Merge tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Allow unprivileged PSI poll()ing

 - Fix performance regression introduced by mm_cid

 - Improve livepatch stalls by adding livepatch task switching to
   cond_resched(). This resolves livepatching busy-loop stalls with
   certain CPU-bound kthreads

 - Improve sched_move_task() performance on autogroup configs

 - On core-scheduling CPUs, avoid selecting throttled tasks to run

 - Misc cleanups, fixes and improvements

* tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/clock: Fix local_clock() before sched_clock_init()
  sched/rt: Fix bad task migration for rt tasks
  sched: Fix performance regression introduced by mm_cid
  sched/core: Make sched_dynamic_mutex static
  sched/psi: Allow unprivileged polling of N*2s period
  sched/psi: Extract update_triggers side effect
  sched/psi: Rename existing poll members in preparation
  sched/psi: Rearrange polling code in preparation
  sched/fair: Fix inaccurate tally of ttwu_move_affine
  vhost: Fix livepatch timeouts in vhost_worker()
  livepatch,sched: Add livepatch task switching to cond_resched()
  livepatch: Skip task_call_func() for current task
  livepatch: Convert stack entries array to percpu
  sched: Interleave cfs bandwidth timers for improved single thread performance at low utilization
  sched/core: Reduce cost of sched_move_task when config autogroup
  sched/core: Avoid selecting the task that is throttled to run when core-sched enable
  sched/topology: Make sched_energy_mutex,update static

Author: torvalds

Documentation/accounting/psi.rst

@@ -105,6 +105,10 @@ prevent overly frequent polling. Max limit is chosen as a high enough number
 after which monitors are most likely not needed and psi averages can be used
 instead.
 
+Unprivileged users can also create monitors, with the only limitation that the
+window size must be a multiple of 2s, in order to prevent excessive resource
+usage.
+
 When activated, psi monitor stays active for at least the duration of one
 tracking window to avoid repeated activations/deactivations when system is
 bouncing in and out of the stall state.

drivers/vhost/vhost.c

@@ -361,8 +361,7 @@ static int vhost_worker(void *data)
 			kcov_remote_start_common(worker->kcov_handle);
 			work->fn(work);
 			kcov_remote_stop();
-			if (need_resched())
-				schedule();
+			cond_resched();
 		}
 	}
 

include/linux/livepatch.h

@@ -13,6 +13,7 @@
 #include <linux/ftrace.h>
 #include <linux/completion.h>
 #include <linux/list.h>
+#include <linux/livepatch_sched.h>
 
 #if IS_ENABLED(CONFIG_LIVEPATCH)
 

include/linux/livepatch_sched.h

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_LIVEPATCH_SCHED_H_
+#define _LINUX_LIVEPATCH_SCHED_H_
+
+#include <linux/jump_label.h>
+#include <linux/static_call_types.h>
+
+#ifdef CONFIG_LIVEPATCH
+
+void __klp_sched_try_switch(void);
+
+#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+
+DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
+
+static __always_inline void klp_sched_try_switch(void)
+{
+	if (static_branch_unlikely(&klp_sched_try_switch_key))
+		__klp_sched_try_switch();
+}
+
+#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
+#else /* !CONFIG_LIVEPATCH */
+static inline void klp_sched_try_switch(void) {}
+static inline void __klp_sched_try_switch(void) {}
+#endif /* CONFIG_LIVEPATCH */
+
+#endif /* _LINUX_LIVEPATCH_SCHED_H_ */

include/linux/mm_types.h

@@ -573,6 +573,13 @@ struct vm_area_struct {
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
 
