WSL2-Linux-Kernel/security/landlock/syscalls.c

452 строки
13 KiB
C
Исходник Обычный вид История

landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
// 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 "limits.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 __always_inline 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)
{
struct landlock_ruleset_attr ruleset_attr;
struct landlock_path_beneath_attr path_beneath_attr;
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(ruleset_attr.handled_access_fs);
BUILD_BUG_ON(sizeof(ruleset_attr) != ruleset_size);
BUILD_BUG_ON(sizeof(ruleset_attr) != 8);
path_beneath_size = sizeof(path_beneath_attr.allowed_access);
path_beneath_size += sizeof(path_beneath_attr.parent_fd);
BUILD_BUG_ON(sizeof(path_beneath_attr) != path_beneath_size);
BUILD_BUG_ON(sizeof(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,
};
landlock: Enable user space to infer supported features Add a new flag LANDLOCK_CREATE_RULESET_VERSION to landlock_create_ruleset(2). This enables to retreive a Landlock ABI version that is useful to efficiently follow a best-effort security approach. Indeed, it would be a missed opportunity to abort the whole sandbox building, because some features are unavailable, instead of protecting users as much as possible with the subset of features provided by the running kernel. This new flag enables user space to identify the minimum set of Landlock features supported by the running kernel without relying on a filesystem interface (e.g. /proc/version, which might be inaccessible) nor testing multiple syscall argument combinations (i.e. syscall bisection). New Landlock features will be documented and tied to a minimum version number (greater than 1). The current version will be incremented for each new kernel release supporting new Landlock features. User space libraries can leverage this information to seamlessly restrict processes as much as possible while being compatible with newer APIs. This is a much more lighter approach than the previous landlock_get_features(2): the complexity is pushed to user space libraries. This flag meets similar needs as securityfs versions: selinux/policyvers, apparmor/features/*/version* and tomoyo/version. Supporting this flag now will be convenient for backward compatibility. 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> Link: https://lore.kernel.org/r/20210422154123.13086-14-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:23 +03:00
#define LANDLOCK_ABI_VERSION 1
landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
/**
* 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).
landlock: Enable user space to infer supported features Add a new flag LANDLOCK_CREATE_RULESET_VERSION to landlock_create_ruleset(2). This enables to retreive a Landlock ABI version that is useful to efficiently follow a best-effort security approach. Indeed, it would be a missed opportunity to abort the whole sandbox building, because some features are unavailable, instead of protecting users as much as possible with the subset of features provided by the running kernel. This new flag enables user space to identify the minimum set of Landlock features supported by the running kernel without relying on a filesystem interface (e.g. /proc/version, which might be inaccessible) nor testing multiple syscall argument combinations (i.e. syscall bisection). New Landlock features will be documented and tied to a minimum version number (greater than 1). The current version will be incremented for each new kernel release supporting new Landlock features. User space libraries can leverage this information to seamlessly restrict processes as much as possible while being compatible with newer APIs. This is a much more lighter approach than the previous landlock_get_features(2): the complexity is pushed to user space libraries. This flag meets similar needs as securityfs versions: selinux/policyvers, apparmor/features/*/version* and tomoyo/version. Supporting this flag now will be convenient for backward compatibility. 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> Link: https://lore.kernel.org/r/20210422154123.13086-14-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:23 +03:00
* @flags: Supported value: %LANDLOCK_CREATE_RULESET_VERSION.
landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
*
* This system call enables to create a new Landlock ruleset, and returns the
* related file descriptor on success.
