1 files changed, 104 insertions, 34 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e943370107d0..d398f6bf6d74 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -30,6 +30,7 @@
 #include <linux/security.h>
 #include <linux/hugetlb.h>
 #include <linux/swapops.h>
+#include <linux/miscdevice.h>
 
 int sysctl_unprivileged_userfaultfd __read_mostly;
 
@@ -413,13 +414,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 
 	if (ctx->features & UFFD_FEATURE_SIGBUS)
 		goto out;
-	if ((vmf->flags & FAULT_FLAG_USER) == 0 &&
-	    ctx->flags & UFFD_USER_MODE_ONLY) {
-		printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
-			"sysctl knob to 1 if kernel faults must be handled "
-			"without obtaining CAP_SYS_PTRACE capability\n");
+	if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY))
 		goto out;
-	}
 
 	/*
 	 * If it's already released don't get it. This avoids to loop
@@ -613,14 +609,16 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	if (release_new_ctx) {
 		struct vm_area_struct *vma;
 		struct mm_struct *mm = release_new_ctx->mm;
+		VMA_ITERATOR(vmi, mm, 0);
 
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		mmap_write_lock(mm);
-		for (vma = mm->mmap; vma; vma = vma->vm_next)
+		for_each_vma(vmi, vma) {
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 				vma->vm_flags &= ~__VM_UFFD_FLAGS;
 			}
+		}
 		mmap_write_unlock(mm);
 
 		userfaultfd_ctx_put(release_new_ctx);
@@ -801,11 +799,13 @@ static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
 	return false;
 }
 
-int userfaultfd_unmap_prep(struct vm_area_struct *vma,
-			   unsigned long start, unsigned long end,
-			   struct list_head *unmaps)
+int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start,
+			   unsigned long end, struct list_head *unmaps)
 {
-	for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
+	VMA_ITERATOR(vmi, mm, start);
+	struct vm_area_struct *vma;
+
+	for_each_vma_range(vmi, vma, end) {
 		struct userfaultfd_unmap_ctx *unmap_ctx;
 		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
 
@@ -855,6 +855,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
 	unsigned long new_flags;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	WRITE_ONCE(ctx->released, true);
 
@@ -871,7 +872,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 */
 	mmap_write_lock(mm);
 	prev = NULL;
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+	mas_for_each(&mas, vma, ULONG_MAX) {
 		cond_resched();
 		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
 		       !!(vma->vm_flags & __VM_UFFD_FLAGS));
@@ -885,10 +886,13 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 				 vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
 				 NULL_VM_UFFD_CTX, anon_vma_name(vma));
-		if (prev)
+		if (prev) {
+			mas_pause(&mas);
 			vma = prev;
-		else
+		} else {
 			prev = vma;
+		}
+
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
@@ -1270,6 +1274,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	bool found;
 	bool basic_ioctls;
 	unsigned long start, end, vma_end;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
 
@@ -1312,7 +1317,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	vma = find_vma_prev(mm, start, &prev);
+	mas_set(&mas, start);
+	vma = mas_find(&mas, ULONG_MAX);
 	if (!vma)
 		goto out_unlock;
 
@@ -1337,7 +1343,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	 */
 	found = false;
 	basic_ioctls = false;
-	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+	for (cur = vma; cur; cur = mas_next(&mas, end - 1)) {
 		cond_resched();
 
 		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
@@ -1397,8 +1403,10 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	}
 	BUG_ON(!found);
 
-	if (vma->vm_start < start)
-		prev = vma;
+	mas_set(&mas, start);
+	prev = mas_prev(&mas, 0);
+	if (prev != vma)
+		mas_next(&mas, ULONG_MAX);
 
 	ret = 0;
 	do {
@@ -1428,6 +1436,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				 ((struct vm_userfaultfd_ctx){ ctx }),
 				 anon_vma_name(vma));
 		if (prev) {
+			/* vma_merge() invalidated the mas */
+			mas_pause(&mas);
 			vma = prev;
 			goto next;
 		}
@@ -1435,11 +1445,15 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 			ret = split_vma(mm, vma, start, 1);
 			if (ret)
 				break;
+			/* split_vma() invalidated the mas */
+			mas_pause(&mas);
 		}
 		if (vma->vm_end > end) {
 			ret = split_vma(mm, vma, end, 0);
 			if (ret)
 				break;
+			/* split_vma() invalidated the mas */
+			mas_pause(&mas);
 		}
 	next:
 		/*
@@ -1456,8 +1470,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	skip:
 		prev = vma;
 		start = vma->vm_end;
-		vma = vma->vm_next;
-	} while (vma && vma->vm_start < end);
+		vma = mas_next(&mas, end - 1);
+	} while (vma);
 out_unlock:
 	mmap_write_unlock(mm);
 	mmput(mm);
@@ -1501,6 +1515,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	bool found;
 	unsigned long start, end, vma_end;
 	const void __user *buf = (void __user *)arg;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
@@ -1519,7 +1534,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	vma = find_vma_prev(mm, start, &prev);
+	mas_set(&mas, start);
+	vma = mas_find(&mas, ULONG_MAX);
 	if (!vma)
 		goto out_unlock;
 
