1 files changed, 601 insertions, 141 deletions

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 23bd09cd042..adf98622cb3 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -8,21 +8,31 @@
  */
 
 #include <linux/capability.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/errno.h>
 #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/uio.h>
 #include <linux/audit.h>
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/cn_proc.h>
+#include <linux/compat.h>
+
 
+static int ptrace_trapping_sleep_fn(void *flags)
+{
+	schedule();
+	return 0;
+}
 
 /*
  * ptrace a task: make the debugger its new parent and
@@ -37,53 +47,135 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 	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.
+/**
+ * __ptrace_unlink - unlink ptracee and restore its execution state
+ * @child: ptracee to be unlinked
+ *
+ * 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)
  */
-static void ptrace_untrace(struct task_struct *child)
+void __ptrace_unlink(struct task_struct *child)
 {
+	BUG_ON(!child->ptrace);
+
+	child->ptrace = 0;
+	child->parent = child->real_parent;
+	list_del_init(&child->ptrace_entry);
+
 	spin_lock(&child->sighand->siglock);
-	if (task_is_traced(child)) {
+
+	/*
+	 * Clear all pending traps and TRAPPING.  TRAPPING should be
+	 * cleared regardless of JOBCTL_STOP_PENDING.  Do it explicitly.
+	 */
+	task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK);
+	task_clear_jobctl_trapping(child);
+
+	/*
+	 * Reinstate JOBCTL_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->jobctl |= JOBCTL_STOP_PENDING;
+
 		/*
-		 * If the group stop is completed or in progress,
-		 * this thread was already counted as stopped.
+		 * This is only possible if this thread was cloned by the
+		 * traced task running in the stopped group, set the signal
+		 * for the future reports.
+		 * FIXME: we should change ptrace_init_task() to handle this
+		 * case.
 		 */
-		if (child->signal->flags & SIGNAL_STOP_STOPPED ||
-		    child->signal->group_stop_count)
-			__set_task_state(child, TASK_STOPPED);
-		else
-			signal_wake_up(child, 1);
+		if (!(child->jobctl & JOBCTL_STOP_SIGMASK))
+			child->jobctl |= SIGSTOP;
 	}
+
+	/*
+	 * 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->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child))
+		ptrace_signal_wake_up(child, true);
+
 	spin_unlock(&child->sighand->siglock);
 }
 
-/*
- * unptrace a task: move it back to its original parent and
- * remove it from the ptrace list.
- *
- * Must be called with the tasklist lock write-held.
- */
-void __ptrace_unlink(struct task_struct *child)
+/* Ensure that nothing can wake it up, even SIGKILL */
+static bool ptrace_freeze_traced(struct task_struct *task)
 {
-	BUG_ON(!child->ptrace);
+	bool ret = false;
 
-	child->ptrace = 0;
-	child->parent = child->real_parent;
-	list_del_init(&child->ptrace_entry);
+	/* Lockless, nobody but us can set this flag */
+	if (task->jobctl & JOBCTL_LISTENING)
+		return ret;
 
-	arch_ptrace_untrace(child);
-	if (task_is_traced(child))
-		ptrace_untrace(child);
+	spin_lock_irq(&task->sighand->siglock);
+	if (task_is_traced(task) && !__fatal_signal_pending(task)) {
+		task->state = __TASK_TRACED;
+		ret = true;
+	}
+	spin_unlock_irq(&task->sighand->siglock);
+
+	return ret;
 }
 
-/*
- * Check that we have indeed attached to the thing..
+static void ptrace_unfreeze_traced(struct task_struct *task)
+{
+	if (task->state != __TASK_TRACED)
+		return;
+
+	WARN_ON(!task->ptrace || task->parent != current);
+
+	spin_lock_irq(&task->sighand->siglock);
+	if (__fatal_signal_pending(task))
+		wake_up_state(task, __TASK_TRACED);
+	else
+		task->state = TASK_TRACED;
+	spin_unlock_irq(&task->sighand->siglock);
+}
+
+/**
+ * ptrace_check_attach - check whether ptracee is ready for ptrace operation
+ * @child: ptracee to check for
+ * @ignore_state: don't check whether @child is currently %TASK_TRACED
+ *
+ * Check whether @child is being ptraced by %current and ready for further
+ * ptrace operations.  If @ignore_state is %false, @child also should be in
+ * %TASK_TRACED state and on return the child is guaranteed to be traced
+ * and not executing.  If @ignore_state is %true, @child can be in any
+ * state.
+ *
+ * CONTEXT:
+ * Grabs and releases tasklist_lock and @child->sighand->siglock.
+ *
+ * RETURNS:
+ * 0 on success, -ESRCH if %child is not ready.
  */
-int ptrace_check_attach(struct task_struct *child, int kill)
+static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 {
 	int ret = -ESRCH;
 
