psi: cgroup support

On a system that executes multiple cgrouped jobs and independent
workloads, we don't just care about the health of the overall system, but
also that of individual jobs, so that we can ensure individual job health,
fairness between jobs, or prioritize some jobs over others.

This patch implements pressure stall tracking for cgroups.  In kernels
with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure,
and io.pressure files that track aggregate pressure stall times for only
the tasks inside the cgroup.

Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 44 insertions, 0 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 22254c1fe1c5..5e1694fe035b 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -20,6 +20,7 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/workqueue.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/psi_types.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -436,6 +437,9 @@ struct cgroup {
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
 
+	/* used to track pressure stalls */
+	struct psi_group psi;
+
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b622d6608605..9968332cceed 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -650,6 +650,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+	return &cgrp->psi;
+}
+
 static inline void cgroup_init_kthreadd(void)
 {
 	/*
@@ -703,6 +708,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
 	return NULL;
 }
 
+static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
+{
+	return NULL;
+}
+
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+	return NULL;
+}
+
 static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 					       struct cgroup *ancestor)
 {
diff --git a/include/linux/psi.h b/include/linux/psi.h
index b0daf050de58..8e0725aac0aa 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -4,6 +4,9 @@
 #include <linux/psi_types.h>
 #include <linux/sched.h>
 
+struct seq_file;
+struct css_set;
+
 #ifdef CONFIG_PSI
 
 extern bool psi_disabled;
@@ -16,6 +19,14 @@ void psi_memstall_tick(struct task_struct *task, int cpu);
 void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 
+int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
+
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgrp);
+void psi_cgroup_free(struct cgroup *cgrp);
+void cgroup_move_task(struct task_struct *p, struct css_set *to);
+#endif
+
 #else /* CONFIG_PSI */
 
 static inline void psi_init(void) {}
@@ -23,6 +34,20 @@ static inline void psi_init(void) {}
 static inline void psi_memstall_enter(unsigned long *flags) {}
 static inline void psi_memstall_leave(unsigned long *flags) {}
 
+#ifdef CONFIG_CGROUPS
+static inline int psi_cgroup_alloc(struct cgroup *cgrp)
+{
+	return 0;
+}
+static inline void psi_cgroup_free(struct cgroup *cgrp)
+{
+}
+static inline void cgroup_move_task(struct task_struct *p, struct css_set *to)
+{
+	rcu_assign_pointer(p->cgroups, to);
+}
+#endif
+
 #endif /* CONFIG_PSI */
 
 #endif /* _LINUX_PSI_H */