.52.120]:64896 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932931AbcAHTuA (ORCPT ); Fri, 8 Jan 2016 14:50:00 -0500 Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga104.fm.intel.com with ESMTP; 08 Jan 2016 11:49:58 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.20,540,1444719600"; d="scan'208";a="889316767" Received: from unknown (HELO thog.int.wil.cx) ([10.254.79.238]) by fmsmga002.fm.intel.com with SMTP; 08 Jan 2016 11:49:57 -0800 Received: by thog.int.wil.cx (Postfix, from userid 1000) id 671CC5F8B5; Fri, 8 Jan 2016 14:49:54 -0500 (EST) From: Matthew Wilcox To: Andrew Morton Cc: Matthew Wilcox , linux-mm@kvack.org, linux-nvdimm@lists.01.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, x86@kernel.org Subject: [PATCH v3 7/8] dax: Support for transparent PUD pages Date: Fri, 8 Jan 2016 14:49:51 -0500 Message-Id: <1452282592-27290-8-git-send-email-matthew.r.wilcox@intel.com> X-Mailer: git-send-email 2.6.4 In-Reply-To: <1452282592-27290-1-git-send-email-matthew.r.wilcox@intel.com> References: <1452282592-27290-1-git-send-email-matthew.r.wilcox@intel.com> Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, 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 From: Matthew Wilcox The DAX support for transparent huge PUD pages Signed-off-by: Matthew Wilcox --- fs/dax.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 175 insertions(+) diff --git a/fs/dax.c b/fs/dax.c index 05ed547..f4cb4dd 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -906,6 +906,178 @@ static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, } #endif /* !CONFIG_TRANSPARENT_HUGEPAGE */ +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +/* + * The 'colour' (ie low bits) within a PUD of a page offset. This comes up + * more often than one might expect in the below function. + */ +#define PG_PUD_COLOUR ((PUD_SIZE >> PAGE_SHIFT) - 1) + +#define dax_pud_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pud") + +static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address, + pud_t *pud, unsigned int flags, get_block_t get_block, + dax_iodone_t complete_unwritten) +{ + struct file *file = vma->vm_file; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + struct buffer_head bh; + unsigned blkbits = inode->i_blkbits; + unsigned long pud_addr = address & PUD_MASK; + bool write = flags & FAULT_FLAG_WRITE; + struct block_device *bdev = NULL; + pgoff_t size, pgoff; + sector_t block; + int result = 0; + + /* dax pud mappings require pfn_t_devmap() */ + if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) + return VM_FAULT_FALLBACK; + + /* Fall back to PTEs if we're going to COW */ + if (write && !(vma->vm_flags & VM_SHARED)) { + split_huge_pud(vma, pud, address); + dax_pud_dbg(NULL, address, "cow write"); + return VM_FAULT_FALLBACK; + } + /* If the PUD would extend outside the VMA */ + if (pud_addr < vma->vm_start) { + dax_pud_dbg(NULL, address, "vma start unaligned"); + return VM_FAULT_FALLBACK; + } + if ((pud_addr + PUD_SIZE) > vma->vm_end) { + dax_pud_dbg(NULL, address, "vma end unaligned"); + return VM_FAULT_FALLBACK; + } + + pgoff = linear_page_index(vma, pud_addr); + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (pgoff >= size) + return VM_FAULT_SIGBUS; + /* If the PUD would cover blocks out of the file */ + if ((pgoff | PG_PUD_COLOUR) >= size) { + dax_pud_dbg(NULL, address, + "offset + huge page size > file size"); + return VM_FAULT_FALLBACK; + } + + memset(&bh, 0, sizeof(bh)); + block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); + + bh.b_size = PUD_SIZE; + if (get_block(inode, block, &bh, write) != 0) + return VM_FAULT_SIGBUS; + bdev = bh.b_bdev; + i_mmap_lock_read(mapping); + + /* + * If the filesystem isn't willing to tell us the length of a hole, + * just fall back to PTEs. Calling get_block 512 times in a loop + * would be silly. + */ + if (!buffer_size_valid(&bh) || bh.b_size < PUD_SIZE) { + dax_pud_dbg(&bh, address, "allocated block too small"); + goto fallback; + } + + /* + * If we allocated new storage, make sure no process has any + * zero pages covering this hole + */ + if (buffer_new(&bh)) { + i_mmap_unlock_read(mapping); + unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PUD_SIZE, 0); + i_mmap_lock_read(mapping); + } + + /* + * If a truncate happened while we were allocating blocks, we may + * leave blocks allocated to the file that are beyond EOF. We can't + * take i_mutex here, so just leave them hanging; they'll be freed + * when the file is deleted. + */ + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (pgoff >= size) { + result = VM_FAULT_SIGBUS; + goto out; + } + if ((pgoff | PG_PUD_COLOUR) >= size) { + dax_pud_dbg(&bh, address, "pgoff unaligned"); + goto fallback; + } + + if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) { + dax_pud_dbg(&bh, address, "no zero page"); + goto fallback; + } else { + struct blk_dax_ctl dax = { + .sector = to_sector(&bh, inode), + .size = PUD_SIZE, + }; + long length = dax_map_atomic(bdev, &dax); + + if (length < 0) { + result = VM_FAULT_SIGBUS; + goto out; + } + if (length < PUD_SIZE) { + dax_pud_dbg(&bh, address, "dax-length too small"); + dax_unmap_atomic(bdev, &dax); + goto fallback; + } + if (pfn_t_to_pfn(dax.pfn) & PG_PUD_COLOUR) { + dax_pud_dbg(&bh, address, "pfn unaligned"); + dax_unmap_atomic(bdev, &dax); + goto fallback; + } + + if (!pfn_t_devmap(dax.pfn)) { + dax_unmap_atomic(bdev, &dax); + dax_pud_dbg(&bh, address, "pfn not in memmap"); + goto fallback; + } + + if (buffer_unwritten(&bh) || buffer_new(&bh)) { + clear_pmem(dax.addr, PUD_SIZE); + wmb_pmem(); + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + result |= VM_FAULT_MAJOR; + } + dax_unmap_atomic(bdev, &dax); + + dev_dbg(part_to_dev(bdev->bd_part), + "%s: %s addr: %lx pfn: %lx sect: %llx\n", + __func__, current->comm, address, + pfn_t_to_pfn(dax.pfn), + (unsigned long long) dax.sector); + result |= vmf_insert_pfn_pud(vma, address, pud, + dax.pfn, write); + } + + out: + i_mmap_unlock_read(mapping); + + if (buffer_unwritten(&bh)) + complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); + + return result; + + fallback: + count_vm_event(THP_FAULT_FALLBACK); + result = VM_FAULT_FALLBACK; + goto out; +} +#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address, + pud_t *pud, unsigned int flags, get_block_t get_block, + dax_iodone_t complete_unwritten) +{ + return VM_FAULT_FALLBACK; +} +#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + /** * dax_fault - handle a page fault on a DAX file * @vma: The virtual memory area where the fault occurred @@ -932,6 +1104,9 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, case FAULT_FLAG_SIZE_PMD: return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags, get_block, iodone); + case FAULT_FLAG_SIZE_PUD: + return dax_pud_fault(vma, address, vmf->pud, vmf->flags, + get_block, iodone); default: return VM_FAULT_FALLBACK; }