@@ -95,29 +187,42 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 	 * be changed by us so it's not changing right after this.
 	 */
 	read_lock(&tasklist_lock);
-	if ((child->ptrace & PT_PTRACED) && child->parent == current) {
-		ret = 0;
+	if (child->ptrace && child->parent == current) {
+		WARN_ON(child->state == __TASK_TRACED);
 		/*
 		 * 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;
-		spin_unlock_irq(&child->sighand->siglock);
+		if (ignore_state || ptrace_freeze_traced(child))
+			ret = 0;
 	}
 	read_unlock(&tasklist_lock);
 
-	if (!ret && !kill)
-		ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
+	if (!ret && !ignore_state) {
+		if (!wait_task_inactive(child, __TASK_TRACED)) {
+			/*
+			 * This can only happen if may_ptrace_stop() fails and
+			 * ptrace_stop() changes ->state back to TASK_RUNNING,
+			 * so we should not worry about leaking __TASK_TRACED.
+			 */
+			WARN_ON(child->state == __TASK_TRACED);
+			ret = -ESRCH;
+		}
+	}
 
-	/* All systems go.. */
 	return ret;
 }
 
-int __ptrace_may_access(struct task_struct *task, unsigned int mode)
+static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
+{
+	if (mode & PTRACE_MODE_NOAUDIT)
+		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
+	else
+		return has_ns_capability(current, ns, CAP_SYS_PTRACE);
+}
+
+/* Returns 0 on success, -errno on denial. */
+static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	const struct cred *cred = current_cred(), *tcred;
 
@@ -131,26 +236,33 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	 */
 	int dumpable = 0;
 	/* Don't let security modules deny introspection */
-	if (task == current)
+	if (same_thread_group(task, current))
 		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 (uid_eq(cred->uid, tcred->euid) &&
+	    uid_eq(cred->uid, tcred->suid) &&
+	    uid_eq(cred->uid, tcred->uid)  &&
+	    gid_eq(cred->gid, tcred->egid) &&
+	    gid_eq(cred->gid, tcred->sgid) &&
+	    gid_eq(cred->gid, tcred->gid))
+		goto ok;
+	if (ptrace_has_cap(tcred->user_ns, mode))
+		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))
+	rcu_read_lock();
+	if (dumpable != SUID_DUMP_USER &&
+	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+		rcu_read_unlock();
 		return -EPERM;
+	}
+	rcu_read_unlock();
 
 	return security_ptrace_access_check(task, mode);
 }
@@ -164,10 +276,24 @@ 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, long request,
+			 unsigned long addr,
+			 unsigned long flags)
 {
+	bool seize = (request == PTRACE_SEIZE);
 	int retval;
 
+	retval = -EIO;
+	if (seize) {
+		if (addr != 0)
+			goto out;
+		if (flags & ~(unsigned long)PTRACE_O_MASK)
+			goto out;
+		flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT);
+	} else {
+		flags = PT_PTRACED;
+	}
+
 	audit_ptrace(task);
 
 	retval = -EPERM;
@@ -178,11 +304,11 @@ int ptrace_attach(struct task_struct *task)
 
 	/*
 	 * Protect exec's credential calculations against our interference;
-	 * interference; SUID, SGID and LSM creds get determined differently
+	 * SUID, SGID and LSM creds get determined differently
 	 * under ptrace.
 	 */
 	retval = -ERESTARTNOINTR;
-	if (mutex_lock_interruptible(&task->cred_guard_mutex))
+	if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
 		goto out;
 
 	task_lock(task);
@@ -198,19 +324,57 @@ int ptrace_attach(struct task_struct *task)
 	if (task->ptrace)
 		goto unlock_tasklist;
 
-	task->ptrace = PT_PTRACED;
-	if (capable(CAP_SYS_PTRACE))
-		task->ptrace |= PT_PTRACE_CAP;
+	if (seize)
+		flags |= PT_SEIZED;
+	rcu_read_lock();
+	if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
+		flags |= PT_PTRACE_CAP;
+	rcu_read_unlock();
+	task->ptrace = flags;
 
