X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fmm%2Fmlock.c;h=d6006b146fea38c0f897bbcb721dec70a189c92c;hb=e09b41010ba33a20a87472ee821fa407a5b8da36;hp=6fd2cf15e8687d32114f8e81516aed0a52997147;hpb=f93b97fd65072de626c074dbe099a1fff05ce060;p=kvmfornfv.git

diff --git a/kernel/mm/mlock.c b/kernel/mm/mlock.c
index 6fd2cf15e..d6006b146 100644
--- a/kernel/mm/mlock.c
+++ b/kernel/mm/mlock.c
@@ -172,7 +172,7 @@ static void __munlock_isolation_failed(struct page *page)
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int nr_pages;
+	int nr_pages;
 	struct zone *zone = page_zone(page);
 
 	/* For try_to_munlock() and to serialize with page migration */
@@ -422,7 +422,7 @@ 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;
+	vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
 
 	while (start < end) {
 		struct page *page = NULL;
@@ -506,11 +506,13 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
-		goto out;	/* don't set VM_LOCKED,  don't count */
+		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+		goto out;
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
-			  vma->vm_file, pgoff, vma_policy(vma));
+			  vma->vm_file, pgoff, vma_policy(vma),
+			  vma->vm_userfaultfd_ctx);
 	if (*prev) {
 		vma = *prev;
 		goto success;
@@ -553,13 +555,14 @@ out:
 	return ret;
 }
 
-static int do_mlock(unsigned long start, size_t len, int on)
+static int apply_vma_lock_flags(unsigned long start, size_t len,
+				vm_flags_t flags)
 {
 	unsigned long nstart, end, tmp;
 	struct vm_area_struct * vma, * prev;
 	int error;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(offset_in_page(start));
 	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 	if (end < start)
@@ -575,14 +578,11 @@ static int do_mlock(unsigned long start, size_t len, int on)
 		prev = vma;
 
 	for (nstart = start ; ; ) {
-		vm_flags_t newflags;
-
-		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
+		vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
 
-		newflags = vma->vm_flags & ~VM_LOCKED;
-		if (on)
-			newflags |= VM_LOCKED;
+		newflags |= flags;
 
+		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
 		tmp = vma->vm_end;
 		if (tmp > end)
 			tmp = end;
@@ -604,7 +604,7 @@ static int do_mlock(unsigned long start, size_t len, int on)
 	return error;
 }
 
-SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
+static int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
 {
 	unsigned long locked;
 	unsigned long lock_limit;
@@ -615,7 +615,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 	lru_add_drain_all();	/* flush pagevec */
 
-	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
+	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
@@ -628,7 +628,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 	/* check against resource limits */
 	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
-		error = do_mlock(start, len, 1);
+		error = apply_vma_lock_flags(start, len, flags);
 
 	up_write(&current->mm->mmap_sem);
 	if (error)
@@ -640,37 +640,75 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 	return 0;
 }
 
+SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
+{
+	return do_mlock(start, len, VM_LOCKED);
+}
+
+SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
+{
+	vm_flags_t vm_flags = VM_LOCKED;
+
+	if (flags & ~MLOCK_ONFAULT)
+		return -EINVAL;
+
+	if (flags & MLOCK_ONFAULT)
+		vm_flags |= VM_LOCKONFAULT;
+
+	return do_mlock(start, len, vm_flags);
+}
+
 SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
-	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
+	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 
 	down_write(&current->mm->mmap_sem);
-	ret = do_mlock(start, len, 0);
+	ret = apply_vma_lock_flags(start, len, 0);
 	up_write(&current->mm->mmap_sem);
 
 	return ret;
 }
 
-static int do_mlockall(int flags)
+/*
+ * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
+ * and translate into the appropriate modifications to mm->def_flags and/or the
+ * flags for all current VMAs.
+ *
+ * There are a couple of subtleties with this.  If mlockall() is called multiple
+ * times with different flags, the values do not necessarily stack.  If mlockall
+ * is called once including the MCL_FUTURE flag and then a second time without
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ */
+static int apply_mlockall_flags(int flags)
 {
 	struct vm_area_struct * vma, * prev = NULL;
+	vm_flags_t to_add = 0;
 
-	if (flags & MCL_FUTURE)
+	current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
+	if (flags & MCL_FUTURE) {
 		current->mm->def_flags |= VM_LOCKED;
-	else
-		current->mm->def_flags &= ~VM_LOCKED;
-	if (flags == MCL_FUTURE)
-		goto out;
+
+		if (flags & MCL_ONFAULT)
+			current->mm->def_flags |= VM_LOCKONFAULT;
+
+		if (!(flags & MCL_CURRENT))
+			goto out;
+	}
+
+	if (flags & MCL_CURRENT) {
+		to_add |= VM_LOCKED;
+		if (flags & MCL_ONFAULT)
+			to_add |= VM_LOCKONFAULT;
+	}
 
 	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
 		vm_flags_t newflags;
 
-		newflags = vma->vm_flags & ~VM_LOCKED;
-		if (flags & MCL_CURRENT)
-			newflags |= VM_LOCKED;
+		newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+		newflags |= to_add;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -683,14 +721,13 @@ out:
 SYSCALL_DEFINE1(mlockall, int, flags)
 {
 	unsigned long lock_limit;
-	int ret = -EINVAL;
+	int ret;
 
-	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
-		goto out;
+	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)))
+		return -EINVAL;
 
-	ret = -EPERM;
 	if (!can_do_mlock())
-		goto out;
+		return -EPERM;
 
 	if (flags & MCL_CURRENT)
 		lru_add_drain_all();	/* flush pagevec */
@@ -703,11 +740,11 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 
 	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
 	    capable(CAP_IPC_LOCK))
-		ret = do_mlockall(flags);
+		ret = apply_mlockall_flags(flags);
 	up_write(&current->mm->mmap_sem);
 	if (!ret && (flags & MCL_CURRENT))
 		mm_populate(0, TASK_SIZE);
-out:
+
 	return ret;
 }
 
@@ -716,7 +753,7 @@ SYSCALL_DEFINE0(munlockall)
 	int ret;
 
 	down_write(&current->mm->mmap_sem);
-	ret = do_mlockall(0);
+	ret = apply_mlockall_flags(0);
 	up_write(&current->mm->mmap_sem);
 	return ret;
 }