diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index aa719245ee33..3346e956b008 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -902,12 +902,17 @@ The default value is 60. unprivileged_userfaultfd ======================== -This flag controls whether unprivileged users can use the userfaultfd -system calls. Set this to 1 to allow unprivileged users to use the -userfaultfd system calls, or set this to 0 to restrict userfaultfd to only -privileged users (with SYS_CAP_PTRACE capability). +This flag controls the mode in which unprivileged users can use the +userfaultfd system calls. Set this to 0 to restrict unprivileged users +to handle page faults in user mode only. In this case, users without +SYS_CAP_PTRACE must pass UFFD_USER_MODE_ONLY in order for userfaultfd to +succeed. Prohibiting use of userfaultfd for handling faults from kernel +mode may make certain vulnerabilities more difficult to exploit. -The default value is 1. +Set this to 1 to allow unprivileged users to use the userfaultfd system +calls without any restrictions. + +The default value is 0. user_reserve_kbytes diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 98c064338416..23f78606fd74 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -29,7 +29,7 @@ #include #include -int sysctl_unprivileged_userfaultfd __read_mostly = 1; +int sysctl_unprivileged_userfaultfd __read_mostly; static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; @@ -1963,8 +1963,14 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) struct userfaultfd_ctx *ctx; int fd; - if (!sysctl_unprivileged_userfaultfd && !capable(CAP_SYS_PTRACE)) + 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);