1 files changed, 137 insertions, 67 deletions

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index f34d798ef4a2..7a81fc071344 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
 
 
 /*
@@ -37,35 +38,33 @@ 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.
- */
-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)
 {
@@ -75,8 +74,27 @@ void __ptrace_unlink(struct task_struct *child)
 	child->parent = child->real_parent;
 	list_del_init(&child->ptrace_entry);
 
-	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);
 }
 
 /*
@@ -95,16 +113,14 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 	 */
 	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);
@@ -134,21 +150,24 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 		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_access_check(task, mode);
@@ -163,8 +182,9 @@ 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;
 
 	audit_ptrace(task);
@@ -181,7 +201,7 @@ int ptrace_attach(struct task_struct *task)
 	 * 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);
@@ -198,18 +218,48 @@ int ptrace_attach(struct task_struct *task)
 		goto unlock_tasklist;
 
 	task->ptrace = PT_PTRACED;
-	if (capable(CAP_SYS_PTRACE))
+	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);
 
+	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->cred_guard_mutex);
+	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;
 }
 
@@ -219,7 +269,7 @@ 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;
 
@@ -293,7 +343,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 	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;
 
@@ -312,8 +362,6 @@ 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);
 
@@ -329,6 +377,8 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
  * 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);
@@ -402,7 +452,7 @@ 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;
 
@@ -481,7 +531,8 @@ 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;
@@ -558,10 +609,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
 #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:
@@ -578,19 +631,17 @@ 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_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);
@@ -621,7 +672,7 @@ int ptrace_request(struct task_struct *child, long request,
 		}
 		mmput(mm);
 
-		ret = put_user(tmp, (unsigned long __user *) data);
+		ret = put_user(tmp, datalp);
 		break;
 	}
 #endif
@@ -650,7 +701,7 @@ int ptrace_request(struct task_struct *child, long request,
 	case PTRACE_SETREGSET:
 	{
 		struct iovec kiov;
-		struct iovec __user *uiov = (struct iovec __user *) data;
+		struct iovec __user *uiov = datavp;
 
 		if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
 			return -EFAULT;
@@ -691,7 +742,8 @@ 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;
@@ -732,7 +784,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 	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;
@@ -743,7 +796,8 @@ 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;
 
@@ -870,3 +924,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	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 */