Merge: Sched/psi: updates to v6.3-rc1

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/2325

JIRA: https://issues.redhat.com/browse/RHEL-311
Tested: Enabled PSI and ran various stress tests.

Updates and bug fixes for the PSI subsystem. This brings
the code up to about v6.3-rc1. It does not include the
runtime enablement interface (34f26a1 "sched/psi: Per-cgroup
PSI accounting disable/re-enable interfaceas") that required a larger
set of cgroup and kernfs patches. That may be take later if the
prerequisites are provided.

Signed-off-by: Phil Auld <pauld@redhat.com>

Approved-by: Waiman Long <longman@redhat.com>
Approved-by: Rafael Aquini <aquini@redhat.com>
Approved-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Approved-by: Jerry Snitselaar <jsnitsel@redhat.com>

Signed-off-by: Jan Stancek <jstancek@redhat.com>

Author: jstancek

Documentation/admin-guide/cgroup-v2.rst

@@ -968,6 +968,12 @@ All cgroup core files are prefixed with "cgroup."
 	killing cgroups is a process directed operation, i.e. it affects
 	the whole thread-group.
 
+  irq.pressure
+	A read-write nested-keyed file.
+
+	Shows pressure stall information for IRQ/SOFTIRQ. See
+	:ref:`Documentation/accounting/psi.rst <psi>` for details.
+
 Controllers
 ===========
 

include/linux/cgroup.h

@@ -673,11 +673,6 @@ 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;
-}
-
 bool cgroup_psi_enabled(void);
 
 static inline void cgroup_init_kthreadd(void)

include/linux/psi.h

@@ -5,6 +5,8 @@
 #include <linux/psi_types.h>
 #include <linux/sched.h>
 #include <linux/poll.h>
+#include <linux/cgroup-defs.h>
+#include <linux/cgroup.h>
 
 struct seq_file;
 struct css_set;
@@ -16,10 +18,6 @@ extern struct psi_group psi_system;
 
 void psi_init(void);
 
-void psi_task_change(struct task_struct *task, int clear, int set);
-void psi_task_switch(struct task_struct *prev, struct task_struct *next,
-		     bool sleep);
-
 void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 
@@ -32,6 +30,11 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
 			poll_table *wait);
 
 #ifdef CONFIG_CGROUPS
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+	return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+}
+
 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);

include/linux/psi_types.h

@@ -15,27 +15,36 @@ enum psi_task_count {
 	NR_MEMSTALL,
 	NR_RUNNING,
 	/*
-	 * This can't have values other than 0 or 1 and could be
-	 * implemented as a bit flag. But for now we still have room
-	 * in the first cacheline of psi_group_cpu, and this way we
-	 * don't have to special case any state tracking for it.
+	 * For IO and CPU stalls the presence of running/oncpu tasks
+	 * in the domain means a partial rather than a full stall.
+	 * For memory it's not so simple because of page reclaimers:
+	 * they are running/oncpu while representing a stall. To tell
+	 * whether a domain has productivity left or not, we need to
+	 * distinguish between regular running (i.e. productive)
+	 * threads and memstall ones.
 	 */
-	NR_ONCPU,
+	NR_MEMSTALL_RUNNING,
 	NR_PSI_TASK_COUNTS = 4,
 };
 
 /* Task state bitmasks */
 #define TSK_IOWAIT	(1 << NR_IOWAIT)
 #define TSK_MEMSTALL	(1 << NR_MEMSTALL)
 #define TSK_RUNNING	(1 << NR_RUNNING)
-#define TSK_ONCPU	(1 << NR_ONCPU)
+#define TSK_MEMSTALL_RUNNING	(1 << NR_MEMSTALL_RUNNING)
+
+/* Only one task can be scheduled, no corresponding task count */
+#define TSK_ONCPU	(1 << NR_PSI_TASK_COUNTS)
 
 /* Resources that workloads could be stalled on */
 enum psi_res {
 	PSI_IO,
 	PSI_MEM,
 	PSI_CPU,
-	NR_PSI_RESOURCES = 3,
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	PSI_IRQ,
+#endif
+	NR_PSI_RESOURCES,
 };
 
 /*
@@ -51,11 +60,20 @@ enum psi_states {
 	PSI_MEM_FULL,
 	PSI_CPU_SOME,
 	PSI_CPU_FULL,
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	PSI_IRQ_FULL,
+#endif
 	/* Only per-CPU, to weigh the CPU in the global average: */
 	PSI_NONIDLE,
-	NR_PSI_STATES = 7,
+	NR_PSI_STATES,
 };
 
