linux-kernel - BFS 420: nuke the sticky bits

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>] [day] [month] [year] [list]

Message-ID: <CAJd=RBAEavw-LE94_j9-9uz2c+SRjgzoRuHVAxyjGa7ac3j9+g@mail.gmail.com>
Date:	Tue, 15 May 2012 21:25:03 +0800
From:	Hillf Danton <dhillf@...il.com>
To:	LKML <linux-kernel@...r.kernel.org>,
	Hillf Danton <dhillf@...il.com>
Subject: BFS 420: nuke the sticky bits

Right task could be selected without maitaining the sticky stuff but based on
CPU cache locality.

--- a/kernel/sched/bfs.c	Mon May 14 20:50:38 2012
+++ b/kernel/sched/bfs.c	Tue May 15 21:12:54 2012
@@ -1095,6 +1095,7 @@ resched_closest_idle(struct rq *rq, int
 static inline void
 swap_sticky(struct rq *rq, int cpu, struct task_struct *p)
 {
+	return;
 	if (rq->sticky_task) {
 		if (rq->sticky_task == p) {
 			p->sticky = true;
@@ -3065,18 +3066,11 @@ task_struct *earliest_deadline_task(stru
 				continue;

 			/*
-			 * Soft affinity happens here by not scheduling a task
-			 * with its sticky flag set that ran on a different CPU
-			 * last when the CPU is scaling, or by greatly biasing
-			 * against its deadline when not, based on cpu cache
-			 * locality.
+			 * Soft affinity happens here by biasing against
+			 * deadline when the CPU is scaling, based on CPU
+			 * cache locality.
 			 */
-			if (task_sticky(p) && task_rq(p) != rq) {
-				if (scaling_rq(rq))
-					continue;
-				dl = p->deadline << locality_diff(p, rq);
-			} else
-				dl = p->deadline;
+			dl = p->deadline << (locality_diff(p, rq) + !!scaling_rq(rq));

 			if (deadline_before(dl, earliest_deadline)) {
 				earliest_deadline = dl;
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/