Merge branch 'ptrace' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc

* 'ptrace' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc: (39 commits)
  ptrace: do_wait(traced_leader_killed_by_mt_exec) can block forever
  ptrace: fix ptrace_signal() && STOP_DEQUEUED interaction
  connector: add an event for monitoring process tracers
  ptrace: dont send SIGSTOP on auto-attach if PT_SEIZED
  ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task()
  ptrace_init_task: initialize child->jobctl explicitly
  has_stopped_jobs: s/task_is_stopped/SIGNAL_STOP_STOPPED/
  ptrace: make former thread ID available via PTRACE_GETEVENTMSG after PTRACE_EVENT_EXEC stop
  ptrace: wait_consider_task: s/same_thread_group/ptrace_reparented/
  ptrace: kill real_parent_is_ptracer() in in favor of ptrace_reparented()
  ptrace: ptrace_reparented() should check same_thread_group()
  redefine thread_group_leader() as exit_signal >= 0
  do not change dead_task->exit_signal
  kill task_detached()
  reparent_leader: check EXIT_DEAD instead of task_detached()
  make do_notify_parent() __must_check, update the callers
  __ptrace_detach: avoid task_detached(), check do_notify_parent()
  kill tracehook_notify_death()
  make do_notify_parent() return bool
  ptrace: s/tracehook_tracer_task()/ptrace_parent()/
  ...

arch/s390/kernel/traps.c

@@ -331,7 +331,7 @@ void __kprobes do_per_trap(struct pt_regs *regs)
 {
 	if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP)
 		return;
-	if (tracehook_consider_fatal_signal(current, SIGTRAP))
+	if (current->ptrace)
 		force_sig(SIGTRAP, current);
 }
 
@@ -425,7 +425,7 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
 		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
 			return;
 		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
-			if (tracehook_consider_fatal_signal(current, SIGTRAP))
+			if (current->ptrace)
 				force_sig(SIGTRAP, current);
 			else
 				signal = SIGILL;

drivers/connector/cn_proc.c

@@ -28,6 +28,7 @@
 #include <linux/init.h>
 #include <linux/connector.h>
 #include <linux/gfp.h>
+#include <linux/ptrace.h>
 #include <asm/atomic.h>
 #include <asm/unaligned.h>
 
@@ -166,6 +167,40 @@ void proc_sid_connector(struct task_struct *task)
 	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
 }
 
+void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
+{
+	struct cn_msg *msg;
+	struct proc_event *ev;
+	struct timespec ts;
+	__u8 buffer[CN_PROC_MSG_SIZE];
+	struct task_struct *tracer;
+
+	if (atomic_read(&proc_event_num_listeners) < 1)
+		return;
+
+	msg = (struct cn_msg *)buffer;
+	ev = (struct proc_event *)msg->data;
+	get_seq(&msg->seq, &ev->cpu);
+	ktime_get_ts(&ts); /* get high res monotonic timestamp */
+	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->what = PROC_EVENT_PTRACE;
+	ev->event_data.ptrace.process_pid  = task->pid;
+	ev->event_data.ptrace.process_tgid = task->tgid;
+	if (ptrace_id == PTRACE_ATTACH) {
+		ev->event_data.ptrace.tracer_pid  = current->pid;
+		ev->event_data.ptrace.tracer_tgid = current->tgid;
+	} else if (ptrace_id == PTRACE_DETACH) {
+		ev->event_data.ptrace.tracer_pid  = 0;
+		ev->event_data.ptrace.tracer_tgid = 0;
+	} else
+		return;
+
+	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
+	msg->ack = 0; /* not used */
+	msg->len = sizeof(*ev);
+	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+}
+
 void proc_exit_connector(struct task_struct *task)
 {
 	struct cn_msg *msg;

fs/exec.c

@@ -963,9 +963,18 @@ static int de_thread(struct task_struct *tsk)
 		leader->group_leader = tsk;
 
 		tsk->exit_signal = SIGCHLD;
+		leader->exit_signal = -1;
 
 		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
 		leader->exit_state = EXIT_DEAD;
+
+		/*
+		 * We are going to release_task()->ptrace_unlink() silently,
+		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
+		 * the tracer wont't block again waiting for this thread.
+		 */
+		if (unlikely(leader->ptrace))
+			__wake_up_parent(leader, leader->parent);
 		write_unlock_irq(&tasklist_lock);
 
 		release_task(leader);
@@ -1225,7 +1234,12 @@ int check_unsafe_exec(struct linux_binprm *bprm)
 	unsigned n_fs;
 	int res = 0;
 
-	bprm->unsafe = tracehook_unsafe_exec(p);
+	if (p->ptrace) {
+		if (p->ptrace & PT_PTRACE_CAP)
+			bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP;
+		else
+			bprm->unsafe |= LSM_UNSAFE_PTRACE;
+	}
 
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
@@ -1353,6 +1367,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	unsigned int depth = bprm->recursion_depth;
 	int try,retval;
 	struct linux_binfmt *fmt;
+	pid_t old_pid;
 
 	retval = security_bprm_check(bprm);
 	if (retval)
@@ -1362,6 +1377,11 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	if (retval)
 		return retval;
 
+	/* Need to fetch pid before load_binary changes it */
+	rcu_read_lock();
+	old_pid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
+	rcu_read_unlock();
+
 	retval = -ENOENT;
 	for (try=0; try<2; try++) {
 		read_lock(&binfmt_lock);
@@ -1381,7 +1401,8 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			bprm->recursion_depth = depth;
 			if (retval >= 0) {
 				if (depth == 0)
-					tracehook_report_exec(fmt, bprm, regs);
+					ptrace_event(PTRACE_EVENT_EXEC,
+							old_pid);
 				put_binfmt(fmt);
 				allow_write_access(bprm->file);
 				if (bprm->file)
@@ -1769,7 +1790,7 @@ static int zap_process(struct task_struct *start, int exit_code)
 
 	t = start;
 	do {
-		task_clear_group_stop_pending(t);
+		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		if (t != current && t->mm) {
 			sigaddset(&t->pending.signal, SIGKILL);
 			signal_wake_up(t, 1);

fs/proc/array.c

@@ -172,7 +172,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
 	tpid = 0;
 	if (pid_alive(p)) {
-		struct task_struct *tracer = tracehook_tracer_task(p);
+		struct task_struct *tracer = ptrace_parent(p);
 		if (tracer)
 			tpid = task_pid_nr_ns(tracer, ns);
 	}

fs/proc/base.c

@@ -216,7 +216,7 @@ static struct mm_struct *__check_mem_permission(struct task_struct *task)
 	if (task_is_stopped_or_traced(task)) {
 		int match;
 		rcu_read_lock();
-		match = (tracehook_tracer_task(task) == current);
+		match = (ptrace_parent(task) == current);
 		rcu_read_unlock();
 		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
 			return mm;

include/linux/cn_proc.h

@@ -53,6 +53,7 @@ struct proc_event {
 		PROC_EVENT_UID  = 0x00000004,
 		PROC_EVENT_GID  = 0x00000040,
 		PROC_EVENT_SID  = 0x00000080,
+		PROC_EVENT_PTRACE = 0x00000100,
 		/* "next" should be 0x00000400 */
 		/* "last" is the last process event: exit */
 		PROC_EVENT_EXIT = 0x80000000
@@ -95,6 +96,13 @@ struct proc_event {
 			__kernel_pid_t process_tgid;
 		} sid;
 
+		struct ptrace_proc_event {
+			__kernel_pid_t process_pid;
+			__kernel_pid_t process_tgid;
+			__kernel_pid_t tracer_pid;
+			__kernel_pid_t tracer_tgid;
+		} ptrace;
+
 		struct exit_proc_event {
 			__kernel_pid_t process_pid;
 			__kernel_pid_t process_tgid;
@@ -109,6 +117,7 @@ void proc_fork_connector(struct task_struct *task);
 void proc_exec_connector(struct task_struct *task);
 void proc_id_connector(struct task_struct *task, int which_id);
 void proc_sid_connector(struct task_struct *task);
+void proc_ptrace_connector(struct task_struct *task, int which_id);
 void proc_exit_connector(struct task_struct *task);
 #else
 static inline void proc_fork_connector(struct task_struct *task)
@@ -124,6 +133,10 @@ static inline void proc_id_connector(struct task_struct *task,
 static inline void proc_sid_connector(struct task_struct *task)
 {}
 
+static inline void proc_ptrace_connector(struct task_struct *task,
+					 int ptrace_id)
+{}
+
 static inline void proc_exit_connector(struct task_struct *task)
 {}
 #endif	/* CONFIG_PROC_EVENTS */

include/linux/ptrace.h

@@ -47,6 +47,13 @@
 #define PTRACE_GETREGSET	0x4204
 #define PTRACE_SETREGSET	0x4205
 
+#define PTRACE_SEIZE		0x4206
+#define PTRACE_INTERRUPT	0x4207
+#define PTRACE_LISTEN		0x4208
+
+/* flags in @data for PTRACE_SEIZE */
+#define PTRACE_SEIZE_DEVEL	0x80000000 /* temp flag for development */
+
 /* options set using PTRACE_SETOPTIONS */
 #define PTRACE_O_TRACESYSGOOD	0x00000001
 #define PTRACE_O_TRACEFORK	0x00000002
@@ -65,6 +72,7 @@
 #define PTRACE_EVENT_EXEC	4
 #define PTRACE_EVENT_VFORK_DONE	5
 #define PTRACE_EVENT_EXIT	6
+#define PTRACE_EVENT_STOP	7
 
 #include <asm/ptrace.h>
 
@@ -77,16 +85,22 @@
  * flags.  When the a task is stopped the ptracer owns task->ptrace.
  */
 
