| Message ID | 20201027200358.557003-9-mic@digikod.net |
|---|---|
| State | Superseded |
| Headers | show |
| Series | Landlock LSM | expand |
On Tue, Oct 27, 2020 at 9:04 PM Mickaël Salaün <mic@digikod.net> wrote: > These 3 system calls are designed to be used by unprivileged processes > to sandbox themselves: > * landlock_create_ruleset(2): Creates a ruleset and returns its file > descriptor. > * landlock_add_rule(2): Adds a rule (e.g. file hierarchy access) to a > ruleset, identified by the dedicated file descriptor. > * landlock_enforce_ruleset_current(2): Enforces a ruleset on the current > thread and its future children (similar to seccomp). This syscall has > the same usage restrictions as seccomp(2): the caller must have the > no_new_privs attribute set or have CAP_SYS_ADMIN in the current user > namespace. [...] > Cc: Arnd Bergmann <arnd@arndb.de> > Cc: James Morris <jmorris@namei.org> > Cc: Jann Horn <jannh@google.com> > Cc: Kees Cook <keescook@chromium.org> > Cc: Serge E. Hallyn <serge@hallyn.com> > Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> [...] > diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h [...] > +/** > + * struct landlock_path_beneath_attr - Path hierarchy definition > + * > + * Argument of sys_landlock_add_rule(). > + */ > +struct landlock_path_beneath_attr { > + /** > + * @allowed_access: Bitmask of allowed actions for this file hierarchy > + * (cf. `Filesystem flags`_). > + */ > + __u64 allowed_access; > + /** > + * @parent_fd: File descriptor, open with ``O_PATH``, which identify nit: "identifies" > + * the parent directory of a file hierarchy, or just a file. > + */ > + __s32 parent_fd; > + /* > + * This struct is packed to avoid trailing reserved members. > + * Cf. security/landlock/syscall.c:build_check_abi() > + */ > +} __attribute__((packed)); [...] > diff --git a/security/landlock/syscall.c b/security/landlock/syscall.c [...] > +static int copy_min_struct_from_user(void *const dst, const size_t ksize, > + const size_t ksize_min, const void __user *const src, > + const size_t usize) > +{ > + /* Checks buffer inconsistencies. */ > + BUILD_BUG_ON(!dst); > + if (!src) > + return -EFAULT; > + > + /* Checks size ranges. */ > + BUILD_BUG_ON(ksize <= 0); > + BUILD_BUG_ON(ksize < ksize_min); To make these checks work reliably, you should add __always_inline to the function. > + if (usize < ksize_min) > + return -EINVAL; > + if (usize > PAGE_SIZE) > + return -E2BIG; > + > + /* Copies user buffer and fills with zeros. */ > + return copy_struct_from_user(dst, ksize, src, usize); > +} [...] > +static int get_path_from_fd(const s32 fd, struct path *const path) > +{ > + struct fd f; > + int err = 0; > + > + BUILD_BUG_ON(!__same_type(fd, > + ((struct landlock_path_beneath_attr *)NULL)->parent_fd)); > + > + /* Handles O_PATH. */ > + f = fdget_raw(fd); > + if (!f.file) > + return -EBADF; > + /* > + * Only allows O_PATH file descriptor: enables to restrict ambient > + * filesystem access without requiring to open and risk leaking or > + * misusing a file descriptor. Forbid internal filesystems (e.g. > + * nsfs), including pseudo filesystems that will never be mountable > + * (e.g. sockfs, pipefs). > + */ > + if (!(f.file->f_mode & FMODE_PATH) || > + (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) || > + (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) || > + d_is_negative(f.file->f_path.dentry) || > + IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) { > + err = -EBADFD; > + goto out_fdput; > + } > + path->mnt = f.file->f_path.mnt; > + path->dentry = f.file->f_path.dentry; those two lines can be replaced with "*path = f.file->f_path" > + path_get(path); > + > +out_fdput: > + fdput(f); > + return err; > +} [...] > +/** > + * sys_landlock_enforce_ruleset_current - Enforce a ruleset on the current task > + * > + * @ruleset_fd: File descriptor tied to the ruleset to merge with the target. > + * @flags: Must be 0. > + * > + * This system call enables to enforce