BACKPORT: 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>

(cherry picked from commit 2ce7135adc9ad081aa3c49744144376ac74fea60)

Conflicts:
        Documentation/cgroup-v2.txt
        include/linux/cgroup.h
        kernel/cgroup/cgroup.c

(1. manual merge from Documentation/admin-guide/cgroup-v2.rst
2. manually merged changes from kernel/cgroup/cgroup.c into kernel/cgroup.c
3. manual merge in css_free_work_fn to allow psi support only for cgroup v2
4. manual merge in cgroup_create to allow psi support only for cgroup v2)

Bug: 111308141
Test: modified lmkd to use PSI and tested using lmkd_unit_test

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Change-Id: I2ffb9d50ba87f8b7655bed215a625784e098879c

8 files changed, 229 insertions, 9 deletions

diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt
index 3753a82..b8ca28b 100644
--- a/Documentation/accounting/psi.txt
+++ b/Documentation/accounting/psi.txt
@@ -62,3 +62,12 @@ well as medium and long term trends. The total absolute stall time is
 tracked and exported as well, to allow detection of latency spikes
 which wouldn't necessarily make a dent in the time averages, or to
 average trends over custom time frames.
+
+Cgroup2 interface
+=================
+
+In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem
+mounted, pressure stall information is also tracked for tasks grouped
+into cgroups. Each subdirectory in the cgroupfs mountpoint contains
+cpu.pressure, memory.pressure, and io.pressure files; the format is
+the same as the /proc/pressure/ files.
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 4cc07ce..73950fd 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -717,6 +717,12 @@ All time durations are in microseconds.
 	$PERIOD duration.  If only one number is written, $MAX is
 	updated.
 
+  cpu.pressure
+	A read-only nested-key file which exists on non-root cgroups.
+
+	Shows pressure stall information for CPU. See
+	Documentation/accounting/psi.txt for details.
+
 
 5-2. Memory
 
@@ -925,6 +931,12 @@ PAGE_SIZE multiple when read back.
 	Swap usage hard limit.  If a cgroup's swap usage reaches this
 	limit, anonymous meomry of the cgroup will not be swapped out.
 
+  memory.pressure
+	A read-only nested-key file which exists on non-root cgroups.
+
+	Shows pressure stall information for memory. See
+	Documentation/accounting/psi.txt for details.
+
 
 5-2-2. Usage Guidelines
 
@@ -1055,6 +1067,12 @@ blk-mq devices.
 
 	  8:16 rbps=2097152 wbps=max riops=max wiops=max
 
+  io.pressure
+	A read-only nested-key file which exists on non-root cgroups.
+
+	Shows pressure stall information for IO. See
+	Documentation/accounting/psi.txt for details.
+
 
 5-3-2. Writeback
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 9c72b21..6ac410b 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -17,6 +17,7 @@
 #include <linux/percpu-rwsem.h>
 #include <linux/workqueue.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/psi_types.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -302,6 +303,9 @@ 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 8a76712..9a5966f 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -614,6 +614,11 @@ 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)
 {
 	/*
@@ -656,6 +661,16 @@ static inline int cgroup_init(void) { return 0; }
 static inline void cgroup_init_kthreadd(void) {}
 static inline void cgroup_kthread_ready(void) {}
 
+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 b0daf05..8e0725a 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 */
diff --git a/init/Kconfig b/init/Kconfig
index 56725a4..f59eafe 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -490,6 +490,10 @@ config PSI
 	  the share of walltime in which some or all tasks in the system are
 	  delayed due to contention of the respective resource.
 
+	  In kernels with cgroup support, cgroups (cgroup2 only) will
+	  have cpu.pressure, memory.pressure, and io.pressure files,
+	  which aggregate pressure stalls for the grouped tasks only.
+
 	  For more details see Documentation/accounting/psi.txt.
 
 	  Say N if unsure.
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 42c9665..e918edb 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -62,6 +62,7 @@
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
 #include <linux/file.h>
+#include <linux/psi.h>
 #include <net/sock.h>
 
 #define CREATE_TRACE_POINTS
@@ -761,7 +762,7 @@ static void css_set_move_task(struct task_struct *task,
 		 */
 		WARN_ON_ONCE(task->flags & PF_EXITING);
 
-		rcu_assign_pointer(task->cgroups, to_cset);
+		cgroup_move_task(task, to_cset);
 		list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
 							     &to_cset->tasks);
 	}
@@ -3485,6 +3486,21 @@ static int cgroup_events_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
+#ifdef CONFIG_PSI
+static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
+{
+	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO);
+}
+static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
+{
+	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM);
+}
+static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
+{
+	return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU);
+}
+#endif
+
 static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
@@ -4900,6 +4916,23 @@ static struct cftype cgroup_dfl_base_files[] = {
 		.file_offset = offsetof(struct cgroup, events_file),
 		.seq_show = cgroup_events_show,
 	},
+#ifdef CONFIG_PSI
+	{
+		.name = "io.pressure",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_io_pressure_show,
+	},
+	{
+		.name = "memory.pressure",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_memory_pressure_show,
+	},
+	{
+		.name = "cpu.pressure",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_cpu_pressure_show,
+	},
+#endif
 	{ }	/* terminate */
 };
 