+#define PT_SEIZED	0x00010000	/* SEIZE used, enable new behavior */
 #define PT_PTRACED	0x00000001
 #define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
 #define PT_TRACESYSGOOD	0x00000004
 #define PT_PTRACE_CAP	0x00000008	/* ptracer can follow suid-exec */
-#define PT_TRACE_FORK	0x00000010
-#define PT_TRACE_VFORK	0x00000020
-#define PT_TRACE_CLONE	0x00000040
-#define PT_TRACE_EXEC	0x00000080
-#define PT_TRACE_VFORK_DONE	0x00000100
-#define PT_TRACE_EXIT	0x00000200
+
+/* PT_TRACE_* event enable flags */
+#define PT_EVENT_FLAG_SHIFT	4
+#define PT_EVENT_FLAG(event)	(1 << (PT_EVENT_FLAG_SHIFT + (event) - 1))
+
+#define PT_TRACE_FORK		PT_EVENT_FLAG(PTRACE_EVENT_FORK)
+#define PT_TRACE_VFORK		PT_EVENT_FLAG(PTRACE_EVENT_VFORK)
+#define PT_TRACE_CLONE		PT_EVENT_FLAG(PTRACE_EVENT_CLONE)
+#define PT_TRACE_EXEC		PT_EVENT_FLAG(PTRACE_EVENT_EXEC)
+#define PT_TRACE_VFORK_DONE	PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE)
+#define PT_TRACE_EXIT		PT_EVENT_FLAG(PTRACE_EVENT_EXIT)
 
 #define PT_TRACE_MASK	0x000003f4
 
@@ -105,7 +119,7 @@ extern long arch_ptrace(struct task_struct *child, long request,
 extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
 extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len);
 extern void ptrace_disable(struct task_struct *);
-extern int ptrace_check_attach(struct task_struct *task, int kill);
+extern int ptrace_check_attach(struct task_struct *task, bool ignore_state);
 extern int ptrace_request(struct task_struct *child, long request,
 			  unsigned long addr, unsigned long data);
 extern void ptrace_notify(int exit_code);
@@ -122,7 +136,7 @@ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
 static inline int ptrace_reparented(struct task_struct *child)
 {
-	return child->real_parent != child->parent;
+	return !same_thread_group(child->real_parent, child->parent);
 }
 
 static inline void ptrace_unlink(struct task_struct *child)
@@ -137,36 +151,56 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
 			    unsigned long data);
 
 /**
- * task_ptrace - return %PT_* flags that apply to a task
- * @task:	pointer to &task_struct in question
+ * ptrace_parent - return the task that is tracing the given task
+ * @task: task to consider
  *
- * Returns the %PT_* flags that apply to @task.
+ * Returns %NULL if no one is tracing @task, or the &struct task_struct
+ * pointer to its tracer.
+ *
+ * Must called under rcu_read_lock().  The pointer returned might be kept
+ * live only by RCU.  During exec, this may be called with task_lock() held
+ * on @task, still held from when check_unsafe_exec() was called.
  */
-static inline int task_ptrace(struct task_struct *task)
+static inline struct task_struct *ptrace_parent(struct task_struct *task)
 {
-	return task->ptrace;
+	if (unlikely(task->ptrace))
+		return rcu_dereference(task->parent);
+	return NULL;
+}
+
+/**
+ * ptrace_event_enabled - test whether a ptrace event is enabled
+ * @task: ptracee of interest
+ * @event: %PTRACE_EVENT_* to test
+ *
+ * Test whether @event is enabled for ptracee @task.
+ *
+ * Returns %true if @event is enabled, %false otherwise.
+ */
+static inline bool ptrace_event_enabled(struct task_struct *task, int event)
+{
+	return task->ptrace & PT_EVENT_FLAG(event);
 }
 
 /**
  * ptrace_event - possibly stop for a ptrace event notification
- * @mask:	%PT_* bit to check in @current->ptrace
- * @event:	%PTRACE_EVENT_* value to report if @mask is set
+ * @event:	%PTRACE_EVENT_* value to report
  * @message:	value for %PTRACE_GETEVENTMSG to return
  *
- * This checks the @mask bit to see if ptrace wants stops for this event.
- * If so we stop, reporting @event and @message to the ptrace parent.
- *
- * Returns nonzero if we did a ptrace notification, zero if not.
+ * Check whether @event is enabled and, if so, report @event and @message
+ * to the ptrace parent.
  *
  * Called without locks.
  */
-static inline int ptrace_event(int mask, int event, unsigned long message)
+static inline void ptrace_event(int event, unsigned long message)
 {
-	if (mask && likely(!(current->ptrace & mask)))
-		return 0;
+	if (unlikely(ptrace_event_enabled(current, event))) {
 		current->ptrace_message = message;
 		ptrace_notify((event << 8) | SIGTRAP);
-	return 1;
+	} else if (event == PTRACE_EVENT_EXEC && unlikely(current->ptrace)) {
+		/* legacy EXEC report via SIGTRAP */
+		send_sig(SIGTRAP, current, 0);
+	}
 }
 
 /**
@@ -183,16 +217,24 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 {
 	INIT_LIST_HEAD(&child->ptrace_entry);
 	INIT_LIST_HEAD(&child->ptraced);
-	child->parent = child->real_parent;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	atomic_set(&child->ptrace_bp_refcnt, 1);
+#endif
+	child->jobctl = 0;
 	child->ptrace = 0;
-	if (unlikely(ptrace) && (current->ptrace & PT_PTRACED)) {
+	child->parent = child->real_parent;
+
+	if (unlikely(ptrace) && current->ptrace) {
 		child->ptrace = current->ptrace;
 		__ptrace_link(child, current->parent);
-	}
 
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	atomic_set(&child->ptrace_bp_refcnt, 1);
-#endif
+		if (child->ptrace & PT_SEIZED)
+			task_set_jobctl_pending(child, JOBCTL_TRAP_STOP);
+		else
+			sigaddset(&child->pending.signal, SIGSTOP);
+
+		set_tsk_thread_flag(child, TIF_SIGPENDING);
+	}
 }
 
 /**

include/linux/sched.h

@@ -1292,7 +1292,7 @@ struct task_struct {
 	int exit_state;
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
-	unsigned int group_stop;	/* GROUP_STOP_*, siglock protected */
+	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
 	/* ??? */
 	unsigned int personality;
 	unsigned did_exec:1;
@@ -1813,15 +1813,34 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define used_math() tsk_used_math(current)
 
 /*
- * task->group_stop flags
- */
-#define GROUP_STOP_SIGMASK	0xffff    /* signr of the last group stop */
-#define GROUP_STOP_PENDING	(1 << 16) /* task should stop for group stop */
-#define GROUP_STOP_CONSUME	(1 << 17) /* consume group stop count */
-#define GROUP_STOP_TRAPPING	(1 << 18) /* switching from STOPPED to TRACED */
-#define GROUP_STOP_DEQUEUED	(1 << 19) /* stop signal dequeued */
-
-extern void task_clear_group_stop_pending(struct task_struct *task);
+ * task->jobctl flags
+ */
+#define JOBCTL_STOP_SIGMASK	0xffff	/* signr of the last group stop */
+
+#define JOBCTL_STOP_DEQUEUED_BIT 16	/* stop signal dequeued */
+#define JOBCTL_STOP_PENDING_BIT	17	/* task should stop for group stop */
+#define JOBCTL_STOP_CONSUME_BIT	18	/* consume group stop count */
+#define JOBCTL_TRAP_STOP_BIT	19	/* trap for STOP */
+#define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
+#define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
+#define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
+
+#define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING	(1 << JOBCTL_LISTENING_BIT)
+
+#define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+
+extern bool task_set_jobctl_pending(struct task_struct *task,
+				    unsigned int mask);
+extern void task_clear_jobctl_trapping(struct task_struct *task);
+extern void task_clear_jobctl_pending(struct task_struct *task,
+				      unsigned int mask);
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -2151,7 +2170,7 @@ extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_
 extern int kill_pgrp(struct pid *pid, int sig, int priv);
 extern int kill_pid(struct pid *pid, int sig, int priv);
 extern int kill_proc_info(int, struct siginfo *, pid_t);
-extern int do_notify_parent(struct task_struct *, int);
+extern __must_check bool do_notify_parent(struct task_struct *, int);
 extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
 extern void force_sig(int, struct task_struct *);
 extern int send_sig(int, struct task_struct *, int);
@@ -2275,8 +2294,10 @@ static inline int get_nr_threads(struct task_struct *tsk)
 	return tsk->signal->nr_threads;
 }
 
-/* de_thread depends on thread_group_leader not being a pid based check */
-#define thread_group_leader(p)	(p == p->group_leader)
+static inline bool thread_group_leader(struct task_struct *p)
+{
+	return p->exit_signal >= 0;
+}
 
 /* Do to the insanities of de_thread it is possible for a process
  * to have the pid of the thread group leader without actually being
@@ -2309,11 +2330,6 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
-static inline int task_detached(struct task_struct *p)
-{
-	return p->exit_signal == -1;
-}
-
 /*
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also

include/linux/tracehook.h

@@ -51,27 +51,12 @@
 #include <linux/security.h>
 struct linux_binprm;
 
-/**
- * tracehook_expect_breakpoints - guess if task memory might be touched
- * @task:		current task, making a new mapping
- *
- * Return nonzero if @task is expected to want breakpoint insertion in
- * its memory at some point.  A zero return is no guarantee it won't
- * be done, but this is a hint that it's known to be likely.
- *
- * May be called with @task->mm->mmap_sem held for writing.
- */
-static inline int tracehook_expect_breakpoints(struct task_struct *task)
-{
-	return (task_ptrace(task) & PT_PTRACED) != 0;
-}
-
 /*
  * ptrace report for syscall entry and exit looks identical.
  */
 static inline void ptrace_report_syscall(struct pt_regs *regs)
 {
-	int ptrace = task_ptrace(current);
+	int ptrace = current->ptrace;
 
 	if (!(ptrace & PT_PTRACED))
 		return;
@@ -144,229 +129,6 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
 	ptrace_report_syscall(regs);
 }
 
