[PATCH v5] do_wait: make PIDTYPE_PID case O(1) instead of O(n)

[Jim Newsome]

do_wait is an internal function used to implement waitpid, waitid,
wait4, etc. To handle the general case, it does an O(n) linear scan of
the thread group's children and tracees.

This patch adds a special-case when waiting on a pid to skip these scans
and instead do an O(1) lookup. This improves performance when waiting on
a pid from a thread group with many children and/or tracees.

Signed-off-by: James Newsome <jnewsome@xxxxxxxxxxxxxx>
---

v4: https://lkml.org/lkml/2021/3/11/1333

* Added back missing target->ptrace check.
* Added explicit thread_group_leader check instead of double-lookup.

 kernel/exit.c | 69 +++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 59 insertions(+), 10 deletions(-)

diff --git a/kernel/exit.c b/kernel/exit.c
index 04029e35e69a..65c862c604a7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1439,9 +1439,50 @@ void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
 			   TASK_INTERRUPTIBLE, p);
 }
 
+static bool is_effectively_child(struct wait_opts *wo, bool ptrace,
+				 struct task_struct *target)
+{
+	struct task_struct *parent =
+		!ptrace ? target->real_parent : target->parent;
+
+	return current == parent || (!(wo->wo_flags & __WNOTHREAD) &&
+				     same_thread_group(current, parent));
+}
+
+/*
+ * Optimization for waiting on PIDTYPE_PID. No need to iterate through child
+ * and tracee lists to find the target task.
+ */
+static int do_wait_pid(struct wait_opts *wo)
+{
+	bool ptrace;
+	struct task_struct *target;
+	int retval;
+
+	target = pid_task(wo->wo_pid, PIDTYPE_PID);
+	if (!target)
+		return 0;
+
+	ptrace = false;
+	if (thread_group_leader(target) &&
+	    is_effectively_child(wo, ptrace, target)) {
+		retval = wait_consider_task(wo, ptrace, target);
+		if (retval)
+			return retval;
+	}
+
+	ptrace = true;
+	if (target->ptrace && is_effectively_child(wo, ptrace, target)) {
+		retval = wait_consider_task(wo, ptrace, target);
+		if (retval)
+			return retval;
+	}
+
+	return 0;
+}
+
 static long do_wait(struct wait_opts *wo)
 {
-	struct task_struct *tsk;
 	int retval;
 
 	trace_sched_process_wait(wo->wo_pid);
@@ -1463,19 +1504,27 @@ static long do_wait(struct wait_opts *wo)
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	read_lock(&tasklist_lock);
-	tsk = current;
-	do {
-		retval = do_wait_thread(wo, tsk);
-		if (retval)
-			goto end;
 
-		retval = ptrace_do_wait(wo, tsk);
+	if (wo->wo_type == PIDTYPE_PID) {
+		retval = do_wait_pid(wo);
 		if (retval)
 			goto end;
+	} else {
+		struct task_struct *tsk = current;
+
+		do {
+			retval = do_wait_thread(wo, tsk);
+			if (retval)
+				goto end;
 
-		if (wo->wo_flags & __WNOTHREAD)
-			break;
-	} while_each_thread(current, tsk);
+			retval = ptrace_do_wait(wo, tsk);
+			if (retval)
+				goto end;
+
+			if (wo->wo_flags & __WNOTHREAD)
+				break;
+		} while_each_thread(current, tsk);
+	}
 	read_unlock(&tasklist_lock);
 
 notask:
-- 
2.30.1