asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
{
unsigned long ip;
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return scno;
if (!(current->ptrace & PT_PTRACED))
return scno;
/*
* Save IP. IP is used to denote syscall entry/exit:
* IP = 0 -> entry, = 1 -> exit
*/
ip = regs->ARM_ip;
regs->ARM_ip = why;
current_thread_info()->syscall = scno;
/* the 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
regs->ARM_ip = ip;
return current_thread_info()->syscall;
}
// kernel/fork.c
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr);
//...
{//vfork_done
struct completion vfork;
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
}
//...
if (clone_flags & CLONE_VFORK) {
wait_for_completion(&vfork);
if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
}
//...
return pid;
}
asmlinkage void syscall_trace(void)
{
pr_debug("syscall_trace called\n");
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
pr_debug("syscall_trace: notifying parent\n");
/* The 0x80 provides a way for the tracing parent to
* distinguish between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it
* will do for normal use. strace only continues with a
* signal if the stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
pr_debug("syscall_trace: sending signal %d to PID %u\n",
current->exit_code, current->pid);
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
int setup_signal_stack_si(unsigned long stack_top, int sig,
struct k_sigaction *ka, struct pt_regs *regs,
siginfo_t *info, sigset_t *mask)
{
struct rt_sigframe __user *frame;
void __user *restorer;
unsigned long save_sp = PT_REGS_SP(regs);
int err = 0;
stack_top &= -8UL;
frame = (struct rt_sigframe __user *) stack_top - 1;
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return 1;
restorer = frame->retcode;
if(ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
/* See comment above about why this is here */
PT_REGS_SP(regs) = (unsigned long) frame;
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
err |= __put_user(&frame->info, &frame->pinfo);
err |= __put_user(&frame->uc, &frame->puc);
err |= copy_siginfo_to_user(&frame->info, info);
err |= copy_ucontext_to_user(&frame->uc, &frame->fpstate, mask,
save_sp);
/*
* This is movl $,%eax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
err |= __put_user(0xb8, (char __user *)(frame->retcode+0));
err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1));
err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
if(err)
goto err;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
PT_REGS_EAX(regs) = (unsigned long) sig;
PT_REGS_EDX(regs) = (unsigned long) &frame->info;
PT_REGS_ECX(regs) = (unsigned long) &frame->uc;
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return 0;
err:
PT_REGS_SP(regs) = save_sp;
return err;
}
asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
{
unsigned long ip;
current_thread_info()->syscall = scno;
if (why)
audit_syscall_exit(regs);
else {
if (secure_computing(scno) == -1)
return -1;
audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0,
regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
}
if (why == 0 && test_and_clear_thread_flag(TIF_SYSCALL_RESTARTSYS))
scno = __NR_restart_syscall - __NR_SYSCALL_BASE;
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return scno;
if (!(current->ptrace & PT_PTRACED))
return scno;
/*
* IP is used to denote syscall entry/exit:
* IP = 0 -> entry, =1 -> exit
*/
ip = regs->ARM_ip;
regs->ARM_ip = why;
/*
* IP is used to denote syscall entry/exit:
* IP = 0 -> entry, =1 -> exit
*/
ip = regs->ARM_ip;
regs->ARM_ip = why;
/* the 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
regs->ARM_ip = ip;
return current_thread_info()->syscall;
}
int setup_signal_stack_sc(unsigned long stack_top, int sig,
struct k_sigaction *ka, struct pt_regs *regs,
sigset_t *mask)
{
struct sigframe __user *frame;
void *restorer;
int err = 0;
stack_top &= -8UL;
frame = (struct sigframe *) stack_top - 1;
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return 1;
restorer = (void *) frame->retcode;
if(ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
err |= copy_sc_to_user(&frame->sc, NULL, regs);
err |= __put_user(mask->sig[0], &frame->sc.oldmask);
if (_NSIG_WORDS > 1)
err |= __copy_to_user(&frame->extramask, &mask->sig[1],
sizeof(frame->extramask));
/*
* This is popl %eax ; movl $,%eax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
err |= __put_user(0xb858, (short __user *)(frame->retcode+0));
err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2));
err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
if(err)
return(err);
PT_REGS_SP(regs) = (unsigned long) frame;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
PT_REGS_EAX(regs) = (unsigned long) sig;
PT_REGS_EDX(regs) = (unsigned long) 0;
PT_REGS_ECX(regs) = (unsigned long) 0;
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return(0);
}
/*
* XXX Check PT_DTRACE vs TIF_SINGLESTEP for singlestepping check and
* PT_PTRACED vs TIF_SYSCALL_TRACE for syscall tracing check
*/
void syscall_trace(struct uml_pt_regs *regs, int entryexit)
{
int is_singlestep = (current->ptrace & PT_DTRACE) && entryexit;
int tracesysgood;
if (unlikely(current->audit_context)) {
if (!entryexit)
audit_syscall_entry(HOST_AUDIT_ARCH,
UPT_SYSCALL_NR(regs),
UPT_SYSCALL_ARG1(regs),
UPT_SYSCALL_ARG2(regs),
UPT_SYSCALL_ARG3(regs),
UPT_SYSCALL_ARG4(regs));
else audit_syscall_exit(AUDITSC_RESULT(UPT_SYSCALL_RET(regs)),
UPT_SYSCALL_RET(regs));
}
/* Fake a debug trap */
if (is_singlestep)
send_sigtrap(current, regs, 0);
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
/*
* the 0x80 provides a way for the tracing parent to distinguish
* between a syscall stop and SIGTRAP delivery
*/
tracesysgood = (current->ptrace & PT_TRACESYSGOOD);
ptrace_notify(SIGTRAP | (tracesysgood ? 0x80 : 0));
if (entryexit) /* force do_signal() --> is_syscall() */
set_thread_flag(TIF_SIGPENDING);
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
static void do_syscall_trace(void)
{
/* the 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
asmlinkage void syscall_trace(void)
{
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
static asmlinkage void syscall_trace(void)
{
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
/* The 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
void do_syscall_trace(void)
{
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
/* the 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
/*
* This isn't the same as continuing with a signal, but it will do for
* normal use.
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
/*
* Notification of system call entry/exit
* - triggered by current->work.syscall_trace
*/
asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
{
/* do the secure computing check first */
if (!entryexit)
secure_computing(regs->regs[0]);
if (unlikely(current->audit_context) && entryexit)
audit_syscall_exit(AUDITSC_RESULT(regs->regs[2]),
regs->regs[2]);
if (!(current->ptrace & PT_PTRACED))
goto out;
if (!test_thread_flag(TIF_SYSCALL_TRACE))
goto out;
/* The 0x80 provides a way for the tracing parent to distinguish
between a syscall stop and SIGTRAP delivery */
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ?
0x80 : 0));
/*
* this isn't the same as continuing with a signal, but it will do
* for normal use. strace only continues with a signal if the
* stopping signal is not SIGTRAP. -brl
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
out:
if (unlikely(current->audit_context) && !entryexit)
audit_syscall_entry(audit_arch(), regs->regs[0],
regs->regs[4], regs->regs[5],
regs->regs[6], regs->regs[7]);
}
asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
{
unsigned long ip;
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return scno;
if (!(current->ptrace & PT_PTRACED))
return scno;
ip = regs->UCreg_ip;
regs->UCreg_ip = why;
current_thread_info()->syscall = scno;
ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
? 0x80 : 0));
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
regs->UCreg_ip = ip;
return current_thread_info()->syscall;
}
void do_syscall_trace(void)
{
if (!test_thread_flag(TIF_SYSCALL_TRACE))
return;
if (!(current->ptrace & PT_PTRACED))
return;
/*
*/
ptrace_notify(SIGTRAP|((current->ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
/*
*/
if (current->exit_code) {
send_sig(current->exit_code, current, 1);
current->exit_code = 0;
}
}
static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs * regs)
{
void __user *restorer;
struct rt_sigframe __user *frame;
int err = 0;
int usig;
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
usig = current_thread_info()->exec_domain
&& current_thread_info()->exec_domain->signal_invmap
&& sig < 32
? current_thread_info()->exec_domain->signal_invmap[sig]
: sig;
err |= __put_user(usig, &frame->sig);
err |= __put_user(&frame->info, &frame->pinfo);
err |= __put_user(&frame->uc, &frame->puc);
err |= copy_siginfo_to_user(&frame->info, info);
if (err)
goto give_sigsegv;
/* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->esp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
goto give_sigsegv;
/* Set up to return from userspace. */
restorer = (void *)VDSO_SYM(&__kernel_rt_sigreturn);
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
err |= __put_user(restorer, &frame->pretcode);
/*
* This is movl $,%eax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
err |= __put_user(0xb8, (char __user *)(frame->retcode+0));
err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1));
err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
if (err)
goto give_sigsegv;
/* Set up registers for signal handler */
regs->esp = (unsigned long) frame;
regs->eip = (unsigned long) ka->sa.sa_handler;
regs->eax = (unsigned long) usig;
regs->edx = (unsigned long) &frame->info;
regs->ecx = (unsigned long) &frame->uc;
set_fs(USER_DS);
regs->xds = __USER_DS;
regs->xes = __USER_DS;
regs->xss = __USER_DS;
regs->xcs = __USER_CS;
/*
* Clear TF when entering the signal handler, but
* notify any tracer that was single-stepping it.