a Landlock ruleset on the current > + * thread. Enforcing a ruleset requires that the task has CAP_SYS_ADMIN in its > + * namespace or be running with no_new_privs. This avoids scenarios where s/be/is/ > + * unprivileged tasks can affect the behavior of privileged children. > + * > + * Possible returned errors are: > + * > + * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; > + * - EINVAL: @flags is not 0. > + * - EBADF: @ruleset_fd is not a file descriptor for the current thread; > + * - EBADFD: @ruleset_fd is not a ruleset file descriptor; > + * - EPERM: @ruleset_fd has no read access to the underlying ruleset, or the > + * current thread is not running with no_new_privs (or doesn't have > + * CAP_SYS_ADMIN in its namespace). > + */ > +SYSCALL_DEFINE2(landlock_enforce_ruleset_current, > + const int, ruleset_fd, const __u32, flags) > +{ > + struct landlock_ruleset *new_dom, *ruleset; > + struct cred *new_cred; > + struct landlock_cred_security *new_llcred; > + int err; > + > + if (!landlock_initialized) > + return -EOPNOTSUPP; > + > + /* No flag for now. */ > + if (flags) > + return -EINVAL; > + > + /* > + * Similar checks as for seccomp(2), except that an -EPERM may be > + * returned. > + */ > + if (!task_no_new_privs(current)) { > + err = security_capable(current_cred(), current_user_ns(), > + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); I think this should be ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)? > + if (err) > + return err; > + } > + > + /* Gets and checks the ruleset. */ > + ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ); > + if (IS_ERR(ruleset)) > + return PTR_ERR(ruleset); > + > + /* Prepares new credentials. */ > + new_cred = prepare_creds(); > + if (!new_cred) { > + err = -ENOMEM; > + goto out_put_ruleset; > + } > + new_llcred = landlock_cred(new_cred); > + > + /* > + * There is no possible race condition while copying and manipulating > + * the current credentials because they are dedicated per thread. > + */ > + new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset); > + if (IS_ERR(new_dom)) { > + err = PTR_ERR(new_dom); > + goto out_put_creds; > + } > + > + /* Replaces the old (prepared) domain. */ > + landlock_put_ruleset(new_llcred->domain); > + new_llcred->domain = new_dom; > + > + landlock_put_ruleset(ruleset); > + return commit_creds(new_cred); > + > +out_put_creds: > + abort_creds(new_cred); > + return err; I think this "return err" is wrong - don't we still have to put "ruleset" here? > +out_put_ruleset: > + landlock_put_ruleset(ruleset); > + return err; > +} > -- > 2.28.0 >
On 29/10/2020 02:06, Jann Horn wrote: > On Tue, Oct 27, 2020 at 9:04 PM Mickaël Salaün <mic@digikod.net> wrote: >> These 3 system calls are designed to be used by unprivileged processes >> to sandbox themselves: >> * landlock_create_ruleset(2): Creates a ruleset and returns its file >> descriptor. >> * landlock_add_rule(2): Adds a rule (e.g. file hierarchy access) to a >> ruleset, identified by the dedicated file descriptor. >> * landlock_enforce_ruleset_current(2): Enforces a ruleset on the current >> thread and its future children (similar to seccomp). This syscall has >> the same usage restrictions as seccomp(2): the caller must have the >> no_new_privs attribute set or have CAP_SYS_ADMIN in the current user >> namespace. > [...] >> Cc: Arnd Bergmann <arnd@arndb.de> >> Cc: James Morris <jmorris@namei.org> >> Cc: Jann Horn <jannh@google.com> >> Cc: Kees Cook <keescook@chromium.org> >> Cc: Serge E. Hallyn <serge@hallyn.com> >> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> > [...] >> diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h > [...] >> +/** >> + * struct landlock_path_beneath_attr - Path hierarchy definition >> + * >> + * Argument of sys_landlock_add_rule(). >> + */ >> +struct landlock_path_beneath_attr { >> + /** >> + * @allowed_access: Bitmask of allowed actions for this file hierarchy >> + * (cf. `Filesystem flags`_). >> + */ >> + __u64 