linux-kernel - [PATCHv2, RFC 28/30] thp: handle write-protect exception to file-backed huge pages

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: <1363283435-7666-29-git-send-email-kirill.shutemov@linux.intel.com>
Date:	Thu, 14 Mar 2013 19:50:33 +0200
From:	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To:	Andrea Arcangeli <aarcange@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Al Viro <viro@...iv.linux.org.uk>,
	Hugh Dickins <hughd@...gle.com>
Cc:	Wu Fengguang <fengguang.wu@...el.com>, Jan Kara <jack@...e.cz>,
	Mel Gorman <mgorman@...e.de>, linux-mm@...ck.org,
	Andi Kleen <ak@...ux.intel.com>,
	Matthew Wilcox <matthew.r.wilcox@...el.com>,
	"Kirill A. Shutemov" <kirill@...temov.name>,
	Hillf Danton <dhillf@...il.com>, linux-fsdevel@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCHv2, RFC 28/30] thp: handle write-protect exception to file-backed huge pages

From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
 mm/huge_memory.c |   69 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 67 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d1adaea..a416a77 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1339,7 +1339,6 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
-	VM_BUG_ON(!vma->anon_vma);
 	haddr = address & HPAGE_PMD_MASK;
 	if (is_huge_zero_pmd(orig_pmd))
 		goto alloc;
@@ -1349,7 +1348,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	page = pmd_page(orig_pmd);
 	VM_BUG_ON(!PageCompound(page) || !PageHead(page));
-	if (page_mapcount(page) == 1) {
+	if (PageAnon(page) && page_mapcount(page) == 1) {
 		pmd_t entry;
 		entry = pmd_mkyoung(orig_pmd);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
@@ -1357,10 +1356,72 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			update_mmu_cache_pmd(vma, address, pmd);
 		ret |= VM_FAULT_WRITE;
 		goto out_unlock;
+	} else if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+			(VM_WRITE|VM_SHARED)) {
+		struct vm_fault vmf;
+		pmd_t entry;
+		struct address_space *mapping;
+
+		/* not yet impemented */
+		VM_BUG_ON(!vma->vm_ops || !vma->vm_ops->page_mkwrite);
+
+		vmf.virtual_address = (void __user *)haddr;
+		vmf.pgoff = page->index;
+		vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+		vmf.page = page;
+
+		page_cache_get(page);
+		spin_unlock(&mm->page_table_lock);
+
+		ret = vma->vm_ops->page_mkwrite(vma, &vmf);
+		if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
+			page_cache_release(page);
+			goto out;
+		}
+		if (unlikely(!(ret & VM_FAULT_LOCKED))) {
+			lock_page(page);
+			if (!page->mapping) {
+				ret = 0; /* retry */
+				unlock_page(page);
+				page_cache_release(page);
+				goto out;
+			}
+		} else
+			VM_BUG_ON(!PageLocked(page));
+		spin_lock(&mm->page_table_lock);
+		if (unlikely(!pmd_same(*pmd, orig_pmd))) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto out_unlock;
+		}
+
+		flush_cache_page(vma, address, pmd_pfn(orig_pmd));
+		entry = pmd_mkyoung(orig_pmd);
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+		if (pmdp_set_access_flags(vma, haddr, pmd, entry,  1))
+			update_mmu_cache_pmd(vma, address, pmd);
+		ret = VM_FAULT_WRITE;
+		spin_unlock(&mm->page_table_lock);
+
+		mapping = page->mapping;
+		set_page_dirty(page);
+		unlock_page(page);
+		page_cache_release(page);
+		if (mapping)	{
+			/*
+			 * Some device drivers do not set page.mapping
+			 * but still dirty their pages
+			 */
+			balance_dirty_pages_ratelimited(mapping);
+		}
+		return ret;
 	}
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
 alloc:
+	if (unlikely(anon_vma_prepare(vma)))
+		return VM_FAULT_OOM;
+
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow())
 		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
@@ -1424,6 +1485,10 @@ alloc:
 			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 			put_huge_zero_page();
 		} else {
+			if (!PageAnon(page)) {
+				add_mm_counter(mm, MM_FILEPAGES, -HPAGE_PMD_NR);
+				add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
+			}
 			VM_BUG_ON(!PageHead(page));
 			page_remove_rmap(page);
 			put_page(page);
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/