summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-06-06 09:59:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-06 09:59:34 -0700
commit4a7e89c5ec0238017a757131eb9ab8dc111f961c (patch)
tree17b7e40564d50e1d813371055bc3b2a668ceffc2
parent3c0ad98c2eda5ff30d23777e30744be6f7b8f097 (diff)
parent936f2a70f2077f64fab1dcb3eca71879e82ecd3f (diff)
downloadlinux-4a7e89c5ec0238017a757131eb9ab8dc111f961c.tar.bz2
Merge branch 'for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup updates from Tejun Heo: "Just two patches: one to add system-level cpu.stat to the root cgroup for convenience and a trivial comment update" * 'for-5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: cgroup: add cpu.stat file to root cgroup cgroup: Remove stale comments
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst6
-rw-r--r--kernel/cgroup/cgroup.c10
-rw-r--r--kernel/cgroup/rstat.c60
3 files changed, 55 insertions, 21 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index b8c0460730f3..c2a4b652bd1a 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -714,9 +714,7 @@ Conventions
- Settings for a single feature should be contained in a single file.
- The root cgroup should be exempt from resource control and thus
- shouldn't have resource control interface files. Also,
- informational files on the root cgroup which end up showing global
- information available elsewhere shouldn't exist.
+ shouldn't have resource control interface files.
- The default time unit is microseconds. If a different unit is ever
used, an explicit unit suffix must be present.
@@ -985,7 +983,7 @@ CPU Interface Files
All time durations are in microseconds.
cpu.stat
- A read-only flat-keyed file which exists on non-root cgroups.
+ A read-only flat-keyed file.
This file exists whether the controller is enabled or not.
It always reports the following three stats:
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 557a9b9d2244..1ea181a58465 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -153,11 +153,7 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu);
-/*
- * The default hierarchy, reserved for the subsystems that are otherwise
- * unattached - it never has more than a single cgroup, and all tasks are
- * part of that cgroup.
- */
+/* the default hierarchy */
struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu };
EXPORT_SYMBOL_GPL(cgrp_dfl_root);
@@ -251,9 +247,6 @@ bool cgroup_ssid_enabled(int ssid)
* cases where a subsystem should behave differnetly depending on the
* interface version.
*
- * The set of behaviors which change on the default hierarchy are still
- * being determined and the mount option is prefixed with __DEVEL__.
- *
* List of changed behaviors:
*
* - Mount options "noprefix", "xattr", "clone_children", "release_agent"
@@ -4881,7 +4874,6 @@ static struct cftype cgroup_base_files[] = {
},
{
.name = "cpu.stat",
- .flags = CFTYPE_NOT_ON_ROOT,
.seq_show = cpu_stat_show,
},
#ifdef CONFIG_PSI
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 41ca996568df..b6397a186ce9 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -389,18 +389,62 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
cgroup_base_stat_cputime_account_end(cgrp, rstatc);
}
+/*
+ * compute the cputime for the root cgroup by getting the per cpu data
+ * at a global level, then categorizing the fields in a manner consistent
+ * with how it is done by __cgroup_account_cputime_field for each bit of
+ * cpu time attributed to a cgroup.
+ */
+static void root_cgroup_cputime(struct task_cputime *cputime)
+{
+ int i;
+
+ cputime->stime = 0;
+ cputime->utime = 0;
+ cputime->sum_exec_runtime = 0;
+ for_each_possible_cpu(i) {
+ struct kernel_cpustat kcpustat;
+ u64 *cpustat = kcpustat.cpustat;
+ u64 user = 0;
+ u64 sys = 0;
+
+ kcpustat_cpu_fetch(&kcpustat, i);
+
+ user += cpustat[CPUTIME_USER];
+ user += cpustat[CPUTIME_NICE];
+ cputime->utime += user;
+
+ sys += cpustat[CPUTIME_SYSTEM];
+ sys += cpustat[CPUTIME_IRQ];
+ sys += cpustat[CPUTIME_SOFTIRQ];
+ cputime->stime += sys;
+
+ cputime->sum_exec_runtime += user;
+ cputime->sum_exec_runtime += sys;
+ cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
+ cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST];
+ cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST_NICE];
+ }
+}
+
void cgroup_base_stat_cputime_show(struct seq_file *seq)
{
struct cgroup *cgrp = seq_css(seq)->cgroup;
u64 usage, utime, stime;
-
- if (!cgroup_parent(cgrp))
- return;
-
- cgroup_rstat_flush_hold(cgrp);
- usage = cgrp->bstat.cputime.sum_exec_runtime;
- cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime);
- cgroup_rstat_flush_release();
+ struct task_cputime cputime;
+
+ if (cgroup_parent(cgrp)) {
+ cgroup_rstat_flush_hold(cgrp);
+ usage = cgrp->bstat.cputime.sum_exec_runtime;
+ cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
+ &utime, &stime);
+ cgroup_rstat_flush_release();
+ } else {
+ root_cgroup_cputime(&cputime);
+ usage = cputime.sum_exec_runtime;
+ utime = cputime.utime;
+ stime = cputime.stime;
+ }
do_div(usage, NSEC_PER_USEC);
do_div(utime, NSEC_PER_USEC);