linux-kernel - [PATCH cgroup/for-5.5] cgroup: use cgroup->last_bstat instead of cgroup->bstat

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: <20191106204957.GT3622521@devbig004.ftw2.facebook.com>
Date:   Wed, 6 Nov 2019 12:49:57 -0800
From:   Tejun Heo <tj@...nel.org>
To:     cgroups@...r.kernel.org
Cc:     Li Zefan <lizefan@...wei.com>,
        Johannes Weiner <hannes@...xchg.org>, kernel-team@...com,
        linux-kernel@...r.kernel.org
Subject: [PATCH cgroup/for-5.5] cgroup: use cgroup->last_bstat instead of
 cgroup->bstat_pending for consistency

cgroup->bstat_pending is used to determine the base stat delta to
propagate to the parent.  While correct, this is different from how
percpu delta is determined for no good reason and the inconsistency
makes the code more difficult to understand.

This patch makes parent propagation delta calculation use the same
method as percpu to global propagation.

* cgroup_base_stat_accumulate() is renamed to cgroup_base_stat_add()
  and cgroup_base_stat_sub() is added.

* percpu propagation calculation is updated to use the above helpers.

* cgroup->bstat_pending is replaced with cgroup->last_bstat and
  updated to use the same calculation as percpu propagation.

Signed-off-by: Tejun Heo <tj@...nel.org>
---
Applying to cgroup/for-5.5.

Thanks.

 include/linux/cgroup-defs.h |    2 -
 kernel/cgroup/rstat.c       |   46 +++++++++++++++++++++++---------------------
 2 files changed, 26 insertions(+), 22 deletions(-)

--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -458,7 +458,7 @@ struct cgroup {
 	struct list_head rstat_css_list;
 
 	/* cgroup basic resource statistics */
-	struct cgroup_base_stat pending_bstat;	/* pending from children */
+	struct cgroup_base_stat last_bstat;
 	struct cgroup_base_stat bstat;
 	struct prev_cputime prev_cputime;	/* for printing out cputime */
 
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -304,44 +304,48 @@ void __init cgroup_rstat_boot(void)
  * Functions for cgroup basic resource statistics implemented on top of
  * rstat.
  */
-static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat,
-					struct cgroup_base_stat *src_bstat)
+static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
+				 struct cgroup_base_stat *src_bstat)
 {
 	dst_bstat->cputime.utime += src_bstat->cputime.utime;
 	dst_bstat->cputime.stime += src_bstat->cputime.stime;
 	dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
 }
 
+static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
+				 struct cgroup_base_stat *src_bstat)
+{
+	dst_bstat->cputime.utime -= src_bstat->cputime.utime;
+	dst_bstat->cputime.stime -= src_bstat->cputime.stime;
+	dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime;
+}
+
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
 	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
-	struct task_cputime *last_cputime = &rstatc->last_bstat.cputime;
-	struct task_cputime cputime;
-	struct cgroup_base_stat delta;
+	struct cgroup_base_stat cur, delta;
 	unsigned seq;
 
 	/* fetch the current per-cpu values */
 	do {
 		seq = __u64_stats_fetch_begin(&rstatc->bsync);
-		cputime = rstatc->bstat.cputime;
+		cur.cputime = rstatc->bstat.cputime;
 	} while (__u64_stats_fetch_retry(&rstatc->bsync, seq));
 
-	/* calculate the delta to propgate */
-	delta.cputime.utime = cputime.utime - last_cputime->utime;
-	delta.cputime.stime = cputime.stime - last_cputime->stime;
-	delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime -
-					 last_cputime->sum_exec_runtime;
-	*last_cputime = cputime;
-
-	/* transfer the pending stat into delta */
-	cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat);
-	memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat));
-
-	/* propagate delta into the global stat and the parent's pending */
-	cgroup_base_stat_accumulate(&cgrp->bstat, &delta);
-	if (parent)
-		cgroup_base_stat_accumulate(&parent->pending_bstat, &delta);
+	/* propagate percpu delta to global */
+	delta = cur;
+	cgroup_base_stat_sub(&delta, &rstatc->last_bstat);
+	cgroup_base_stat_add(&cgrp->bstat, &delta);
+	cgroup_base_stat_add(&rstatc->last_bstat, &delta);
+
+	/* propagate global delta to parent */
+	if (parent) {
+		delta = cgrp->bstat;
+		cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
+		cgroup_base_stat_add(&parent->bstat, &delta);
+		cgroup_base_stat_add(&cgrp->last_bstat, &delta);
+	}
 }
 
 static struct cgroup_rstat_cpu *