linux-kernel - [PATCH v2] do_wait: make PIDTYPE

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210309161548.18786-1-jnewsome@torproject.org>
Date:   Tue,  9 Mar 2021 10:15:48 -0600
From:   Jim Newsome <jnewsome@...project.org>
To:     Andrew Morton <akpm@...ux-foundation.org>
Cc:     Oleg Nesterov <oleg@...hat.com>,
        "Eric W . Biederman" <ebiederm@...ssion.com>,
        Christian Brauner <christian@...uner.io>,
        linux-kernel@...r.kernel.org, Jim Newsome <jnewsome@...project.org>
Subject: [PATCH v2] do_wait: make PIDTYPE_PID case O(1) instead of O(n)

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
---
 kernel/exit.c | 54 ++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 45 insertions(+), 9 deletions(-)

diff --git a/kernel/exit.c b/kernel/exit.c
index 04029e35e69a..312c4dfc9555 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1439,6 +1439,33 @@ void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
 			   TASK_INTERRUPTIBLE, p);
 }
 
+// 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, struct task_struct *tsk)
+{
+	struct task_struct *target = pid_task(wo->wo_pid, PIDTYPE_PID);
+	if (!target) {
+		return 0;
+	}
+	if (tsk == target->real_parent ||
+	    (!(wo->wo_flags & __WNOTHREAD) &&
+	     same_thread_group(tsk, target->real_parent))) {
+		int retval = wait_consider_task(wo, /* ptrace= */ 0, target);
+		if (retval) {
+			return retval;
+		}
+	}
+	if (target->ptrace && (tsk == target->parent ||
+			       (!(wo->wo_flags & __WNOTHREAD) &&
+				same_thread_group(tsk, target->parent)))) {
+		int retval = wait_consider_task(wo, /* ptrace= */ 1, target);
+		if (retval) {
+			return retval;
+		}
+	}
+	return 0;
+}
+
 static long do_wait(struct wait_opts *wo)
 {
 	struct task_struct *tsk;
@@ -1464,18 +1491,27 @@ 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 (retval)
+	if (wo->wo_type == PIDTYPE_PID) {
+		retval = do_wait_pid(wo, tsk);
+		if (retval) {
 			goto end;
+		}
+	} else {
+		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