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.
Signed-off-by: Axel Rasmussen axelrasmussen@google.com --- fs/userfaultfd.c | 79 ++++++++++++++++++++++++++------ include/uapi/linux/userfaultfd.h | 4 ++ 2 files changed, 69 insertions(+), 14 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index aa0c47cb0d16..16d7573ab41a 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -29,6 +29,7 @@ #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> +#include <linux/miscdevice.h>
int sysctl_unprivileged_userfaultfd __read_mostly;
@@ -65,6 +66,8 @@ struct userfaultfd_ctx { unsigned int flags; /* features requested from the userspace */ unsigned int features; + /* whether or not to handle kernel faults */ + bool handle_kernel_faults; /* released */ bool released; /* memory mappings are changing because of non-cooperative event */ @@ -410,13 +413,8 @@ 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->handle_kernel_faults) goto out; - }
/* * If it's already released don't get it. This avoids to loop @@ -2064,19 +2062,33 @@ 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);
@@ -2095,6 +2107,11 @@ 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->handle_kernel_faults = !(flags & UFFD_USER_MODE_ONLY); ctx->released = false; atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; @@ -2110,8 +2127,42 @@ 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 = compat_ptr_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, diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index ef739054cb1c..032a35b3bbd2 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/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 _IOWR(USERFAULTFD_IOC, 0x00, int) + /* * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In