From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ml01.01.org (Postfix) with ESMTPS id 0DA8A207DF293 for ; Wed, 4 Jul 2018 14:50:31 -0700 (PDT) Subject: [PATCH v5 02/11] device-dax: Enable page_mapping() From: Dan Williams Date: Wed, 04 Jul 2018 14:40:34 -0700 Message-ID: <153074043405.27838.13174871137034713893.stgit@dwillia2-desk3.amr.corp.intel.com> In-Reply-To: <153074042316.27838.17319837331947007626.stgit@dwillia2-desk3.amr.corp.intel.com> References: <153074042316.27838.17319837331947007626.stgit@dwillia2-desk3.amr.corp.intel.com> MIME-Version: 1.0 List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: linux-nvdimm-bounces@lists.01.org Sender: "Linux-nvdimm" To: linux-nvdimm@lists.01.org Cc: jack@suse.cz, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, hch@lst.de List-ID: In support of enabling memory_failure() handling for device-dax mappings, set the ->mapping association of pages backing device-dax mappings. The rmap implementation requires page_mapping() to return the address_space hosting the vmas that map the page. The ->mapping pointer is never cleared. There is no possibility for the page to become associated with another address_space while the device is enabled. When the device is disabled the 'struct page' array for the device is destroyed / later reinitialized to zero. Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- drivers/dax/device.c | 55 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 38 insertions(+), 17 deletions(-) diff --git a/drivers/dax/device.c b/drivers/dax/device.c index ad5e7b4a15dc..95cfcfd612df 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -245,12 +245,11 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, } static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf) + struct vm_fault *vmf, pfn_t *pfn) { struct device *dev = &dev_dax->dev; struct dax_region *dax_region; phys_addr_t phys; - pfn_t pfn; unsigned int fault_size = PAGE_SIZE; if (check_vma(dev_dax, vmf->vma, __func__)) @@ -272,20 +271,19 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax, return VM_FAULT_SIGBUS; } - pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); + *pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); - return vmf_insert_mixed(vmf->vma, vmf->address, pfn); + return vmf_insert_mixed(vmf->vma, vmf->address, *pfn); } static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf) + struct vm_fault *vmf, pfn_t *pfn) { unsigned long pmd_addr = vmf->address & PMD_MASK; struct device *dev = &dev_dax->dev; struct dax_region *dax_region; phys_addr_t phys; pgoff_t pgoff; - pfn_t pfn; unsigned int fault_size = PMD_SIZE; if (check_vma(dev_dax, vmf->vma, __func__)) @@ -321,22 +319,21 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax, return VM_FAULT_SIGBUS; } - pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); + *pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); - return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn, + return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, *pfn, vmf->flags & FAULT_FLAG_WRITE); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf) + struct vm_fault *vmf, pfn_t *pfn) { unsigned long pud_addr = vmf->address & PUD_MASK; struct device *dev = &dev_dax->dev; struct dax_region *dax_region; phys_addr_t phys; pgoff_t pgoff; - pfn_t pfn; unsigned int fault_size = PUD_SIZE; @@ -373,14 +370,14 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, return VM_FAULT_SIGBUS; } - pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); + *pfn = phys_to_pfn_t(phys, dax_region->pfn_flags); - return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, pfn, + return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, *pfn, vmf->flags & FAULT_FLAG_WRITE); } #else static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, - struct vm_fault *vmf) + struct vm_fault *vmf, pfn_t *pfn) { return VM_FAULT_FALLBACK; } @@ -389,8 +386,10 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax, static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, enum page_entry_size pe_size) { - int rc, id; struct file *filp = vmf->vma->vm_file; + unsigned long fault_size; + int rc, id; + pfn_t pfn; struct dev_dax *dev_dax = filp->private_data; dev_dbg(&dev_dax->dev, "%s: %s (%#lx - %#lx) size = %d\n", current->comm, @@ -400,17 +399,39 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, id = dax_read_lock(); switch (pe_size) { case PE_SIZE_PTE: - rc = __dev_dax_pte_fault(dev_dax, vmf); + fault_size = PAGE_SIZE; + rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn); break; case PE_SIZE_PMD: - rc = __dev_dax_pmd_fault(dev_dax, vmf); + fault_size = PMD_SIZE; + rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn); break; case PE_SIZE_PUD: - rc = __dev_dax_pud_fault(dev_dax, vmf); + fault_size = PUD_SIZE; + rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn); break; default: rc = VM_FAULT_SIGBUS; } + + if (rc == VM_FAULT_NOPAGE) { + unsigned long i; + + /* + * In the device-dax case the only possibility for a + * VM_FAULT_NOPAGE result is when device-dax capacity is + * mapped. No need to consider the zero page, or racing + * conflicting mappings. + */ + for (i = 0; i < fault_size / PAGE_SIZE; i++) { + struct page *page; + + page = pfn_to_page(pfn_t_to_pfn(pfn) + i); + if (page->mapping) + continue; + page->mapping = filp->f_mapping; + } + } dax_read_unlock(id); return rc; _______________________________________________ Linux-nvdimm mailing list Linux-nvdimm@lists.01.org https://lists.01.org/mailman/listinfo/linux-nvdimm