#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
-#include <linux/smp_lock.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/signal.h>
#include <linux/pid_namespace.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
/*
child->parent = new_parent;
}
-/*
- * Turn a tracing stop into a normal stop now, since with no tracer there
- * would be no way to wake it up with SIGCONT or SIGKILL. If there was a
- * signal sent that would resume the child, but didn't because it was in
- * TASK_TRACED, resume it now.
- * Requires that irqs be disabled.
- */
-static void ptrace_untrace(struct task_struct *child)
-{
- spin_lock(&child->sighand->siglock);
- if (task_is_traced(child)) {
- /*
- * If the group stop is completed or in progress,
- * this thread was already counted as stopped.
- */
- if (child->signal->flags & SIGNAL_STOP_STOPPED ||
- child->signal->group_stop_count)
- __set_task_state(child, TASK_STOPPED);
- else
- signal_wake_up(child, 1);
- }
- spin_unlock(&child->sighand->siglock);
-}
-
-/*
- * unptrace a task: move it back to its original parent and
- * remove it from the ptrace list.
+/**
+ * __ptrace_unlink - unlink ptracee and restore its execution state
+ * @child: ptracee to be unlinked
*
- * Must be called with the tasklist lock write-held.
+ * Remove @child from the ptrace list, move it back to the original parent,
+ * and restore the execution state so that it conforms to the group stop
+ * state.
+ *
+ * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer
+ * exiting. For PTRACE_DETACH, unless the ptracee has been killed between
+ * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED.
+ * If the ptracer is exiting, the ptracee can be in any state.
+ *
+ * After detach, the ptracee should be in a state which conforms to the
+ * group stop. If the group is stopped or in the process of stopping, the
+ * ptracee should be put into TASK_STOPPED; otherwise, it should be woken
+ * up from TASK_TRACED.
+ *
+ * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED,
+ * it goes through TRACED -> RUNNING -> STOPPED transition which is similar
+ * to but in the opposite direction of what happens while attaching to a
+ * stopped task. However, in this direction, the intermediate RUNNING
+ * state is not hidden even from the current ptracer and if it immediately
+ * re-attaches and performs a WNOHANG wait(2), it may fail.
+ *
+ * CONTEXT:
+ * write_lock_irq(tasklist_lock)
*/
void __ptrace_unlink(struct task_struct *child)
{
child->parent = child->real_parent;
list_del_init(&child->ptrace_entry);
- arch_ptrace_untrace(child);
- if (task_is_traced(child))
- ptrace_untrace(child);
+ spin_lock(&child->sighand->siglock);
+
+ /*
+ * Reinstate GROUP_STOP_PENDING if group stop is in effect and
+ * @child isn't dead.
+ */
+ if (!(child->flags & PF_EXITING) &&
+ (child->signal->flags & SIGNAL_STOP_STOPPED ||
+ child->signal->group_stop_count))
+ child->group_stop |= GROUP_STOP_PENDING;
+
+ /*
+ * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
+ * @child in the butt. Note that @resume should be used iff @child
+ * is in TASK_TRACED; otherwise, we might unduly disrupt
+ * TASK_KILLABLE sleeps.
+ */
+ if (child->group_stop & GROUP_STOP_PENDING || task_is_traced(child))
+ signal_wake_up(child, task_is_traced(child));
+
+ spin_unlock(&child->sighand->siglock);
}
/*
*/
read_lock(&tasklist_lock);
if ((child->ptrace & PT_PTRACED) && child->parent == current) {
- ret = 0;
/*
* child->sighand can't be NULL, release_task()
* does ptrace_unlink() before __exit_signal().