-/**
- * tracehook_unsafe_exec - check for exec declared unsafe due to tracing
- * @task:		current task doing exec
- *
- * Return %LSM_UNSAFE_* bits applied to an exec because of tracing.
- *
- * @task->signal->cred_guard_mutex is held by the caller through the do_execve().
- */
-static inline int tracehook_unsafe_exec(struct task_struct *task)
-{
-	int unsafe = 0;
-	int ptrace = task_ptrace(task);
-	if (ptrace & PT_PTRACED) {
-		if (ptrace & PT_PTRACE_CAP)
-			unsafe |= LSM_UNSAFE_PTRACE_CAP;
-		else
-			unsafe |= LSM_UNSAFE_PTRACE;
-	}
-	return unsafe;
-}
-
-/**
- * tracehook_tracer_task - return the task that is tracing the given task
- * @tsk:		task to consider
- *
- * Returns NULL if no one is tracing @task, or the &struct task_struct
- * pointer to its tracer.
- *
- * Must called under rcu_read_lock().  The pointer returned might be kept
- * live only by RCU.  During exec, this may be called with task_lock()
- * held on @task, still held from when tracehook_unsafe_exec() was called.
- */
-static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk)
-{
-	if (task_ptrace(tsk) & PT_PTRACED)
-		return rcu_dereference(tsk->parent);
-	return NULL;
-}
-
-/**
- * tracehook_report_exec - a successful exec was completed
- * @fmt:		&struct linux_binfmt that performed the exec
- * @bprm:		&struct linux_binprm containing exec details
- * @regs:		user-mode register state
- *
- * An exec just completed, we are shortly going to return to user mode.
- * The freshly initialized register state can be seen and changed in @regs.
- * The name, file and other pointers in @bprm are still on hand to be
- * inspected, but will be freed as soon as this returns.
- *
- * Called with no locks, but with some kernel resources held live
- * and a reference on @fmt->module.
- */
-static inline void tracehook_report_exec(struct linux_binfmt *fmt,
-					 struct linux_binprm *bprm,
-					 struct pt_regs *regs)
-{
-	if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) &&
-	    unlikely(task_ptrace(current) & PT_PTRACED))
-		send_sig(SIGTRAP, current, 0);
-}
-
-/**
- * tracehook_report_exit - task has begun to exit
- * @exit_code:		pointer to value destined for @current->exit_code
- *
- * @exit_code points to the value passed to do_exit(), which tracing
- * might change here.  This is almost the first thing in do_exit(),
- * before freeing any resources or setting the %PF_EXITING flag.
- *
- * Called with no locks held.
- */
-static inline void tracehook_report_exit(long *exit_code)
-{
-	ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code);
-}
-
-/**
- * tracehook_prepare_clone - prepare for new child to be cloned
- * @clone_flags:	%CLONE_* flags from clone/fork/vfork system call
- *
- * This is called before a new user task is to be cloned.
- * Its return value will be passed to tracehook_finish_clone().
- *
- * Called with no locks held.
- */
-static inline int tracehook_prepare_clone(unsigned clone_flags)
-{
-	if (clone_flags & CLONE_UNTRACED)
-		return 0;
-
-	if (clone_flags & CLONE_VFORK) {
-		if (current->ptrace & PT_TRACE_VFORK)
-			return PTRACE_EVENT_VFORK;
-	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-		if (current->ptrace & PT_TRACE_CLONE)
-			return PTRACE_EVENT_CLONE;
-	} else if (current->ptrace & PT_TRACE_FORK)
-		return PTRACE_EVENT_FORK;
-
-	return 0;
-}
-
-/**
- * tracehook_finish_clone - new child created and being attached
- * @child:		new child task
- * @clone_flags:	%CLONE_* flags from clone/fork/vfork system call
- * @trace:		return value from tracehook_prepare_clone()
- *
- * This is called immediately after adding @child to its parent's children list.
- * The @trace value is that returned by tracehook_prepare_clone().
- *
- * Called with current's siglock and write_lock_irq(&tasklist_lock) held.
- */
-static inline void tracehook_finish_clone(struct task_struct *child,
-					  unsigned long clone_flags, int trace)
-{
-	ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace);
-}
-
-/**
- * tracehook_report_clone - in parent, new child is about to start running
- * @regs:		parent's user register state
- * @clone_flags:	flags from parent's system call
- * @pid:		new child's PID in the parent's namespace
- * @child:		new child task
- *
- * Called after a child is set up, but before it has been started running.
- * This is not a good place to block, because the child has not started
- * yet.  Suspend the child here if desired, and then block in
- * tracehook_report_clone_complete().  This must prevent the child from
- * self-reaping if tracehook_report_clone_complete() uses the @child
- * pointer; otherwise it might have died and been released by the time
- * tracehook_report_clone_complete() is called.
- *
- * Called with no locks held, but the child cannot run until this returns.
- */
-static inline void tracehook_report_clone(struct pt_regs *regs,
-					  unsigned long clone_flags,
-					  pid_t pid, struct task_struct *child)
-{
-	if (unlikely(task_ptrace(child))) {
-		/*
-		 * It doesn't matter who attached/attaching to this
-		 * task, the pending SIGSTOP is right in any case.
-		 */
-		sigaddset(&child->pending.signal, SIGSTOP);
-		set_tsk_thread_flag(child, TIF_SIGPENDING);
-	}
-}
-
-/**
- * tracehook_report_clone_complete - new child is running
- * @trace:		return value from tracehook_prepare_clone()
- * @regs:		parent's user register state
- * @clone_flags:	flags from parent's system call
- * @pid:		new child's PID in the parent's namespace
- * @child:		child task, already running
- *
- * This is called just after the child has started running.  This is
- * just before the clone/fork syscall returns, or blocks for vfork
- * child completion if @clone_flags has the %CLONE_VFORK bit set.
- * The @child pointer may be invalid if a self-reaping child died and
- * tracehook_report_clone() took no action to prevent it from self-reaping.
- *
- * Called with no locks held.
- */
-static inline void tracehook_report_clone_complete(int trace,
-						   struct pt_regs *regs,
-						   unsigned long clone_flags,
-						   pid_t pid,
-						   struct task_struct *child)
-{
-	if (unlikely(trace))
-		ptrace_event(0, trace, pid);
-}
-
-/**
- * tracehook_report_vfork_done - vfork parent's child has exited or exec'd
- * @child:		child task, already running
- * @pid:		new child's PID in the parent's namespace
- *
- * Called after a %CLONE_VFORK parent has waited for the child to complete.
- * The clone/vfork system call will return immediately after this.
- * The @child pointer may be invalid if a self-reaping child died and
- * tracehook_report_clone() took no action to prevent it from self-reaping.
- *
- * Called with no locks held.
- */
-static inline void tracehook_report_vfork_done(struct task_struct *child,
-					       pid_t pid)
-{
-	ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid);
-}
-
-/**
- * tracehook_prepare_release_task - task is being reaped, clean up tracing
- * @task:		task in %EXIT_DEAD state
- *
- * This is called in release_task() just before @task gets finally reaped
- * and freed.  This would be the ideal place to remove and clean up any
- * tracing-related state for @task.
- *
- * Called with no locks held.
- */
-static inline void tracehook_prepare_release_task(struct task_struct *task)
-{
-}
-
-/**
- * tracehook_finish_release_task - final tracing clean-up
- * @task:		task in %EXIT_DEAD state
- *
- * This is called in release_task() when @task is being in the middle of
- * being reaped.  After this, there must be no tracing entanglements.
- *
- * Called with write_lock_irq(&tasklist_lock) held.
- */
-static inline void tracehook_finish_release_task(struct task_struct *task)
-{
-	ptrace_release_task(task);
-}
-
 /**
  * tracehook_signal_handler - signal handler setup is complete
  * @sig:		number of signal being delivered
@@ -390,151 +152,6 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info,
 		ptrace_notify(SIGTRAP);
 }
 