* The tracer may want to single-step inside the
* handler too.
*/
regs->eflags &= ~TF_MASK;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#if DEBUG_SIG
printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
current->comm, current->pid, frame, regs->eip, frame->pretcode);
#endif
return 0;
give_sigsegv:
force_sigsegv(sig, current);
return -EFAULT;
}
static int
handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
sigset_t *oldset, struct pt_regs *regs)
{
int ret;
/* Are we from a system call? */
if (current_syscall(regs) >= 0) {
/* If so, check system call restarting.. */
switch (current_syscall_ret(regs)) {
case -ERESTART_RESTARTBLOCK:
case -ERESTARTNOHAND:
regs->ax = -EINTR;
break;
case -ERESTARTSYS:
if (!(ka->sa.sa_flags & SA_RESTART)) {
regs->ax = -EINTR;
break;
}
/* fallthrough */
case -ERESTARTNOINTR:
regs->ax = regs->orig_ax;
regs->ip -= 2;
break;
}
}
/*
* If TF is set due to a debugger (TIF_FORCED_TF), clear the TF
* flag so that register information in the sigcontext is correct.
*/
if (unlikely(regs->flags & X86_EFLAGS_TF) &&
likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
regs->flags &= ~X86_EFLAGS_TF;
#ifdef CONFIG_IA32_EMULATION
if (test_thread_flag(TIF_IA32)) {
if (ka->sa.sa_flags & SA_SIGINFO)
ret = ia32_setup_rt_frame(sig, ka, info, oldset, regs);
else
ret = ia32_setup_frame(sig, ka, oldset, regs);
} else
#endif
ret = setup_rt_frame(sig, ka, info, oldset, regs);
if (ret == 0) {
/*
* This has nothing to do with segment registers,
* despite the name. This magic affects uaccess.h
* macros' behavior. Reset it to the normal setting.
*/
set_fs(USER_DS);
/*
* Clear the direction flag as per the ABI for function entry.
*/
regs->flags &= ~X86_EFLAGS_DF;
/*
* Clear TF when entering the signal handler, but
* notify any tracer that was single-stepping it.
* The tracer may want to single-step inside the
* handler too.
*/
regs->flags &= ~X86_EFLAGS_TF;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
spin_lock_irq(¤t->sighand->siglock);
sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NODEFER))
sigaddset(¤t->blocked,sig);
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
}
return ret;
}
/*
* load an fdpic binary into various bits of memory
*/
static int load_elf_fdpic_binary(struct linux_binprm *bprm, struct pt_regs *regs)
{
struct elf_fdpic_params exec_params, interp_params;
struct elf_phdr *phdr;
unsigned long stack_size;
struct file *interpreter = NULL; /* to shut gcc up */
char *interpreter_name = NULL;
int executable_stack;
int retval, i;
memset(&exec_params, 0, sizeof(exec_params));
memset(&interp_params, 0, sizeof(interp_params));
exec_params.hdr = *(struct elfhdr *) bprm->buf;
exec_params.flags = ELF_FDPIC_FLAG_PRESENT | ELF_FDPIC_FLAG_EXECUTABLE;
/* check that this is a binary we know how to deal with */
retval = -ENOEXEC;
if (!is_elf_fdpic(&exec_params.hdr, bprm->file))
goto error;
/* read the program header table */
retval = elf_fdpic_fetch_phdrs(&exec_params, bprm->file);
if (retval < 0)
goto error;
/* scan for a program header that specifies an interpreter */
phdr = exec_params.phdrs;
for (i = 0; i < exec_params.hdr.e_phnum; i++, phdr++) {
switch (phdr->p_type) {
case PT_INTERP:
retval = -ENOMEM;
if (phdr->p_filesz > PATH_MAX)
goto error;
retval = -ENOENT;
if (phdr->p_filesz < 2)
goto error;
/* read the name of the interpreter into memory */
interpreter_name = (char *) kmalloc(phdr->p_filesz, GFP_KERNEL);
if (!interpreter_name)
goto error;
retval = kernel_read(bprm->file,
phdr->p_offset,
interpreter_name,
phdr->p_filesz);
if (retval < 0)
goto error;
retval = -ENOENT;
if (interpreter_name[phdr->p_filesz - 1] != '\0')
goto error;
kdebug("Using ELF interpreter %s", interpreter_name);
/* replace the program with the interpreter */
interpreter = open_exec(interpreter_name);
retval = PTR_ERR(interpreter);
if (IS_ERR(interpreter)) {
interpreter = NULL;
goto error;
}
retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE);
if (retval < 0)
goto error;
interp_params.hdr = *((struct elfhdr *) bprm->buf);
break;
case PT_LOAD:
#ifdef CONFIG_MMU
if (exec_params.load_addr == 0)
exec_params.load_addr = phdr->p_vaddr;
#endif
break;
}
}
if (elf_check_const_displacement(&exec_params.hdr))
exec_params.flags |= ELF_FDPIC_FLAG_CONSTDISP;
/* perform insanity checks on the interpreter */
if (interpreter_name) {
retval = -ELIBBAD;
if (!is_elf_fdpic(&interp_params.hdr, interpreter))
goto error;
interp_params.flags = ELF_FDPIC_FLAG_PRESENT;
/* read the interpreter's program header table */
retval = elf_fdpic_fetch_phdrs(&interp_params, interpreter);
if (retval < 0)
goto error;
}
stack_size = exec_params.stack_size;
if (stack_size < interp_params.stack_size)
stack_size = interp_params.stack_size;
if (exec_params.flags & ELF_FDPIC_FLAG_EXEC_STACK)
executable_stack = EXSTACK_ENABLE_X;
else if (exec_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK)
executable_stack = EXSTACK_DISABLE_X;
else if (interp_params.flags & ELF_FDPIC_FLAG_EXEC_STACK)
executable_stack = EXSTACK_ENABLE_X;
else if (interp_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK)
executable_stack = EXSTACK_DISABLE_X;
else
executable_stack = EXSTACK_DEFAULT;
retval = -ENOEXEC;
if (stack_size == 0)
goto error;
if (elf_check_const_displacement(&interp_params.hdr))
interp_params.flags |= ELF_FDPIC_FLAG_CONSTDISP;
/* flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
goto error;
/* there's now no turning back... the old userspace image is dead,
* defunct, deceased, etc. after this point we have to exit via
* error_kill */
set_personality(PER_LINUX_FDPIC);
set_binfmt(&elf_fdpic_format);
current->mm->start_code = 0;
current->mm->end_code = 0;
current->mm->start_stack = 0;
current->mm->start_data = 0;
current->mm->end_data = 0;
current->mm->context.exec_fdpic_loadmap = 0;
current->mm->context.interp_fdpic_loadmap = 0;
current->flags &= ~PF_FORKNOEXEC;
#ifdef CONFIG_MMU
elf_fdpic_arch_lay_out_mm(&exec_params,
&interp_params,
¤t->mm->start_stack,
¤t->mm->start_brk);
#endif
/* do this so that we can load the interpreter, if need be
* - we will change some of these later
*/
set_mm_counter(current->mm, rss, 0);
#ifdef CONFIG_MMU
retval = setup_arg_pages(bprm, current->mm->start_stack, executable_stack);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto error_kill;
}
#endif
/* load the executable and interpreter into memory */
retval = elf_fdpic_map_file(&exec_params, bprm->file, current->mm, "executable");
if (retval < 0)
goto error_kill;
if (interpreter_name) {
retval = elf_fdpic_map_file(&interp_params, interpreter,
current->mm, "interpreter");
if (retval < 0) {
printk(KERN_ERR "Unable to load interpreter\n");
goto error_kill;
}
allow_write_access(interpreter);
fput(interpreter);
interpreter = NULL;
}
#ifdef CONFIG_MMU
if (!current->mm->start_brk)
current->mm->start_brk = current->mm->end_data;
current->mm->brk = current->mm->start_brk = PAGE_ALIGN(current->mm->start_brk);
#else
/* create a stack and brk area big enough for everyone
* - the brk heap starts at the bottom and works up
* - the stack starts at the top and works down
*/
stack_size = (stack_size + PAGE_SIZE - 1) & PAGE_MASK;
if (stack_size < PAGE_SIZE * 2)
stack_size = PAGE_SIZE * 2;
down_write(¤t->mm->mmap_sem);
current->mm->start_brk = do_mmap(NULL,
0,
stack_size,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_PRIVATE | MAP_ANON | MAP_GROWSDOWN,
0);
if (IS_ERR((void *) current->mm->start_brk)) {
up_write(¤t->mm->mmap_sem);
retval = current->mm->start_brk;
current->mm->start_brk = 0;
goto error_kill;
}
if (do_mremap(current->mm->start_brk,
stack_size,
ksize((char *) current->mm->start_brk),
0, 0
) == current->mm->start_brk
)
stack_size = ksize((char *) current->mm->start_brk);
up_write(¤t->mm->mmap_sem);
current->mm->brk = current->mm->start_brk;
current->mm->context.end_brk = current->mm->start_brk;
current->mm->context.end_brk += (stack_size > PAGE_SIZE) ? (stack_size - PAGE_SIZE) : 0;
current->mm->start_stack = current->mm->start_brk + stack_size;
#endif
compute_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0)
goto error_kill;
kdebug("- start_code %lx", (long) current->mm->start_code);
kdebug("- end_code %lx", (long) current->mm->end_code);
kdebug("- start_data %lx", (long) current->mm->start_data);
kdebug("- end_data %lx", (long) current->mm->end_data);
kdebug("- start_brk %lx", (long) current->mm->start_brk);
kdebug("- brk %lx", (long) current->mm->brk);
kdebug("- start_stack %lx", (long) current->mm->start_stack);
#ifdef ELF_FDPIC_PLAT_INIT
/*
* The ABI may specify that certain registers be set up in special
* ways (on i386 %edx is the address of a DT_FINI function, for
* example. This macro performs whatever initialization to
* the regs structure is required.