*/
spin_lock_irq(&child->sighand->siglock);
- if (task_is_stopped(child))
- child->state = TASK_TRACED;
- else if (!task_is_traced(child) && !kill)
- ret = -ESRCH;
+ WARN_ON_ONCE(task_is_stopped(child));
+ if (task_is_traced(child) || kill)
+ ret = 0;
spin_unlock_irq(&child->sighand->siglock);
}
read_unlock(&tasklist_lock);
return 0;
rcu_read_lock();
tcred = __task_cred(task);
- if ((cred->uid != tcred->euid ||
- cred->uid != tcred->suid ||
- cred->uid != tcred->uid ||
- cred->gid != tcred->egid ||
- cred->gid != tcred->sgid ||
- cred->gid != tcred->gid) &&
- !capable(CAP_SYS_PTRACE)) {
- rcu_read_unlock();
- return -EPERM;
- }
+ if (cred->user->user_ns == tcred->user->user_ns &&
+ (cred->uid == tcred->euid &&
+ cred->uid == tcred->suid &&
+ cred->uid == tcred->uid &&
+ cred->gid == tcred->egid &&
+ cred->gid == tcred->sgid &&
+ cred->gid == tcred->gid))
+ goto ok;
+ if (ns_capable(tcred->user->user_ns, CAP_SYS_PTRACE))
+ goto ok;
+ rcu_read_unlock();
+ return -EPERM;
+ok:
rcu_read_unlock();
smp_rmb();
if (task->mm)
dumpable = get_dumpable(task->mm);
- if (!dumpable && !capable(CAP_SYS_PTRACE))
+ if (!dumpable && !task_ns_capable(task, CAP_SYS_PTRACE))
return -EPERM;
- return security_ptrace_may_access(task, mode);
+ return security_ptrace_access_check(task, mode);
}
bool ptrace_may_access(struct task_struct *task, unsigned int mode)
return !err;
}
-int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task)
{
+ bool wait_trap = false;
int retval;
- unsigned long flags;
audit_ptrace(task);
retval = -EPERM;
+ if (unlikely(task->flags & PF_KTHREAD))
+ goto out;
if (same_thread_group(task, current))
goto out;
- /* Protect exec's credential calculations against our interference;
- * SUID, SGID and LSM creds get determined differently under ptrace.
+ /*
+ * Protect exec's credential calculations against our interference;
+ * interference; SUID, SGID and LSM creds get determined differently
+ * under ptrace.
*/
- retval = mutex_lock_interruptible(¤t->cred_exec_mutex);
- if (retval < 0)
+ retval = -ERESTARTNOINTR;
+ if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
goto out;
- retval = -EPERM;
-repeat:
- /*
- * Nasty, nasty.
- *
- * We want to hold both the task-lock and the
- * tasklist_lock for writing at the same time.
- * But that's against the rules (tasklist_lock
- * is taken for reading by interrupts on other
- * cpu's that may have task_lock).
- */
task_lock(task);
- if (!write_trylock_irqsave(&tasklist_lock, flags)) {
- task_unlock(task);
- do {
- cpu_relax();
- } while (!write_can_lock(&tasklist_lock));
- goto repeat;
- }
-
- if (!task->mm)
- goto bad;
- /* the same process cannot be attached many times */
- if (task->ptrace & PT_PTRACED)
- goto bad;
retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+ task_unlock(task);
if (retval)
- goto bad;
+ goto unlock_creds;
- /* Go */
- task->ptrace |= PT_PTRACED;
- if (capable(CAP_SYS_PTRACE))
+ write_lock_irq(&tasklist_lock);
+ retval = -EPERM;
+ if (unlikely(task->exit_state))
+ goto unlock_tasklist;
+ if (task->ptrace)
+ goto unlock_tasklist;
+
+ task->ptrace = PT_PTRACED;
+ if (task_ns_capable(task, CAP_SYS_PTRACE))
task->ptrace |= PT_PTRACE_CAP;
__ptrace_link(task, current);
-
send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
-bad:
- write_unlock_irqrestore(&tasklist_lock, flags);
- task_unlock(task);
- mutex_unlock(¤t->cred_exec_mutex);
+
+ spin_lock(&task->sighand->siglock);
+
+ /*
+ * If the task is already STOPPED, set GROUP_STOP_PENDING and
+ * TRAPPING, and kick it so that it transits to TRACED. TRAPPING
+ * will be cleared if the child completes the transition or any
+ * event which clears the group stop states happens. We'll wait
+ * for the transition to complete before returning from this
+ * function.
+ *
+ * This hides STOPPED -> RUNNING -> TRACED transition from the
+ * attaching thread but a different thread in the same group can
+ * still observe the transient RUNNING state. IOW, if another
+ * thread's WNOHANG wait(2) on the stopped tracee races against
+ * ATTACH, the wait(2) may fail due to the transient RUNNING.
+ *
+ * The following task_is_stopped() test is safe as both transitions
+ * in and out of STOPPED are protected by siglock.