@@ -5005,6 +5038,8 @@ static void css_free_work_fn(struct work_struct *work)
 			 */
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
+			if (cgroup_on_dfl(cgrp))
+				psi_cgroup_free(cgrp);
 			kfree(cgrp);
 		} else {
 			/*
@@ -5274,6 +5309,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	if (!cgroup_on_dfl(cgrp))
 		cgrp->subtree_control = cgroup_control(cgrp);
 
+	if (cgroup_on_dfl(cgrp)) {
+		ret = psi_cgroup_alloc(cgrp);
+		if (ret)
+			goto out_idr_free;
+	}
+
 	if (parent)
 		cgroup_bpf_inherit(cgrp, parent);
 
@@ -5281,6 +5322,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 
 	return cgrp;
 
+out_idr_free:
+	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 5954145..7cdecfc 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -473,9 +473,35 @@ static void psi_group_change(struct psi_group *group, int cpu,
 		schedule_delayed_work(&group->clock_work, PSI_FREQ);
 }
 
+static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
+{
+#ifdef CONFIG_CGROUPS
+	struct cgroup *cgroup = NULL;
+
+	if (!*iter)
+		cgroup = task->cgroups->dfl_cgrp;
+	else if (*iter == &psi_system)
+		return NULL;
+	else
+		cgroup = cgroup_parent(*iter);
+
+	if (cgroup && cgroup_parent(cgroup)) {
+		*iter = cgroup;
+		return cgroup_psi(cgroup);
+	}
+#else
+	if (*iter)
+		return NULL;
+#endif
+	*iter = &psi_system;
+	return &psi_system;
+}
+
 void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
+	struct psi_group *group;
+	void *iter = NULL;
 
 	if (!task->pid)
 		return;
@@ -492,17 +518,23 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 	task->psi_flags &= ~clear;
 	task->psi_flags |= set;
 
-	psi_group_change(&psi_system, cpu, clear, set);
+	while ((group = iterate_groups(task, &iter)))
+		psi_group_change(group, cpu, clear, set);
 }
 
 void psi_memstall_tick(struct task_struct *task, int cpu)
 {
-	struct psi_group_cpu *groupc;
+	struct psi_group *group;
+	void *iter = NULL;
 
-	groupc = per_cpu_ptr(psi_system.pcpu, cpu);
-	write_seqcount_begin(&groupc->seq);
-	record_times(groupc, cpu, true);
-	write_seqcount_end(&groupc->seq);
+	while ((group = iterate_groups(task, &iter))) {
+		struct psi_group_cpu *groupc;
+
+		groupc = per_cpu_ptr(group->pcpu, cpu);
+		write_seqcount_begin(&groupc->seq);
+		record_times(groupc, cpu, true);
+		write_seqcount_end(&groupc->seq);
+	}
 }
 
 /**
@@ -565,8 +597,78 @@ void psi_memstall_leave(unsigned long *flags)
 	rq_unlock_irq(rq, &rf);
 }
 
-static int psi_show(struct seq_file *m, struct psi_group *group,
-		    enum psi_res res)
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgroup)
+{
+	if (psi_disabled)
+		return 0;
+
+	cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu);
+	if (!cgroup->psi.pcpu)
+		return -ENOMEM;
+	group_init(&cgroup->psi);
+	return 0;
+}
+
+void psi_cgroup_free(struct cgroup *cgroup)
+{
+	if (psi_disabled)
+		return;
+
+	cancel_delayed_work_sync(&cgroup->psi.clock_work);
+	free_percpu(cgroup->psi.pcpu);
+}
+
+/**
+ * cgroup_move_task - move task to a different cgroup
+ * @task: the task
+ * @to: the target css_set
+ *
+ * Move task to a new cgroup and safely migrate its associated stall
+ * state between the different groups.
+ *
+ * This function acquires the task's rq lock to lock out concurrent
+ * changes to the task's scheduling state and - in case the task is
+ * running - concurrent changes to its stall state.
+ */
+void cgroup_move_task(struct task_struct *task, struct css_set *to)
+{
+	bool move_psi = !psi_disabled;
+	unsigned int task_flags = 0;
+	struct rq_flags rf;
+	struct rq *rq;
+
+	if (move_psi) {
+		rq = task_rq_lock(task, &rf);
+
+		if (task_on_rq_queued(task))
+			task_flags = TSK_RUNNING;
+		else if (task->in_iowait)
+			task_flags = TSK_IOWAIT;
+
+		if (task->flags & PF_MEMSTALL)
+			task_flags |= TSK_MEMSTALL;
+
+		if (task_flags)
+			psi_task_change(task, task_flags, 0);
+	}
+
+	/*
+	 * Lame to do this here, but the scheduler cannot be locked
+	 * from the outside, so we move cgroups from inside sched/.
+	 */
+	rcu_assign_pointer(task->cgroups, to);
+
+	if (move_psi) {
+		if (task_flags)
+			psi_task_change(task, 0, task_flags);
+
+		task_rq_unlock(rq, task, &rf);
+	}
+}
+#endif /* CONFIG_CGROUPS */
+
+int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 {
 	int full;