From 202e14222fadb246dfdf182e67de1518e86a1e20 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Mon, 14 Aug 2023 18:40:58 +1000 Subject: memfd: do not -EACCES old memfd_create() users with vm.memfd_noexec=2 Given the difficulty of auditing all of userspace to figure out whether every memfd_create() user has switched to passing MFD_EXEC and MFD_NOEXEC_SEAL flags, it seems far less distruptive to make it possible for older programs that don't make use of executable memfds to run under vm.memfd_noexec=2. Otherwise, a small dependency change can result in spurious errors. For programs that don't use executable memfds, passing MFD_NOEXEC_SEAL is functionally a no-op and thus having the same In addition, every failure under vm.memfd_noexec=2 needs to print to the kernel log so that userspace can figure out where the error came from. The concerns about pr_warn_ratelimited() spam that caused the switch to pr_warn_once()[1,2] do not apply to the vm.memfd_noexec=2 case. This is a user-visible API change, but as it allows programs to do something that would be blocked before, and the sysctl itself was broken and recently released, it seems unlikely this will cause any issues. [1]: https://lore.kernel.org/Y5yS8wCnuYGLHMj4@x1n/ [2]: https://lore.kernel.org/202212161233.85C9783FB@keescook/ Link: https://lkml.kernel.org/r/20230814-memfd-vm-noexec-uapi-fixes-v2-2-7ff9e3e10ba6@cyphar.com Fixes: 105ff5339f49 ("mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC") Signed-off-by: Aleksa Sarai Cc: Dominique Martinet Cc: Christian Brauner Cc: Daniel Verkamp Cc: Jeff Xu Cc: Kees Cook Cc: Shuah Khan Cc: Signed-off-by: Andrew Morton --- mm/memfd.c | 30 +++++++++++------------------- 1 file changed, 11 insertions(+), 19 deletions(-) (limited to 'mm/memfd.c') diff --git a/mm/memfd.c b/mm/memfd.c index 0bdbd2335af7..d65485c762de 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -271,30 +271,22 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg) static int check_sysctl_memfd_noexec(unsigned int *flags) { #ifdef CONFIG_SYSCTL - char comm[TASK_COMM_LEN]; - int sysctl = MEMFD_NOEXEC_SCOPE_EXEC; - struct pid_namespace *ns; - - ns = task_active_pid_ns(current); - if (ns) - sysctl = ns->memfd_noexec_scope; + int sysctl = task_active_pid_ns(current)->memfd_noexec_scope; if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { - if (sysctl == MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL) + if (sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL) *flags |= MFD_NOEXEC_SEAL; else *flags |= MFD_EXEC; } - if (*flags & MFD_EXEC && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) { - pr_warn_once( - "memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n", - task_pid_nr(current), get_task_comm(comm, current)); - + if (!(*flags & MFD_NOEXEC_SEAL) && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) { + pr_err_ratelimited( + "%s[%d]: memfd_create() requires MFD_NOEXEC_SEAL with vm.memfd_noexec=%d\n", + current->comm, task_pid_nr(current), sysctl); return -EACCES; } #endif - return 0; } @@ -302,7 +294,6 @@ SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags) { - char comm[TASK_COMM_LEN]; unsigned int *file_seals; struct file *file; int fd, error; @@ -325,12 +316,13 @@ SYSCALL_DEFINE2(memfd_create, if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { pr_warn_once( - "memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL, pid=%d '%s'\n", - task_pid_nr(current), get_task_comm(comm, current)); + "%s[%d]: memfd_create() called without MFD_EXEC or MFD_NOEXEC_SEAL set\n", + current->comm, task_pid_nr(current)); } - if (check_sysctl_memfd_noexec(&flags) < 0) - return -EACCES; + error = check_sysctl_memfd_noexec(&flags); + if (error < 0) + return error; /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); -- cgit v1.2.3