*
landlock: Enable user space to infer supported features Add a new flag LANDLOCK_CREATE_RULESET_VERSION to landlock_create_ruleset(2). This enables to retreive a Landlock ABI version that is useful to efficiently follow a best-effort security approach. Indeed, it would be a missed opportunity to abort the whole sandbox building, because some features are unavailable, instead of protecting users as much as possible with the subset of features provided by the running kernel. This new flag enables user space to identify the minimum set of Landlock features supported by the running kernel without relying on a filesystem interface (e.g. /proc/version, which might be inaccessible) nor testing multiple syscall argument combinations (i.e. syscall bisection). New Landlock features will be documented and tied to a minimum version number (greater than 1). The current version will be incremented for each new kernel release supporting new Landlock features. User space libraries can leverage this information to seamlessly restrict processes as much as possible while being compatible with newer APIs. This is a much more lighter approach than the previous landlock_get_features(2): the complexity is pushed to user space libraries. This flag meets similar needs as securityfs versions: selinux/policyvers, apparmor/features/*/version* and tomoyo/version. Supporting this flag now will be convenient for backward compatibility. 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> Link: https://lore.kernel.org/r/20210422154123.13086-14-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:23 +03:00
* If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is
* 0, then the returned value is the highest supported Landlock ABI version
* (starting at 1).
*
landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
* Possible returned errors are:
*
* - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
landlock: Enable user space to infer supported features Add a new flag LANDLOCK_CREATE_RULESET_VERSION to landlock_create_ruleset(2). This enables to retreive a Landlock ABI version that is useful to efficiently follow a best-effort security approach. Indeed, it would be a missed opportunity to abort the whole sandbox building, because some features are unavailable, instead of protecting users as much as possible with the subset of features provided by the running kernel. This new flag enables user space to identify the minimum set of Landlock features supported by the running kernel without relying on a filesystem interface (e.g. /proc/version, which might be inaccessible) nor testing multiple syscall argument combinations (i.e. syscall bisection). New Landlock features will be documented and tied to a minimum version number (greater than 1). The current version will be incremented for each new kernel release supporting new Landlock features. User space libraries can leverage this information to seamlessly restrict processes as much as possible while being compatible with newer APIs. This is a much more lighter approach than the previous landlock_get_features(2): the complexity is pushed to user space libraries. This flag meets similar needs as securityfs versions: selinux/policyvers, apparmor/features/*/version* and tomoyo/version. Supporting this flag now will be convenient for backward compatibility. 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> Link: https://lore.kernel.org/r/20210422154123.13086-14-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:23 +03:00
* - EINVAL: unknown @flags, or unknown access, or too small @size;
landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
* - 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;
landlock: Enable user space to infer supported features Add a new flag LANDLOCK_CREATE_RULESET_VERSION to landlock_create_ruleset(2). This enables to retreive a Landlock ABI version that is useful to efficiently follow a best-effort security approach. Indeed, it would be a missed opportunity to abort the whole sandbox building, because some features are unavailable, instead of protecting users as much as possible with the subset of features provided by the running kernel. This new flag enables user space to identify the minimum set of Landlock features supported by the running kernel without relying on a filesystem interface (e.g. /proc/version, which might be inaccessible) nor testing multiple syscall argument combinations (i.e. syscall bisection). New Landlock features will be documented and tied to a minimum version number (greater than 1). The current version will be incremented for each new kernel release supporting new Landlock features. User space libraries can leverage this information to seamlessly restrict processes as much as possible while being compatible with newer APIs. This is a much more lighter approach than the previous landlock_get_features(2): the complexity is pushed to user space libraries. This flag meets similar needs as securityfs versions: selinux/policyvers, apparmor/features/*/version* and tomoyo/version. Supporting this flag now will be convenient for backward compatibility. 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> Link: https://lore.kernel.org/r/20210422154123.13086-14-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:23 +03:00
if (flags) {
if ((flags == LANDLOCK_CREATE_RULESET_VERSION)
&& !attr && !size)
return LANDLOCK_ABI_VERSION;
landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
return -EINVAL;