 	__ptrace_link(task, current);
-	send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
+
+	/* SEIZE doesn't trap tracee on attach */
+	if (!seize)
+		send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
+
+	spin_lock(&task->sighand->siglock);
+
+	/*
+	 * If the task is already STOPPED, set JOBCTL_TRAP_STOP 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_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
+		signal_wake_up_state(task, __TASK_STOPPED);
+
+	spin_unlock(&task->sighand->siglock);
 
 	retval = 0;
 unlock_tasklist:
 	write_unlock_irq(&tasklist_lock);
 unlock_creds:
-	mutex_unlock(&task->cred_guard_mutex);
+	mutex_unlock(&task->signal->cred_guard_mutex);
 out:
+	if (!retval) {
+		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
+			    ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE);
+		proc_ptrace_connector(task, PTRACE_ATTACH);
+	}
+
 	return retval;
 }
 
@@ -220,7 +384,7 @@ out:
  * Performs checks and sets PT_PTRACED.
  * Should be used by all ptrace implementations for PTRACE_TRACEME.
  */
-int ptrace_traceme(void)
+static int ptrace_traceme(void)
 {
 	int ret = -EPERM;
 
@@ -273,28 +437,30 @@ static int ignoring_children(struct sighand_struct *sigh)
  */
 static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 {
+	bool dead;
+
 	__ptrace_unlink(p);
 
-	if (p->exit_state == EXIT_ZOMBIE) {
-		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)) {
-				__wake_up_parent(p, tracer);
-				p->exit_signal = -1;
-			}
-		}
-		if (task_detached(p)) {
-			/* Mark it as in the process of being reaped. */
-			p->exit_state = EXIT_DEAD;
-			return true;
+	if (p->exit_state != EXIT_ZOMBIE)
+		return false;
+
+	dead = !thread_group_leader(p);
+
+	if (!dead && thread_group_empty(p)) {
+		if (!same_thread_group(p->real_parent, tracer))
+			dead = do_notify_parent(p, p->exit_signal);
+		else if (ignoring_children(tracer->sighand)) {
+			__wake_up_parent(p, tracer);
+			dead = true;
 		}
 	}
-
-	return false;
+	/* Mark it as in the process of being reaped. */
+	if (dead)
+		p->exit_state = EXIT_DEAD;
+	return dead;
 }
 
-int ptrace_detach(struct task_struct *child, unsigned int data)
+static int ptrace_detach(struct task_struct *child, unsigned int data)
 {
 	bool dead = false;
 
@@ -313,11 +479,10 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 	if (child->ptrace) {
 		child->exit_code = data;
 		dead = __ptrace_detach(current, child);
-		if (!child->exit_state)
-			wake_up_process(child);
 	}
 	write_unlock_irq(&tasklist_lock);
 
+	proc_ptrace_connector(child, PTRACE_DETACH);
 	if (unlikely(dead))
 		release_task(child);
 
@@ -325,26 +490,37 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 }
 
 /*
- * 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 (unlikely(p->ptrace & PT_EXITKILL))
+			send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
+
 		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)
@@ -397,32 +573,20 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
 	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;
-
-	if (data & PTRACE_O_TRACESYSGOOD)
-		child->ptrace |= PT_TRACESYSGOOD;
-
-	if (data & PTRACE_O_TRACEFORK)
-		child->ptrace |= PT_TRACE_FORK;
-
-	if (data & PTRACE_O_TRACEVFORK)
-		child->ptrace |= PT_TRACE_VFORK;
+	unsigned flags;
 
-	if (data & PTRACE_O_TRACECLONE)
-		child->ptrace |= PT_TRACE_CLONE;
+	if (data & ~(unsigned long)PTRACE_O_MASK)
+		return -EINVAL;
 
-	if (data & PTRACE_O_TRACEEXEC)
-		child->ptrace |= PT_TRACE_EXEC;
+	/* Avoid intermediate state when all opts are cleared */
+	flags = child->ptrace;
+	flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT);
+	flags |= (data << PT_OPT_FLAG_SHIFT);
+	child->ptrace = flags;
 
-	if (data & PTRACE_O_TRACEVFORKDONE)
-		child->ptrace |= PT_TRACE_VFORK_DONE;
-
-	if (data & PTRACE_O_TRACEEXIT)
-		child->ptrace |= PT_TRACE_EXIT;
-
-	return (data & ~PTRACE_O_MASK) ? -EINVAL : 0;
+	return 0;
 }
 
 static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
@@ -457,6 +621,83 @@ static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
 	return error;
 }
 
