userfaultfd: add /dev/userfaultfd for fine grained access control

Historically, it has been shown that intercepting kernel faults with
userfaultfd (thereby forcing the kernel to wait for an arbitrary amount of
time) can be exploited, or at least can make some kinds of exploits
easier.  So, in 37cd0575b8 "userfaultfd: add UFFD_USER_MODE_ONLY" we
changed things so, in order for kernel faults to be handled by
userfaultfd, either the process needs CAP_SYS_PTRACE, or this sysctl must
be configured so that any unprivileged user can do it.

In a typical implementation of a hypervisor with live migration (take
QEMU/KVM as one such example), we do indeed need to be able to handle
kernel faults.  But, both options above are less than ideal:

- Toggling the sysctl increases attack surface by allowing any
  unprivileged user to do it.

- Granting the live migration process CAP_SYS_PTRACE gives it this
  ability, but *also* the ability to "observe and control the
  execution of another process [...], and examine and change [its]
  memory and registers" (from ptrace(2)). This isn't something we need
  or want to be able to do, so granting this permission violates the
  "principle of least privilege".

This is all a long winded way to say: we want a more fine-grained way to
grant access to userfaultfd, without granting other additional permissions
at the same time.

To achieve this, add a /dev/userfaultfd misc device.  This device provides
an alternative to the userfaultfd(2) syscall for the creation of new
userfaultfds.  The idea is, any userfaultfds created this way will be able
to handle kernel faults, without the caller having any special
capabilities.  Access to this mechanism is instead restricted using e.g. 
standard filesystem permissions.

[axelrasmussen@google.com: Handle misc_register() failure properly]
  Link: https://lkml.kernel.org/r/20220819205201.658693-3-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-3-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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;
 
@@ -415,13 +416,8 @@ 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 &&
+	if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY))
-	    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");
 		goto out;
-	}
 
 	/*
 	 * If it's already released don't get it. This avoids to loop
@@ -2056,20 +2052,11 @@ 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 int new_userfaultfd(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");
-		return -EPERM;
-	}
-
 	BUG_ON(!current->mm);
 
 	/* Check the UFFD_* constants for consistency.  */
@@ -2102,8 +2089,60 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	return fd;
 }
 
+static inline bool userfaultfd_syscall_allowed(int flags)
+{
+	/* Userspace-only page faults are always allowed */
+	if (flags & UFFD_USER_MODE_ONLY)
+		return true;
+
+	/*
+	 * The user is requesting a userfaultfd which can handle kernel faults.
+	 * Privileged users are always allowed to do this.
+	 */
+	if (capable(CAP_SYS_PTRACE))
+		return true;
+
+	/* Otherwise, access to kernel fault handling is sysctl controlled. */
+	return sysctl_unprivileged_userfaultfd;
+}
+
+SYSCALL_DEFINE1(userfaultfd, int, flags)
+{
+	if (!userfaultfd_syscall_allowed(flags))
+		return -EPERM;
+
+	return new_userfaultfd(flags);
+}
+
+static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags)
+{
+	if (cmd != USERFAULTFD_IOC_NEW)
+		return -EINVAL;
+
+	return new_userfaultfd(flags);
+}
+
+static const struct file_operations userfaultfd_dev_fops = {
+	.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)
 {
+	int ret;
+
+	ret = misc_register(&userfaultfd_misc);
+	if (ret)
+		return ret;
+
 	userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
 						sizeof(struct userfaultfd_ctx),
 						0,

include/uapi/linux/userfaultfd.h

@@ -12,6 +12,10 @@
 
 #include <linux/types.h>
 
+/* ioctls for /dev/userfaultfd */
+#define USERFAULTFD_IOC 0xAA
+#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00)
+
 /*
  * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
  * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR.  In