*/
ELF_FDPIC_PLAT_INIT(regs,
exec_params.map_addr,
interp_params.map_addr,
interp_params.dynamic_addr ?: exec_params.dynamic_addr
);
#endif
/* everything is now ready... get the userspace context ready to roll */
start_thread(regs,
interp_params.entry_addr ?: exec_params.entry_addr,
current->mm->start_stack);
if (unlikely(current->ptrace & PT_PTRACED)) {
if (current->ptrace & PT_TRACE_EXEC)
ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
else
send_sig(SIGTRAP, current, 0);
}
retval = 0;
error:
if (interpreter) {
allow_write_access(interpreter);
fput(interpreter);
}
if (interpreter_name)
kfree(interpreter_name);
if (exec_params.phdrs)
kfree(exec_params.phdrs);
if (exec_params.loadmap)
kfree(exec_params.loadmap);
if (interp_params.phdrs)
kfree(interp_params.phdrs);
if (interp_params.loadmap)
kfree(interp_params.loadmap);
return retval;
/* unrecoverable error - kill the process */
error_kill:
send_sig(SIGSEGV, current, 0);
goto error;
} /* end load_elf_fdpic_binary() */
static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set)
{
struct rt_sigframe __user *frame;
int rsig;
set_fs(USER_DS);
frame = get_sigframe(ka, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
rsig = sig;
if (sig < 32 &&
__current_thread_info->exec_domain &&
__current_thread_info->exec_domain->signal_invmap)
rsig = __current_thread_info->exec_domain->signal_invmap[sig];
if (__put_user(rsig, &frame->sig) ||
__put_user(&frame->info, &frame->pinfo) ||
__put_user(&frame->uc, &frame->puc))
goto give_sigsegv;
if (copy_siginfo_to_user(&frame->info, info))
goto give_sigsegv;
/* Create the ucontext. */
if (__put_user(0, &frame->uc.uc_flags) ||
__put_user(NULL, &frame->uc.uc_link) ||
__put_user((void __user *)current->sas_ss_sp, &frame->uc.uc_stack.ss_sp) ||
__put_user(sas_ss_flags(__frame->sp), &frame->uc.uc_stack.ss_flags) ||
__put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size))
goto give_sigsegv;
if (setup_sigcontext(&frame->uc.uc_mcontext, set->sig[0]))
goto give_sigsegv;
if (__copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)))
goto give_sigsegv;
/* Set up to return from userspace. If provided, use a stub
* already in userspace. */
if (ka->sa.sa_flags & SA_RESTORER) {
if (__put_user(ka->sa.sa_restorer, &frame->pretcode))
goto give_sigsegv;
}
else {
/* Set up the following code on the stack:
* setlos #__NR_sigreturn,gr7
* tira gr0,0
*/
if (__put_user((__sigrestore_t)frame->retcode, &frame->pretcode) ||
__put_user(0x8efc0000|__NR_rt_sigreturn, &frame->retcode[0]) ||
__put_user(0xc0700000, &frame->retcode[1]))
goto give_sigsegv;
flush_icache_range((unsigned long) frame->retcode,
(unsigned long) (frame->retcode + 2));
}
/* Set up registers for signal handler */
if (current->personality & FDPIC_FUNCPTRS) {
struct fdpic_func_descriptor __user *funcptr =
(struct fdpic_func_descriptor __user *) ka->sa.sa_handler;
struct fdpic_func_descriptor desc;
if (copy_from_user(&desc, funcptr, sizeof(desc)))
goto give_sigsegv;
__frame->pc = desc.text;
__frame->gr15 = desc.GOT;
} else {
__frame->pc = (unsigned long) ka->sa.sa_handler;
__frame->gr15 = 0;
}
__frame->sp = (unsigned long) frame;
__frame->lr = (unsigned long) &frame->retcode;
__frame->gr8 = sig;
__frame->gr9 = (unsigned long) &frame->info;
/* the tracer may want to single-step inside the handler */
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#if DEBUG_SIG
printk("SIG deliver %d (%s:%d): sp=%p pc=%lx ra=%p\n",
sig, current->comm, current->pid, frame, __frame->pc,
frame->pretcode);
#endif
return 0;
give_sigsegv:
force_sigsegv(sig, current);
return -EFAULT;
} /* end setup_rt_frame() */
static int load_exeso_binary(struct linux_binprm *bprm, struct pt_regs *regs)
{
struct elfhdr *elf_ex;
struct elf_phdr *elf_phdata = NULL;
struct mm_struct *mm;
unsigned long load_addr = 0;
unsigned long error;
int retval = 0;
unsigned long pe_entry, ntdll_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long ntdll_entry;
int executable_stack = EXSTACK_DEFAULT;
unsigned long def_flags = 0;
unsigned long stack_top;
#ifdef NTDLL_SO
unsigned long interp_load_addr;
unsigned long interp_entry;
#endif
struct eprocess *process;
struct ethread *thread;
PRTL_USER_PROCESS_PARAMETERS ppb;
OBJECT_ATTRIBUTES ObjectAttributes;
INITIAL_TEB init_teb;
BOOLEAN is_win32=FALSE;
struct startup_info *info=NULL;
struct eprocess *parent_eprocess=NULL;
struct ethread *parent_ethread=NULL;
struct w32process* child_w32process =NULL;
struct w32process* parent_w32process =NULL;
elf_ex = (struct elfhdr *)bprm->buf;
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
if (memcmp(elf_ex->e_ident, ELFMAG, SELFMAG) != 0)
goto out;
if (elf_ex->e_type != ET_EXEC && elf_ex->e_type != ET_DYN)
goto out;
if (!elf_check_arch(elf_ex))
goto out;
if (!bprm->file->f_op||!bprm->file->f_op->mmap)
goto out;
if (elf_ex->e_phentsize != sizeof(struct elf_phdr))
goto out;
if (elf_ex->e_phnum < 1 ||
elf_ex->e_phnum > 65536U / sizeof(struct elf_phdr))
goto out;
if(!check_exeso(bprm))
goto out;
start_code = ~0UL;
end_code = 0;
start_data = 0;
end_data = 0;
if(current->parent->ethread)
{
is_win32 = TRUE;
parent_ethread = current->parent->ethread;
parent_eprocess = parent_ethread->threads_process;
}
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval) {
goto out;
}
/* OK, This is the point of no return */
mm = current->mm;
current->flags &= ~PF_FORKNOEXEC;
mm->def_flags = def_flags;
current->signal->rlim[RLIMIT_STACK].rlim_cur = WIN32_STACK_LIMIT;
current->signal->rlim[RLIMIT_STACK].rlim_max = WIN32_STACK_LIMIT;
current->personality |= ADDR_COMPAT_LAYOUT;
arch_pick_mmap_layout(mm);
/* Do this so that we can load the ntdll, if need be. We will