+/* Use one bit in the state mask to track TSK_ONCPU */
+#define PSI_ONCPU	(1 << NR_PSI_STATES)
+
+/* Flag whether to re-arm avgs_work, see details in get_recent_times() */
+#define PSI_STATE_RESCHEDULE	(1 << (NR_PSI_STATES + 1))
+
 enum psi_aggregators {
 	PSI_AVGS = 0,
 	PSI_POLL,
@@ -135,6 +153,8 @@ struct psi_trigger {
 };
 
 struct psi_group {
+	struct psi_group *parent;
+
 	/* Protects data used by the aggregator */
 	struct mutex avgs_lock;
 
@@ -158,6 +178,7 @@ struct psi_group {
 	struct timer_list poll_timer;
 	wait_queue_head_t poll_wait;
 	atomic_t poll_wakeup;
+	atomic_t poll_scheduled;
 
 	/* Protects data used by the monitor */
 	struct mutex trigger_lock;

include/linux/sched.h

@@ -902,9 +902,6 @@ struct task_struct {
 	unsigned			sched_reset_on_fork:1;
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
-#ifdef CONFIG_PSI
-	unsigned			sched_psi_wake_requeue:1;
-#endif
 
 	/* Force alignment to the next boundary: */
 	unsigned			:0;

include/linux/wait.h

@@ -217,6 +217,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void
 void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
 void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
 void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
+void __wake_up_pollfree(struct wait_queue_head *wq_head);
 
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
@@ -245,6 +246,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
 #define wake_up_interruptible_sync_poll_locked(x, m)				\
 	__wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
 
+/**
+ * wake_up_pollfree - signal that a polled waitqueue is going away
+ * @wq_head: the wait queue head
+ *
+ * In the very rare cases where a ->poll() implementation uses a waitqueue whose
+ * lifetime is tied to a task rather than to the 'struct file' being polled,
+ * this function must be called before the waitqueue is freed so that
+ * non-blocking polls (e.g. epoll) are notified that the queue is going away.
+ *
+ * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via
+ * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU.
+ */
+static inline void wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	/*
+	 * For performance reasons, we don't always take the queue lock here.
+	 * Therefore, we might race with someone removing the last entry from
+	 * the queue, and proceed while they still hold the queue lock.
+	 * However, rcu_read_lock() is required to be held in such cases, so we
+	 * can safely proceed with an RCU-delayed free.
+	 */
+	if (waitqueue_active(wq_head))
+		__wake_up_pollfree(wq_head);
+}
+
 #define ___wait_cond_timeout(condition)						\
 ({										\
 	bool __cond = (condition);						\

kernel/cgroup/cgroup.c

@@ -3683,21 +3683,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v)
 static int cgroup_io_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_IO);
 }
 static int cgroup_memory_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_MEM);
 }
 static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	struct psi_group *psi = cgroup_psi(cgrp);
 
 	return psi_show(seq, psi, PSI_CPU);
 }
@@ -3723,7 +3723,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
 		return -EBUSY;
 	}
 
-	psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
+	psi = cgroup_psi(cgrp);
 	new = psi_trigger_create(psi, buf, res);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
@@ -3757,6 +3757,23 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of,
 	return cgroup_pressure_write(of, buf, nbytes, PSI_CPU);
 }
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static int cgroup_irq_pressure_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+	struct psi_group *psi = cgroup_psi(cgrp);
+
+	return psi_show(seq, psi, PSI_IRQ);
+}
+
+static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of,
+					 char *buf, size_t nbytes,
+					 loff_t off)
+{
+	return cgroup_pressure_write(of, buf, nbytes, PSI_IRQ);
+}
+#endif
+
 static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 					  poll_table *pt)
 {
@@ -3774,6 +3791,9 @@ static void cgroup_pressure_release(struct kernfs_open_file *of)
 
 bool cgroup_psi_enabled(void)
 {
+	if (static_branch_likely(&psi_disabled))
+		return false;
+
 	return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0;
 }
 
@@ -5150,6 +5170,16 @@ static struct cftype cgroup_base_files[] = {
 		.poll = cgroup_pressure_poll,
 		.release = cgroup_pressure_release,
 	},
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	{
+		.name = "irq.pressure",
+		.flags = CFTYPE_PRESSURE,
+		.seq_show = cgroup_irq_pressure_show,
+		.write = cgroup_irq_pressure_write,
+		.poll = cgroup_pressure_poll,
+		.release = cgroup_pressure_release,
+	},
+#endif
 #endif /* CONFIG_PSI */
 	{ }	/* terminate */
 };

kernel/sched/core.c

@@ -709,6 +709,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->prev_irq_time += irq_delta;
 	delta -= irq_delta;
+	psi_account_irqtime(rq->curr, irq_delta);
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 	if (static_key_false((&paravirt_steal_rq_enabled))) {
@@ -2100,7 +2101,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!(flags & ENQUEUE_RESTORE)) {
 		sched_info_enqueue(rq, p);
-		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+		psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED));
 	}
 
 	uclamp_rq_inc(rq, p);