@@ -1544,7 +1560,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	 */
 	found = false;
 	ret = -EINVAL;
-	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
+	for (cur = vma; cur; cur = mas_next(&mas, end - 1)) {
 		cond_resched();
 
 		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
@@ -1564,8 +1580,10 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	}
 	BUG_ON(!found);
 
-	if (vma->vm_start < start)
-		prev = vma;
+	mas_set(&mas, start);
+	prev = mas_prev(&mas, 0);
+	if (prev != vma)
+		mas_next(&mas, ULONG_MAX);
 
 	ret = 0;
 	do {
@@ -1630,8 +1648,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	skip:
 		prev = vma;
 		start = vma->vm_end;
-		vma = vma->vm_next;
-	} while (vma && vma->vm_start < end);
+		vma = mas_next(&mas, end - 1);
+	} while (vma);
 out_unlock:
 	mmap_write_unlock(mm);
 	mmput(mm);
@@ -2052,19 +2070,33 @@ static void init_once_userfaultfd_ctx(void *mem)
 	seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
 }
 
-SYSCALL_DEFINE1(userfaultfd, int, flags)
+static inline bool userfaultfd_allowed(bool is_syscall, int flags)
+{
+	bool kernel_faults = !(flags & UFFD_USER_MODE_ONLY);
+	bool allow_unprivileged = sysctl_unprivileged_userfaultfd;
+
+	/* userfaultfd(2) access is controlled by sysctl + capability. */
+	if (is_syscall && kernel_faults) {
+		if (!allow_unprivileged && !capable(CAP_SYS_PTRACE))
+			return false;
+	}
+
+	/*
+	 * For /dev/userfaultfd, access is to be controlled using e.g.
+	 * permissions on the device node. We assume this is correctly
+	 * configured by userspace, so we simply allow access here.
+	 */
+
+	return true;
+}
+
+static int new_userfaultfd(bool is_syscall, int flags)
 {
 	struct userfaultfd_ctx *ctx;
 	int fd;
 
-	if (!sysctl_unprivileged_userfaultfd &&
-	    (flags & UFFD_USER_MODE_ONLY) == 0 &&
-	    !capable(CAP_SYS_PTRACE)) {
-		printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
-			"sysctl knob to 1 if kernel faults must be handled "
-			"without obtaining CAP_SYS_PTRACE capability\n");
+	if (!userfaultfd_allowed(is_syscall, flags))
 		return -EPERM;
-	}
 
 	BUG_ON(!current->mm);
 
@@ -2083,6 +2115,10 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	refcount_set(&ctx->refcount, 1);
 	ctx->flags = flags;
 	ctx->features = 0;
+	/*
+	 * If UFFD_USER_MODE_ONLY is not set, then userfaultfd_allowed() above
+	 * decided that kernel faults were allowed and should be handled.
+	 */
 	ctx->released = false;
 	atomic_set(&ctx->mmap_changing, 0);
 	ctx->mm = current->mm;
@@ -2098,8 +2134,42 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	return fd;
 }
 
+SYSCALL_DEFINE1(userfaultfd, int, flags)
+{
+	return new_userfaultfd(true, flags);
+}
+
+static int userfaultfd_dev_open(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+
+static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags)
+{
+	if (cmd != USERFAULTFD_IOC_NEW)
+		return -EINVAL;
+
+	return new_userfaultfd(false, flags);
+}
+
+static const struct file_operations userfaultfd_dev_fops = {
+	.open = userfaultfd_dev_open,
+	.unlocked_ioctl = userfaultfd_dev_ioctl,
+	.compat_ioctl = userfaultfd_dev_ioctl,
+	.owner = THIS_MODULE,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice userfaultfd_misc = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "userfaultfd",
+	.fops = &userfaultfd_dev_fops
+};
+
 static int __init userfaultfd_init(void)
 {
+	WARN_ON(misc_register(&userfaultfd_misc));
+
 	userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
 						sizeof(struct userfaultfd_ctx),
 						0,