+static int ptrace_peek_siginfo(struct task_struct *child,
+				unsigned long addr,
+				unsigned long data)
+{
+	struct ptrace_peeksiginfo_args arg;
+	struct sigpending *pending;
+	struct sigqueue *q;
+	int ret, i;
+
+	ret = copy_from_user(&arg, (void __user *) addr,
+				sizeof(struct ptrace_peeksiginfo_args));
+	if (ret)
+		return -EFAULT;
+
+	if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED)
+		return -EINVAL; /* unknown flags */
+
+	if (arg.nr < 0)
+		return -EINVAL;
+
+	if (arg.flags & PTRACE_PEEKSIGINFO_SHARED)
+		pending = &child->signal->shared_pending;
+	else
+		pending = &child->pending;
+
+	for (i = 0; i < arg.nr; ) {
+		siginfo_t info;
+		s32 off = arg.off + i;
+
+		spin_lock_irq(&child->sighand->siglock);
+		list_for_each_entry(q, &pending->list, list) {
+			if (!off--) {
+				copy_siginfo(&info, &q->info);
+				break;
+			}
+		}
+		spin_unlock_irq(&child->sighand->siglock);
+
+		if (off >= 0) /* beyond the end of the list */
+			break;
+
+#ifdef CONFIG_COMPAT
+		if (unlikely(is_compat_task())) {
+			compat_siginfo_t __user *uinfo = compat_ptr(data);
+
+			if (copy_siginfo_to_user32(uinfo, &info) ||
+			    __put_user(info.si_code, &uinfo->si_code)) {
+				ret = -EFAULT;
+				break;
+			}
+
+		} else
+#endif
+		{
+			siginfo_t __user *uinfo = (siginfo_t __user *) data;
+
+			if (copy_siginfo_to_user(uinfo, &info) ||
+			    __put_user(info.si_code, &uinfo->si_code)) {
+				ret = -EFAULT;
+				break;
+			}
+		}
+
+		data += sizeof(siginfo_t);
+		i++;
+
+		if (signal_pending(current))
+			break;
+
+		cond_resched();
+	}
+
+	if (i > 0)
+		return i;
+
+	return ret;
+}
 
 #ifdef PTRACE_SINGLESTEP
 #define is_singlestep(request)		((request) == PTRACE_SINGLESTEP)
@@ -476,7 +717,8 @@ static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
 #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;
@@ -506,16 +748,67 @@ static int ptrace_resume(struct task_struct *child, long request, long data)
 	}
 
 	child->exit_code = data;
-	wake_up_process(child);
+	wake_up_state(child, __TASK_TRACED);
 
 	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);
+}
+
+/*
+ * This is declared in linux/regset.h and defined in machine-dependent
+ * code.  We put the export here, near the primary machine-neutral use,
+ * to ensure no machine forgets it.
+ */
+EXPORT_SYMBOL_GPL(task_user_regset_view);
+#endif
+
 int ptrace_request(struct task_struct *child, long request,
-		   long addr, long data)
+		   unsigned long addr, unsigned long data)
 {
+	bool seized = child->ptrace & PT_SEIZED;
 	int ret = -EIO;
-	siginfo_t siginfo;
+	siginfo_t siginfo, *si;
+	void __user *datavp = (void __user *) data;
+	unsigned long __user *datalp = datavp;
+	unsigned long flags;
 
 	switch (request) {
 	case PTRACE_PEEKTEXT:
@@ -532,28 +825,150 @@ int ptrace_request(struct task_struct *child, long request,
 		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_PEEKSIGINFO:
+		ret = ptrace_peek_siginfo(child, addr, data);
 		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);
 		break;
 
