449325b52b
Introduce helper:
int fork_usermode_blob(void *data, size_t len, struct umh_info *info);
struct umh_info {
struct file *pipe_to_umh;
struct file *pipe_from_umh;
pid_t pid;
};
that GPLed kernel modules (signed or unsigned) can use it to execute part
of its own data as swappable user mode process.
The kernel will do:
- allocate a unique file in tmpfs
- populate that file with [data, data + len] bytes
- user-mode-helper code will do_execve that file and, before the process
starts, the kernel will create two unix pipes for bidirectional
communication between kernel module and umh
- close tmpfs file, effectively deleting it
- the fork_usermode_blob will return zero on success and populate
'struct umh_info' with two unix pipes and the pid of the user process
As the first step in the development of the bpfilter project
the fork_usermode_blob() helper is introduced to allow user mode code
to be invoked from a kernel module. The idea is that user mode code plus
normal kernel module code are built as part of the kernel build
and installed as traditional kernel module into distro specified location,
such that from a distribution point of view, there is
no difference between regular kernel modules and kernel modules + umh code.
Such modules can be signed, modprobed, rmmod, etc. The use of this new helper
by a kernel module doesn't make it any special from kernel and user space
tooling point of view.
Such approach enables kernel to delegate functionality traditionally done
by the kernel modules into the user space processes (either root or !root) and
reduces security attack surface of the new code. The buggy umh code would crash
the user process, but not the kernel. Another advantage is that umh code
of the kernel module can be debugged and tested out of user space
(e.g. opening the possibility to run clang sanitizers, fuzzers or
user space test suites on the umh code).
In case of the bpfilter project such architecture allows complex control plane
to be done in the user space while bpf based data plane stays in the kernel.
Since umh can crash, can be oom-ed by the kernel, killed by the admin,
the kernel module that uses them (like bpfilter) needs to manage life
time of umh on its own via two unix pipes and the pid of umh.
The exit code of such kernel module should kill the umh it started,
so that rmmod of the kernel module will cleanup the corresponding umh.
Just like if the kernel module does kmalloc() it should kfree() it
in the exit code.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
155 lines
5 KiB
C
155 lines
5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_BINFMTS_H
|
|
#define _LINUX_BINFMTS_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/unistd.h>
|
|
#include <asm/exec.h>
|
|
#include <uapi/linux/binfmts.h>
|
|
|
|
struct filename;
|
|
|
|
#define CORENAME_MAX_SIZE 128
|
|
|
|
/*
|
|
* This structure is used to hold the arguments that are used when loading binaries.
|
|
*/
|
|
struct linux_binprm {
|
|
char buf[BINPRM_BUF_SIZE];
|
|
#ifdef CONFIG_MMU
|
|
struct vm_area_struct *vma;
|
|
unsigned long vma_pages;
|
|
#else
|
|
# define MAX_ARG_PAGES 32
|
|
struct page *page[MAX_ARG_PAGES];
|
|
#endif
|
|
struct mm_struct *mm;
|
|
unsigned long p; /* current top of mem */
|
|
unsigned int
|
|
/*
|
|
* True after the bprm_set_creds hook has been called once
|
|
* (multiple calls can be made via prepare_binprm() for
|
|
* binfmt_script/misc).
|
|
*/
|
|
called_set_creds:1,
|
|
/*
|
|
* True if most recent call to the commoncaps bprm_set_creds
|
|
* hook (due to multiple prepare_binprm() calls from the
|
|
* binfmt_script/misc handlers) resulted in elevated
|
|
* privileges.
|
|
*/
|
|
cap_elevated:1,
|
|
/*
|
|
* Set by bprm_set_creds hook to indicate a privilege-gaining
|
|
* exec has happened. Used to sanitize execution environment
|
|
* and to set AT_SECURE auxv for glibc.