+#ifdef CONFIG_SCHED_MM_CID
+struct mm_cid {
+	u64 time;
+	int cid;
+};
+#endif
+
 struct kioctx_table;
 struct mm_struct {
 	struct {
@@ -623,15 +630,19 @@ struct mm_struct {
 		atomic_t mm_count;
 #ifdef CONFIG_SCHED_MM_CID
 		/**
-		 * @cid_lock: Protect cid bitmap updates vs lookups.
+		 * @pcpu_cid: Per-cpu current cid.
 		 *
-		 * Prevent situations where updates to the cid bitmap happen
-		 * concurrently with lookups. Those can lead to situations
-		 * where a lookup cannot find a free bit simply because it was
-		 * unlucky enough to load, non-atomically, bitmap words as they
-		 * were being concurrently updated by the updaters.
+		 * Keep track of the currently allocated mm_cid for each cpu.
+		 * The per-cpu mm_cid values are serialized by their respective
+		 * runqueue locks.
 		 */
-		raw_spinlock_t cid_lock;
+		struct mm_cid __percpu *pcpu_cid;
+		/*
+		 * @mm_cid_next_scan: Next mm_cid scan (in jiffies).
+		 *
+		 * When the next mm_cid scan is due (in jiffies).
+		 */
+		unsigned long mm_cid_next_scan;
 #endif
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* size of all page tables */
@@ -899,6 +910,37 @@ static inline void vma_iter_init(struct vma_iterator *vmi,
 }
 
 #ifdef CONFIG_SCHED_MM_CID
+
+enum mm_cid_state {
+	MM_CID_UNSET = -1U,		/* Unset state has lazy_put flag set. */
+	MM_CID_LAZY_PUT = (1U << 31),
+};
+
+static inline bool mm_cid_is_unset(int cid)
+{
+	return cid == MM_CID_UNSET;
+}
+
+static inline bool mm_cid_is_lazy_put(int cid)
+{
+	return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT);
+}
+
+static inline bool mm_cid_is_valid(int cid)
+{
+	return !(cid & MM_CID_LAZY_PUT);
+}
+
+static inline int mm_cid_set_lazy_put(int cid)
+{
+	return cid | MM_CID_LAZY_PUT;
+}
+
+static inline int mm_cid_clear_lazy_put(int cid)
+{
+	return cid & ~MM_CID_LAZY_PUT;
+}
+
 /* Accessor for struct mm_struct's cidmask. */
 static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
 {
@@ -912,16 +954,40 @@ static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
 
 static inline void mm_init_cid(struct mm_struct *mm)
 {
-	raw_spin_lock_init(&mm->cid_lock);
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i);
+
+		pcpu_cid->cid = MM_CID_UNSET;
+		pcpu_cid->time = 0;
+	}
 	cpumask_clear(mm_cidmask(mm));
 }
 
+static inline int mm_alloc_cid(struct mm_struct *mm)
+{
+	mm->pcpu_cid = alloc_percpu(struct mm_cid);
+	if (!mm->pcpu_cid)
+		return -ENOMEM;
+	mm_init_cid(mm);
+	return 0;
+}
+
+static inline void mm_destroy_cid(struct mm_struct *mm)
+{
+	free_percpu(mm->pcpu_cid);
+	mm->pcpu_cid = NULL;
+}
+
 static inline unsigned int mm_cid_size(void)
 {
 	return cpumask_size();
 }
 #else /* CONFIG_SCHED_MM_CID */
 static inline void mm_init_cid(struct mm_struct *mm) { }
+static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; }
+static inline void mm_destroy_cid(struct mm_struct *mm) { }
 static inline unsigned int mm_cid_size(void)
 {
 	return 0;

include/linux/psi.h

@@ -24,7 +24,7 @@ void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, enum psi_res res);
+			char *buf, enum psi_res res, struct file *file);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,

include/linux/psi_types.h

@@ -151,6 +151,9 @@ struct psi_trigger {
 
 	/* Deferred event(s) from previous ratelimit window */
 	bool pending_event;
+
+	/* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */
+	enum psi_aggregators aggregator;
 };
 
 struct psi_group {
@@ -171,30 +174,34 @@ struct psi_group {
 	/* Aggregator work control */
 	struct delayed_work avgs_work;
 
+	/* Unprivileged triggers against N*PSI_FREQ windows */
+	struct list_head avg_triggers;
+	u32 avg_nr_triggers[NR_PSI_STATES - 1];
+
 	/* Total stall times and sampled pressure averages */
 	u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1];
 	unsigned long avg[NR_PSI_STATES - 1][3];
 