allowed_access; >> + /** >> + * @parent_fd: File descriptor, open with ``O_PATH``, which identify > > nit: "identifies" OK > >> + * the parent directory of a file hierarchy, or just a file. >> + */ >> + __s32 parent_fd; >> + /* >> + * This struct is packed to avoid trailing reserved members. >> + * Cf. security/landlock/syscall.c:build_check_abi() >> + */ >> +} __attribute__((packed)); > [...] >> diff --git a/security/landlock/syscall.c b/security/landlock/syscall.c > [...] >> +static int copy_min_struct_from_user(void *const dst, const size_t ksize, >> + const size_t ksize_min, const void __user *const src, >> + const size_t usize) >> +{ >> + /* Checks buffer inconsistencies. */ >> + BUILD_BUG_ON(!dst); >> + if (!src) >> + return -EFAULT; >> + >> + /* Checks size ranges. */ >> + BUILD_BUG_ON(ksize <= 0); >> + BUILD_BUG_ON(ksize < ksize_min); > > To make these checks work reliably, you should add __always_inline to > the function. Done. > >> + if (usize < ksize_min) >> + return -EINVAL; >> + if (usize > PAGE_SIZE) >> + return -E2BIG; >> + >> + /* Copies user buffer and fills with zeros. */ >> + return copy_struct_from_user(dst, ksize, src, usize); >> +} > [...] >> +static int get_path_from_fd(const s32 fd, struct path *const path) >> +{ >> + struct fd f; >> + int err = 0; >> + >> + BUILD_BUG_ON(!__same_type(fd, >> + ((struct landlock_path_beneath_attr *)NULL)->parent_fd)); >> + >> + /* Handles O_PATH. */ >> + f = fdget_raw(fd); >> + if (!f.file) >> + return -EBADF; >> + /* >> + * Only allows O_PATH file descriptor: enables to restrict ambient >> + * filesystem access without requiring to open and risk leaking or >> + * misusing a file descriptor. Forbid internal filesystems (e.g. >> + * nsfs), including pseudo filesystems that will never be mountable >> + * (e.g. sockfs, pipefs). >> + */ >> + if (!(f.file->f_mode & FMODE_PATH) || >> + (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) || >> + (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) || >> + d_is_negative(f.file->f_path.dentry) || >> + IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) { >> + err = -EBADFD; >> + goto out_fdput; >> + } >> + path->mnt = f.file->f_path.mnt; >> + path->dentry = f.file->f_path.dentry; > > those two lines can be replaced with "*path = f.file->f_path" Done. > >> + path_get(path); >> + >> +out_fdput: >> + fdput(f); >> + return err; >> +} > [...] >> +/** >> + * sys_landlock_enforce_ruleset_current - Enforce a ruleset on the current task >> + * >> + * @ruleset_fd: File descriptor tied to the ruleset to merge with the target. >> + * @flags: Must be 0. >> + * >> + * This system call enables to enforce a Landlock ruleset on the current >> + * thread. Enforcing a ruleset requires that the task has CAP_SYS_ADMIN in its >> + * namespace or be running with no_new_privs. This avoids scenarios where > > s/be/is/ OK. > >> + * unprivileged tasks can affect the behavior of privileged children. >> + * >> + * Possible returned errors are: >> + * >> + * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; >> + * - EINVAL: @flags is not 0. >> + * - EBADF: @ruleset_fd is not a file descriptor for the current thread; >> + * - EBADFD: @ruleset_fd is not a ruleset file descriptor; >> + * - EPERM: @ruleset_fd has no read access to the underlying ruleset, or the >> + * current thread is not running with no_new_privs (or doesn't have >> + * CAP_SYS_ADMIN in its namespace). >> + */ >> +SYSCALL_DEFINE2(landlock_enforce_ruleset_current, >> + const int, ruleset_fd, const __u32, flags) >> +{ >> + struct landlock_ruleset *new_dom, *ruleset; >> + struct cred *new_cred; >> + struct landlock_cred_security *new_llcred; >> + int err; >> + >> + if (!landlock_initialized) >> + return -EOPNOTSUPP; >> + >> + /* No flag for now. */ >> + if (flags) >> + return -EINVAL; >> + >> + /* >> + * Similar checks as for seccomp(2), except that an -EPERM may be >> + * returned. >> + */ >> + if (!task_no_new_privs(current)) { >> + err = security_capable(current_cred(), current_user_ns(), >> + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); > > I think this should be ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)? Right. The main difference is that ns_capable*() set PF_SUPERPRIV in current->flags. I guess seccomp should use ns_capable_noaudit() as well? > >> + if (err) >> + return err; >> + } >> + >> + /* Gets and checks the ruleset. */ >> + ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ); >> + if (IS_ERR(ruleset)) >> + return PTR_ERR(ruleset); >> + >> + /* Prepares new credentials. */ >> + new_cred = prepare_creds(); >> + if (!new_cred) { >> + err = -ENOMEM; >> + goto out_put_ruleset; >> + } >> + new_llcred = landlock_cred(new_cred); >> + >> + /* >> + * There is no possible race condition while copying and manipulating >> + * the current credentials because they are dedicated per thread. >> + */ >> + new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset); >> + if (IS_ERR(new_dom)) { >> + err = PTR_ERR(new_dom); >> + goto out_put_creds; >> + } >> + >> + /* Replaces the old (prepared) domain. */ >> + landlock_put_ruleset(new_llcred->domain); >> + new_llcred->domain = new_dom; >> + >> + landlock_put_ruleset(ruleset); >> + return commit_creds(new_cred); >> + >> +out_put_creds: >> + abort_creds(new_cred); >> + return err; > > I think this "return err" is wrong - don't we still have to put "ruleset" here? Oh yes, good catch! > > >> +out_put_ruleset: >> + landlock_put_ruleset(ruleset); >> + return err; >> +} >> -- >> 2.28.0 >>
On Thu, Oct 29, 2020 at 12:30 PM Mickaël Salaün <mic@digikod.net> wrote: > On 29/10/2020 02:06, Jann Horn wrote: > > On Tue, Oct 27, 2020 at 9:04 PM Mickaël Salaün <mic@digikod.net> wrote: > >> These 3 system calls are designed to be used by unprivileged processes > >> to sandbox themselves: [...] > >> + /* > >> + * Similar checks as for seccomp(2), except that an -EPERM may be > >> + * returned. > >> + */ > >> + if (!task_no_new_privs(current)) { > >> + err = security_capable(current_cred(), current_user_ns(), > >> + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); > > > > I think this should be ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)? > > Right. The main difference is that ns_capable*() set PF_SUPERPRIV in > current->flags. I guess seccomp should use ns_capable_noaudit() as well? Yeah. That seccomp code is from commit e2cfabdfd0756, with commit date in April 2012, while ns_capable_noaudit() was introduced in commit 98f368e9e263, with commit date in June 2016; the seccomp code predates the availability of that API. Do you want to send a patch to Kees for that, or should I?
On 30/10/2020 04:07, Jann Horn wrote: > On Thu, Oct 29, 2020 at 12:30 PM Mickaël Salaün <mic@digikod.net> wrote: >> On 29/10/2020 02:06, Jann Horn wrote: >>> On Tue, Oct 27, 2020 at 9:04 PM Mickaël Salaün <mic@digikod.net> wrote: >>>> These 3 system calls are designed to be used by unprivileged processes >>>> to sandbox themselves: > [...] >>>> + /* >>>> + * Similar checks as for seccomp(2), except that an -EPERM may be >>>> + * returned. >>>> + */ >>>> + if (!task_no_new_privs(current)) { >>>> + err = security_capable(current_cred(), current_user_ns(), >>>> + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); >>> >>> I think this should be ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)? >> >> Right. The main difference is that ns_capable*() set PF_SUPERPRIV in >> current->flags. I guess seccomp should use ns_capable_noaudit() as well? > > Yeah. That seccomp code is from commit e2cfabdfd0756, with commit date > in April 2012, while ns_capable_noaudit() was introduced in commit > 98f368e9e263, with commit date in June 2016; the seccomp code predates > the availability of that API. > > Do you want to send a patch to Kees for that, or should I? > I found another case of this inconsistency in ptrace. I sent patches: https://lore.kernel.org/lkml/20201030123849.770769-1-mic@digikod.net/
