linux_dsm_epyc7002/include/linux/binfmts.h
Eric W. Biederman eea9673250 exec: Add exec_update_mutex to replace cred_guard_mutex
The cred_guard_mutex is problematic as it is held over possibly
indefinite waits for userspace.  The possible indefinite waits for
userspace that I have identified are: The cred_guard_mutex is held in
PTRACE_EVENT_EXIT waiting for the tracer.  The cred_guard_mutex is
held over "put_user(0, tsk->clear_child_tid)" in exit_mm().  The
cred_guard_mutex is held over "get_user(futex_offset, ...")  in
exit_robust_list.  The cred_guard_mutex held over copy_strings.

The functions get_user and put_user can trigger a page fault which can
potentially wait indefinitely in the case of userfaultfd or if
userspace implements part of the page fault path.

In any of those cases the userspace process that the kernel is waiting
for might make a different system call that winds up taking the
cred_guard_mutex and result in deadlock.

Holding a mutex over any of those possibly indefinite waits for
userspace does not appear necessary.  Add exec_update_mutex that will
just cover updating the process during exec where the permissions and
the objects pointed to by the task struct may be out of sync.

The plan is to switch the users of cred_guard_mutex to
exec_update_mutex one by one.  This lets us move forward while still
being careful and not introducing any regressions.

Link: https://lore.kernel.org/lkml/20160921152946.GA24210@dhcp22.suse.cz/
Link: https://lore.kernel.org/lkml/AM6PR03MB5170B06F3A2B75EFB98D071AE4E60@AM6PR03MB5170.eurprd03.prod.outlook.com/
Link: https://lore.kernel.org/linux-fsdevel/20161102181806.GB1112@redhat.com/
Link: https://lore.kernel.org/lkml/20160923095031.GA14923@redhat.com/
Link: https://lore.kernel.org/lkml/20170213141452.GA30203@redhat.com/
Ref: 45c1a159b85b ("Add PTRACE_O_TRACEVFORKDONE and PTRACE_O_TRACEEXIT facilities.")
Ref: 456f17cd1a28 ("[PATCH] user-vm-unlock-2.5.31-A2")
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-03-25 10:03:36 -05:00

163 lines
5.1 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 {
#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 long argmin; /* rlimit marker for copy_strings() */
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,
/*
* Set by flush_old_exec, when exec_mmap has been called.
* This is past the point of no return, when the
* exec_update_mutex has been taken.
*/
called_exec_mmap: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. */
char buf[BINPRM_BUF_SIZE];
} __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 kernel_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 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 */