+ */
+ if (task_is_stopped(task)) {
+ task->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING;
+ signal_wake_up(task, 1);
+ wait_trap = true;
+ }
+
+ spin_unlock(&task->sighand->siglock);
+
+ retval = 0;
+unlock_tasklist:
+ write_unlock_irq(&tasklist_lock);
+unlock_creds:
+ mutex_unlock(&task->signal->cred_guard_mutex);
out:
+ if (wait_trap)
+ wait_event(current->signal->wait_chldexit,
+ !(task->group_stop & GROUP_STOP_TRAPPING));
return retval;
}
+/**
+ * ptrace_traceme -- helper for PTRACE_TRACEME
+ *
+ * Performs checks and sets PT_PTRACED.
+ * Should be used by all ptrace implementations for PTRACE_TRACEME.
+ */
+static int ptrace_traceme(void)
+{
+ int ret = -EPERM;
+
+ write_lock_irq(&tasklist_lock);
+ /* Are we already being traced? */
+ if (!current->ptrace) {
+ ret = security_ptrace_traceme(current->parent);
+ /*
+ * Check PF_EXITING to ensure ->real_parent has not passed
+ * exit_ptrace(). Otherwise we don't report the error but
+ * pretend ->real_parent untraces us right after return.
+ */
+ if (!ret && !(current->real_parent->flags & PF_EXITING)) {
+ current->ptrace = PT_PTRACED;
+ __ptrace_link(current, current->real_parent);
+ }
+ }
+ write_unlock_irq(&tasklist_lock);
+
+ return ret;
+}
+
/*
* Called with irqs disabled, returns true if childs should reap themselves.
*/
* or self-reaping. Do notification now if it would have happened earlier.
* If it should reap itself, return true.
*
- * If it's our own child, there is no notification to do.
- * But if our normal children self-reap, then this child
- * was prevented by ptrace and we must reap it now.
+ * If it's our own child, there is no notification to do. But if our normal
+ * children self-reap, then this child was prevented by ptrace and we must
+ * reap it now, in that case we must also wake up sub-threads sleeping in
+ * do_wait().
*/
static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
{
if (!task_detached(p) && thread_group_empty(p)) {
if (!same_thread_group(p->real_parent, tracer))
do_notify_parent(p, p->exit_signal);
- else if (ignoring_children(tracer->sighand))
+ else if (ignoring_children(tracer->sighand)) {
+ __wake_up_parent(p, tracer);
p->exit_signal = -1;
+ }
}
if (task_detached(p)) {
/* Mark it as in the process of being reaped. */
return false;
}
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
{
bool dead = false;
}
/*
- * Detach all tasks we were using ptrace on.
+ * Detach all tasks we were using ptrace on. Called with tasklist held
+ * for writing, and returns with it held too. But note it can release
+ * and reacquire the lock.
*/
void exit_ptrace(struct task_struct *tracer)
+ __releases(&tasklist_lock)
+ __acquires(&tasklist_lock)
{
struct task_struct *p, *n;
LIST_HEAD(ptrace_dead);
- write_lock_irq(&tasklist_lock);
+ if (likely(list_empty(&tracer->ptraced)))
+ return;
+
list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
if (__ptrace_detach(tracer, p))
list_add(&p->ptrace_entry, &ptrace_dead);
}
- write_unlock_irq(&tasklist_lock);
+ write_unlock_irq(&tasklist_lock);
BUG_ON(!list_empty(&tracer->ptraced));
list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
release_task(p);
}
+
+ write_lock_irq(&tasklist_lock);
}
int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
return copied;
}
-static int ptrace_setoptions(struct task_struct *child, long data)
+static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
child->ptrace &= ~PT_TRACE_MASK;
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
{
+ unsigned long flags;
int error = -ESRCH;
- read_lock(&tasklist_lock);
- if (likely(child->sighand != NULL)) {
+ if (lock_task_sighand(child, &flags)) {
error = -EINVAL;
- spin_lock_irq(&child->sighand->siglock);
if (likely(child->last_siginfo != NULL)) {
*info = *child->last_siginfo;
error = 0;
}
