[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20211205183220.818872-6-longman@redhat.com>
Date: Sun, 5 Dec 2021 13:32:18 -0500
From: Waiman Long <longman@...hat.com>
To: Tejun Heo <tj@...nel.org>, Zefan Li <lizefan.x@...edance.com>,
Johannes Weiner <hannes@...xchg.org>,
Jonathan Corbet <corbet@....net>, Shuah Khan <shuah@...nel.org>
Cc: cgroups@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-kselftest@...r.kernel.org,
Andrew Morton <akpm@...ux-foundation.org>,
Roman Gushchin <guro@...com>, Phil Auld <pauld@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...hat.com>,
Frederic Weisbecker <frederic@...nel.org>,
Marcelo Tosatti <mtosatti@...hat.com>,
Michal Koutný <mkoutny@...e.com>,
Waiman Long <longman@...hat.com>
Subject: [PATCH v9 5/7] cgroup/cpuset: Show invalid partition reason string
There are a number of different reasons which can cause a partition to
become invalid. A user seeing an invalid partition may not know exactly
why. To help user to get a better understanding of the underlying reason,
The cpuset.cpus.partition control file, when read, will now report the
reason why a partition become invalid. When a partition does become
invalid, reading the control file will show "root invalid (<reason>)"
where <reason> is a string that describes why the partition is invalid.
Signed-off-by: Waiman Long <longman@...hat.com>
---
kernel/cgroup/cpuset.c | 58 ++++++++++++++++++++++++++++++++++++++----
1 file changed, 53 insertions(+), 5 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index cfab10911682..d1025470b9ea 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -85,6 +85,26 @@ struct fmeter {
spinlock_t lock; /* guards read or write of above */
};
+/*
+ * Invalid partition error code
+ */
+enum prs_errcode {
+ PERR_NONE = 0,
+ PERR_INVCPUS,
+ PERR_INVPARENT,
+ PERR_NOTPART,
+ PERR_NOCPUS,
+ PERR_HOTPLUG,
+};
+
+static const char * const perr_strings[] = {
+ [PERR_INVCPUS] = "Invalid change to cpuset.cpus",
+ [PERR_INVPARENT] = "Parent is an invalid partition root",
+ [PERR_NOTPART] = "Parent is not a partition root",
+ [PERR_NOCPUS] = "Parent unable to distribute cpu downstream",
+ [PERR_HOTPLUG] = "No cpu available due to hotplug",
+};
+
struct cpuset {
struct cgroup_subsys_state css;
@@ -168,6 +188,9 @@ struct cpuset {
int use_parent_ecpus;
int child_ecpus_count;
+ /* Invalid partition error code, not lock protected */
+ enum prs_errcode prs_err;
+
/* Handle for cpuset.cpus.partition */
struct cgroup_file partition_file;
};
@@ -282,8 +305,13 @@ static inline int is_partition_root(const struct cpuset *cs)
static inline void notify_partition_change(struct cpuset *cs,
int old_prs, int new_prs)
{
- if (old_prs != new_prs)
- cgroup_file_notify(&cs->partition_file);
+ if (old_prs == new_prs)
+ return;
+ cgroup_file_notify(&cs->partition_file);
+
+ /* Reset prs_err if not invalid */
+ if (new_prs != PRS_ERROR)
+ WRITE_ONCE(cs->prs_err, PERR_NONE);
}
static struct cpuset top_cpuset = {
@@ -1292,6 +1320,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
part_error = partition_is_populated(parent, cpuset) &&
cpumask_subset(parent->effective_cpus, tmp->addmask) &&
!cpumask_intersects(tmp->delmask, cpu_active_mask);
+
+ if ((READ_ONCE(cpuset->prs_err) == PERR_NONE) && part_error)
+ WRITE_ONCE(cpuset->prs_err, PERR_INVCPUS);
} else {
/*
* partcmd_update w/o newmask:
@@ -1315,6 +1346,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
!parent->nr_subparts_cpus) ||
(cpumask_equal(parent->effective_cpus, tmp->addmask) &&
partition_is_populated(parent, cpuset));
+
+ if (is_partition_root(cpuset) && part_error)
+ WRITE_ONCE(cpuset->prs_err, PERR_NOCPUS);
}
if (cmd == partcmd_update) {
@@ -1471,6 +1505,9 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
* invalid too.
*/
new_prs = PRS_ERROR;
+ WRITE_ONCE(cp->prs_err,
+ (parent->partition_root_state == PRS_ERROR)
+ ? PERR_INVPARENT : PERR_NOTPART);
break;
}
}
@@ -2632,7 +2669,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
static int sched_partition_show(struct seq_file *seq, void *v)
{
struct cpuset *cs = css_cs(seq_css(seq));
- const char *type;
+ const char *err, *type;
switch (cs->partition_root_state) {
case PRS_ENABLED:
@@ -2646,7 +2683,11 @@ static int sched_partition_show(struct seq_file *seq, void *v)
break;
case PRS_ERROR:
type = is_sched_load_balance(cs) ? "root" : "isolated";
- seq_printf(seq, "%s invalid\n", type);
+ err = perr_strings[READ_ONCE(cs->prs_err)];
+ if (err)
+ seq_printf(seq, "%s invalid (%s)\n", type, err);
+ else
+ seq_printf(seq, "%s invalid\n", type);
break;
}
return 0;
@@ -3236,7 +3277,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
if (is_partition_root(cs) &&
((cpumask_empty(&new_cpus) && partition_is_populated(cs, NULL)) ||
!parent->nr_subparts_cpus)) {
- int old_prs;
+ int old_prs, parent_prs;
update_parent_subparts_cpumask(cs, partcmd_disable,
NULL, tmp);
@@ -3249,10 +3290,17 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
}
old_prs = cs->partition_root_state;
+ parent_prs = parent->partition_root_state;
if (old_prs != PRS_ERROR) {
spin_lock_irq(&callback_lock);
cs->partition_root_state = PRS_ERROR;
spin_unlock_irq(&callback_lock);
+ if (parent_prs == PRS_ERROR)
+ WRITE_ONCE(cs->prs_err, PERR_INVPARENT);
+ else if (!parent_prs)
+ WRITE_ONCE(cs->prs_err, PERR_NOTPART);
+ else
+ WRITE_ONCE(cs->prs_err, PERR_HOTPLUG);
notify_partition_change(cs, old_prs, PRS_ERROR);
}
cpuset_force_rebuild();
--
2.27.0
Powered by blists - more mailing lists