linux-kernel - [PATCH 07/30] sched: Factor out cgroup weight conversion functions

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

Date:   Fri, 27 Jan 2023 14:16:16 -1000
From:   Tejun Heo <tj@...nel.org>
To:     torvalds@...ux-foundation.org, mingo@...hat.com,
        peterz@...radead.org, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        bristot@...hat.com, vschneid@...hat.com, ast@...nel.org,
        daniel@...earbox.net, andrii@...nel.org, martin.lau@...nel.org,
        joshdon@...gle.com, brho@...gle.com, pjt@...gle.com,
        derkling@...gle.com, haoluo@...gle.com, dvernet@...a.com,
        dschatzberg@...a.com, dskarlat@...cmu.edu, riel@...riel.com
Cc:     linux-kernel@...r.kernel.org, bpf@...r.kernel.org,
        kernel-team@...a.com, Tejun Heo <tj@...nel.org>
Subject: [PATCH 07/30] sched: Factor out cgroup weight conversion functions

Factor out sched_weight_from/to_cgroup() which convert between scheduler
shares and cgroup weight. No functional change. The factored out functions
will be used by a new BPF extensible sched_class so that the weights can be
exposed to the BPF programs in a way which is consistent cgroup weights and
easier to interpret.

Signed-off-by: Tejun Heo <tj@...nel.org>
Reviewed-by: David Vernet <dvernet@...a.com>
Acked-by: Josh Don <joshdon@...gle.com>
Acked-by: Hao Luo <haoluo@...gle.com>
Acked-by: Barret Rhoden <brho@...gle.com>
---
 kernel/sched/core.c  | 28 +++++++++++++---------------
 kernel/sched/sched.h | 18 ++++++++++++++++++
 2 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e6d5374edf58..70698725f6de 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11072,29 +11072,27 @@ static int cpu_extra_stat_show(struct seq_file *sf,
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static unsigned long tg_weight(struct task_group *tg)
+{
+	return scale_load_down(tg->shares);
+}
+
 static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
-	struct task_group *tg = css_tg(css);
-	u64 weight = scale_load_down(tg->shares);
-
-	return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
+	return sched_weight_to_cgroup(tg_weight(css_tg(css)));
 }
 
 static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
-				struct cftype *cft, u64 weight)
+				struct cftype *cft, u64 cgrp_weight)
 {
-	/*
-	 * cgroup weight knobs should use the common MIN, DFL and MAX
-	 * values which are 1, 100 and 10000 respectively.  While it loses
-	 * a bit of range on both ends, it maps pretty well onto the shares
-	 * value used by scheduler and the round-trip conversions preserve
-	 * the original value over the entire range.
-	 */
-	if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
+	unsigned long weight;
+
+	if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
 		return -ERANGE;
 
-	weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
+	weight = sched_weight_from_cgroup(cgrp_weight);
 
 	return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
@@ -11102,7 +11100,7 @@ static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
 static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
 				    struct cftype *cft)
 {
-	unsigned long weight = scale_load_down(css_tg(css)->shares);
+	unsigned long weight = tg_weight(css_tg(css));
 	int last_delta = INT_MAX;
 	int prio, delta;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c083395c5477..946fdb51b6e6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -435,6 +435,24 @@ struct task_group {
 #define MAX_SHARES		(1UL << 18)
 #endif
 
+/*
+ * cgroup weight knobs should use the common MIN, DFL and MAX values which are
+ * 1, 100 and 10000 respectively. While it loses a bit of range on both ends, it
+ * maps pretty well onto the shares value used by scheduler and the round-trip
+ * conversions preserve the original value over the entire range.
+ */
+static inline unsigned long sched_weight_from_cgroup(unsigned long cgrp_weight)
+{
+	return DIV_ROUND_CLOSEST_ULL(cgrp_weight * 1024, CGROUP_WEIGHT_DFL);
+}
+
+static inline unsigned long sched_weight_to_cgroup(unsigned long weight)
+{
+	return clamp_t(unsigned long,
+		       DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024),
+		       CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
+}
+
 typedef int (*tg_visitor)(struct task_group *, void *);
 
 extern int walk_tg_tree_from(struct task_group *from,
-- 
2.39.1