- spin_unlock_irq(&child->sighand->siglock);
+ unlock_task_sighand(child, &flags);
}
- read_unlock(&tasklist_lock);
return error;
}
static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
{
+ unsigned long flags;
int error = -ESRCH;
- read_lock(&tasklist_lock);
- if (likely(child->sighand != NULL)) {
+ if (lock_task_sighand(child, &flags)) {
error = -EINVAL;
- spin_lock_irq(&child->sighand->siglock);
if (likely(child->last_siginfo != NULL)) {
*child->last_siginfo = *info;
error = 0;
}
- spin_unlock_irq(&child->sighand->siglock);
+ unlock_task_sighand(child, &flags);
}
- read_unlock(&tasklist_lock);
return error;
}
#define is_sysemu_singlestep(request) 0
#endif
-static int ptrace_resume(struct task_struct *child, long request, long data)
+static int ptrace_resume(struct task_struct *child, long request,
+ unsigned long data)
{
if (!valid_signal(data))
return -EIO;
return 0;
}
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+
+static const struct user_regset *
+find_regset(const struct user_regset_view *view, unsigned int type)
+{
+ const struct user_regset *regset;
+ int n;
+
+ for (n = 0; n < view->n; ++n) {
+ regset = view->regsets + n;
+ if (regset->core_note_type == type)
+ return regset;
+ }
+
+ return NULL;
+}
+
+static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
+ struct iovec *kiov)
+{
+ const struct user_regset_view *view = task_user_regset_view(task);
+ const struct user_regset *regset = find_regset(view, type);
+ int regset_no;
+
+ if (!regset || (kiov->iov_len % regset->size) != 0)
+ return -EINVAL;
+
+ regset_no = regset - view->regsets;
+ kiov->iov_len = min(kiov->iov_len,
+ (__kernel_size_t) (regset->n * regset->size));
+
+ if (req == PTRACE_GETREGSET)
+ return copy_regset_to_user(task, view, regset_no, 0,
+ kiov->iov_len, kiov->iov_base);
+ else
+ return copy_regset_from_user(task, view, regset_no, 0,
+ kiov->iov_len, kiov->iov_base);
+}
+
+#endif
+
int ptrace_request(struct task_struct *child, long request,
- long addr, long data)
+ unsigned long addr, unsigned long data)
{
int ret = -EIO;
siginfo_t siginfo;
+ void __user *datavp = (void __user *) data;
+ unsigned long __user *datalp = datavp;
switch (request) {
case PTRACE_PEEKTEXT:
ret = ptrace_setoptions(child, data);
break;
case PTRACE_GETEVENTMSG:
- ret = put_user(child->ptrace_message, (unsigned long __user *) data);
+ ret = put_user(child->ptrace_message, datalp);
break;
case PTRACE_GETSIGINFO:
ret = ptrace_getsiginfo(child, &siginfo);
if (!ret)
- ret = copy_siginfo_to_user((siginfo_t __user *) data,
- &siginfo);
+ ret = copy_siginfo_to_user(datavp, &siginfo);
break;
case PTRACE_SETSIGINFO:
- if (copy_from_user(&siginfo, (siginfo_t __user *) data,
- sizeof siginfo))
+ if (copy_from_user(&siginfo, datavp, sizeof siginfo))
ret = -EFAULT;
else
ret = ptrace_setsiginfo(child, &siginfo);
ret = ptrace_detach(child, data);
break;
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+ case PTRACE_GETFDPIC: {
+ struct mm_struct *mm = get_task_mm(child);
+ unsigned long tmp = 0;
+
+ ret = -ESRCH;
+ if (!mm)
+ break;
+
+ switch (addr) {
+ case PTRACE_GETFDPIC_EXEC:
+ tmp = mm->context.exec_fdpic_loadmap;
+ break;
+ case PTRACE_GETFDPIC_INTERP:
+ tmp = mm->context.interp_fdpic_loadmap;
+ break;
+ default:
+ break;
+ }
+ mmput(mm);
+
+ ret = put_user(tmp, datalp);
+ break;
+ }
+#endif
+
#ifdef PTRACE_SINGLESTEP
case PTRACE_SINGLESTEP:
#endif
return 0;
return ptrace_resume(child, request, SIGKILL);
- default:
- break;
- }
-
- return ret;
-}
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+ case PTRACE_GETREGSET:
+ case PTRACE_SETREGSET:
+ {
+ struct iovec kiov;
+ struct iovec __user *uiov = datavp;
-/**
- * ptrace_traceme -- helper for PTRACE_TRACEME
- *
- * Performs checks and sets PT_PTRACED.
- * Should be used by all ptrace implementations for PTRACE_TRACEME.