|
|
*/
|
|
secureexec:1;
|
|
#ifdef __alpha__
|
|
unsigned int taso:1;
|
|
#endif
|
|
unsigned int recursion_depth; /* only for search_binary_handler() */
|
|
struct file * file;
|
|
struct cred *cred; /* new credentials */
|
|
int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */
|
|
unsigned int per_clear; /* bits to clear in current->personality */
|
|
int argc, envc;
|
|
const char * filename; /* Name of binary as seen by procps */
|
|
const char * interp; /* Name of the binary really executed. Most
|
|
of the time same as filename, but could be
|
|
different for binfmt_{misc,script} */
|
|
unsigned interp_flags;
|
|
unsigned interp_data;
|
|
unsigned long loader, exec;
|
|
|
|
struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */
|
|
} __randomize_layout;
|
|
|
|
#define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
|
|
#define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT)
|
|
|
|
/* fd of the binary should be passed to the interpreter */
|
|
#define BINPRM_FLAGS_EXECFD_BIT 1
|
|
#define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT)
|
|
|
|
/* filename of the binary will be inaccessible after exec */
|
|
#define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2
|
|
#define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT)
|
|
|
|
/* Function parameter for binfmt->coredump */
|
|
struct coredump_params {
|
|
const siginfo_t *siginfo;
|
|
struct pt_regs *regs;
|
|
struct file *file;
|
|
unsigned long limit;
|
|
unsigned long mm_flags;
|
|
loff_t written;
|
|
loff_t pos;
|
|
};
|
|
|
|
/*
|
|
* This structure defines the functions that are used to load the binary formats that
|
|
* linux accepts.
|
|
*/
|
|
struct linux_binfmt {
|
|
struct list_head lh;
|
|
struct module *module;
|
|
int (*load_binary)(struct linux_binprm *);
|
|
int (*load_shlib)(struct file *);
|
|
int (*core_dump)(struct coredump_params *cprm);
|
|
unsigned long min_coredump; /* minimal dump size */
|
|
} __randomize_layout;
|
|
|
|
extern void __register_binfmt(struct linux_binfmt *fmt, int insert);
|
|
|
|
/* Registration of default binfmt handlers */
|
|
static inline void register_binfmt(struct linux_binfmt *fmt)
|
|
{
|
|
__register_binfmt(fmt, 0);
|
|
}
|
|
/* Same as above, but adds a new binfmt at the top of the list */
|
|
static inline void insert_binfmt(struct linux_binfmt *fmt)
|
|
{
|
|
__register_binfmt(fmt, 1);
|
|
}
|
|
|
|
extern void unregister_binfmt(struct linux_binfmt *);
|
|
|
|
extern int prepare_binprm(struct linux_binprm *);
|
|
extern int __must_check remove_arg_zero(struct linux_binprm *);
|
|
extern int search_binary_handler(struct linux_binprm *);
|
|
extern int flush_old_exec(struct linux_binprm * bprm);
|
|
extern void setup_new_exec(struct linux_binprm * bprm);
|
|
extern void finalize_exec(struct linux_binprm *bprm);
|
|
extern void would_dump(struct linux_binprm *, struct file *);
|
|
|
|
extern int suid_dumpable;
|
|
|
|
/* Stack area protections */
|
|
#define EXSTACK_DEFAULT 0 /* Whatever the arch defaults to */
|
|
#define EXSTACK_DISABLE_X 1 /* Disable executable stacks */
|
|
#define EXSTACK_ENABLE_X 2 /* Enable executable stacks */
|
|
|
|
extern int setup_arg_pages(struct linux_binprm * bprm,
|
|
unsigned long stack_top,
|
|
int executable_stack);
|
|
extern int transfer_args_to_stack(struct linux_binprm *bprm,
|
|
unsigned long *sp_location);
|
|
extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm);
|
|
extern int copy_strings_kernel(int argc, const char *const *argv,
|
|
struct linux_binprm *bprm);
|
|
extern int prepare_bprm_creds(struct linux_binprm *bprm);
|
|
extern void install_exec_creds(struct linux_binprm *bprm);
|
|
extern void set_binfmt(struct linux_binfmt *new);
|
|
extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t);
|
|
|
|
extern int do_execve(struct filename *,
|
|
const char __user * const __user *,
|
|
const char __user * const __user *);
|
|
extern int do_execveat(int, struct filename *,
|
|
const char __user * const __user *,
|
|
const char __user * const __user *,
|
|
int);
|
|
int do_execve_file(struct file *file, void *__argv, void *__envp);
|
|
|
|
#endif /* _LINUX_BINFMTS_H */
|