change some of these later */
mm->free_area_cache = mm->mmap_base = WIN32_UNMAPPED_BASE;
mm->cached_hole_size = 0;
stack_top = WIN32_STACK_LIMIT + WIN32_LOWEST_ADDR;
retval = setup_arg_pages(bprm, stack_top, executable_stack);
if (retval < 0)
goto out_free_file;
down_write(&mm->mmap_sem);
/* reserve first 0x100000 */
do_mmap_pgoff(NULL, 0, WIN32_LOWEST_ADDR, PROT_NONE, MAP_PRIVATE | MAP_FIXED | MAP_ANONYMOUS, 0);
/* reserve first 0x7fff0000 - 0x80000000 */
do_mmap_pgoff(NULL, WIN32_TASK_SIZE - 0x10000, 0x10000,
PROT_NONE, MAP_PRIVATE | MAP_FIXED | MAP_ANONYMOUS, 0);
/* reserve first 0x81000000 - 0xc0000000
* 0x80000000 - 0x81000000 used for wine SYSTEM_HEAP */
do_mmap_pgoff(NULL, WIN32_TASK_SIZE + WIN32_SYSTEM_HEAP_SIZE,
TASK_SIZE - WIN32_TASK_SIZE - WIN32_SYSTEM_HEAP_SIZE,
PROT_NONE, MAP_PRIVATE | MAP_FIXED | MAP_ANONYMOUS, 0);
up_write(&mm->mmap_sem);
#ifdef NTDLL_SO
/* search ntdll.dll.so in $PATH, default is /usr/local/lib/wine/ntdll.dll.so */
if (!*ntdll_name)
search_ntdll();
/* map ntdll.dll.so */
map_system_dll(current, ntdll_name, &ntdll_load_addr, &interp_load_addr);
pe_entry = get_pe_entry();
ntdll_entry = get_ntdll_entry();
interp_entry = get_interp_entry();
#endif
set_binfmt(&exeso_format);
#ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
retval = arch_setup_additional_pages(bprm, executable_stack);
if (retval < 0) {
goto out_free_file;
}
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
install_exec_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
#ifdef NTDLL_SO
/* copy argv, env, and auxvec to stack, all for interpreter */
create_elf_tables_aux(bprm,
ntdll_load_addr, ntdll_phoff, ntdll_phnum, get_ntdll_start_thunk(),
load_addr, elf_ex->e_phoff, elf_ex->e_phnum, 0,
interp_load_addr, interp_entry, 0);
#endif
mm->end_code = end_code;
mm->start_code = start_code;
mm->start_data = start_data;
mm->end_data = end_data;
mm->start_stack = bprm->p;
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
and some applications "depend" upon this behavior.
Since we do not have the power to recompile these, we
emulate the SVr4 behavior. Sigh. */
down_write(&mm->mmap_sem);
error = do_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE, 0);
up_write(&mm->mmap_sem);
}
/* create win-related structure */
INIT_OBJECT_ATTR(&ObjectAttributes, NULL, 0, NULL, NULL);
/* Create EPROCESS */
retval = create_object(KernelMode,
process_object_type,
&ObjectAttributes,
KernelMode,
NULL,
sizeof(struct eprocess),
0,
0,
(PVOID *)&process);
if (retval != STATUS_SUCCESS) {
goto out_free_file;
}
/* init eprocess */
eprocess_init(NULL, FALSE, process);
process->unique_processid = create_cid_handle(process, process_object_type);
if (!process->unique_processid)
goto out_free_eproc;
/* initialize EProcess and KProcess */
process->section_base_address = (void *)load_addr;
/* FIXME: PsCreateCidHandle */
/* Create PEB */
if ((retval = create_peb(process)))
goto out_free_process_cid;
/* Create PPB */
if(is_win32 == FALSE)
{
create_ppb(&ppb, process, bprm, bprm->filename, NULL, NULL, NULL, NULL, NULL, NULL, NULL);
((PEB *)process->peb)->ProcessParameters = ppb;
}
/* allocate a Win32 thread object */
retval = create_object(KernelMode,
thread_object_type,
&ObjectAttributes,
KernelMode,
NULL,
sizeof(struct ethread),
0,
0,
(PVOID *)&thread);
if (retval) {
goto out_free_process_cid;
}
thread->cid.unique_thread = create_cid_handle(thread, thread_object_type);
thread->cid.unique_process = process->unique_processid;
if (!thread->cid.unique_thread)
goto out_free_ethread;
/* set the teb */
init_teb.StackBase = (PVOID)(bprm->p);
init_teb.StackLimit = (PVOID)WIN32_LOWEST_ADDR + PAGE_SIZE;
thread->tcb.teb = create_teb(process, (PCLIENT_ID)&thread->cid, &init_teb);
if (IS_ERR(thread->tcb.teb)) {
retval = PTR_ERR(thread->tcb.teb);
goto out_free_thread_cid;
}
/* Init KThreaad */
ethread_init(thread, process, current);
sema_init(&thread->exec_semaphore,0);
if (is_win32 == TRUE) //parent is a windows process
{
down(&thread->exec_semaphore); //wait for the parent
child_w32process = process->win32process;
parent_w32process = parent_eprocess->win32process;
info = child_w32process->startup_info;
//now parent has finished its work
if(thread->inherit_all)
{
create_handle_table(parent_eprocess, TRUE, process);
child_w32process = create_w32process(parent_w32process, TRUE, process);
}
}
deref_object(process);
deref_object(thread);
set_teb_selector(current, (long)thread->tcb.teb);
thread->start_address = (void *)pe_entry; /* FIXME */
/* save current trap frame */
thread->tcb.trap_frame = (struct ktrap_frame *)regs;
/* init apc, to call LdrInitializeThunk */
#if 0
thread_apc = kmalloc(sizeof(KAPC), GFP_KERNEL);
if (!thread_apc) {
retval = -ENOMEM;
goto out_free_thread_cid;
}
apc_init(thread_apc,
&thread->tcb,
OriginalApcEnvironment,
thread_special_apc,
NULL,
(PKNORMAL_ROUTINE)ntdll_entry,
UserMode,
(void *)(bprm->p + 12));
insert_queue_apc(thread_apc, (void *)interp_entry, (void *)extra_page, IO_NO_INCREMENT);
#ifndef TIF_APC
#define TIF_APC 13
#endif
set_tsk_thread_flag(current, TIF_APC);
#endif
#ifdef ELF_PLAT_INIT
/*
* The ABI may specify that certain registers be set up in special
* ways (on i386 %edx is the address of a DT_FINI function, for
* example. In addition, it may also specify (eg, PowerPC64 ELF)
* that the e_entry field is the address of the function descriptor
* for the startup routine, rather than the address of the startup
* routine itself. This macro performs whatever initialization to
* the regs structure is required as well as any relocations to the
* function descriptor entries when executing dynamically links apps.