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 37bea07c12f2..ee3e24095c5f 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -68,6 +68,8 @@ union bpf_attr; struct io_uring_params; struct clone_args; struct open_how; +struct landlock_ruleset_attr; +enum landlock_rule_type; #include <linux/types.h> #include <linux/aio_abi.h> @@ -1008,6 +1010,11 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig, siginfo_t __user *info, unsigned int flags); asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags); +asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr __user *attr, + size_t size, __u32 flags); +asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type, + const void __user *rule_attr, __u32 flags); +asmlinkage long sys_landlock_enforce_ruleset_current(int ruleset_fd, __u32 flags); /* * Architecture-specific system calls diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index db6e300b92e3..fd58c56a5aa6 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -9,6 +9,59 @@ #ifndef _UAPI__LINUX_LANDLOCK_H__ #define _UAPI__LINUX_LANDLOCK_H__ +#include <linux/types.h> + +/** + * struct landlock_ruleset_attr - Ruleset definition + * + * Argument of sys_landlock_create_ruleset(). This structure can grow in + * future versions. + */ +struct landlock_ruleset_attr { + /** + * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_) + * that is handled by this ruleset and should then be forbidden if no + * rule explicitly allow them. This is needed for backward + * compatibility reasons. + */ + __u64 handled_access_fs; +}; + +/** + * enum landlock_rule_type - Landlock rule type + * + * Argument of sys_landlock_add_rule(). + */ +enum landlock_rule_type { + /** + * @LANDLOCK_RULE_PATH_BENEATH: Type of a &struct + * landlock_path_beneath_attr . + */ + LANDLOCK_RULE_PATH_BENEATH = 1, +}; + +/** + * struct landlock_path_beneath_attr - Path hierarchy definition + * + * Argument of sys_landlock_add_rule(). + */ +struct landlock_path_beneath_attr { + /** + * @allowed_access: Bitmask of allowed actions for this file hierarchy + * (cf. `Filesystem flags`_). + */ + __u64 allowed_access; + /** + * @parent_fd: File descriptor, open with ``O_PATH``, which identify + * the parent directory of a file hierarchy, or just a file. + */ + __s32 parent_fd; + /* + * This struct is packed to avoid trailing reserved members. + * Cf. security/landlock/syscall.c:build_check_abi() + */ +} __attribute__((packed)); + /** * DOC: fs_access * diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index f27ac94d5fa7..0906cb79e801 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -264,6 +264,11 @@ COND_SYSCALL(request_key); COND_SYSCALL(keyctl); COND_SYSCALL_COMPAT(keyctl); +/* security/landlock/syscall.c */ +COND_SYSCALL(landlock_create_ruleset); +COND_SYSCALL(landlock_add_rule); +COND_SYSCALL(landlock_enforce_ruleset_current); + /* arch/example/kernel/sys_example.c */ /* mm/fadvise.c */ diff --git a/security/landlock/Makefile b/security/landlock/Makefile index 92e3d80ab8ed..4388494779ec 100644 --- a/security/landlock/Makefile +++ b/security/landlock/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_SECURITY_LANDLOCK) := landlock.o -landlock-y := setup.o object.o ruleset.o \ +landlock-y := setup.o syscall.o object.o ruleset.o \ cred.o ptrace.o fs.o diff --git a/security/landlock/syscall.c b/security/landlock/syscall.c new file mode 100644 index 000000000000..e761bd152ca5 --- /dev/null +++ b/security/landlock/syscall.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Landlock LSM - System call implementations and user space interfaces + * + * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> + * Copyright © 2018-2020 ANSSI + */ + +#include <asm/current.h> +#include <linux/anon_inodes.h> +#include <linux/build_bug.h> +#include <linux/capability.h> +#include <linux/compiler_types.h> +#include <linux/dcache.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/limits.h> +#include <linux/mount.h> +#include <linux/path.h> +#include <linux/sched.h> +#include <linux/security.h> +#include <linux/stddef.h> +#include <linux/syscalls.