linux-kernel - [PATCH 4.7 060/184] mm: fix cache mode of dax pmd mappings

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20160922174051.277200926@linuxfoundation.org>
Date:   Thu, 22 Sep 2016 19:39:54 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Matthew Wilcox <mawilcox@...rosoft.com>,
        Ross Zwisler <ross.zwisler@...ux.intel.com>,
        Nilesh Choudhury <nilesh.choudhury@...cle.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Toshi Kani <toshi.kani@....com>,
        Kai Zhang <kai.ka.zhang@...cle.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Dan Williams <dan.j.williams@...el.com>
Subject: [PATCH 4.7 060/184] mm: fix cache mode of dax pmd mappings

4.7-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@...el.com>

commit 9049771f7d5490a302589976984810064c83ab40 upstream.

track_pfn_insert() in vmf_insert_pfn_pmd() is marking dax mappings as
uncacheable rendering them impractical for application usage.  DAX-pte
mappings are cached and the goal of establishing DAX-pmd mappings is to
attain more performance, not dramatically less (3 orders of magnitude).

track_pfn_insert() relies on a previous call to reserve_memtype() to
establish the expected page_cache_mode for the range.  While memremap()
arranges for reserve_memtype() to be called, devm_memremap_pages() does
not.  So, teach track_pfn_insert() and untrack_pfn() how to handle
tracking without a vma, and arrange for devm_memremap_pages() to
establish the write-back-cache reservation in the memtype tree.

Cc: Matthew Wilcox <mawilcox@...rosoft.com>
Cc: Ross Zwisler <ross.zwisler@...ux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@...cle.com>
Cc: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Reported-by: Toshi Kani <toshi.kani@....com>
Reported-by: Kai Zhang <kai.ka.zhang@...cle.com>
Acked-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@...el.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 arch/x86/mm/pat.c |   17 ++++++++++-------
 kernel/memremap.c |    9 +++++++++
 2 files changed, 19 insertions(+), 7 deletions(-)

--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -931,9 +931,10 @@ int track_pfn_copy(struct vm_area_struct
 }
 
 /*
- * prot is passed in as a parameter for the new mapping. If the vma has a
- * linear pfn mapping for the entire range reserve the entire vma range with
- * single reserve_pfn_range call.
+ * prot is passed in as a parameter for the new mapping. If the vma has
+ * a linear pfn mapping for the entire range, or no vma is provided,
+ * reserve the entire pfn + size range with single reserve_pfn_range
+ * call.
  */
 int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 		    unsigned long pfn, unsigned long addr, unsigned long size)
@@ -942,11 +943,12 @@ int track_pfn_remap(struct vm_area_struc
 	enum page_cache_mode pcm;
 
 	/* reserve the whole chunk starting from paddr */
-	if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
+	if (!vma || (addr == vma->vm_start
+				&& size == (vma->vm_end - vma->vm_start))) {
 		int ret;
 
 		ret = reserve_pfn_range(paddr, size, prot, 0);
-		if (!ret)
+		if (ret == 0 && vma)
 			vma->vm_flags |= VM_PAT;
 		return ret;
 	}
@@ -1001,7 +1003,7 @@ void untrack_pfn(struct vm_area_struct *
 	resource_size_t paddr;
 	unsigned long prot;
 
-	if (!(vma->vm_flags & VM_PAT))
+	if (vma && !(vma->vm_flags & VM_PAT))
 		return;
 
 	/* free the chunk starting from pfn or the whole chunk */
@@ -1015,7 +1017,8 @@ void untrack_pfn(struct vm_area_struct *
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
-	vma->vm_flags &= ~VM_PAT;
+	if (vma)
+		vma->vm_flags &= ~VM_PAT;
 }
 
 /*
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -253,6 +253,7 @@ static void devm_memremap_pages_release(
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	arch_remove_memory(align_start, align_size);
+	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
 			"%s: failed to free all reserved pages\n", __func__);
@@ -288,6 +289,7 @@ void *devm_memremap_pages(struct device
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
 	resource_size_t key, align_start, align_size, align_end;
+	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	int error, nid, is_ram;
@@ -363,6 +365,11 @@ void *devm_memremap_pages(struct device
 	if (nid < 0)
 		nid = numa_mem_id();
 
+	error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
+			align_size);
+	if (error)
+		goto err_pfn_remap;
+
 	error = arch_add_memory(nid, align_start, align_size, true);
 	if (error)
 		goto err_add_memory;
@@ -383,6 +390,8 @@ void *devm_memremap_pages(struct device
 	return __va(res->start);
 
  err_add_memory:
+	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+ err_pfn_remap:
  err_radix:
 	pgmap_radix_release(res);
 	devres_free(page_map);