*/
ELF_PLAT_INIT(regs, reloc_func_desc);
#endif
start_thread(regs, interp_entry, bprm->p);
if (unlikely(current->ptrace & PT_PTRACED)) {
if (current->ptrace & PT_TRACE_EXEC)
ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
else
send_sig(SIGTRAP, current, 0);
}
retval = 0;
try_module_get(THIS_MODULE);
/* return from w32syscall_exit, not syscall_exit */
((unsigned long *)regs)[-1] = (unsigned long)w32syscall_exit;
regs->fs = TEB_SELECTOR;
out:
if(elf_phdata)
kfree(elf_phdata);
return retval;
/* error cleanup */
out_free_thread_cid:
delete_cid_handle(thread->cid.unique_thread, thread_object_type);
out_free_ethread:
deref_object(thread);
out_free_process_cid:
delete_cid_handle(process->unique_processid, process_object_type);
out_free_eproc:
deref_object(process);
out_free_file:
send_sig(SIGKILL, current, 0);
goto out;
}
/*
* set up a realtime signal frame
*/
static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
int rsig;
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
rsig = sig;
if (sig < 32 &&
current_thread_info()->exec_domain &&
current_thread_info()->exec_domain->signal_invmap)
rsig = current_thread_info()->exec_domain->signal_invmap[sig];
if (__put_user(rsig, &frame->sig) ||
__put_user(&frame->info, &frame->pinfo) ||
__put_user(&frame->uc, &frame->puc) ||
copy_siginfo_to_user(&frame->info, info))
goto give_sigsegv;
/* create the ucontext. */
if (__put_user(0, &frame->uc.uc_flags) ||
__put_user(0, &frame->uc.uc_link) ||
__put_user((void *)current->sas_ss_sp, &frame->uc.uc_stack.ss_sp) ||
__put_user(sas_ss_flags(regs->sp), &frame->uc.uc_stack.ss_flags) ||
__put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size) ||
setup_sigcontext(&frame->uc.uc_mcontext,
&frame->fpuctx, regs, set->sig[0]) ||
__copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)))
goto give_sigsegv;
/* set up to return from userspace. If provided, use a stub already in
* userspace */
if (ka->sa.sa_flags & SA_RESTORER) {
if (__put_user(ka->sa.sa_restorer, &frame->pretcode))
goto give_sigsegv;
} else {
if (__put_user((void(*)(void))frame->retcode,
&frame->pretcode) ||
/* This is mov $,d0; syscall 0 */
__put_user(0x2c, (char *)(frame->retcode + 0)) ||
__put_user(__NR_rt_sigreturn,
(char *)(frame->retcode + 1)) ||
__put_user(0x00, (char *)(frame->retcode + 2)) ||
__put_user(0xf0, (char *)(frame->retcode + 3)) ||
__put_user(0xe0, (char *)(frame->retcode + 4)))
goto give_sigsegv;
flush_icache_range((u_long) frame->retcode,
(u_long) frame->retcode + 5);
}
/* Set up registers for signal handler */
regs->sp = (unsigned long) frame;
regs->pc = (unsigned long) ka->sa.sa_handler;
regs->d0 = sig;
regs->d1 = (long) &frame->info;
/* the tracer may want to single-step inside the handler */
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#if DEBUG_SIG
printk(KERN_DEBUG "SIG deliver %d (%s:%d): sp=%p pc=%lx ra=%p\n",
sig, current->comm, current->pid, frame, regs->pc,
frame->pretcode);
#endif
return 0;
give_sigsegv:
force_sigsegv(sig, current);
return -EFAULT;
}
int compat_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs *regs)
{
unsigned long restorer;
struct compat_rt_sigframe __user *frame;
int err = 0;
int usig;
frame = compat_get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
usig = current_thread_info()->exec_domain
&& current_thread_info()->exec_domain->signal_invmap
&& sig < 32
? current_thread_info()->exec_domain->signal_invmap[sig]
: sig;
if (ka->sa.sa_flags & SA_SIGINFO) {
err |= copy_siginfo_to_user32(&frame->info, info);
regs->flags |= PT_FLAGS_RESTORE_REGS;
} else {
err |= __put_user(info->si_signo, &frame->info.si_signo);
}
err |= __clear_user(&frame->save_area, sizeof(frame->save_area));
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(ptr_to_compat((void *)(current->sas_ss_sp)),
&frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= setup_sigcontext(&frame->uc.uc_mcontext, regs);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
goto give_sigsegv;
restorer = VDSO_BASE;
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ptr_to_compat_reg(ka->sa.sa_restorer);
regs->pc = ptr_to_compat_reg(ka->sa.sa_handler);
regs->ex1 = PL_ICS_EX1(USER_PL, 1);
regs->sp = ptr_to_compat_reg(frame);
regs->lr = restorer;
regs->regs[0] = (unsigned long) usig;
regs->regs[1] = ptr_to_compat_reg(&frame->info);
regs->regs[2] = ptr_to_compat_reg(&frame->uc);
regs->flags |= PT_FLAGS_CALLER_SAVES;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
return 0;
give_sigsegv:
signal_fault("bad setup frame", regs, frame, sig);
return -EFAULT;
}
static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs * regs)
{
struct rt_sigframe __user *frame;
struct _fpstate __user *fp = NULL;
int err = 0;
struct task_struct *me = current;
if (used_math()) {
fp = get_stack(ka, regs, sizeof(struct _fpstate));
frame = (void __user *)round_down(
(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate)))
goto give_sigsegv;
if (save_i387(fp) < 0)
err |= -1;
} else
frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
if (ka->sa.sa_flags & SA_SIGINFO) {
err |= copy_siginfo_to_user(&frame->info, info);
if (err)
goto give_sigsegv;
}
/* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->rsp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
if (sizeof(*set) == 16) {
__put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
__put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
} else
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
/* x86-64 should always use SA_RESTORER. */
if (ka->sa.sa_flags & SA_RESTORER) {
err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
} else {
/* could use a vstub here */
goto give_sigsegv;
}
if (err)
goto give_sigsegv;
#ifdef DEBUG_SIG
printk("%d old rip %lx old rsp %lx old rax %lx\n", current->pid,regs->rip,regs->rsp,regs->rax);
#endif
/* Set up registers for signal handler */
regs->rdi = sig;
/* In case the signal handler was declared without prototypes */
regs->rax = 0;
/* This also works for non SA_SIGINFO handlers because they expect the
next argument after the signal number on the stack. */
regs->rsi = (unsigned long)&frame->info;
regs->rdx = (unsigned long)&frame->uc;
regs->rip = (unsigned long) ka->sa.sa_handler;
regs->rsp = (unsigned long)frame;
/* Set up the CS register to run signal handlers in 64-bit mode,
even if the handler happens to be interrupting 32-bit code. */
regs->cs = __USER_CS;
/* This, by contrast, has nothing to do with segment registers -
see include/asm-x86_64/uaccess.h for details. */
set_fs(USER_DS);
regs->eflags &= ~TF_MASK;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#ifdef DEBUG_SIG
printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n",
current->comm, current->pid, frame, regs->rip, frame->pretcode);
#endif
return 0;
give_sigsegv:
force_sigsegv(sig, current);
return -EFAULT;
}
/*
* OK, we're invoking a handler:
*/
static int
handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
sigset_t *oldset, struct pt_regs *regs)
{
int ret;
/* Are we from a system call? */
if ((long)regs->orig_ax >= 0) {
/* If so, check system call restarting.. */
switch (regs->ax) {
case -ERESTART_RESTARTBLOCK:
case -ERESTARTNOHAND:
regs->ax = -EINTR;
break;
case -ERESTARTSYS:
if (!(ka->sa.sa_flags & SA_RESTART)) {
regs->ax = -EINTR;
break;
}
/* fallthrough */
case -ERESTARTNOINTR:
regs->ax = regs->orig_ax;
regs->ip -= 2;
break;
}
}
/*
* If TF is set due to a debugger (TIF_FORCED_TF), clear the TF
* flag so that register information in the sigcontext is correct.
*/
if (unlikely(regs->flags & X86_EFLAGS_TF) &&
likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
regs->flags &= ~X86_EFLAGS_TF;
/* Set up the stack frame */
if (ka->sa.sa_flags & SA_SIGINFO)
ret = setup_rt_frame(sig, ka, info, oldset, regs);
else
ret = setup_frame(sig, ka, oldset, regs);
if (ret)
return ret;
/*
* Clear the direction flag as per the ABI for function entry.
*/
regs->flags &= ~X86_EFLAGS_DF;
/*
* Clear TF when entering the signal handler, but
* notify any tracer that was single-stepping it.
* The tracer may want to single-step inside the
* handler too.
*/
regs->flags &= ~X86_EFLAGS_TF;
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
spin_lock_irq(¤t->sighand->siglock);
sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NODEFER))
sigaddset(¤t->blocked, sig);
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
return 0;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long pid;
if (unlikely(current->ptrace)) {
trace = fork_traceflag (clone_flags);
if (trace)
clone_flags |= CLONE_PTRACE;
}
p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
pid = IS_ERR(p) ? PTR_ERR(p) : p->pid;
if (!IS_ERR(p)) {
struct completion vfork;
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
/*
* We'll start up with an immediate SIGSTOP.
*/
sigaddset(&p->pending.signal, SIGSTOP);
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
if (!(clone_flags & CLONE_STOPPED)) {
/*
* Do the wakeup last. On SMP we treat fork() and
* CLONE_VM separately, because fork() has already
* created cache footprint on this CPU (due to
* copying the pagetables), hence migration would
* probably be costy. Threads on the other hand
* have less traction to the current CPU, and if
* there's an imbalance then the scheduler can
* migrate this fresh thread now, before it
* accumulates a larger cache footprint:
*/
if (clone_flags & CLONE_VM)
wake_up_forked_thread(p);
else
wake_up_forked_process(p);
} else {
int cpu = get_cpu();
p->state = TASK_STOPPED;
if (cpu_is_offline(task_cpu(p)))
set_task_cpu(p, cpu);
put_cpu();
}
++total_forks;
if (unlikely (trace)) {
current->ptrace_message = pid;
ptrace_notify ((trace << 8) | SIGTRAP);
}
if (clone_flags & CLONE_VFORK) {
wait_for_completion(&vfork);
if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
} else
/*
* Let the child process run first, to avoid most of the
* COW overhead when the child exec()s afterwards.