-/**
- * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal
- * @task:		task receiving the signal
- * @sig:		signal number being sent
- *
- * Return zero iff tracing doesn't care to examine this ignored signal,
- * so it can short-circuit normal delivery and never even get queued.
- *
- * Called with @task->sighand->siglock held.
- */
-static inline int tracehook_consider_ignored_signal(struct task_struct *task,
-						    int sig)
-{
-	return (task_ptrace(task) & PT_PTRACED) != 0;
-}
-
-/**
- * tracehook_consider_fatal_signal - suppress special handling of fatal signal
- * @task:		task receiving the signal
- * @sig:		signal number being sent
- *
- * Return nonzero to prevent special handling of this termination signal.
- * Normally handler for signal is %SIG_DFL.  It can be %SIG_IGN if @sig is
- * ignored, in which case force_sig() is about to reset it to %SIG_DFL.
- * When this returns zero, this signal might cause a quick termination
- * that does not give the debugger a chance to intercept the signal.
- *
- * Called with or without @task->sighand->siglock held.
- */
-static inline int tracehook_consider_fatal_signal(struct task_struct *task,
-						  int sig)
-{
-	return (task_ptrace(task) & PT_PTRACED) != 0;
-}
-
-/**
- * tracehook_force_sigpending - let tracing force signal_pending(current) on
- *
- * Called when recomputing our signal_pending() flag.  Return nonzero
- * to force the signal_pending() flag on, so that tracehook_get_signal()
- * will be called before the next return to user mode.
- *
- * Called with @current->sighand->siglock held.
- */
-static inline int tracehook_force_sigpending(void)
-{
-	return 0;
-}
-
-/**
- * tracehook_get_signal - deliver synthetic signal to traced task
- * @task:		@current
- * @regs:		task_pt_regs(@current)
- * @info:		details of synthetic signal
- * @return_ka:		sigaction for synthetic signal
- *
- * Return zero to check for a real pending signal normally.
- * Return -1 after releasing the siglock to repeat the check.
- * Return a signal number to induce an artificial signal delivery,
- * setting *@info and *@return_ka to specify its details and behavior.
- *
- * The @return_ka->sa_handler value controls the disposition of the
- * signal, no matter the signal number.  For %SIG_DFL, the return value
- * is a representative signal to indicate the behavior (e.g. %SIGTERM
- * for death, %SIGQUIT for core dump, %SIGSTOP for job control stop,
- * %SIGTSTP for stop unless in an orphaned pgrp), but the signal number
- * reported will be @info->si_signo instead.
- *
- * Called with @task->sighand->siglock held, before dequeuing pending signals.
- */
-static inline int tracehook_get_signal(struct task_struct *task,
-				       struct pt_regs *regs,
-				       siginfo_t *info,
-				       struct k_sigaction *return_ka)
-{
-	return 0;
-}
-
-/**
- * tracehook_finish_jctl - report about return from job control stop
- *
- * This is called by do_signal_stop() after wakeup.
- */
-static inline void tracehook_finish_jctl(void)
-{
-}
-
-#define DEATH_REAP			-1
-#define DEATH_DELAYED_GROUP_LEADER	-2
-
-/**
- * tracehook_notify_death - task is dead, ready to notify parent
- * @task:		@current task now exiting
- * @death_cookie:	value to pass to tracehook_report_death()
- * @group_dead:		nonzero if this was the last thread in the group to die
- *
- * A return value >= 0 means call do_notify_parent() with that signal
- * number.  Negative return value can be %DEATH_REAP to self-reap right
- * now, or %DEATH_DELAYED_GROUP_LEADER to a zombie without notifying our
- * parent.  Note that a return value of 0 means a do_notify_parent() call
- * that sends no signal, but still wakes up a parent blocked in wait*().
- *
- * Called with write_lock_irq(&tasklist_lock) held.
- */
-static inline int tracehook_notify_death(struct task_struct *task,
-					 void **death_cookie, int group_dead)
-{
-	if (task_detached(task))
-		return task->ptrace ? SIGCHLD : DEATH_REAP;
-
-	/*
-	 * If something other than our normal parent is ptracing us, then
-	 * send it a SIGCHLD instead of honoring exit_signal.  exit_signal
-	 * only has special meaning to our real parent.
-	 */
-	if (thread_group_empty(task) && !ptrace_reparented(task))
-		return task->exit_signal;
-
-	return task->ptrace ? SIGCHLD : DEATH_DELAYED_GROUP_LEADER;
-}
-
-/**
- * tracehook_report_death - task is dead and ready to be reaped
- * @task:		@current task now exiting
- * @signal:		return value from tracheook_notify_death()
- * @death_cookie:	value passed back from tracehook_notify_death()
- * @group_dead:		nonzero if this was the last thread in the group to die
- *
- * Thread has just become a zombie or is about to self-reap.  If positive,
- * @signal is the signal number just sent to the parent (usually %SIGCHLD).
- * If @signal is %DEATH_REAP, this thread will self-reap.  If @signal is
- * %DEATH_DELAYED_GROUP_LEADER, this is a delayed_group_leader() zombie.
- * The @death_cookie was passed back by tracehook_notify_death().
- *
- * If normal reaping is not inhibited, @task->exit_state might be changing
- * in parallel.
- *
- * Called without locks.
- */
-static inline void tracehook_report_death(struct task_struct *task,
-					  int signal, void *death_cookie,
-					  int group_dead)
-{
-}
-
 #ifdef TIF_NOTIFY_RESUME
 /**
  * set_notify_resume - cause tracehook_notify_resume() to be called

kernel/exit.c

@@ -169,7 +169,6 @@ void release_task(struct task_struct * p)
 	struct task_struct *leader;
 	int zap_leader;
 repeat:
-	tracehook_prepare_release_task(p);
 	/* don't need to get the RCU readlock here - the process is dead and
 	 * can't be modifying its own credentials. But shut RCU-lockdep up */
 	rcu_read_lock();
@@ -179,7 +178,7 @@ void release_task(struct task_struct * p)
 	proc_flush_task(p);
 
 	write_lock_irq(&tasklist_lock);
-	tracehook_finish_release_task(p);
+	ptrace_release_task(p);
 	__exit_signal(p);
 
 	/*
@@ -190,22 +189,12 @@ void release_task(struct task_struct * p)
 	zap_leader = 0;
 	leader = p->group_leader;
 	if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
-		BUG_ON(task_detached(leader));
-		do_notify_parent(leader, leader->exit_signal);
 		/*
 		 * If we were the last child thread and the leader has
 		 * exited already, and the leader's parent ignores SIGCHLD,
 		 * then we are the one who should release the leader.
-		 *
-		 * do_notify_parent() will have marked it self-reaping in
-		 * that case.
-		 */
-		zap_leader = task_detached(leader);
-
-		/*
-		 * This maintains the invariant that release_task()
-		 * only runs on a task in EXIT_DEAD, just for sanity.
 		 */
+		zap_leader = do_notify_parent(leader, leader->exit_signal);
 		if (zap_leader)
 			leader->exit_state = EXIT_DEAD;
 	}
@@ -277,18 +266,16 @@ int is_current_pgrp_orphaned(void)
 	return retval;
 }
 
-static int has_stopped_jobs(struct pid *pgrp)
+static bool has_stopped_jobs(struct pid *pgrp)
 {
-	int retval = 0;
 	struct task_struct *p;
 
 	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
-		if (!task_is_stopped(p))
-			continue;
-		retval = 1;
-		break;
+		if (p->signal->flags & SIGNAL_STOP_STOPPED)
+			return true;
 	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
-	return retval;
+
+	return false;
 }
 
 /*
@@ -751,7 +738,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
 
-	if (task_detached(p))
+	if (p->exit_state == EXIT_DEAD)
 		return;
 	/*
 	 * If this is a threaded reparent there is no need to
@@ -764,10 +751,9 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	p->exit_signal = SIGCHLD;
 
 	/* If it has exited notify the new parent about this child's death. */
-	if (!task_ptrace(p) &&
+	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
-		do_notify_parent(p, p->exit_signal);
-		if (task_detached(p)) {
+		if (do_notify_parent(p, p->exit_signal)) {
 			p->exit_state = EXIT_DEAD;
 			list_move_tail(&p->sibling, dead);
 		}
@@ -794,7 +780,7 @@ static void forget_original_parent(struct task_struct *father)
 		do {
 			t->real_parent = reaper;
 			if (t->parent == father) {
-				BUG_ON(task_ptrace(t));
+				BUG_ON(t->ptrace);
 				t->parent = t->real_parent;
 			}
 			if (t->pdeath_signal)
@@ -819,8 +805,7 @@ static void forget_original_parent(struct task_struct *father)
  */
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
-	int signal;
-	void *cookie;
+	bool autoreap;
 
 	/*
 	 * This does two things:
@@ -851,26 +836,33 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	 * we have changed execution domain as these two values started
 	 * the same after a fork.
 	 */
-	if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
+	if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
 	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
 	     tsk->self_exec_id != tsk->parent_exec_id))
 		tsk->exit_signal = SIGCHLD;
 
-	signal = tracehook_notify_death(tsk, &cookie, group_dead);
-	if (signal >= 0)
-		signal = do_notify_parent(tsk, signal);
+	if (unlikely(tsk->ptrace)) {
+		int sig = thread_group_leader(tsk) &&
+				thread_group_empty(tsk) &&
+				!ptrace_reparented(tsk) ?
+			tsk->exit_signal : SIGCHLD;
+		autoreap = do_notify_parent(tsk, sig);
+	} else if (thread_group_leader(tsk)) {
+		autoreap = thread_group_empty(tsk) &&
+			do_notify_parent(tsk, tsk->exit_signal);
+	} else {
+		autoreap = true;
+	}
 
-	tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
+	tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
 
 	/* mt-exec, de_thread() is waiting for group leader */
 	if (unlikely(tsk->signal->notify_count < 0))
 		wake_up_process(tsk->signal->group_exit_task);
 	write_unlock_irq(&tasklist_lock);
 
-	tracehook_report_death(tsk, signal, cookie, group_dead);
-
 	/* If the process is dead, release it - nobody will wait for it */
-	if (signal == DEATH_REAP)
+	if (autoreap)
 		release_task(tsk);
 }
 
@@ -923,7 +915,7 @@ NORET_TYPE void do_exit(long code)
 	 */
 	set_fs(USER_DS);
 
-	tracehook_report_exit(&code);
+	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);
 
