diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 07481bb87d4e..c758809d5bcf 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -16,6 +16,21 @@ struct fs_pin; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +/* + * sysctl for vm.memfd_noexec + * 0: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL + * acts like MFD_EXEC was set. + * 1: memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL + * acts like MFD_NOEXEC_SEAL was set. + * 2: memfd_create() without MFD_NOEXEC_SEAL will be + * rejected. + */ +#define MEMFD_NOEXEC_SCOPE_EXEC 0 +#define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 +#define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 +#endif + struct pid_namespace { struct idr idr; struct rcu_head rcu; @@ -31,6 +46,10 @@ struct pid_namespace { struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) + /* sysctl for vm.memfd_noexec */ + int memfd_noexec_scope; +#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 7a8a26751c23..273a4e15dfcf 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -8,6 +8,10 @@ #define MFD_CLOEXEC 0x0001U #define MFD_ALLOW_SEALING 0x0002U #define MFD_HUGETLB 0x0004U +/* not executable and sealed to prevent changing to executable. */ +#define MFD_NOEXEC_SEAL 0x0008U +/* executable */ +#define MFD_EXEC 0x0010U /* * Huge page size encoding when MFD_HUGETLB is specified, and a huge page diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index f4f8cb0435b4..8a98b1af9376 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -23,6 +23,7 @@ #include #include #include +#include "pid_sysctl.h" static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; @@ -110,6 +111,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; + initialize_memfd_noexec_scope(ns); + return ns; out_free_idr: @@ -455,6 +458,8 @@ static __init int pid_namespaces_init(void) #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_paths(kern_path, pid_ns_ctl_table); #endif + + register_pid_ns_sysctl_table_vm(); return 0; } diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h new file mode 100644 index 000000000000..e22d072e1e24 --- /dev/null +++ b/kernel/pid_sysctl.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_PID_SYSCTL_H +#define LINUX_PID_SYSCTL_H + +#include + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) +{ + ns->memfd_noexec_scope = + task_active_pid_ns(current)->memfd_noexec_scope; +} + +static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table, + int write, void *buf, size_t *lenp, loff_t *ppos) +{ + struct pid_namespace *ns = task_active_pid_ns(current); + struct ctl_table table_copy; + + if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + table_copy = *table; + if (ns != &init_pid_ns) + table_copy.data = &ns->memfd_noexec_scope; + + /* + * set minimum to current value, the effect is only bigger + * value is accepted. + */ + if (*(int *)table_copy.data > *(int *)table_copy.extra1) + table_copy.extra1 = table_copy.data; + + return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos); +} + +static struct ctl_table pid_ns_ctl_table_vm[] = { + { + .procname = "memfd_noexec", + .data = &init_pid_ns.memfd_noexec_scope, + .maxlen = sizeof(init_pid_ns.memfd_noexec_scope), + .mode = 0644, + .proc_handler = pid_mfd_noexec_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; +static struct ctl_path vm_path[] = { { .procname = "vm", }, { } }; +static inline void register_pid_ns_sysctl_table_vm(void) +{ + register_sysctl_paths(vm_path, pid_ns_ctl_table_vm); +} +#else +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void register_pid_ns_sysctl_table_vm(void) {} +#endif + +#endif /* LINUX_PID_SYSCTL_H */ diff --git a/mm/memfd.c b/mm/memfd.c index 4ebeab94aa74..bc214390e28d 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -263,12 +264,13 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg) #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) -#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC) 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; @@ -285,6 +287,40 @@ SYSCALL_DEFINE2(memfd_create, return -EINVAL; } + /* Invalid if both EXEC and NOEXEC_SEAL are set.*/ + if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) + return -EINVAL; + + if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { +#ifdef CONFIG_SYSCTL + int sysctl = MEMFD_NOEXEC_SCOPE_EXEC; + struct pid_namespace *ns; + + ns = task_active_pid_ns(current); + if (ns) + sysctl = ns->memfd_noexec_scope; + + switch (sysctl) { + case MEMFD_NOEXEC_SCOPE_EXEC: + flags |= MFD_EXEC; + break; + case MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL: + flags |= MFD_NOEXEC_SEAL; + break; + default: + pr_warn_once( + "memfd_create(): MFD_NOEXEC_SEAL is enforced, pid=%d '%s'\n", + task_pid_nr(current), get_task_comm(comm, current)); + return -EINVAL; + } +#else + flags |= MFD_EXEC; +#endif + 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)); + } + /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); if (len <= 0) @@ -328,7 +364,15 @@ SYSCALL_DEFINE2(memfd_create, file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; - if (flags & MFD_ALLOW_SEALING) { + if (flags & MFD_NOEXEC_SEAL) { + struct inode *inode = file_inode(file); + + inode->i_mode &= ~0111; + file_seals = memfd_file_seals_ptr(file); + *file_seals &= ~F_SEAL_SEAL; + *file_seals |= F_SEAL_EXEC; + } else if (flags & MFD_ALLOW_SEALING) { + /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); *file_seals &= ~F_SEAL_SEAL; }