landlock: Enable user space to infer supported features Add a new flag LANDLOCK_CREATE_RULESET_VERSION to landlock_create_ruleset(2). This enables to retreive a Landlock ABI version that is useful to efficiently follow a best-effort security approach. Indeed, it would be a missed opportunity to abort the whole sandbox building, because some features are unavailable, instead of protecting users as much as possible with the subset of features provided by the running kernel. This new flag enables user space to identify the minimum set of Landlock features supported by the running kernel without relying on a filesystem interface (e.g. /proc/version, which might be inaccessible) nor testing multiple syscall argument combinations (i.e. syscall bisection). New Landlock features will be documented and tied to a minimum version number (greater than 1). The current version will be incremented for each new kernel release supporting new Landlock features. User space libraries can leverage this information to seamlessly restrict processes as much as possible while being compatible with newer APIs. This is a much more lighter approach than the previous landlock_get_features(2): the complexity is pushed to user space libraries. This flag meets similar needs as securityfs versions: selinux/policyvers, apparmor/features/*/version* and tomoyo/version. Supporting this flag now will be convenient for backward compatibility. 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> Link: https://lore.kernel.org/r/20210422154123.13086-14-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:23 +03:00
}
landlock: Add syscall implementations 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_restrict_self(2): Enforces a ruleset on the calling 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. All these syscalls have a "flags" argument (not currently used) to enable extensibility. Here are the motivations for these new syscalls: * A sandboxed process may not have access to file systems, including /dev, /sys or /proc, but it should still be able to add more restrictions to itself. * Neither prctl(2) nor seccomp(2) (which was used in a previous version) fit well with the current definition of a Landlock security policy. All passed structs (attributes) are checked at build time to ensure that they don't contain holes and that they are aligned the same way for each architecture. See the user and kernel documentation for more details (provided by a following commit): * Documentation/userspace-api/landlock.rst * Documentation/security/landlock.rst Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Morris <jmorris@namei.org> Cc: Jann Horn <jannh@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com> Acked-by: Serge Hallyn <serge@hallyn.com> Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net Signed-off-by: James Morris <jamorris@linux.microsoft.com>
2021-04-22 18:41:18 +03:00
/* 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_MASK_ACCESS_FS) !=
LANDLOCK_MASK_ACCESS_FS)
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;
ruleset_f = fdget(fd);
if (!ruleset_f.file)
return ERR_PTR(-EBADF);
/* Checks FD type and access right. */
if (ruleset_f.file->f_op != &ruleset_fops) {
ruleset = ERR_PTR(-EBADFD);
goto out_fdput;
}
if (!(ruleset_f.file->f_mode & mode)) {
ruleset = ERR_PTR(-EPERM);
goto out_fdput;
}
ruleset = ruleset_f.file->private_data;
if (WARN_ON_ONCE(ruleset->num_layers != 1)) {
ruleset = ERR_PTR(-EINVAL);
goto out_fdput;
}
landlock_get_ruleset(ruleset);
out_fdput:
fdput(ruleset_f);
return 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;
/*
* Forbids ruleset FDs, internal filesystems (e.g. nsfs), including
* pseudo filesystems that will never be mountable (e.g. sockfs,
* pipefs).
*/
if ((f.file->f_op == &ruleset_fops) ||
(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 = f.file->f_path;
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 that 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);
* - ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access);
* - EBADF: @ruleset_fd is not a file descriptor for the current thread, or a
* member of @rule_attr is not a file descriptor as expected;
* - EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of
* @rule_attr is not the expected file descriptor type (e.g. file open
* without O_PATH);
* - 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);
/*
* Informs about useless rule: empty allowed_access (i.e. deny rules)
* are ignored in path walks.
*/
if (!path_beneath_attr.allowed_access) {
err = -ENOMSG;
goto out_put_ruleset;
}
/*
* Checks that allowed_access matches the @ruleset constraints
* (ruleset->fs_access_masks[0] is automatically upgraded to 64-bits).
*/
if ((path_beneath_attr.allowed_access | ruleset->fs_access_masks[0]) !=
ruleset->fs_access_masks[0]) {
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_restrict_self - Enforce a ruleset on the calling thread
*
* @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 is 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 it doesn't have
* CAP_SYS_ADMIN in its namespace.
* - E2BIG: The maximum number of stacked rulesets is reached for the current
* thread.
*/
SYSCALL_DEFINE2(landlock_restrict_self,
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) &&
!ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
return -EPERM;
/* 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);
out_put_ruleset:
landlock_put_ruleset(ruleset);
return err;
}