mm: protect VMA modifications using VMA sequence count

The VMA sequence count has been introduced to allow fast detection of
VMA modification when running a page fault handler without holding
the mmap_sem.

This patch provides protection against the VMA modification done in :
	- madvise()
	- mpol_rebind_policy()
	- vma_replace_policy()
	- change_prot_numa()
	- mlock(), munlock()
	- mprotect()
	- mmap_region()
	- collapse_huge_page()
	- userfaultd registering services

In addition, VMA fields which will be read during the speculative fault
path needs to be written using WRITE_ONCE to prevent write to be split
and intermediate values to be pushed to other CPUs.

Change-Id: Ic36046b7254e538b6baf7144c50ae577ee7f2074
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Patch-mainline: linux-mm @ Tue, 17 Apr 2018 16:33:15
[vinmenon@codeaurora.org: trivial merge conflict fixes]
Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org>

fs/proc/task_mmu.c

@@ -1221,8 +1221,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 					goto out_mm;
 				}
 				for (vma = mm->mmap; vma; vma = vma->vm_next) {
-					vma->vm_flags &= ~VM_SOFTDIRTY;
+					vm_write_begin(vma);
+					WRITE_ONCE(vma->vm_flags,
+						vma->vm_flags & ~VM_SOFTDIRTY);
 					vma_set_page_prot(vma);
+					vm_write_end(vma);
 				}
 				downgrade_write(&mm->mmap_sem);
 				break;

fs/userfaultfd.c

@@ -656,8 +656,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 
 	octx = vma->vm_userfaultfd_ctx.ctx;
 	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+		vm_write_begin(vma);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+		WRITE_ONCE(vma->vm_flags,
+			   vma->vm_flags & ~(VM_UFFD_WP | VM_UFFD_MISSING));
+		vm_write_end(vma);
 		return 0;
 	}
 
@@ -883,8 +886,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			vma = prev;
 		else
 			prev = vma;
-		vma->vm_flags = new_flags;
+		vm_write_begin(vma);
+		WRITE_ONCE(vma->vm_flags, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+		vm_write_end(vma);
 	}
 	up_write(&mm->mmap_sem);
 	mmput(mm);
@@ -1443,8 +1448,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
-		vma->vm_flags = new_flags;
+		vm_write_begin(vma);
+		WRITE_ONCE(vma->vm_flags, new_flags);
 		vma->vm_userfaultfd_ctx.ctx = ctx;
+		vm_write_end(vma);
 
 	skip:
 		prev = vma;
@@ -1602,8 +1609,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * the next vma was merged into the current one and
 		 * the current one has not been updated yet.
 		 */
-		vma->vm_flags = new_flags;
+		vm_write_begin(vma);
+		WRITE_ONCE(vma->vm_flags, new_flags);
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+		vm_write_end(vma);
 
 	skip:
 		prev = vma;

mm/khugepaged.c

@@ -1011,6 +1011,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	if (mm_find_pmd(mm, address) != pmd)
 		goto out;
 
+	vm_write_begin(vma);
 	anon_vma_lock_write(vma->anon_vma);
 
 	pte = pte_offset_map(pmd, address);
@@ -1046,6 +1047,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
 		spin_unlock(pmd_ptl);
 		anon_vma_unlock_write(vma->anon_vma);
+		vm_write_end(vma);
 		result = SCAN_FAIL;
 		goto out;
 	}
@@ -1080,6 +1082,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache_pmd(vma, address, pmd);
 	spin_unlock(pmd_ptl);
+	vm_write_end(vma);
 
 	*hpage = NULL;
 

mm/madvise.c

@@ -184,7 +184,9 @@ success:
 	/*
 	 * vm_flags is protected by the mmap_sem held in write mode.
 	 */
-	vma->vm_flags = new_flags;
+	vm_write_begin(vma);
+	WRITE_ONCE(vma->vm_flags, new_flags);
+	vm_write_end(vma);
 out:
 	return error;
 }
@@ -450,9 +452,11 @@ static void madvise_free_page_range(struct mmu_gather *tlb,
 		.private = tlb,
 	};
 