-	/* Monitor work control */
-	struct task_struct __rcu *poll_task;
-	struct timer_list poll_timer;
-	wait_queue_head_t poll_wait;
-	atomic_t poll_wakeup;
-	atomic_t poll_scheduled;
+	/* Monitor RT polling work control */
+	struct task_struct __rcu *rtpoll_task;
+	struct timer_list rtpoll_timer;
+	wait_queue_head_t rtpoll_wait;
+	atomic_t rtpoll_wakeup;
+	atomic_t rtpoll_scheduled;
 
 	/* Protects data used by the monitor */
-	struct mutex trigger_lock;
-
-	/* Configured polling triggers */
-	struct list_head triggers;
-	u32 nr_triggers[NR_PSI_STATES - 1];
-	u32 poll_states;
-	u64 poll_min_period;
-
-	/* Total stall times at the start of monitor activation */
-	u64 polling_total[NR_PSI_STATES - 1];
-	u64 polling_next_update;
-	u64 polling_until;
+	struct mutex rtpoll_trigger_lock;
+
+	/* Configured RT polling triggers */
+	struct list_head rtpoll_triggers;
+	u32 rtpoll_nr_triggers[NR_PSI_STATES - 1];
+	u32 rtpoll_states;
+	u64 rtpoll_min_period;
+
+	/* Total stall times at the start of RT polling monitor activation */
+	u64 rtpoll_total[NR_PSI_STATES - 1];
+	u64 rtpoll_next_update;
+	u64 rtpoll_until;
 };
 
 #else /* CONFIG_PSI */

include/linux/sched.h

@@ -36,6 +36,7 @@
 #include <linux/seqlock.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
+#include <linux/livepatch_sched.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -1313,7 +1314,10 @@ struct task_struct {
 
 #ifdef CONFIG_SCHED_MM_CID
 	int				mm_cid;		/* Current cid in mm */
+	int				last_mm_cid;	/* Most recent cid in mm */
+	int				migrate_from_cpu;
 	int				mm_cid_active;	/* Whether cid bitmap is active */
+	struct callback_head		cid_work;
 #endif
 
 	struct tlbflush_unmap_batch	tlb_ubc;
@@ -2067,6 +2071,9 @@ extern int __cond_resched(void);
 
 #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
+void sched_dynamic_klp_enable(void);
+void sched_dynamic_klp_disable(void);
+
 DECLARE_STATIC_CALL(cond_resched, __cond_resched);
 
 static __always_inline int _cond_resched(void)
@@ -2075,27 +2082,33 @@ static __always_inline int _cond_resched(void)
 }
 
 #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+
 extern int dynamic_cond_resched(void);
 
 static __always_inline int _cond_resched(void)
 {
 	return dynamic_cond_resched();
 }
 
-#else
+#else /* !CONFIG_PREEMPTION */
 
 static inline int _cond_resched(void)
 {
+	klp_sched_try_switch();
 	return __cond_resched();
 }
 
-#endif /* CONFIG_PREEMPT_DYNAMIC */
+#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
-#else
+#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */
 
-static inline int _cond_resched(void) { return 0; }
+static inline int _cond_resched(void)
+{
+	klp_sched_try_switch();
+	return 0;
+}
 
-#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */
+#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */
 
 #define cond_resched() ({			\
 	__might_resched(__FILE__, __LINE__, 0);	\

include/linux/sched/mm.h

@@ -37,6 +37,11 @@ static inline void mmgrab(struct mm_struct *mm)
 	atomic_inc(&mm->mm_count);
 }
 
+static inline void smp_mb__after_mmgrab(void)
+{
+	smp_mb__after_atomic();
+}
+
 extern void __mmdrop(struct mm_struct *mm);
 
 static inline void mmdrop(struct mm_struct *mm)

kernel/cgroup/cgroup.c

@@ -3771,7 +3771,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_psi(cgrp);
-	new = psi_trigger_create(psi, buf, res);
+	new = psi_trigger_create(psi, buf, res, of->file);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);