linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: linux-nvdimm@lists.01.org
Cc: hch@lst.de, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
	jack@suse.cz
Subject: [PATCH v3 03/12] device-dax: Enable page_mapping()
Date: Mon, 04 Jun 2018 16:11:55 -0700	[thread overview]
Message-ID: <152815391576.39010.14402839848074832654.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <152815389835.39010.13253559944508110923.stgit@dwillia2-desk3.amr.corp.intel.com>

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.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 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 686de08e120b..7ec246549721 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -245,13 +245,12 @@ __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 vm_area_struct *vma = vmf->vma;
 	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, vma, __func__))
@@ -273,13 +272,13 @@ 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(vma, vmf->address, pfn);
+	return vmf_insert_mixed(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 vm_area_struct *vma = vmf->vma;
@@ -287,7 +286,6 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 	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, vma, __func__))
@@ -322,15 +320,15 @@ 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(vma, vmf->address, vmf->pmd, pfn,
+	return vmf_insert_pfn_pmd(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 vm_area_struct *vma = vmf->vma;
@@ -338,7 +336,6 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
-	pfn_t pfn;
 	unsigned int fault_size = PUD_SIZE;
 
 
@@ -374,14 +371,14 @@ 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(vma, vmf->address, vmf->pud, pfn,
+	return vmf_insert_pfn_pud(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;
 }
@@ -390,9 +387,11 @@ 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 vm_area_struct *vma = vmf->vma;
 	struct file *filp = 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,
@@ -402,17 +401,39 @@ 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;

  parent reply	other threads:[~2018-06-04 23:11 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-04 23:11 [PATCH v3 00/12] mm: Teach memory_failure() about ZONE_DEVICE pages Dan Williams
2018-06-04 23:11 ` [PATCH v3 01/12] device-dax: Convert to vmf_insert_mixed and vm_fault_t Dan Williams
2018-06-04 23:11 ` [PATCH v3 02/12] device-dax: Cleanup vm_fault de-reference chains Dan Williams
2018-06-04 23:11 ` Dan Williams [this message]
2018-06-07 15:39   ` [PATCH v3 03/12] device-dax: Enable page_mapping() Jan Kara
2018-06-04 23:12 ` [PATCH v3 04/12] device-dax: Set page->index Dan Williams
2018-06-07 15:50   ` Jan Kara
2018-06-04 23:12 ` [PATCH v3 05/12] filesystem-dax: " Dan Williams
2018-06-07 16:02   ` Jan Kara
2018-06-04 23:12 ` [PATCH v3 06/12] mm, madvise_inject_error: Let memory_failure() optionally take a page reference Dan Williams
2018-06-04 23:12 ` [PATCH v3 07/12] x86/mm/pat: Prepare {reserve, free}_memtype() for "decoy" addresses Dan Williams
2018-06-04 23:12 ` [PATCH v3 08/12] x86/memory_failure: Introduce {set, clear}_mce_nospec() Dan Williams
2018-06-07  4:42   ` Dan Williams
2018-06-07 17:02     ` Luck, Tony
2018-06-04 23:12 ` [PATCH v3 09/12] mm, memory_failure: Pass page size to kill_proc() Dan Williams
2018-06-04 23:12 ` [PATCH v3 10/12] mm, memory_failure: Fix page->mapping assumptions relative to the page lock Dan Williams
2018-06-04 23:12 ` [PATCH v3 11/12] mm, memory_failure: Teach memory_failure() about dev_pagemap pages Dan Williams
2018-06-07  4:22   ` Dan Williams
2018-06-07 16:30   ` Jan Kara
2018-06-07 16:45     ` Dan Williams
2018-06-04 23:12 ` [PATCH v3 12/12] libnvdimm, pmem: Restore page attributes when clearing errors Dan Williams

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=152815391576.39010.14402839848074832654.stgit@dwillia2-desk3.amr.corp.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=hch@lst.de \
    --cc=jack@suse.cz \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --subject='Re: [PATCH v3 03/12] device-dax: Enable page_mapping()' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).