+	vm_write_begin(vma);
 	tlb_start_vma(tlb, vma);
 	walk_page_range(addr, end, &free_walk);
 	tlb_end_vma(tlb, vma);
+	vm_write_end(vma);
 }
 
 static int madvise_free_single_vma(struct vm_area_struct *vma,

mm/mempolicy.c

@@ -379,8 +379,11 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
 	struct vm_area_struct *vma;
 
 	down_write(&mm->mmap_sem);
-	for (vma = mm->mmap; vma; vma = vma->vm_next)
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		vm_write_begin(vma);
 		mpol_rebind_policy(vma->vm_policy, new);
+		vm_write_end(vma);
+	}
 	up_write(&mm->mmap_sem);
 }
 
@@ -578,9 +581,11 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 {
 	int nr_updated;
 
+	vm_write_begin(vma);
 	nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
+	vm_write_end(vma);
 
 	return nr_updated;
 }
@@ -681,6 +686,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
+	vm_write_begin(vma);
 	if (vma->vm_ops && vma->vm_ops->set_policy) {
 		err = vma->vm_ops->set_policy(vma, new);
 		if (err)
@@ -688,11 +694,17 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 	}
 
 	old = vma->vm_policy;
-	vma->vm_policy = new; /* protected by mmap_sem */
+	/*
+	 * The speculative page fault handler accesses this field without
+	 * hodling the mmap_sem.
+	 */
+	WRITE_ONCE(vma->vm_policy,  new);
+	vm_write_end(vma);
 	mpol_put(old);
 
 	return 0;
  err_out:
+	vm_write_end(vma);
 	mpol_put(new);
 	return err;
 }
@@ -1584,23 +1596,28 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
 {
-	struct mempolicy *pol = NULL;
+	struct mempolicy *pol;
 
-	if (vma) {
-		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			pol = vma->vm_ops->get_policy(vma, addr);
-		} else if (vma->vm_policy) {
-			pol = vma->vm_policy;
+	if (!vma)
+		return NULL;
 
-			/*
-			 * shmem_alloc_page() passes MPOL_F_SHARED policy with
-			 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
-			 * count on these policies which will be dropped by
-			 * mpol_cond_put() later
-			 */
-			if (mpol_needs_cond_ref(pol))
-				mpol_get(pol);
-		}
+	if (vma->vm_ops && vma->vm_ops->get_policy)
+		return vma->vm_ops->get_policy(vma, addr);
+
+	/*
+	 * This could be called without holding the mmap_sem in the
+	 * speculative page fault handler's path.
+	 */
+	pol = READ_ONCE(vma->vm_policy);
+	if (pol) {
+		/*
+		 * shmem_alloc_page() passes MPOL_F_SHARED policy with
+		 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+		 * count on these policies which will be dropped by
+		 * mpol_cond_put() later
+		 */
+		if (mpol_needs_cond_ref(pol))
+			mpol_get(pol);
 	}
 
 	return pol;

mm/mlock.c

@@ -439,7 +439,9 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 void munlock_vma_pages_range(struct vm_area_struct *vma,
 			     unsigned long start, unsigned long end)
 {
-	vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
+	vm_write_begin(vma);
+	WRITE_ONCE(vma->vm_flags, vma->vm_flags & VM_LOCKED_CLEAR_MASK);
+	vm_write_end(vma);
 
 	while (start < end) {
 		struct page *page;
@@ -562,10 +564,11 @@ success:
 	 * It's okay if try_to_unmap_one unmaps a page just after we
 	 * set VM_LOCKED, populate_vma_page_range will bring it back.
 	 */
-
-	if (lock)
-		vma->vm_flags = newflags;
-	else
+	if (lock) {
+		vm_write_begin(vma);
+		WRITE_ONCE(vma->vm_flags, newflags);
+		vm_write_end(vma);
+	} else
 		munlock_vma_pages_range(vma, start, end);
 
 out:

mm/mmap.c

@@ -843,17 +843,18 @@ again:
 	}
 
 	if (start != vma->vm_start) {
-		vma->vm_start = start;
+		WRITE_ONCE(vma->vm_start, start);
 		start_changed = true;
 	}
 	if (end != vma->vm_end) {
-		vma->vm_end = end;
+		WRITE_ONCE(vma->vm_end, end);
 		end_changed = true;
 	}
-	vma->vm_pgoff = pgoff;
+	WRITE_ONCE(vma->vm_pgoff, pgoff);
 	if (adjust_next) {
-		next->vm_start += adjust_next << PAGE_SHIFT;
-		next->vm_pgoff += adjust_next;
+		WRITE_ONCE(next->vm_start,
+			   next->vm_start + (adjust_next << PAGE_SHIFT));
+		WRITE_ONCE(next->vm_pgoff, next->vm_pgoff + adjust_next);
 	}
 
 	if (root) {
@@ -1760,13 +1761,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 out:
 	perf_event_mmap(vma);
 
+	vm_write_begin(vma);
 	vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT);
 	if (vm_flags & VM_LOCKED) {
 		if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) ||
 					vma == get_gate_vma(current->mm)))
 			mm->locked_vm += (len >> PAGE_SHIFT);
 		else
-			vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
+			WRITE_ONCE(vma->vm_flags,
+				   vma->vm_flags & VM_LOCKED_CLEAR_MASK);
 	}
 
 	if (file)
@@ -1779,9 +1782,10 @@ out:
 	 * then new mapped in-place (which must be aimed as
 	 * a completely new data area).
 	 */
-	vma->vm_flags |= VM_SOFTDIRTY;
+	WRITE_ONCE(vma->vm_flags, vma->vm_flags | VM_SOFTDIRTY);
 
 	vma_set_page_prot(vma);
+	vm_write_end(vma);
 
 	return addr;
 
@@ -2410,8 +2414,8 @@ int expand_downwards(struct vm_area_struct *vma,
 					mm->locked_vm += grow;
 				vm_stat_account(mm, vma->vm_flags, grow);
 				anon_vma_interval_tree_pre_update_vma(vma);
-				vma->vm_start = address;
-				vma->vm_pgoff -= grow;
+				WRITE_ONCE(vma->vm_start, address);
+				WRITE_ONCE(vma->vm_pgoff, vma->vm_pgoff - grow);
 				anon_vma_interval_tree_post_update_vma(vma);
 				vma_gap_update(vma);
 				spin_unlock(&mm->page_table_lock);

mm/mprotect.c

@@ -361,12 +361,14 @@ success:
 	 * vm_flags and vm_page_prot are protected by the mmap_sem
 	 * held in write mode.
 	 */
-	vma->vm_flags = newflags;
+	vm_write_begin(vma);
+	WRITE_ONCE(vma->vm_flags, newflags);
 	dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
 	vma_set_page_prot(vma);
 
 	change_protection(vma, start, end, vma->vm_page_prot,
 			  dirty_accountable, 0);
+	vm_write_end(vma);
 
 	/*
 	 * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major

mm/swap_state.c

@@ -560,6 +560,10 @@ static unsigned long swapin_nr_pages(unsigned long offset)
  * the readahead.
  *
  * Caller must hold down_read on the vma->vm_mm if vmf->vma is not NULL.
+ * This is needed to ensure the VMA will not be freed in our back. In the case
+ * of the speculative page fault handler, this cannot happen, even if we don't
+ * hold the mmap_sem. Callees are assumed to take care of reading VMA's fields
+ * using READ_ONCE() to read consistent values.
  */
 struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 				struct vm_fault *vmf)
@@ -652,9 +656,9 @@ static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma,
 				     unsigned long *start,
 				     unsigned long *end)
 {
-	*start = max3(lpfn, PFN_DOWN(vma->vm_start),
+	*start = max3(lpfn, PFN_DOWN(READ_ONCE(vma->vm_start)),
 		      PFN_DOWN(faddr & PMD_MASK));
-	*end = min3(rpfn, PFN_DOWN(vma->vm_end),
+	*end = min3(rpfn, PFN_DOWN(READ_ONCE(vma->vm_end)),
 		    PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE));
 }