+	case PTRACE_GETSIGMASK:
+		if (addr != sizeof(sigset_t)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t)))
+			ret = -EFAULT;
+		else
+			ret = 0;
+
+		break;
+
+	case PTRACE_SETSIGMASK: {
+		sigset_t new_set;
+
+		if (addr != sizeof(sigset_t)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) {
+			ret = -EFAULT;
+			break;
+		}
+
+		sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP));
+
+		/*
+		 * Every thread does recalc_sigpending() after resume, so
+		 * retarget_shared_pending() and recalc_sigpending() are not
+		 * called here.
+		 */
+		spin_lock_irq(&child->sighand->siglock);
+		child->blocked = new_set;
+		spin_unlock_irq(&child->sighand->siglock);
+
+		ret = 0;
+		break;
+	}
+
+	case PTRACE_INTERRUPT:
+		/*
+		 * Stop tracee without any side-effect on signal or job
+		 * control.  At least one trap is guaranteed to happen
+		 * after this request.  If @child is already trapped, the
+		 * current trap is not disturbed and another trap will
+		 * happen after the current trap is ended with PTRACE_CONT.
+		 *
+		 * The actual trap might not be PTRACE_EVENT_STOP trap but
+		 * the pending condition is cleared regardless.
+		 */
+		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
+			break;
+
+		/*
+		 * INTERRUPT doesn't disturb existing trap sans one
+		 * exception.  If ptracer issued LISTEN for the current
+		 * STOP, this INTERRUPT should clear LISTEN and re-trap
+		 * tracee into STOP.
+		 */
+		if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
+			ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
+
+		unlock_task_sighand(child, &flags);
+		ret = 0;
+		break;
+
+	case PTRACE_LISTEN:
+		/*
+		 * Listen for events.  Tracee must be in STOP.  It's not
+		 * resumed per-se but is not considered to be in TRACED by
+		 * wait(2) or ptrace(2).  If an async event (e.g. group
+		 * stop state change) happens, tracee will enter STOP trap
+		 * again.  Alternatively, ptracer can issue INTERRUPT to
+		 * finish listening and re-trap tracee into STOP.
+		 */
+		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
+			break;
+
+		si = child->last_siginfo;
+		if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) {
+			child->jobctl |= JOBCTL_LISTENING;
+			/*
+			 * If NOTIFY is set, it means event happened between
+			 * start of this trap and now.  Trigger re-trap.
+			 */
+			if (child->jobctl & JOBCTL_TRAP_NOTIFY)
+				ptrace_signal_wake_up(child, true);
+			ret = 0;
+		}
+		unlock_task_sighand(child, &flags);
+		break;
+
 	case PTRACE_DETACH:	 /* detach a process that was attached. */
 		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
@@ -573,6 +988,25 @@ int ptrace_request(struct task_struct *child, long request,
 			return 0;
 		return ptrace_resume(child, request, SIGKILL);
 
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+	case PTRACE_GETREGSET:
+	case PTRACE_SETREGSET: {
+		struct iovec kiov;
+		struct iovec __user *uiov = datavp;
+
+		if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+			return -EFAULT;
+
+		if (__get_user(kiov.iov_base, &uiov->iov_base) ||
+		    __get_user(kiov.iov_len, &uiov->iov_len))
+			return -EFAULT;
+
+		ret = ptrace_regset(child, request, addr, &kiov);
+		if (!ret)
+			ret = __put_user(kiov.iov_len, &uiov->iov_len);
+		break;
+	}
+#endif
 	default:
 		break;
 	}
@@ -599,15 +1033,12 @@ static struct task_struct *ptrace_get_task_struct(pid_t pid)
 #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)
@@ -621,8 +1052,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 		goto out;
 	}
 
-	if (request == PTRACE_ATTACH) {
-		ret = ptrace_attach(child);
+	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
+		ret = ptrace_attach(child, request, addr, data);
 		/*
 		 * Some architectures need to do book-keeping after
 		 * a ptrace attach.
@@ -632,20 +1063,23 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 		goto out_put_task_struct;
 	}
 
-	ret = ptrace_check_attach(child, request == PTRACE_KILL);
+	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+				  request == PTRACE_INTERRUPT);
 	if (ret < 0)
 		goto out_put_task_struct;
 
 	ret = arch_ptrace(child, request, addr, data);
+	if (ret || request != PTRACE_DETACH)
+		ptrace_unfreeze_traced(child);
 
  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;
@@ -656,7 +1090,8 @@ int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data)
 	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;
 
@@ -711,6 +1146,32 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 		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);
@@ -719,16 +1180,12 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 	return ret;
 }
 
-asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
-				  compat_long_t addr, compat_long_t data)
+COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
+		       compat_long_t, addr, compat_long_t, 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;
@@ -740,8 +1197,8 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 		goto out;
 	}
 
-	if (request == PTRACE_ATTACH) {
-		ret = ptrace_attach(child);
+	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
+		ret = ptrace_attach(child, request, addr, data);
 		/*
 		 * Some architectures need to do book-keeping after
 		 * a ptrace attach.
@@ -751,14 +1208,17 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 		goto out_put_task_struct;
 	}
 
-	ret = ptrace_check_attach(child, request == PTRACE_KILL);
-	if (!ret)
+	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+				  request == PTRACE_INTERRUPT);
+	if (!ret) {
 		ret = compat_arch_ptrace(child, request, addr, data);
+		if (ret || request != PTRACE_DETACH)
+			ptrace_unfreeze_traced(child);
+	}
 
  out_put_task_struct:
 	put_task_struct(child);
  out:
-	unlock_kernel();
 	return ret;
 }
 #endif	/* CONFIG_COMPAT */