*/
set_need_resched();
}
return pid;
}
static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs *regs)
{
unsigned long restorer;
struct rt_sigframe __user *frame;
int err = 0;
int usig;
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
usig = current_thread_info()->exec_domain
&& current_thread_info()->exec_domain->signal_invmap
&& sig < 32
? current_thread_info()->exec_domain->signal_invmap[sig]
: sig;
/* Always write at least the signal number for the stack backtracer. */
if (ka->sa.sa_flags & SA_SIGINFO) {
/* At sigreturn time, restore the callee-save registers too. */
err |= copy_siginfo_to_user(&frame->info, info);
regs->flags |= PT_FLAGS_RESTORE_REGS;
} else {
err |= __put_user(info->si_signo, &frame->info.si_signo);
}
/* Create the ucontext. */
err |= __clear_user(&frame->save_area, sizeof(frame->save_area));
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(NULL, &frame->uc.uc_link);
err |= __put_user((void __user *)(current->sas_ss_sp),
&frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= setup_sigcontext(&frame->uc.uc_mcontext, regs);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
goto give_sigsegv;
restorer = VDSO_BASE;
if (ka->sa.sa_flags & SA_RESTORER)
restorer = (unsigned long) ka->sa.sa_restorer;
/*
* Set up registers for signal handler.
* Registers that we don't modify keep the value they had from
* user-space at the time we took the signal.
* We always pass siginfo and mcontext, regardless of SA_SIGINFO,
* since some things rely on this (e.g. glibc's debug/segfault.c).
*/
regs->pc = (unsigned long) ka->sa.sa_handler;
regs->ex1 = PL_ICS_EX1(USER_PL, 1); /* set crit sec in handler */
regs->sp = (unsigned long) frame;
regs->lr = restorer;
regs->regs[0] = (unsigned long) usig;
regs->regs[1] = (unsigned long) &frame->info;
regs->regs[2] = (unsigned long) &frame->uc;
regs->flags |= PT_FLAGS_CALLER_SAVES;
/*
* Notify any tracer that was single-stepping it.
* The tracer may want to single-step inside the
* handler too.
*/
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
return 0;
give_sigsegv:
force_sigsegv(sig, current);
return -EFAULT;
}
static int CVE_2010_0307_linux2_6_16_load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs)
{
struct file *interpreter = NULL; /* to shut gcc up */
unsigned long load_addr = 0, load_bias = 0;
int load_addr_set = 0;
char * elf_interpreter = NULL;
unsigned int interpreter_type = INTERPRETER_NONE;
unsigned char ibcs2_interpreter = 0;
unsigned long error;
struct elf_phdr * elf_ppnt, *elf_phdata;
unsigned long elf_bss, elf_brk;
int elf_exec_fileno;
int retval, i;
unsigned int size;
unsigned long elf_entry, interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long reloc_func_desc = 0;
char passed_fileno[6];
struct files_struct *files;
int have_pt_gnu_stack, executable_stack = EXSTACK_DEFAULT;
unsigned long def_flags = 0;
struct {
struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
struct exec interp_ex;
} *loc;
loc = kmalloc(sizeof(*loc), GFP_KERNEL);
if (!loc) {
retval = -ENOMEM;
goto out_ret;
}
/* Get the exec-header */
loc->elf_ex = *((struct elfhdr *) bprm->buf);
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
if (memcmp(loc->elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out;
if (loc->elf_ex.e_type != ET_EXEC && loc->elf_ex.e_type != ET_DYN)
goto out;
if (!elf_check_arch(&loc->elf_ex))
goto out;
if (!bprm->file->f_op||!bprm->file->f_op->mmap)
goto out;
/* Now read in all of the header information */
if (loc->elf_ex.e_phentsize != sizeof(struct elf_phdr))
goto out;
if (loc->elf_ex.e_phnum < 1 ||
loc->elf_ex.e_phnum > 65536U / sizeof(struct elf_phdr))
goto out;
size = loc->elf_ex.e_phnum * sizeof(struct elf_phdr);
retval = -ENOMEM;
elf_phdata = (struct elf_phdr *) kmalloc(size, GFP_KERNEL);
if (!elf_phdata)
goto out;
retval = kernel_read(bprm->file, loc->elf_ex.e_phoff, (char *) elf_phdata, size);
if (retval != size) {
if (retval >= 0)
retval = -EIO;
goto out_free_ph;
}
files = current->files; /* Refcounted so ok */
retval = unshare_files();
if (retval < 0)
goto out_free_ph;
if (files == current->files) {
put_files_struct(files);
files = NULL;
}
/* exec will make our files private anyway, but for the a.out
loader stuff we need to do it earlier */
retval = get_unused_fd();
if (retval < 0)
goto out_free_fh;
get_file(bprm->file);
fd_install(elf_exec_fileno = retval, bprm->file);
elf_ppnt = elf_phdata;
elf_bss = 0;
elf_brk = 0;
start_code = ~0UL;
end_code = 0;
start_data = 0;
end_data = 0;
for (i = 0; i < loc->elf_ex.e_phnum; i++) {
if (elf_ppnt->p_type == PT_INTERP) {
/* This is the program interpreter used for
* shared libraries - for now assume that this
* is an a.out format binary
*/
retval = -ENOEXEC;
if (elf_ppnt->p_filesz > PATH_MAX ||
elf_ppnt->p_filesz < 2)
goto out_free_file;
retval = -ENOMEM;
elf_interpreter = kmalloc(elf_ppnt->p_filesz,
GFP_KERNEL);
if (!elf_interpreter)
goto out_free_file;
retval = kernel_read(bprm->file, elf_ppnt->p_offset,
elf_interpreter,
elf_ppnt->p_filesz);
if (retval != elf_ppnt->p_filesz) {
if (retval >= 0)
retval = -EIO;
goto out_free_interp;
}
/* make sure path is NULL terminated */
retval = -ENOEXEC;
if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
goto out_free_interp;
/* If the program interpreter is one of these two,
* then assume an iBCS2 image. Otherwise assume
* a native linux image.
*/
if (strcmp(elf_interpreter,"/usr/lib/libc.so.1") == 0 ||
strcmp(elf_interpreter,"/usr/lib/ld.so.1") == 0)
ibcs2_interpreter = 1;
/*
* The early SET_PERSONALITY here is so that the lookup
* for the interpreter happens in the namespace of the
* to-be-execed image. SET_PERSONALITY can select an
* alternate root.
*
* However, SET_PERSONALITY is NOT allowed to switch
* this task into the new images's memory mapping
* policy - that is, TASK_SIZE must still evaluate to
* that which is appropriate to the execing application.
* This is because exit_mmap() needs to have TASK_SIZE
* evaluate to the size of the old image.