- */
-int ptrace_traceme(void)
-{
- int ret = -EPERM;
-
- /*
- * Are we already being traced?
- */
-repeat:
- task_lock(current);
- if (!(current->ptrace & PT_PTRACED)) {
- /*
- * See ptrace_attach() comments about the locking here.
- */
- unsigned long flags;
- if (!write_trylock_irqsave(&tasklist_lock, flags)) {
- task_unlock(current);
- do {
- cpu_relax();
- } while (!write_can_lock(&tasklist_lock));
- goto repeat;
- }
-
- ret = security_ptrace_traceme(current->parent);
+ if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+ return -EFAULT;
- /*
- * Check PF_EXITING to ensure ->real_parent has not passed
- * exit_ptrace(). Otherwise we don't report the error but
- * pretend ->real_parent untraces us right after return.
- */
- if (!ret && !(current->real_parent->flags & PF_EXITING)) {
- current->ptrace |= PT_PTRACED;
- __ptrace_link(current, current->real_parent);
- }
+ if (__get_user(kiov.iov_base, &uiov->iov_base) ||
+ __get_user(kiov.iov_len, &uiov->iov_len))
+ return -EFAULT;
- write_unlock_irqrestore(&tasklist_lock, flags);
+ ret = ptrace_regset(child, request, addr, &kiov);
+ if (!ret)
+ ret = __put_user(kiov.iov_len, &uiov->iov_len);
+ break;
}
- task_unlock(current);
+#endif
+ default:
+ break;
+ }
+
return ret;
}
-/**
- * ptrace_get_task_struct -- grab a task struct reference for ptrace
- * @pid: process id to grab a task_struct reference of
- *
- * This function is a helper for ptrace implementations. It checks
- * permissions and then grabs a task struct for use of the actual
- * ptrace implementation.
- *
- * Returns the task_struct for @pid or an ERR_PTR() on failure.
- */
-struct task_struct *ptrace_get_task_struct(pid_t pid)
+static struct task_struct *ptrace_get_task_struct(pid_t pid)
{
struct task_struct *child;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
child = find_task_by_vpid(pid);
if (child)
get_task_struct(child);
+ rcu_read_unlock();
- read_unlock(&tasklist_lock);
if (!child)
return ERR_PTR(-ESRCH);
return child;
#define arch_ptrace_attach(child) do { } while (0)
#endif
-SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
+SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
+ unsigned long, data)
{
struct task_struct *child;
long ret;
- /*
- * This lock_kernel fixes a subtle race with suid exec
- */
- lock_kernel();
if (request == PTRACE_TRACEME) {
ret = ptrace_traceme();
if (!ret)
out_put_task_struct:
put_task_struct(child);
out:
- unlock_kernel();
return ret;
}
-int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data)
+int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
+ unsigned long data)
{
unsigned long tmp;
int copied;
return put_user(tmp, (unsigned long __user *)data);
}
-int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data)
+int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
+ unsigned long data)
{
int copied;
else
ret = ptrace_setsiginfo(child, &siginfo);
break;
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+ case PTRACE_GETREGSET:
+ case PTRACE_SETREGSET:
+ {
+ struct iovec kiov;
+ struct compat_iovec __user *uiov =
+ (struct compat_iovec __user *) datap;
+ compat_uptr_t ptr;
+ compat_size_t len;
+
+ if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+ return -EFAULT;
+
+ if (__get_user(ptr, &uiov->iov_base) ||
+ __get_user(len, &uiov->iov_len))
+ return -EFAULT;
+
+ kiov.iov_base = compat_ptr(ptr);
+ kiov.iov_len = len;
+
+ ret = ptrace_regset(child, request, addr, &kiov);
+ if (!ret)
+ ret = __put_user(kiov.iov_len, &uiov->iov_len);
+ break;
+ }
+#endif
default:
ret = ptrace_request(child, request, addr, data);
struct task_struct *child;
long ret;
- /*
- * This lock_kernel fixes a subtle race with suid exec
- */
- lock_kernel();
if (request == PTRACE_TRACEME) {
ret = ptrace_traceme();
goto out;
out_put_task_struct:
put_task_struct(child);
out:
- unlock_kernel();
return ret;
}
#endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+ if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+ return 0;
+
+ return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+ if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+ flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
Code Review / linux-2.6.git / blobdiff