@@ -1235,9 +1227,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	traced = ptrace_reparented(p);
 	/*
 	 * It can be ptraced but not reparented, check
-	 * !task_detached() to filter out sub-threads.
+	 * thread_group_leader() to filter out sub-threads.
 	 */
-	if (likely(!traced) && likely(!task_detached(p))) {
+	if (likely(!traced) && thread_group_leader(p)) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
 		unsigned long maxrss;
@@ -1345,17 +1337,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		/* We dropped tasklist, ptracer could die and untrace */
 		ptrace_unlink(p);
 		/*
-		 * If this is not a detached task, notify the parent.
-		 * If it's still not detached after that, don't release
-		 * it now.
+		 * If this is not a sub-thread, notify the parent.
+		 * If parent wants a zombie, don't release it now.
 		 */
-		if (!task_detached(p)) {
-			do_notify_parent(p, p->exit_signal);
-			if (!task_detached(p)) {
+		if (thread_group_leader(p) &&
+		    !do_notify_parent(p, p->exit_signal)) {
 			p->exit_state = EXIT_ZOMBIE;
 			p = NULL;
 		}
-		}
 		write_unlock_irq(&tasklist_lock);
 	}
 	if (p != NULL)
@@ -1367,7 +1356,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 static int *task_stopped_code(struct task_struct *p, bool ptrace)
 {
 	if (ptrace) {
-		if (task_is_stopped_or_traced(p))
+		if (task_is_stopped_or_traced(p) &&
+		    !(p->jobctl & JOBCTL_LISTENING))
 			return &p->exit_code;
 	} else {
 		if (p->signal->flags & SIGNAL_STOP_STOPPED)
@@ -1563,7 +1553,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		 * Notification and reaping will be cascaded to the real
 		 * parent when the ptracer detaches.
 		 */
-		if (likely(!ptrace) && unlikely(task_ptrace(p))) {
+		if (likely(!ptrace) && unlikely(p->ptrace)) {
 			/* it will become visible, clear notask_error */
 			wo->notask_error = 0;
 			return 0;
@@ -1606,8 +1596,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		 * own children, it should create a separate process which
 		 * takes the role of real parent.
 		 */
-		if (likely(!ptrace) && task_ptrace(p) &&
-		    same_thread_group(p->parent, p->real_parent))
+		if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
 			return 0;
 
 		/*

kernel/fork.c

@@ -37,7 +37,6 @@
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
-#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/compat.h>
 #include <linux/kthread.h>
@@ -1340,7 +1339,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (likely(p->pid)) {
-		tracehook_finish_clone(p, clone_flags, trace);
+		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
 
 		if (thread_group_leader(p)) {
 			if (is_child_reaper(pid))
@@ -1481,10 +1480,22 @@ long do_fork(unsigned long clone_flags,
 	}
 
 	/*
-	 * When called from kernel_thread, don't do user tracing stuff.
+	 * Determine whether and which event to report to ptracer.  When
+	 * called from kernel_thread or CLONE_UNTRACED is explicitly
+	 * requested, no event is reported; otherwise, report if the event
+	 * for the type of forking is enabled.
 	 */
-	if (likely(user_mode(regs)))
-		trace = tracehook_prepare_clone(clone_flags);
+	if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) {
+		if (clone_flags & CLONE_VFORK)
+			trace = PTRACE_EVENT_VFORK;
+		else if ((clone_flags & CSIGNAL) != SIGCHLD)
+			trace = PTRACE_EVENT_CLONE;
+		else
+			trace = PTRACE_EVENT_FORK;
+
+		if (likely(!ptrace_event_enabled(current, trace)))
+			trace = 0;
+	}
 
 	p = copy_process(clone_flags, stack_start, regs, stack_size,
 			 child_tidptr, NULL, trace);
@@ -1508,26 +1519,26 @@ long do_fork(unsigned long clone_flags,
 		}
 
 		audit_finish_fork(p);
-		tracehook_report_clone(regs, clone_flags, nr, p);
 
 		/*
 		 * We set PF_STARTING at creation in case tracing wants to
 		 * use this to distinguish a fully live task from one that
-		 * hasn't gotten to tracehook_report_clone() yet.  Now we
-		 * clear it and set the child going.
+		 * hasn't finished SIGSTOP raising yet.  Now we clear it
+		 * and set the child going.
 		 */
 		p->flags &= ~PF_STARTING;
 
 		wake_up_new_task(p);
 
-		tracehook_report_clone_complete(trace, regs,
-						clone_flags, nr, p);
+		/* forking complete and child started to run, tell ptracer */
+		if (unlikely(trace))
+			ptrace_event(trace, nr);
 
 		if (clone_flags & CLONE_VFORK) {
 			freezer_do_not_count();
 			wait_for_completion(&vfork);
 			freezer_count();
-			tracehook_report_vfork_done(p, nr);
+			ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
 		}
 	} else {
 		nr = PTR_ERR(p);

kernel/ptrace.c

@@ -23,8 +23,15 @@
 #include <linux/uaccess.h>
 #include <linux/regset.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/cn_proc.h>
 
 
+static int ptrace_trapping_sleep_fn(void *flags)
+{
+	schedule();
+	return 0;
+}
+
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
@@ -77,13 +84,20 @@ void __ptrace_unlink(struct task_struct *child)
 	spin_lock(&child->sighand->siglock);
 
 	/*
-	 * Reinstate GROUP_STOP_PENDING if group stop is in effect and
+	 * 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->group_stop |= GROUP_STOP_PENDING;
+		child->jobctl |= JOBCTL_STOP_PENDING;
 
 	/*
 	 * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
@@ -91,16 +105,30 @@ void __ptrace_unlink(struct task_struct *child)
 	 * is in TASK_TRACED; otherwise, we might unduly disrupt
 	 * TASK_KILLABLE sleeps.
 	 */
-	if (child->group_stop & GROUP_STOP_PENDING || task_is_traced(child))
+	if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child))
 		signal_wake_up(child, task_is_traced(child));
 
 	spin_unlock(&child->sighand->siglock);
 }
 
-/*
- * Check that we have indeed attached to the thing..
+/**
+ * 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)
+int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 {
 	int ret = -ESRCH;
 
@@ -119,13 +147,14 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 		 */
 		spin_lock_irq(&child->sighand->siglock);
 		WARN_ON_ONCE(task_is_stopped(child));
-		if (task_is_traced(child) || kill)
+		if (ignore_state || (task_is_traced(child) &&
+				     !(child->jobctl & JOBCTL_LISTENING)))
 			ret = 0;
 		spin_unlock_irq(&child->sighand->siglock);
 	}
 	read_unlock(&tasklist_lock);
 
-	if (!ret && !kill)
+	if (!ret && !ignore_state)
 		ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
 
 	/* All systems go.. */
@@ -182,11 +211,28 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 	return !err;
 }
 
-static int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task, long request,
+			 unsigned long flags)
 {
-	bool wait_trap = false;
+	bool seize = (request == PTRACE_SEIZE);
 	int retval;
 
+	/*
+	 * SEIZE will enable new ptrace behaviors which will be implemented
+	 * gradually.  SEIZE_DEVEL is used to prevent applications
+	 * expecting full SEIZE behaviors trapping on kernel commits which
+	 * are still in the process of implementing them.
+	 *
+	 * Only test programs for new ptrace behaviors being implemented
+	 * should set SEIZE_DEVEL.  If unset, SEIZE will fail with -EIO.
+	 *
+	 * Once SEIZE behaviors are completely implemented, this flag and
+	 * the following test will be removed.
+	 */
+	retval = -EIO;
+	if (seize && !(flags & PTRACE_SEIZE_DEVEL))
+		goto out;
+
 	audit_ptrace(task);
 
 	retval = -EPERM;
@@ -218,16 +264,21 @@ static int ptrace_attach(struct task_struct *task)
 		goto unlock_tasklist;
 
 	task->ptrace = PT_PTRACED;
+	if (seize)
+		task->ptrace |= PT_SEIZED;
 	if (task_ns_capable(task, CAP_SYS_PTRACE))
 		task->ptrace |= PT_PTRACE_CAP;
 
 	__ptrace_link(task, current);
+
+	/* 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 GROUP_STOP_PENDING and
+	 * 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
@@ -243,11 +294,9 @@ static int ptrace_attach(struct task_struct *task)
 	 * 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;
+	if (task_is_stopped(task) &&
+	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
 		signal_wake_up(task, 1);
-		wait_trap = true;
-	}
 
 	spin_unlock(&task->sighand->siglock);
 
@@ -257,9 +306,12 @@ static int ptrace_attach(struct task_struct *task)
 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));
+	if (!retval) {
+		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
+			    ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE);
+		proc_ptrace_connector(task, PTRACE_ATTACH);
+	}
+
 	return retval;
 }
 
@@ -322,25 +374,27 @@ 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 (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))
-				do_notify_parent(p, p->exit_signal);
+			dead = do_notify_parent(p, p->exit_signal);
 		else if (ignoring_children(tracer->sighand)) {
 			__wake_up_parent(p, tracer);
-				p->exit_signal = -1;
+			dead = true;
 		}
 	}
-		if (task_detached(p)) {
 	/* Mark it as in the process of being reaped. */
+	if (dead)
 		p->exit_state = EXIT_DEAD;
-			return true;
-		}
-	}
-
-	return false;
+	return dead;
 }
 
 static int ptrace_detach(struct task_struct *child, unsigned int data)
@@ -365,6 +419,7 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
 	}
 	write_unlock_irq(&tasklist_lock);
 
+	proc_ptrace_connector(child, PTRACE_DETACH);
 	if (unlikely(dead))
 		release_task(child);
 
@@ -611,10 +666,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
 int ptrace_request(struct task_struct *child, long request,
 		   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:
@@ -647,6 +704,62 @@ int ptrace_request(struct task_struct *child, long request,
 			ret = ptrace_setsiginfo(child, &siginfo);
 		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)))
+			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 (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP))
+			break;
+
+		child->jobctl |= JOBCTL_LISTENING;
+
+		/*
+		 * If NOTIFY is set, it means event happened between start
+		 * of this trap and now.  Trigger re-trap immediately.
+		 */
+		if (child->jobctl & JOBCTL_TRAP_NOTIFY)
+			signal_wake_up(child, true);
+
+		unlock_task_sighand(child, &flags);
+		ret = 0;
+		break;
+
 	case PTRACE_DETACH:	 /* detach a process that was attached. */
 		ret = ptrace_detach(child, data);
 		break;
@@ -761,8 +874,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 		goto out;
 	}
 