*
* So if (say) a 64-bit application is execing a 32-bit
* application it is the architecture's responsibility
* to defer changing the value of TASK_SIZE until the
* switch really is going to happen - do this in
* flush_thread(). - akpm
*/
SET_PERSONALITY(loc->elf_ex, ibcs2_interpreter);
interpreter = open_exec(elf_interpreter);
retval = PTR_ERR(interpreter);
if (IS_ERR(interpreter))
goto out_free_interp;
retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE);
if (retval != BINPRM_BUF_SIZE) {
if (retval >= 0)
retval = -EIO;
goto out_free_dentry;
}
/* Get the exec headers */
loc->interp_ex = *((struct exec *) bprm->buf);
loc->interp_elf_ex = *((struct elfhdr *) bprm->buf);
break;
}
elf_ppnt++;
}
elf_ppnt = elf_phdata;
for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
if (elf_ppnt->p_type == PT_GNU_STACK) {
if (elf_ppnt->p_flags & PF_X)
executable_stack = EXSTACK_ENABLE_X;
else
executable_stack = EXSTACK_DISABLE_X;
break;
}
have_pt_gnu_stack = (i < loc->elf_ex.e_phnum);
/* Some simple consistency checks for the interpreter */
if (elf_interpreter) {
interpreter_type = INTERPRETER_ELF | INTERPRETER_AOUT;
/* Now figure out which format our binary is */
if ((N_MAGIC(loc->interp_ex) != OMAGIC) &&
(N_MAGIC(loc->interp_ex) != ZMAGIC) &&
(N_MAGIC(loc->interp_ex) != QMAGIC))
interpreter_type = INTERPRETER_ELF;
if (memcmp(loc->interp_elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
interpreter_type &= ~INTERPRETER_ELF;
retval = -ELIBBAD;
if (!interpreter_type)
goto out_free_dentry;
/* Make sure only one type was selected */
if ((interpreter_type & INTERPRETER_ELF) &&
interpreter_type != INTERPRETER_ELF) {
// FIXME - ratelimit this before re-enabling
// printk(KERN_WARNING "ELF: Ambiguous type, using ELF\n");
interpreter_type = INTERPRETER_ELF;
}
/* Verify the interpreter has a valid arch */
if ((interpreter_type == INTERPRETER_ELF) &&
!elf_check_arch(&loc->interp_elf_ex))
goto out_free_dentry;
} else {
/* Executables without an interpreter also need a personality */
SET_PERSONALITY(loc->elf_ex, ibcs2_interpreter);
}
/* OK, we are done with that, now set up the arg stuff,
and then start this sucker up */
if ((!bprm->sh_bang) && (interpreter_type == INTERPRETER_AOUT)) {
char *passed_p = passed_fileno;
sprintf(passed_fileno, "%d", elf_exec_fileno);
if (elf_interpreter) {
retval = copy_strings_kernel(1, &passed_p, bprm);
if (retval)
goto out_free_dentry;
bprm->argc++;
}
}
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
goto out_free_dentry;
/* Discard our unneeded old files struct */
if (files) {
steal_locks(files);
put_files_struct(files);
files = NULL;
}
/* OK, This is the point of no return */
current->mm->start_data = 0;
current->mm->end_data = 0;
current->mm->end_code = 0;
current->mm->mmap = NULL;
current->flags &= ~PF_FORKNOEXEC;
current->mm->def_flags = def_flags;
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
SET_PERSONALITY(loc->elf_ex, ibcs2_interpreter);
if (elf_read_implies_exec(loc->elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
if ( !(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
current->flags |= PF_RANDOMIZE;
arch_pick_mmap_layout(current->mm);
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
current->mm->free_area_cache = current->mm->mmap_base;
current->mm->cached_hole_size = 0;
retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
executable_stack);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
current->mm->start_stack = bprm->p;
/* Now we do a little grungy work by mmaping the ELF image into
the correct location in memory. At this point, we assume that
the image should be loaded at fixed address, not at a variable
address. */
for(i = 0, elf_ppnt = elf_phdata; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
unsigned long k, vaddr;
if (elf_ppnt->p_type != PT_LOAD)
continue;
if (unlikely (elf_brk > elf_bss)) {
unsigned long nbyte;
/* There was a PT_LOAD segment with p_memsz > p_filesz
before this one. Map anonymous pages, if needed,
and clear the area. */
retval = set_brk (elf_bss + load_bias,
elf_brk + load_bias);
if (retval) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
nbyte = ELF_PAGEOFFSET(elf_bss);
if (nbyte) {
nbyte = ELF_MIN_ALIGN - nbyte;
if (nbyte > elf_brk - elf_bss)
nbyte = elf_brk - elf_bss;
if (clear_user((void __user *)elf_bss +
load_bias, nbyte)) {
/*
* This bss-zeroing can fail if the ELF
* file specifies odd protections. So
* we don't check the return value
*/
}
}
}
if (elf_ppnt->p_flags & PF_R) elf_prot |= PROT_READ;
if (elf_ppnt->p_flags & PF_W) elf_prot |= PROT_WRITE;
if (elf_ppnt->p_flags & PF_X) elf_prot |= PROT_EXEC;
elf_flags = MAP_PRIVATE|MAP_DENYWRITE|MAP_EXECUTABLE;
vaddr = elf_ppnt->p_vaddr;
if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
} else if (loc->elf_ex.e_type == ET_DYN) {
/* Try and get dynamic programs out of the way of the default mmap
base, as well as whatever program they might try to exec. This
is because the brk will follow the loader, and is not movable. */
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
}
error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt, elf_prot, elf_flags);
if (BAD_ADDR(error)) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
if (!load_addr_set) {
load_addr_set = 1;
load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
if (loc->elf_ex.e_type == ET_DYN) {
load_bias += error -
ELF_PAGESTART(load_bias + vaddr);
load_addr += load_bias;
reloc_func_desc = load_bias;
}
}
k = elf_ppnt->p_vaddr;
if (k < start_code) start_code = k;
if (start_data < k) start_data = k;
/*
* Check to see if the section's size will overflow the
* allowed task size. Note that p_filesz must always be
* <= p_memsz so it is only necessary to check p_memsz.
*/
if (k > TASK_SIZE || elf_ppnt->p_filesz > elf_ppnt->p_memsz ||
elf_ppnt->p_memsz > TASK_SIZE ||
TASK_SIZE - elf_ppnt->p_memsz < k) {
/* set_brk can never work. Avoid overflows. */
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz;
if (k > elf_bss)
elf_bss = k;
if ((elf_ppnt->p_flags & PF_X) && end_code < k)
end_code = k;
if (end_data < k)
end_data = k;
k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz;
if (k > elf_brk)
elf_brk = k;
}
loc->elf_ex.e_entry += load_bias;
elf_bss += load_bias;
elf_brk += load_bias;
start_code += load_bias;
end_code += load_bias;
start_data += load_bias;
end_data += load_bias;
/* Calling set_brk effectively mmaps the pages that we need
* for the bss and break sections. We must do this before
* mapping in the interpreter, to make sure it doesn't wind
* up getting placed where the bss needs to go.
*/
retval = set_brk(elf_bss, elf_brk);
if (retval) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
send_sig(SIGSEGV, current, 0);
retval = -EFAULT; /* Nobody gets to see this, but.. */
goto out_free_dentry;
}
if (elf_interpreter) {
if (interpreter_type == INTERPRETER_AOUT)
elf_entry = load_aout_interp(&loc->interp_ex,
interpreter);
else
elf_entry = load_elf_interp(&loc->interp_elf_ex,
interpreter,
&interp_load_addr);
if (BAD_ADDR(elf_entry)) {
printk(KERN_ERR "Unable to load interpreter %.128s\n",
elf_interpreter);
force_sig(SIGSEGV, current);
retval = -ENOEXEC; /* Nobody gets to see this, but.. */
goto out_free_dentry;
}
reloc_func_desc = interp_load_addr;
allow_write_access(interpreter);
fput(interpreter);
kfree(elf_interpreter);
} else {
elf_entry = loc->elf_ex.e_entry;
if (BAD_ADDR(elf_entry)) {
send_sig(SIGSEGV, current, 0);
retval = -ENOEXEC; /* Nobody gets to see this, but.. */
goto out_free_dentry;
}
}
kfree(elf_phdata);
if (interpreter_type != INTERPRETER_AOUT)
sys_close(elf_exec_fileno);
set_binfmt(&elf_format);
#ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
retval = arch_setup_additional_pages(bprm, executable_stack);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out;
}
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
compute_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
create_elf_tables(bprm, &loc->elf_ex, (interpreter_type == INTERPRETER_AOUT),
load_addr, interp_load_addr);
/* N.B. passed_fileno might not be initialized? */
if (interpreter_type == INTERPRETER_AOUT)
current->mm->arg_start += strlen(passed_fileno) + 1;
current->mm->end_code = end_code;
current->mm->start_code = start_code;
current->mm->start_data = start_data;
current->mm->end_data = end_data;
current->mm->start_stack = bprm->p;
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
and some applications "depend" upon this behavior.
Since we do not have the power to recompile these, we
emulate the SVr4 behavior. Sigh. */
down_write(¤t->mm->mmap_sem);
error = do_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE, 0);
up_write(¤t->mm->mmap_sem);
}
#ifdef ELF_PLAT_INIT
/*
* The ABI may specify that certain registers be set up in special
* ways (on i386 %edx is the address of a DT_FINI function, for
* example. In addition, it may also specify (eg, PowerPC64 ELF)
* that the e_entry field is the address of the function descriptor
* for the startup routine, rather than the address of the startup
* routine itself. This macro performs whatever initialization to
* the regs structure is required as well as any relocations to the
* function descriptor entries when executing dynamically links apps.
