kernel_optimize_test/include/linux/binfmts.h
Oleg Nesterov a2a8474c3f exec: do not sleep in TASK_TRACED under ->cred_guard_mutex
Tom Horsley reports that his debugger hangs when it tries to read
/proc/pid_of_tracee/maps, this happens since

	"mm_for_maps: take ->cred_guard_mutex to fix the race with exec"
	04b836cbf19e885f8366bccb2e4b0474346c02d

commit in 2.6.31.

But the root of the problem lies in the fact that do_execve() path calls
tracehook_report_exec() which can stop if the tracer sets PT_TRACE_EXEC.

The tracee must not sleep in TASK_TRACED holding this mutex.  Even if we
remove ->cred_guard_mutex from mm_for_maps() and proc_pid_attr_write(),
another task doing PTRACE_ATTACH should not hang until it is killed or the
tracee resumes.

With this patch do_execve() does not use ->cred_guard_mutex directly and
we do not hold it throughout, instead:

	- introduce prepare_bprm_creds() helper, it locks the mutex
	  and calls prepare_exec_creds() to initialize bprm->cred.

	- install_exec_creds() drops the mutex after commit_creds(),
	  and thus before tracehook_report_exec()->ptrace_stop().

	  or, if exec fails,

	  free_bprm() drops this mutex when bprm->cred != NULL which
	  indicates install_exec_creds() was not called.

Reported-by: Tom Horsley <tom.horsley@att.net>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: David Howells <dhowells@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-05 11:30:42 -07:00

128 lines
4.1 KiB
C

#ifndef _LINUX_BINFMTS_H
#define _LINUX_BINFMTS_H
#include <linux/capability.h>
struct pt_regs;
/*
* These are the maximum length and maximum number of strings passed to the
* execve() system call. MAX_ARG_STRLEN is essentially random but serves to
* prevent the kernel from being unduly impacted by misaddressed pointers.
* MAX_ARG_STRINGS is chosen to fit in a signed 32-bit integer.
*/
#define MAX_ARG_STRLEN (PAGE_SIZE * 32)
#define MAX_ARG_STRINGS 0x7FFFFFFF
/* sizeof(linux_binprm->buf) */
#define BINPRM_BUF_SIZE 128
#ifdef __KERNEL__
#include <linux/list.h>
#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;
#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
cred_prepared:1,/* true if creds already prepared (multiple
* preps happen for interpreters) */
cap_effective:1;/* true if has elevated effective capabilities,
* false if not; except for init which inherits
* its parent's caps anyway */
#ifdef __alpha__
unsigned int taso:1;
#endif
unsigned int recursion_depth;
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;
char * filename; /* Name of binary as seen by procps */
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;
};
#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)
#define BINPRM_MAX_RECURSION 4
/*
* 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 *, struct pt_regs * regs);
int (*load_shlib)(struct file *);
int (*core_dump)(long signr, struct pt_regs *regs, struct file *file, unsigned long limit);
unsigned long min_coredump; /* minimal dump size */
int hasvdso;
};
extern int __register_binfmt(struct linux_binfmt *fmt, int insert);
/* Registration of default binfmt handlers */
static inline int register_binfmt(struct linux_binfmt *fmt)
{
return __register_binfmt(fmt, 0);
}
/* Same as above, but adds a new binfmt at the top of the list */
static inline int insert_binfmt(struct linux_binfmt *fmt)
{
return __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 *,struct pt_regs *);
extern int flush_old_exec(struct linux_binprm * bprm);
extern int suid_dumpable;
#define SUID_DUMP_DISABLE 0 /* No setuid dumping */
#define SUID_DUMP_USER 1 /* Dump as user of process */
#define SUID_DUMP_ROOT 2 /* Dump as root */
/* 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 bprm_mm_init(struct linux_binprm *bprm);
extern int copy_strings_kernel(int argc,char ** 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 do_coredump(long signr, int exit_code, struct pt_regs *regs);
extern int set_binfmt(struct linux_binfmt *new);
extern void free_bprm(struct linux_binprm *);
#endif /* __KERNEL__ */
#endif /* _LINUX_BINFMTS_H */