-	if (request == PTRACE_ATTACH) {
-		ret = ptrace_attach(child);
+	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
+		ret = ptrace_attach(child, request, data);
 		/*
 		 * Some architectures need to do book-keeping after
 		 * a ptrace attach.
@@ -772,7 +885,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 		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;
 
@@ -903,8 +1017,8 @@ 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, data);
 		/*
 		 * Some architectures need to do book-keeping after
 		 * a ptrace attach.
@@ -914,7 +1028,8 @@ 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);
+	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+				  request == PTRACE_INTERRUPT);
 	if (!ret)
 		ret = compat_arch_ptrace(child, request, addr, data);
 

kernel/signal.c

@@ -87,7 +87,7 @@ static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns)
 	/*
 	 * Tracers may want to know about even ignored signals.
 	 */
-	return !tracehook_consider_ignored_signal(t, sig);
+	return !t->ptrace;
 }
 
 /*
@@ -124,7 +124,7 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
 
 static int recalc_sigpending_tsk(struct task_struct *t)
 {
-	if ((t->group_stop & GROUP_STOP_PENDING) ||
+	if ((t->jobctl & JOBCTL_PENDING_MASK) ||
 	    PENDING(&t->pending, &t->blocked) ||
 	    PENDING(&t->signal->shared_pending, &t->blocked)) {
 		set_tsk_thread_flag(t, TIF_SIGPENDING);
@@ -150,9 +150,7 @@ void recalc_sigpending_and_wake(struct task_struct *t)
 
 void recalc_sigpending(void)
 {
-	if (unlikely(tracehook_force_sigpending()))
-		set_thread_flag(TIF_SIGPENDING);
-	else if (!recalc_sigpending_tsk(current) && !freezing(current))
+	if (!recalc_sigpending_tsk(current) && !freezing(current))
 		clear_thread_flag(TIF_SIGPENDING);
 
 }
@@ -224,47 +222,93 @@ static inline void print_dropped_signal(int sig)
 }
 
 /**
- * task_clear_group_stop_trapping - clear group stop trapping bit
+ * task_set_jobctl_pending - set jobctl pending bits
  * @task: target task
+ * @mask: pending bits to set
  *
- * If GROUP_STOP_TRAPPING is set, a ptracer is waiting for us.  Clear it
- * and wake up the ptracer.  Note that we don't need any further locking.
- * @task->siglock guarantees that @task->parent points to the ptracer.
+ * Clear @mask from @task->jobctl.  @mask must be subset of
+ * %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK |
+ * %JOBCTL_TRAPPING.  If stop signo is being set, the existing signo is
+ * cleared.  If @task is already being killed or exiting, this function
+ * becomes noop.
+ *
+ * CONTEXT:
+ * Must be called with @task->sighand->siglock held.
+ *
+ * RETURNS:
+ * %true if @mask is set, %false if made noop because @task was dying.
+ */
+bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask)
+{
+	BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME |
+			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
+	BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
+
+	if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
+		return false;
+
+	if (mask & JOBCTL_STOP_SIGMASK)
+		task->jobctl &= ~JOBCTL_STOP_SIGMASK;
+
+	task->jobctl |= mask;
+	return true;
+}
+
+/**
+ * task_clear_jobctl_trapping - clear jobctl trapping bit
+ * @task: target task
+ *
+ * If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED.
+ * Clear it and wake up the ptracer.  Note that we don't need any further
+ * locking.  @task->siglock guarantees that @task->parent points to the
+ * ptracer.
  *
  * CONTEXT:
  * Must be called with @task->sighand->siglock held.
  */
-static void task_clear_group_stop_trapping(struct task_struct *task)
+void task_clear_jobctl_trapping(struct task_struct *task)
 {
-	if (unlikely(task->group_stop & GROUP_STOP_TRAPPING)) {
-		task->group_stop &= ~GROUP_STOP_TRAPPING;
-		__wake_up_sync_key(&task->parent->signal->wait_chldexit,
-				   TASK_UNINTERRUPTIBLE, 1, task);
+	if (unlikely(task->jobctl & JOBCTL_TRAPPING)) {
+		task->jobctl &= ~JOBCTL_TRAPPING;
+		wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT);
 	}
 }
 
 /**
- * task_clear_group_stop_pending - clear pending group stop
+ * task_clear_jobctl_pending - clear jobctl pending bits
  * @task: target task
+ * @mask: pending bits to clear
  *
- * Clear group stop states for @task.
+ * Clear @mask from @task->jobctl.  @mask must be subset of
+ * %JOBCTL_PENDING_MASK.  If %JOBCTL_STOP_PENDING is being cleared, other
+ * STOP bits are cleared together.
+ *
+ * If clearing of @mask leaves no stop or trap pending, this function calls
+ * task_clear_jobctl_trapping().
  *
  * CONTEXT:
  * Must be called with @task->sighand->siglock held.
  */
-void task_clear_group_stop_pending(struct task_struct *task)
+void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask)
 {
-	task->group_stop &= ~(GROUP_STOP_PENDING | GROUP_STOP_CONSUME |
-			      GROUP_STOP_DEQUEUED);
+	BUG_ON(mask & ~JOBCTL_PENDING_MASK);
+
+	if (mask & JOBCTL_STOP_PENDING)
+		mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED;
+
+	task->jobctl &= ~mask;
+
+	if (!(task->jobctl & JOBCTL_PENDING_MASK))
+		task_clear_jobctl_trapping(task);
 }
 
 /**
  * task_participate_group_stop - participate in a group stop
  * @task: task participating in a group stop
  *
- * @task has GROUP_STOP_PENDING set and is participating in a group stop.
+ * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop.
  * Group stop states are cleared and the group stop count is consumed if
- * %GROUP_STOP_CONSUME was set.  If the consumption completes the group
+ * %JOBCTL_STOP_CONSUME was set.  If the consumption completes the group
  * stop, the appropriate %SIGNAL_* flags are set.
  *
  * CONTEXT:
@@ -277,11 +321,11 @@ void task_clear_group_stop_pending(struct task_struct *task)
 static bool task_participate_group_stop(struct task_struct *task)
 {
 	struct signal_struct *sig = task->signal;
-	bool consume = task->group_stop & GROUP_STOP_CONSUME;
+	bool consume = task->jobctl & JOBCTL_STOP_CONSUME;
 
-	WARN_ON_ONCE(!(task->group_stop & GROUP_STOP_PENDING));
+	WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING));
 
-	task_clear_group_stop_pending(task);
+	task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING);
 
 	if (!consume)
 		return false;
@@ -449,7 +493,8 @@ int unhandled_signal(struct task_struct *tsk, int sig)
 		return 1;
 	if (handler != SIG_IGN && handler != SIG_DFL)
 		return 0;
-	return !tracehook_consider_fatal_signal(tsk, sig);
+	/* if ptraced, let the tracer determine */
+	return !tsk->ptrace;
 }
 
 /*
@@ -604,7 +649,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 		 * is to alert stop-signal processing code when another
 		 * processor has come along and cleared the flag.
 		 */
-		current->group_stop |= GROUP_STOP_DEQUEUED;
+		current->jobctl |= JOBCTL_STOP_DEQUEUED;
 	}
 	if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
 		/*
@@ -773,6 +818,32 @@ static int check_kill_permission(int sig, struct siginfo *info,
 	return security_task_kill(t, info, sig, 0);
 }
 
+/**
+ * ptrace_trap_notify - schedule trap to notify ptracer
+ * @t: tracee wanting to notify tracer
+ *
+ * This function schedules sticky ptrace trap which is cleared on the next
+ * TRAP_STOP to notify ptracer of an event.  @t must have been seized by
+ * ptracer.
+ *
+ * If @t is running, STOP trap will be taken.  If trapped for STOP and
+ * ptracer is listening for events, tracee is woken up so that it can
+ * re-trap for the new event.  If trapped otherwise, STOP trap will be
+ * eventually taken without returning to userland after the existing traps
+ * are finished by PTRACE_CONT.
+ *
+ * CONTEXT:
+ * Must be called with @task->sighand->siglock held.
+ */
+static void ptrace_trap_notify(struct task_struct *t)
+{
+	WARN_ON_ONCE(!(t->ptrace & PT_SEIZED));
+	assert_spin_locked(&t->sighand->siglock);
+
+	task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
+	signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
+}
+
 /*
  * Handle magic process-wide effects of stop/continue signals. Unlike
  * the signal actions, these happen immediately at signal-generation
@@ -809,9 +880,12 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
 		rm_from_queue(SIG_KERNEL_STOP_MASK, &signal->shared_pending);
 		t = p;
 		do {
-			task_clear_group_stop_pending(t);
+			task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING);
 			rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
+			if (likely(!(t->ptrace & PT_SEIZED)))
 				wake_up_state(t, __TASK_STOPPED);
+			else
+				ptrace_trap_notify(t);
 		} while_each_thread(p, t);
 
 		/*
@@ -908,8 +982,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
 	if (sig_fatal(p, sig) &&
 	    !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
 	    !sigismember(&t->real_blocked, sig) &&
-	    (sig == SIGKILL ||
-	     !tracehook_consider_fatal_signal(t, sig))) {
+	    (sig == SIGKILL || !t->ptrace)) {
 		/*
 		 * This signal will be fatal to the whole group.
 		 */
@@ -925,7 +998,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
 			signal->group_stop_count = 0;
 			t = p;
 			do {
-				task_clear_group_stop_pending(t);
+				task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 				sigaddset(&t->pending.signal, SIGKILL);
 				signal_wake_up(t, 1);
 			} while_each_thread(p, t);
@@ -1160,7 +1233,7 @@ int zap_other_threads(struct task_struct *p)
 	p->signal->group_stop_count = 0;
 
 	while_each_thread(p, t) {
-		task_clear_group_stop_pending(t);
+		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		count++;
 
