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: <1503007519-26777-8-git-send-email-ldufour@linux.vnet.ibm.com>
Date:   Fri, 18 Aug 2017 00:05:06 +0200
From:   Laurent Dufour <ldufour@...ux.vnet.ibm.com>
To:     paulmck@...ux.vnet.ibm.com, peterz@...radead.org,
        akpm@...ux-foundation.org, kirill@...temov.name,
        ak@...ux.intel.com, mhocko@...nel.org, dave@...olabs.net,
        jack@...e.cz, Matthew Wilcox <willy@...radead.org>,
        benh@...nel.crashing.org, mpe@...erman.id.au, paulus@...ba.org,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, hpa@...or.com,
        Will Deacon <will.deacon@....com>
Cc:     linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        haren@...ux.vnet.ibm.com, khandual@...ux.vnet.ibm.com,
        npiggin@...il.com, bsingharora@...il.com,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        linuxppc-dev@...ts.ozlabs.org, x86@...nel.org
Subject: [PATCH v2 07/20] mm: Cache some VMA fields in the vm_fault structure

When handling speculative page fault, the vma->vm_flags and
vma->vm_page_prot fields are read once the page table lock is released. So
there is no more guarantee that these fields would not change in our back.
They will be saved in the vm_fault structure before the VMA is checked for
changes.

This patch also set the fields in hugetlb_no_page() and
__collapse_huge_page_swapin even if it is not need for the callee.

Signed-off-by: Laurent Dufour <ldufour@...ux.vnet.ibm.com>
---
 include/linux/mm.h |  6 ++++++
 mm/hugetlb.c       |  2 ++
 mm/khugepaged.c    |  2 ++
 mm/memory.c        | 38 ++++++++++++++++++++------------------
 4 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8763ec96dc78..43d313ff3a5b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -345,6 +345,12 @@ struct vm_fault {
 					 * page table to avoid allocation from
 					 * atomic context.
 					 */
+	/*
+	 * These entries are required when handling speculative page fault.
+	 * This way the page handling is done using consistent field values.
+	 */
+	unsigned long vma_flags;
+	pgprot_t vma_page_prot;
 };
 
 /* page entry size for vm->huge_fault() */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 31e207cb399b..55201b98133e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3676,6 +3676,8 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				.vma = vma,
 				.address = address,
 				.flags = flags,
+				.vma_flags = vma->vm_flags,
+				.vma_page_prot = vma->vm_page_prot,
 				/*
 				 * Hard to debug if it ends up being
 				 * used by a callee that assumes
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 56dd994c05d0..0525a0e74535 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -881,6 +881,8 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		.flags = FAULT_FLAG_ALLOW_RETRY,
 		.pmd = pmd,
 		.pgoff = linear_page_index(vma, address),
+		.vma_flags = vma->vm_flags,
+		.vma_page_prot = vma->vm_page_prot,
 	};
 
 	/* we only decide to swapin, if there is enough young ptes */
diff --git a/mm/memory.c b/mm/memory.c
index 4a2736fe2ef6..da3bd07bb052 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2417,7 +2417,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 		 * Don't let another task, with possibly unlocked vma,
 		 * keep the mlocked page.
 		 */
-		if (page_copied && (vma->vm_flags & VM_LOCKED)) {
+		if (page_copied && (vmf->vma_flags & VM_LOCKED)) {
 			lock_page(old_page);	/* LRU manipulation */
 			if (PageMlocked(old_page))
 				munlock_vma_page(old_page);
@@ -2451,7 +2451,7 @@ static int wp_page_copy(struct vm_fault *vmf)
  */
 int finish_mkwrite_fault(struct vm_fault *vmf)
 {
-	WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED));
+	WARN_ON_ONCE(!(vmf->vma_flags & VM_SHARED));
 	if (!pte_map_lock(vmf))
 		return VM_FAULT_RETRY;
 	/*
@@ -2553,7 +2553,7 @@ static int do_wp_page(struct vm_fault *vmf)
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable and/or call ops->pfn_mkwrite.
 		 */
-		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+		if ((vmf->vma_flags & (VM_WRITE|VM_SHARED)) ==
 				     (VM_WRITE|VM_SHARED))
 			return wp_pfn_shared(vmf);
 
@@ -2600,7 +2600,7 @@ static int do_wp_page(struct vm_fault *vmf)
 			return VM_FAULT_WRITE;
 		}
 		unlock_page(vmf->page);
-	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+	} else if (unlikely((vmf->vma_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		return wp_page_shared(vmf);
 	}
@@ -2817,7 +2817,7 @@ int do_swap_page(struct vm_fault *vmf)
 