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <uapi/linux/landlock.h> + +#include "cred.h" +#include "fs.h" +#include "ruleset.h" +#include "setup.h" + +/** + * copy_min_struct_from_user - Safe future-proof argument copying + * + * Extend copy_struct_from_user() to check for consistent user buffer. + * + * @dst: Kernel space pointer or NULL. + * @ksize: Actual size of the data pointed to by @dst. + * @ksize_min: Minimal required size to be copied. + * @src: User space pointer or NULL. + * @usize: (Alleged) size of the data pointed to by @src. + */ +static int copy_min_struct_from_user(void *const dst, const size_t ksize, + const size_t ksize_min, const void __user *const src, + const size_t usize) +{ + /* Checks buffer inconsistencies. */ + BUILD_BUG_ON(!dst); + if (!src) + return -EFAULT; + + /* Checks size ranges. */ + BUILD_BUG_ON(ksize <= 0); + BUILD_BUG_ON(ksize < ksize_min); + if (usize < ksize_min) + return -EINVAL; + if (usize > PAGE_SIZE) + return -E2BIG; + + /* Copies user buffer and fills with zeros. */ + return copy_struct_from_user(dst, ksize, src, usize); +} + +/* + * This function only contains arithmetic operations with constants, leading to + * BUILD_BUG_ON(). The related code is evaluated and checked at build time, + * but it is then ignored thanks to compiler optimizations. + */ +static void build_check_abi(void) +{ + size_t ruleset_size, path_beneath_size; + + /* + * For each user space ABI structures, first checks that there is no + * hole in them, then checks that all architectures have the same + * struct size. + */ + ruleset_size = sizeof_field(struct landlock_ruleset_attr, handled_access_fs); + BUILD_BUG_ON(sizeof(struct landlock_ruleset_attr) != ruleset_size); + BUILD_BUG_ON(sizeof(struct landlock_ruleset_attr) != 8); + + path_beneath_size = sizeof_field(struct landlock_path_beneath_attr, allowed_access); + path_beneath_size += sizeof_field(struct landlock_path_beneath_attr, parent_fd); + BUILD_BUG_ON(sizeof(struct landlock_path_beneath_attr) != path_beneath_size); + BUILD_BUG_ON(sizeof(struct landlock_path_beneath_attr) != 12); +} + +/* Ruleset handling */ + +static int fop_ruleset_release(struct inode *const inode, + struct file *const filp) +{ + struct landlock_ruleset *ruleset = filp->private_data; + + landlock_put_ruleset(ruleset); + return 0; +} + +static ssize_t fop_dummy_read(struct file *const filp, char __user *const buf, + const size_t size, loff_t *const ppos) +{ + /* Dummy handler to enable FMODE_CAN_READ. */ + return -EINVAL; +} + +static ssize_t fop_dummy_write(struct file *const filp, + const char __user *const buf, const size_t size, + loff_t *const ppos) +{ + /* Dummy handler to enable FMODE_CAN_WRITE. */ + return -EINVAL; +} + +/* + * A ruleset file descriptor enables to build a ruleset by adding (i.e. + * writing) rule after rule, without relying on the task's context. This + * reentrant design is also used in a read way to enforce the ruleset on the + * current task. + */ +static const struct file_operations ruleset_fops = { + .release = fop_ruleset_release, + .read = fop_dummy_read, + .write = fop_dummy_write, +}; + +/** + * sys_landlock_create_ruleset - Create a new ruleset + * + * @attr: Pointer to a &struct landlock_ruleset_attr identifying the scope of + * the new ruleset. + * @size: Size of the pointed &struct landlock_ruleset_attr (needed for + * backward and forward compatibility). + * @flags: Must be 0. + * + * This system call enables to create a new Landlock ruleset, and returns the + * related file descriptor on success. + * + * Possible returned errors are: + * + * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; + * - EINVAL: @flags is not 0, or unknown access, or too small @size; + * - E2BIG or EFAULT: @attr or @size inconsistencies; + * - ENOMSG: empty &landlock_ruleset_attr.handled_access_fs. + */ +SYSCALL_DEFINE3(landlock_create_ruleset, + const struct landlock_ruleset_attr __user *const, attr, + const size_t, size, const __u32, flags) +{ + struct landlock_ruleset_attr ruleset_attr; + struct landlock_ruleset *ruleset; + int err, ruleset_fd; + + /* Build-time checks. */ + build_check_abi(); + + if (!landlock_initialized) + return -EOPNOTSUPP; + + /* No flag for now. */ + if (flags) + return -EINVAL; + + /* Copies raw user space buffer. */ + err = copy_min_struct_from_user(&ruleset_attr, sizeof(ruleset_attr), + offsetofend(typeof(ruleset_attr), handled_access_fs), + attr, size); + if (err) + return err; + + /* Checks content (and 32-bits cast). */ + if ((ruleset_attr.handled_access_fs | _LANDLOCK_ACCESS_FS_MASK) != + _LANDLOCK_ACCESS_FS_MASK) + return -EINVAL; + + /* Checks arguments and transforms to kernel struct. */ + ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs); + if (IS_ERR(ruleset)) + return PTR_ERR(ruleset); + + /* Creates anonymous FD referring to the ruleset. */ + ruleset_fd = anon_inode_getfd("landlock-ruleset", &ruleset_fops, + ruleset, O_RDWR | O_CLOEXEC); + if (ruleset_fd < 0) + landlock_put_ruleset(ruleset); + return ruleset_fd; +} + +/* + * Returns an owned ruleset from a FD. It is thus needed to call + * landlock_put_ruleset() on the return value. + */ +static struct landlock_ruleset *get_ruleset_from_fd(const int fd, + const fmode_t mode) +{ + struct fd ruleset_f; + struct landlock_ruleset *ruleset; + int err; + + ruleset_f = fdget(fd); + if (!ruleset_f.file) + return ERR_PTR(-EBADF); + + /* Checks FD type and access right. */ + err = 0; + if (ruleset_f.file->f_op != &ruleset_fops) + err = -EBADFD; + else if (!(ruleset_f.file->f_mode & mode)) + err = -EPERM; + if (!err) { + ruleset = ruleset_f.file->private_data; + landlock_get_ruleset(ruleset); + } + fdput(ruleset_f); + return err ? ERR_PTR(err) : ruleset; +} + +/* Path handling */ + +/* + * @path: Must call put_path(@path) after the call if it succeeded. + */ +static int get_path_from_fd(const s32 fd, struct path *const path) +{ + struct fd f; + int err = 0; + + BUILD_BUG_ON(!__same_type(fd, + ((struct landlock_path_beneath_attr *)NULL)->parent_fd)); + + /* Handles O_PATH. */ + f = fdget_raw(fd); + if (!f.file) + return -EBADF; + /* + * Only allows O_PATH file descriptor: enables to restrict ambient + * filesystem access without requiring to open and risk leaking or + * misusing a file descriptor. Forbid internal filesystems (e.g. + * nsfs), including pseudo filesystems that will never be mountable + * (e.g. sockfs, pipefs). + */ + if (!(f.file->f_mode & FMODE_PATH) || + (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) || + (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) || + d_is_negative(f.file->f_path.dentry) || + IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) { + err = -EBADFD; + goto out_fdput; + } + path->mnt = f.file->f_path.mnt; + path->dentry = f.file->f_path.dentry; + path_get(path); + +out_fdput: + fdput(f); + return err; +} + +/** + * sys_landlock_add_rule - Add a new rule to a ruleset + * + * @ruleset_fd: File descriptor tied to the ruleset which should be extended + * with the new rule. + * @rule_type: Identify the structure type pointed to by @rule_attr (only + * LANDLOCK_RULE_PATH_BENEATH for now). + * @rule_attr: Pointer to a rule (only of type &struct + * landlock_path_beneath_attr for now). + * @flags: Must be 0. + * + * This system call enables to define a new rule and add it to an existing + * ruleset. + * + * Possible returned errors are: + * + * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; + * - EINVAL: @flags is not 0, or inconsistent access in the rule (i.e. + * &landlock_path_beneath_attr.allowed_access is not a subset of the rule's + * accesses); + * - EBADF: @ruleset_fd is not a file descriptor for the current thread; + * - EBADFD: @ruleset_fd is not a ruleset file descriptor; + * - EPERM: @ruleset_fd has no write access to the underlying ruleset; + * - EFAULT: @rule_attr inconsistency. + */ +SYSCALL_DEFINE4(landlock_add_rule, + const