 		/* Don't bother with already dead threads */
@@ -1511,22 +1584,22 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
  * Let a parent know about the death of a child.
  * For a stopped/continued status change, use do_notify_parent_cldstop instead.
  *
- * Returns -1 if our parent ignored us and so we've switched to
- * self-reaping, or else @sig.
+ * Returns true if our parent ignored us and so we've switched to
+ * self-reaping.
  */
-int do_notify_parent(struct task_struct *tsk, int sig)
+bool do_notify_parent(struct task_struct *tsk, int sig)
 {
 	struct siginfo info;
 	unsigned long flags;
 	struct sighand_struct *psig;
-	int ret = sig;
+	bool autoreap = false;
 
 	BUG_ON(sig == -1);
 
  	/* do_notify_parent_cldstop should have been called instead.  */
  	BUG_ON(task_is_stopped_or_traced(tsk));
 
-	BUG_ON(!task_ptrace(tsk) &&
+	BUG_ON(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 
 	info.si_signo = sig;
@@ -1565,7 +1638,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
 	psig = tsk->parent->sighand;
 	spin_lock_irqsave(&psig->siglock, flags);
-	if (!task_ptrace(tsk) && sig == SIGCHLD &&
+	if (!tsk->ptrace && sig == SIGCHLD &&
 	    (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
 	     (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) {
 		/*
@@ -1583,16 +1656,16 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 		 * is implementation-defined: we do (if you don't want
 		 * it, just use SIG_IGN instead).
 		 */
-		ret = tsk->exit_signal = -1;
+		autoreap = true;
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
-			sig = -1;
+			sig = 0;
 	}
-	if (valid_signal(sig) && sig > 0)
+	if (valid_signal(sig) && sig)
 		__group_send_sig_info(sig, &info, tsk->parent);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
-	return ret;
+	return autoreap;
 }
 
 /**
@@ -1665,7 +1738,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 
 static inline int may_ptrace_stop(void)
 {
-	if (!likely(task_ptrace(current)))
+	if (!likely(current->ptrace))
 		return 0;
 	/*
 	 * Are we in the middle of do_coredump?
@@ -1693,15 +1766,6 @@ static int sigkill_pending(struct task_struct *tsk)
 		sigismember(&tsk->signal->shared_pending.signal, SIGKILL);
 }
 
-/*
- * Test whether the target task of the usual cldstop notification - the
- * real_parent of @child - is in the same group as the ptracer.
- */
-static bool real_parent_is_ptracer(struct task_struct *child)
-{
-	return same_thread_group(child->parent, child->real_parent);
-}
-
 /*
  * This must be called with current->sighand->siglock held.
  *
@@ -1739,31 +1803,34 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	}
 
 	/*
-	 * If @why is CLD_STOPPED, we're trapping to participate in a group
-	 * stop.  Do the bookkeeping.  Note that if SIGCONT was delievered
-	 * while siglock was released for the arch hook, PENDING could be
-	 * clear now.  We act as if SIGCONT is received after TASK_TRACED
-	 * is entered - ignore it.
+	 * We're committing to trapping.  TRACED should be visible before
+	 * TRAPPING is cleared; otherwise, the tracer might fail do_wait().
+	 * Also, transition to TRACED and updates to ->jobctl should be
+	 * atomic with respect to siglock and should be done after the arch
+	 * hook as siglock is released and regrabbed across it.
 	 */
-	if (why == CLD_STOPPED && (current->group_stop & GROUP_STOP_PENDING))
-		gstop_done = task_participate_group_stop(current);
+	set_current_state(TASK_TRACED);
 
 	current->last_siginfo = info;
 	current->exit_code = exit_code;
 
 	/*
-	 * TRACED should be visible before TRAPPING is cleared; otherwise,
-	 * the tracer might fail do_wait().
+	 * If @why is CLD_STOPPED, we're trapping to participate in a group
+	 * stop.  Do the bookkeeping.  Note that if SIGCONT was delievered
+	 * across siglock relocks since INTERRUPT was scheduled, PENDING
+	 * could be clear now.  We act as if SIGCONT is received after
+	 * TASK_TRACED is entered - ignore it.
 	 */
-	set_current_state(TASK_TRACED);
+	if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING))
+		gstop_done = task_participate_group_stop(current);
 
-	/*
-	 * We're committing to trapping.  Clearing GROUP_STOP_TRAPPING and
-	 * transition to TASK_TRACED should be atomic with respect to
-	 * siglock.  This hsould be done after the arch hook as siglock is
-	 * released and regrabbed across it.
-	 */
-	task_clear_group_stop_trapping(current);
+	/* any trap clears pending STOP trap, STOP trap clears NOTIFY */
+	task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP);
+	if (info && info->si_code >> 8 == PTRACE_EVENT_STOP)
+		task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY);
+
+	/* entering a trap, clear TRAPPING */
+	task_clear_jobctl_trapping(current);
 
 	spin_unlock_irq(&current->sighand->siglock);
 	read_lock(&tasklist_lock);
@@ -1779,7 +1846,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		 * separately unless they're gonna be duplicates.
 		 */
 		do_notify_parent_cldstop(current, true, why);
-		if (gstop_done && !real_parent_is_ptracer(current))
+		if (gstop_done && ptrace_reparented(current))
 			do_notify_parent_cldstop(current, false, why);
 
 		/*
@@ -1799,9 +1866,9 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		 *
 		 * If @gstop_done, the ptracer went away between group stop
 		 * completion and here.  During detach, it would have set
-		 * GROUP_STOP_PENDING on us and we'll re-enter TASK_STOPPED
-		 * in do_signal_stop() on return, so notifying the real
-		 * parent of the group stop completion is enough.
+		 * JOBCTL_STOP_PENDING on us and we'll re-enter
+		 * TASK_STOPPED in do_signal_stop() on return, so notifying
+		 * the real parent of the group stop completion is enough.
 		 */
 		if (gstop_done)
 			do_notify_parent_cldstop(current, false, why);
@@ -1827,6 +1894,9 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	spin_lock_irq(&current->sighand->siglock);
 	current->last_siginfo = NULL;
 
+	/* LISTENING can be set only during STOP traps, clear it */
+	current->jobctl &= ~JOBCTL_LISTENING;
+
 	/*
 	 * Queued signals ignored us while we were stopped for tracing.
 	 * So check for any that we should take before resuming user mode.
@@ -1835,44 +1905,66 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	recalc_sigpending_tsk(current);
 }
 
-void ptrace_notify(int exit_code)
+static void ptrace_do_notify(int signr, int exit_code, int why)
 {
 	siginfo_t info;
 
-	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
-
 	memset(&info, 0, sizeof info);
-	info.si_signo = SIGTRAP;
+	info.si_signo = signr;
 	info.si_code = exit_code;
 	info.si_pid = task_pid_vnr(current);
 	info.si_uid = current_uid();
 
 	/* Let the debugger run.  */
+	ptrace_stop(exit_code, why, 1, &info);
+}
+
+void ptrace_notify(int exit_code)
+{
+	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
+
 	spin_lock_irq(&current->sighand->siglock);
-	ptrace_stop(exit_code, CLD_TRAPPED, 1, &info);
+	ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED);
 	spin_unlock_irq(&current->sighand->siglock);
 }
 
-/*
- * This performs the stopping for SIGSTOP and other stop signals.
- * We have to stop all threads in the thread group.
- * Returns non-zero if we've actually stopped and released the siglock.
- * Returns zero if we didn't stop and still hold the siglock.
+/**
+ * do_signal_stop - handle group stop for SIGSTOP and other stop signals
+ * @signr: signr causing group stop if initiating
+ *
+ * If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr
+ * and participate in it.  If already set, participate in the existing
+ * group stop.  If participated in a group stop (and thus slept), %true is
+ * returned with siglock released.
+ *
+ * If ptraced, this function doesn't handle stop itself.  Instead,
+ * %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock
+ * untouched.  The caller must ensure that INTERRUPT trap handling takes
+ * places afterwards.
+ *
+ * CONTEXT:
+ * Must be called with @current->sighand->siglock held, which is released
+ * on %true return.
+ *
+ * RETURNS:
+ * %false if group stop is already cancelled or ptrace trap is scheduled.
+ * %true if participated in group stop.
  */
-static int do_signal_stop(int signr)
+static bool do_signal_stop(int signr)
+	__releases(&current->sighand->siglock)
 {
 	struct signal_struct *sig = current->signal;
 
-	if (!(current->group_stop & GROUP_STOP_PENDING)) {
-		unsigned int gstop = GROUP_STOP_PENDING | GROUP_STOP_CONSUME;
+	if (!(current->jobctl & JOBCTL_STOP_PENDING)) {
+		unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
 		struct task_struct *t;
 
-		/* signr will be recorded in task->group_stop for retries */
-		WARN_ON_ONCE(signr & ~GROUP_STOP_SIGMASK);
+		/* signr will be recorded in task->jobctl for retries */
+		WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK);
 
-		if (!likely(current->group_stop & GROUP_STOP_DEQUEUED) ||
+		if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) ||
 		    unlikely(signal_group_exit(sig)))
-			return 0;
+			return false;
 		/*
 		 * There is no group stop already in progress.  We must
 		 * initiate one now.
@@ -1895,28 +1987,32 @@ static int do_signal_stop(int signr)
 		if (!(sig->flags & SIGNAL_STOP_STOPPED))
 			sig->group_exit_code = signr;
 		else
-			WARN_ON_ONCE(!task_ptrace(current));
+			WARN_ON_ONCE(!current->ptrace);
+
+		sig->group_stop_count = 0;
+
+		if (task_set_jobctl_pending(current, signr | gstop))
+			sig->group_stop_count++;
 