 	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 	dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS);
-	pte = mk_pte(page, vma->vm_page_prot);
+	pte = mk_pte(page, vmf->vma_page_prot);
 	if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		vmf->flags &= ~FAULT_FLAG_WRITE;
@@ -2841,7 +2841,7 @@ int do_swap_page(struct vm_fault *vmf)
 
 	swap_free(entry);
 	if (mem_cgroup_swap_full(page) ||
-	    (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
+	    (vmf->vma_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
 	if (page != swapcache) {
@@ -2897,7 +2897,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	pte_t entry;
 
 	/* File mapping without ->vm_ops ? */
-	if (vma->vm_flags & VM_SHARED)
+	if (vmf->vma_flags & VM_SHARED)
 		return VM_FAULT_SIGBUS;
 
 	/*
@@ -2921,7 +2921,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
 			!mm_forbids_zeropage(vma->vm_mm)) {
 		entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
-						vma->vm_page_prot));
+						vmf->vma_page_prot));
 		if (!pte_map_lock(vmf))
 			return VM_FAULT_RETRY;
 		if (!pte_none(*vmf->pte))
@@ -2951,8 +2951,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	 */
 	__SetPageUptodate(page);
 
-	entry = mk_pte(page, vma->vm_page_prot);
-	if (vma->vm_flags & VM_WRITE)
+	entry = mk_pte(page, vmf->vma_page_prot);
+	if (vmf->vma_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
 	if (!pte_map_lock(vmf)) {
@@ -3144,7 +3144,7 @@ static int do_set_pmd(struct vm_fault *vmf, struct page *page)
 	for (i = 0; i < HPAGE_PMD_NR; i++)
 		flush_icache_page(vma, page + i);
 
-	entry = mk_huge_pmd(page, vma->vm_page_prot);
+	entry = mk_huge_pmd(page, vmf->vma_page_prot);
 	if (write)
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
@@ -3218,11 +3218,11 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 		return VM_FAULT_NOPAGE;
 
 	flush_icache_page(vma, page);
-	entry = mk_pte(page, vma->vm_page_prot);
+	entry = mk_pte(page, vmf->vma_page_prot);
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	/* copy-on-write page */
-	if (write && !(vma->vm_flags & VM_SHARED)) {
+	if (write && !(vmf->vma_flags & VM_SHARED)) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, vmf->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
@@ -3261,7 +3261,7 @@ int finish_fault(struct vm_fault *vmf)
 
 	/* Did we COW the page? */
 	if ((vmf->flags & FAULT_FLAG_WRITE) &&
-	    !(vmf->vma->vm_flags & VM_SHARED))
+	    !(vmf->vma_flags & VM_SHARED))
 		page = vmf->cow_page;
 	else
 		page = vmf->page;
@@ -3507,7 +3507,7 @@ static int do_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_SIGBUS;
 	else if (!(vmf->flags & FAULT_FLAG_WRITE))
 		ret = do_read_fault(vmf);
-	else if (!(vma->vm_flags & VM_SHARED))
+	else if (!(vmf->vma_flags & VM_SHARED))
 		ret = do_cow_fault(vmf);
 	else
 		ret = do_shared_fault(vmf);
@@ -3564,7 +3564,7 @@ static int do_numa_page(struct vm_fault *vmf)
 	 * accessible ptes, some can allow access by kernel mode.
 	 */
 	pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte);
-	pte = pte_modify(pte, vma->vm_page_prot);
+	pte = pte_modify(pte, vmf->vma_page_prot);
 	pte = pte_mkyoung(pte);
 	if (was_writable)
 		pte = pte_mkwrite(pte);
@@ -3598,7 +3598,7 @@ static int do_numa_page(struct vm_fault *vmf)
 	 * Flag if the page is shared between multiple address spaces. This
 	 * is later used when determining whether to group tasks together
 	 */
-	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+	if (page_mapcount(page) > 1 && (vmf->vma_flags & VM_SHARED))
 		flags |= TNF_SHARED;
 
 	last_cpupid = page_cpupid_last(page);
@@ -3642,7 +3642,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
 		return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 
 	/* COW handled on pte level: split pmd */
-	VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
+	VM_BUG_ON_VMA(vmf->vma_flags & VM_SHARED, vmf->vma);
 	__split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL);
 
 	return VM_FAULT_FALLBACK;
@@ -3789,6 +3789,8 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		.flags = flags,
 		.pgoff = linear_page_index(vma, address),
 		.gfp_mask = __get_fault_gfp_mask(vma),
+		.vma_flags = vma->vm_flags,
+		.vma_page_prot = vma->vm_page_prot,
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
-- 
2.7.4

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