int, ruleset_fd, const enum landlock_rule_type, rule_type, + const void __user *const, rule_attr, const __u32, flags) +{ + struct landlock_path_beneath_attr path_beneath_attr; + struct path path; + struct landlock_ruleset *ruleset; + int res, err; + + if (!landlock_initialized) + return -EOPNOTSUPP; + + /* No flag for now. */ + if (flags) + return -EINVAL; + + if (rule_type != LANDLOCK_RULE_PATH_BENEATH) + return -EINVAL; + + /* Copies raw user space buffer, only one type for now. */ + res = copy_from_user(&path_beneath_attr, rule_attr, + sizeof(path_beneath_attr)); + if (res) + return -EFAULT; + + /* Gets and checks the ruleset. */ + ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_WRITE); + if (IS_ERR(ruleset)) + return PTR_ERR(ruleset); + + /* + * Checks that allowed_access matches the @ruleset constraints + * (ruleset->fs_access_mask is automatically upgraded to 64-bits). + * Allows empty allowed_access i.e., deny @ruleset->fs_access_mask . + */ + if ((path_beneath_attr.allowed_access | ruleset->fs_access_mask) != + ruleset->fs_access_mask) { + err = -EINVAL; + goto out_put_ruleset; + } + + /* Gets and checks the new rule. */ + err = get_path_from_fd(path_beneath_attr.parent_fd, &path); + if (err) + goto out_put_ruleset; + + /* Imports the new rule. */ + err = landlock_append_fs_rule(ruleset, &path, + path_beneath_attr.allowed_access); + path_put(&path); + +out_put_ruleset: + landlock_put_ruleset(ruleset); + return err; +} + +/* Enforcement */ + +/** + * sys_landlock_enforce_ruleset_current - Enforce a ruleset on the current task + * + * @ruleset_fd: File descriptor tied to the ruleset to merge with the target. + * @flags: Must be 0. + * + * This system call enables to enforce a Landlock ruleset on the current + * thread. Enforcing a ruleset requires that the task has CAP_SYS_ADMIN in its + * namespace or be running with no_new_privs. This avoids scenarios where + * unprivileged tasks can affect the behavior of privileged children. + * + * Possible returned errors are: + * + * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time; + * - EINVAL: @flags is not 0. + * - EBADF: @ruleset_fd is not a file descriptor for the current thread; + * - EBADFD: @ruleset_fd is not a ruleset file descriptor; + * - EPERM: @ruleset_fd has no read access to the underlying ruleset, or the + * current thread is not running with no_new_privs (or doesn't have + * CAP_SYS_ADMIN in its namespace). + */ +SYSCALL_DEFINE2(landlock_enforce_ruleset_current, + const int, ruleset_fd, const __u32, flags) +{ + struct landlock_ruleset *new_dom, *ruleset; + struct cred *new_cred; + struct landlock_cred_security *new_llcred; + int err; + + if (!landlock_initialized) + return -EOPNOTSUPP; + + /* No flag for now. */ + if (flags) + return -EINVAL; + + /* + * Similar checks as for seccomp(2), except that an -EPERM may be + * returned. + */ + if (!task_no_new_privs(current)) { + err = security_capable(current_cred(), current_user_ns(), + CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); + if (err) + return err; + } + + /* Gets and checks the ruleset. */ + ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ); + if (IS_ERR(ruleset)) + return PTR_ERR(ruleset); + + /* Prepares new credentials. */ + new_cred = prepare_creds(); + if (!new_cred) { + err = -ENOMEM; + goto out_put_ruleset; + } + new_llcred = landlock_cred(new_cred); + + /* + * There is no possible race condition while copying and manipulating + * the current credentials because they are dedicated per thread. + */ + new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset); + if (IS_ERR(new_dom)) { + err = PTR_ERR(new_dom); + goto out_put_creds; + } + + /* Replaces the old (prepared) domain. */ + landlock_put_ruleset(new_llcred->domain); + new_llcred->domain = new_dom; + + landlock_put_ruleset(ruleset); + return commit_creds(new_cred); + +out_put_creds: + abort_creds(new_cred); + return err; + +out_put_ruleset: + landlock_put_ruleset(ruleset); + return err; +}