*/
ELF_PLAT_INIT(regs, reloc_func_desc);
#endif
start_thread(regs, elf_entry, bprm->p);
if (unlikely(current->ptrace & PT_PTRACED)) {
if (current->ptrace & PT_TRACE_EXEC)
ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
else
send_sig(SIGTRAP, current, 0);
}
retval = 0;
out:
kfree(loc);
out_ret:
return retval;
/* error cleanup */
out_free_dentry:
allow_write_access(interpreter);
if (interpreter)
fput(interpreter);
out_free_interp:
kfree(elf_interpreter);
out_free_file:
sys_close(elf_exec_fileno);
out_free_fh:
if (files) {
put_files_struct(current->files);
current->files = files;
}
out_free_ph:
kfree(elf_phdata);
goto out;
}
static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs *regs)
{
struct rt_sigframe __user *frame;
int err = 0;
int signal;
unsigned long address = 0;
#ifdef CONFIG_MMU
pmd_t *pmdp;
pte_t *ptep;
#endif
frame = get_sigframe(ka, regs, sizeof(*frame));
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
signal = current_thread_info()->exec_domain
&& current_thread_info()->exec_domain->signal_invmap
&& sig < 32
? current_thread_info()->exec_domain->signal_invmap[sig]
: sig;
if (info)
err |= copy_siginfo_to_user(&frame->info, info);
/* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |= __put_user((void *)current->sas_ss_sp,
&frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(regs->r1),
&frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= setup_sigcontext(&frame->uc.uc_mcontext,
regs, set->sig[0]);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
/* minus 8 is offset to cater for "rtsd r15,8" */
if (ka->sa.sa_flags & SA_RESTORER) {
regs->r15 = ((unsigned long)ka->sa.sa_restorer)-8;
} else {
/* addi r12, r0, __NR_sigreturn */
err |= __put_user(0x31800000 | __NR_rt_sigreturn ,
frame->tramp + 0);
/* brki r14, 0x8 */
err |= __put_user(0xb9cc0008, frame->tramp + 1);
/* Return from sighandler will jump to the tramp.
Negative 8 offset because return is rtsd r15, 8 */
regs->r15 = ((unsigned long)frame->tramp)-8;
address = ((unsigned long)frame->tramp);
#ifdef CONFIG_MMU
pmdp = pmd_offset(pud_offset(
pgd_offset(current->mm, address),
address), address);
preempt_disable();
ptep = pte_offset_map(pmdp, address);
if (pte_present(*ptep)) {
address = (unsigned long) page_address(pte_page(*ptep));
/* MS: I need add offset in page */
address += ((unsigned long)frame->tramp) & ~PAGE_MASK;
/* MS address is virtual */
address = virt_to_phys(address);
invalidate_icache_range(address, address + 8);
flush_dcache_range(address, address + 8);
}
pte_unmap(ptep);
preempt_enable();
#else
invalidate_icache_range(address, address + 8);
flush_dcache_range(address, address + 8);
#endif
}
if (err)
goto give_sigsegv;
/* Set up registers for signal handler */
regs->r1 = (unsigned long) frame - STATE_SAVE_ARG_SPACE;
/* Signal handler args: */
regs->r5 = signal; /* arg 0: signum */
regs->r6 = (unsigned long) &frame->info; /* arg 1: siginfo */
regs->r7 = (unsigned long) &frame->uc; /* arg2: ucontext */
/* Offset to handle microblaze rtid r14, 0 */
regs->pc = (unsigned long)ka->sa.sa_handler;
set_fs(USER_DS);
/* the tracer may want to single-step inside the handler */
if (test_thread_flag(TIF_SINGLESTEP))
ptrace_notify(SIGTRAP);
#ifdef DEBUG_SIG
printk(KERN_INFO "SIG deliver (%s:%d): sp=%p pc=%08lx\n",
current->comm, current->pid, frame, regs->pc);
#endif
return;
give_sigsegv:
if (sig == SIGSEGV)
ka->sa.sa_handler = SIG_DFL;
force_sig(SIGSEGV, current);
}
static int
setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t * info,
sigset_t * set, struct pt_regs *regs)
{
struct rt_sigframe *frame;
int err = 0;
frame = get_sigframe(ka, regs, sizeof(*frame));
err |= __put_user((current_thread_info()->exec_domain
&& current_thread_info()->exec_domain->signal_invmap
&& sig < 32
? current_thread_info()->exec_domain->
signal_invmap[sig] : sig), &frame->sig);
err |= __put_user(&frame->info, &frame->pinfo);
err |= __put_user(&frame->uc, &frame->puc);
err |= copy_siginfo_to_user(&frame->info, info);
/* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(0, &frame->uc.uc_link);
err |=
__put_user((void *)current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
err |= __put_user(sas_ss_flags(rdusp()), &frame->uc.uc_stack.ss_flags);
err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
err |= rt_setup_sigcontext(&frame->uc.uc_mcontext, regs);
err |= copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
goto give_sigsegv;
/* Set up registers for signal handler */
wrusp((unsigned long)frame);
if (current->personality & FDPIC_FUNCPTRS) {
struct fdpic_func_descriptor __user *funcptr =
(struct fdpic_func_descriptor *) ka->sa.sa_handler;
__get_user(regs->pc, &funcptr->text);
__get_user(regs->p3, &funcptr->GOT);
} else
regs->pc = (unsigned long)ka->sa.sa_handler;
regs->rets = SIGRETURN_STUB;
regs->r0 = frame->sig;
regs->r1 = (unsigned long)(&frame->info);
regs->r2 = (unsigned long)(&frame->uc);
/*
* Clear the trace flag when entering the signal handler, but
* notify any tracer that was single-stepping it. The tracer
* may want to single-step inside the handler too.
*/
if (regs->syscfg & TRACE_BITS) {
regs->syscfg &= ~TRACE_BITS;
ptrace_notify(SIGTRAP);
}
return 0;
give_sigsegv:
if (sig == SIGSEGV)
ka->sa.sa_handler = SIG_DFL;
force_sig(SIGSEGV, current);
return -EFAULT;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long pid = alloc_pidmap();
if (pid < 0)
return -EAGAIN;
if (unlikely(current->ptrace)) {
trace = fork_traceflag (clone_flags);
if (trace)
clone_flags |= CLONE_PTRACE;
}
p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, pid);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
/*
* We'll start up with an immediate SIGSTOP.
*/
sigaddset(&p->pending.signal, SIGSTOP);
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
if (!(clone_flags & CLONE_STOPPED))
wake_up_new_task(p, clone_flags);
else
p->state = TASK_STOPPED;
if (unlikely (trace)) {
current->ptrace_message = pid;
ptrace_notify ((trace << 8) | SIGTRAP);
}
if (clone_flags & CLONE_VFORK) {
wait_for_completion(&vfork);
if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
}
} else {
free_pidmap(pid);
pid = PTR_ERR(p);
}
return pid;
}
int setup_signal_stack_sc(unsigned long stack_top, int sig,
struct k_sigaction *ka, struct pt_regs *regs,
sigset_t *mask)
{
struct sigframe __user *frame;
void __user *restorer;
unsigned long save_sp = PT_REGS_SP(regs);
int err = 0;
/* This is the same calculation as i386 - ((sp + 4) & 15) == 0 */
stack_top = ((stack_top + 4) & -16UL) - 4;
frame = (struct sigframe __user *) stack_top - 1;
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
return 1;
restorer = frame->retcode;
if(ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
/* Update SP now because the page fault handler refuses to extend
* the stack if the faulting address is too far below the current
* SP, which frame now certainly is. If there's an error, the original
* value is restored on the way out.
* When writing the sigcontext to the stack, we have to write the
* original value, so that's passed to copy_sc_to_user, which does
* the right thing with it.
*/
PT_REGS_SP(regs) = (unsigned long) frame;
err |= __put_user(restorer, &frame->pretcode);
err |= __put_user(sig, &frame->sig);
err |= copy_sc_to_user(&frame->sc, NULL, regs, save_sp);
err |= __put_user(mask->sig[0], &frame->sc.oldmask);
if (_NSIG_WORDS > 1)
err |= __copy_to_user(&frame->extramask, &mask->sig[1],
sizeof(frame->extramask));
/*
* This is popl %eax ; movl $,%eax ; int $0x80
*
* WE DO NOT USE IT ANY MORE! It's only left here for historical
* reasons and because gdb uses it as a signature to notice
* signal handler stack frames.
*/
err |= __put_user(0xb858, (short __user *)(frame->retcode+0));
err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2));
err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
if(err)
goto err;
PT_REGS_SP(regs) = (unsigned long) frame;
PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler;
PT_REGS_EAX(regs) = (unsigned long) sig;
PT_REGS_EDX(regs) = (unsigned long) 0;
PT_REGS_ECX(regs) = (unsigned long) 0;
if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
ptrace_notify(SIGTRAP);
return 0;
err:
PT_REGS_SP(regs) = save_sp;
return err;
}