-		current->group_stop &= ~GROUP_STOP_SIGMASK;
-		current->group_stop |= signr | gstop;
-		sig->group_stop_count = 1;
 		for (t = next_thread(current); t != current;
 		     t = next_thread(t)) {
-			t->group_stop &= ~GROUP_STOP_SIGMASK;
 			/*
 			 * Setting state to TASK_STOPPED for a group
 			 * stop is always done with the siglock held,
 			 * so this check has no races.
 			 */
-			if (!(t->flags & PF_EXITING) && !task_is_stopped(t)) {
-				t->group_stop |= signr | gstop;
+			if (!task_is_stopped(t) &&
+			    task_set_jobctl_pending(t, signr | gstop)) {
 				sig->group_stop_count++;
+				if (likely(!(t->ptrace & PT_SEIZED)))
 					signal_wake_up(t, 0);
+				else
+					ptrace_trap_notify(t);
 			}
 		}
 	}
-retry:
-	if (likely(!task_ptrace(current))) {
+
+	if (likely(!current->ptrace)) {
 		int notify = 0;
 
 		/*
@@ -1947,43 +2043,65 @@ static int do_signal_stop(int signr)
 
 		/* Now we don't run again until woken by SIGCONT or SIGKILL */
 		schedule();
-
-		spin_lock_irq(&current->sighand->siglock);
+		return true;
 	} else {
-		ptrace_stop(current->group_stop & GROUP_STOP_SIGMASK,
-			    CLD_STOPPED, 0, NULL);
-		current->exit_code = 0;
-	}
-
 		/*
-	 * GROUP_STOP_PENDING could be set if another group stop has
-	 * started since being woken up or ptrace wants us to transit
-	 * between TASK_STOPPED and TRACED.  Retry group stop.
+		 * While ptraced, group stop is handled by STOP trap.
+		 * Schedule it and let the caller deal with it.
 		 */
-	if (current->group_stop & GROUP_STOP_PENDING) {
-		WARN_ON_ONCE(!(current->group_stop & GROUP_STOP_SIGMASK));
-		goto retry;
+		task_set_jobctl_pending(current, JOBCTL_TRAP_STOP);
+		return false;
 	}
+}
 
-	/* PTRACE_ATTACH might have raced with task killing, clear trapping */
-	task_clear_group_stop_trapping(current);
-
-	spin_unlock_irq(&current->sighand->siglock);
-
-	tracehook_finish_jctl();
-
-	return 1;
+/**
+ * do_jobctl_trap - take care of ptrace jobctl traps
+ *
+ * When PT_SEIZED, it's used for both group stop and explicit
+ * SEIZE/INTERRUPT traps.  Both generate PTRACE_EVENT_STOP trap with
+ * accompanying siginfo.  If stopped, lower eight bits of exit_code contain
+ * the stop signal; otherwise, %SIGTRAP.
+ *
+ * When !PT_SEIZED, it's used only for group stop trap with stop signal
+ * number as exit_code and no siginfo.
+ *
+ * CONTEXT:
+ * Must be called with @current->sighand->siglock held, which may be
+ * released and re-acquired before returning with intervening sleep.
+ */
+static void do_jobctl_trap(void)
+{
+	struct signal_struct *signal = current->signal;
+	int signr = current->jobctl & JOBCTL_STOP_SIGMASK;
+
+	if (current->ptrace & PT_SEIZED) {
+		if (!signal->group_stop_count &&
+		    !(signal->flags & SIGNAL_STOP_STOPPED))
+			signr = SIGTRAP;
+		WARN_ON_ONCE(!signr);
+		ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8),
+				 CLD_STOPPED);
+	} else {
+		WARN_ON_ONCE(!signr);
+		ptrace_stop(signr, CLD_STOPPED, 0, NULL);
+		current->exit_code = 0;
+	}
 }
 
 static int ptrace_signal(int signr, siginfo_t *info,
 			 struct pt_regs *regs, void *cookie)
 {
-	if (!task_ptrace(current))
-		return signr;
-
 	ptrace_signal_deliver(regs, cookie);
-
-	/* Let the debugger run.  */
+	/*
+	 * We do not check sig_kernel_stop(signr) but set this marker
+	 * unconditionally because we do not know whether debugger will
+	 * change signr. This flag has no meaning unless we are going
+	 * to stop after return from ptrace_stop(). In this case it will
+	 * be checked in do_signal_stop(), we should only stop if it was
+	 * not cleared by SIGCONT while we were sleeping. See also the
+	 * comment in dequeue_signal().
+	 */
+	current->jobctl |= JOBCTL_STOP_DEQUEUED;
 	ptrace_stop(signr, CLD_TRAPPED, 0, info);
 
 	/* We're back.  Did the debugger cancel the sig?  */
@@ -2039,7 +2157,6 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 	 * the CLD_ si_code into SIGNAL_CLD_MASK bits.
 	 */
 	if (unlikely(signal->flags & SIGNAL_CLD_MASK)) {
-		struct task_struct *leader;
 		int why;
 
 		if (signal->flags & SIGNAL_CLD_CONTINUED)
@@ -2060,13 +2177,11 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 		 * a duplicate.
 		 */
 		read_lock(&tasklist_lock);
-
 		do_notify_parent_cldstop(current, false, why);
 
-		leader = current->group_leader;
-		if (task_ptrace(leader) && !real_parent_is_ptracer(leader))
-			do_notify_parent_cldstop(leader, true, why);
-
+		if (ptrace_reparented(current->group_leader))
+			do_notify_parent_cldstop(current->group_leader,
+						true, why);
 		read_unlock(&tasklist_lock);
 
 		goto relock;
@@ -2074,28 +2189,23 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 
 	for (;;) {
 		struct k_sigaction *ka;
-		/*
-		 * Tracing can induce an artificial signal and choose sigaction.
-		 * The return value in @signr determines the default action,
-		 * but @info->si_signo is the signal number we will report.
-		 */
-		signr = tracehook_get_signal(current, regs, info, return_ka);
-		if (unlikely(signr < 0))
+
+		if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) &&
+		    do_signal_stop(0))
 			goto relock;
-		if (unlikely(signr != 0))
-			ka = return_ka;
-		else {
-			if (unlikely(current->group_stop &
-				     GROUP_STOP_PENDING) && do_signal_stop(0))
+
+		if (unlikely(current->jobctl & JOBCTL_TRAP_MASK)) {
+			do_jobctl_trap();
+			spin_unlock_irq(&sighand->siglock);
 			goto relock;
+		}
 
-			signr = dequeue_signal(current, &current->blocked,
-					       info);
+		signr = dequeue_signal(current, &current->blocked, info);
 
 		if (!signr)
 			break; /* will return 0 */
 
-			if (signr != SIGKILL) {
+		if (unlikely(current->ptrace) && signr != SIGKILL) {
 			signr = ptrace_signal(signr, info,
 					      regs, cookie);
 			if (!signr)
@@ -2103,7 +2213,6 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 		}
 
 		ka = &sighand->action[signr-1];
-		}
 
 		/* Trace actually delivered signals. */
 		trace_signal_deliver(signr, info, ka);
@@ -2260,7 +2369,7 @@ void exit_signals(struct task_struct *tsk)
 	signotset(&unblocked);
 	retarget_shared_pending(tsk, &unblocked);
 
-	if (unlikely(tsk->group_stop & GROUP_STOP_PENDING) &&
+	if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) &&
 	    task_participate_group_stop(tsk))
 		group_stop = CLD_STOPPED;
 out:

mm/nommu.c

@@ -22,7 +22,6 @@
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <linux/tracehook.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
@@ -1087,7 +1086,7 @@ static unsigned long determine_vm_flags(struct file *file,
 	 * it's being traced - otherwise breakpoints set in it may interfere
 	 * with another untraced process
 	 */
-	if ((flags & MAP_PRIVATE) && tracehook_expect_breakpoints(current))
+	if ((flags & MAP_PRIVATE) && current->ptrace)
 		vm_flags &= ~VM_MAYSHARE;
 
 	return vm_flags;

mm/oom_kill.c

@@ -339,8 +339,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 				 * then wait for it to finish before killing
 				 * some other task unnecessarily.
 				 */
-				if (!(task_ptrace(p->group_leader) &
-							PT_TRACE_EXIT))
+				if (!(p->group_leader->ptrace & PT_TRACE_EXIT))
 					return ERR_PTR(-1UL);
 			}
 		}

security/apparmor/domain.c

@@ -67,7 +67,7 @@ static int may_change_ptraced_domain(struct task_struct *task,
 	int error = 0;
 
 	rcu_read_lock();
-	tracer = tracehook_tracer_task(task);
+	tracer = ptrace_parent(task);
 	if (tracer) {
 		/* released below */
 		cred = get_task_cred(tracer);

security/selinux/hooks.c

@@ -2053,7 +2053,7 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 			u32 ptsid = 0;
 
 			rcu_read_lock();
-			tracer = tracehook_tracer_task(current);
+			tracer = ptrace_parent(current);
 			if (likely(tracer != NULL)) {
 				sec = __task_cred(tracer)->security;
 				ptsid = sec->sid;
@@ -5319,7 +5319,7 @@ static int selinux_setprocattr(struct task_struct *p,
 		   Otherwise, leave SID unchanged and fail. */
 		ptsid = 0;
 		task_lock(p);
-		tracer = tracehook_tracer_task(p);
+		tracer = ptrace_parent(p);
 		if (tracer)
 			ptsid = task_sid(tracer);
 		task_unlock(p);