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

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

+/* 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)
@@ -2075,6 +2082,7 @@ 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)
@@ -2082,20 +2090,25 @@ 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);

kernel/fork.c

@@ -924,6 +924,7 @@ void __mmdrop(struct mm_struct *mm)
 	check_mm(mm);
 	put_user_ns(mm->user_ns);
 	mm_pasid_drop(mm);
+	mm_destroy_cid(mm);
 
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		percpu_counter_destroy(&mm->rss_stat[i]);
@@ -1188,7 +1189,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 
 #ifdef CONFIG_SCHED_MM_CID
 	tsk->mm_cid = -1;
+	tsk->last_mm_cid = -1;
 	tsk->mm_cid_active = 0;
+	tsk->migrate_from_cpu = -1;
 #endif
 	return tsk;
 
@@ -1296,18 +1299,22 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	if (init_new_context(p, mm))
 		goto fail_nocontext;
 
+	if (mm_alloc_cid(mm))
+		goto fail_cid;
+
 	for (i = 0; i < NR_MM_COUNTERS; i++)
 		if (percpu_counter_init(&mm->rss_stat[i], 0, GFP_KERNEL_ACCOUNT))
 			goto fail_pcpu;
 
 	mm->user_ns = get_user_ns(user_ns);
 	lru_gen_init_mm(mm);
-	mm_init_cid(mm);
 	return mm;
 
 fail_pcpu:
 	while (i > 0)
 		percpu_counter_destroy(&mm->rss_stat[--i]);
+	mm_destroy_cid(mm);
+fail_cid:
 	destroy_context(mm);
 fail_nocontext:
 	mm_free_pgd(mm);

kernel/livepatch/core.c

@@ -33,6 +33,7 @@
  *
  * - klp_ftrace_handler()
  * - klp_update_patch_state()
+ * - __klp_sched_try_switch()
  */
 DEFINE_MUTEX(klp_mutex);
 

kernel/livepatch/transition.c

@@ -9,11 +9,14 @@
 
 #include <linux/cpu.h>
 #include <linux/stacktrace.h>
+#include <linux/static_call.h>
 #include "core.h"
 #include "patch.h"
 #include "transition.h"
 
 #define MAX_STACK_ENTRIES  100
+DEFINE_PER_CPU(unsigned long[MAX_STACK_ENTRIES], klp_stack_entries);
+
 #define STACK_ERR_BUF_SIZE 128
 
 #define SIGNALS_TIMEOUT 15
@@ -24,6 +27,25 @@ static int klp_target_state = KLP_UNDEFINED;
 
 static unsigned int klp_signals_cnt;
 
+/*
+ * When a livepatch is in progress, enable klp stack checking in
+ * cond_resched().  This helps CPU-bound kthreads get patched.
+ */
+#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+
+#define klp_cond_resched_enable() sched_dynamic_klp_enable()
+#define klp_cond_resched_disable() sched_dynamic_klp_disable()
+
+#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
+DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
+EXPORT_SYMBOL(klp_sched_try_switch_key);
+
+#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
+#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
+
+#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
 /*
  * This work can be performed periodically to finish patching or unpatching any
  * "straggler" tasks which failed to transition in the first attempt.
@@ -172,8 +194,8 @@ void klp_update_patch_state(struct task_struct *task)
 	 * barrier (smp_rmb) for two cases:
 	 *
 	 * 1) Enforce the order of the TIF_PATCH_PENDING read and the
-	 *    klp_target_state read.  The corresponding write barrier is in
-	 *    klp_init_transition().
+	 *    klp_target_state read.  The corresponding write barriers are in
+	 *    klp_init_transition() and klp_reverse_transition().
 	 *
 	 * 2) Enforce the order of the TIF_PATCH_PENDING read and a future read
 	 *    of func->transition, if klp_ftrace_handler() is called later on
@@ -240,12 +262,15 @@ static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
  */
 static int klp_check_stack(struct task_struct *task, const char **oldname)
 {
-	static unsigned long entries[MAX_STACK_ENTRIES];
+	unsigned long *entries = this_cpu_ptr(klp_stack_entries);
 	struct klp_object *obj;
 	struct klp_func *func;
 	int ret, nr_entries;
 
-	ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
+	/* Protect 'klp_stack_entries' */
+	lockdep_assert_preemption_disabled();
+
+	ret = stack_trace_save_tsk_reliable(task, entries, MAX_STACK_ENTRIES);
 	if (ret < 0)
 		return -EINVAL;
 	nr_entries = ret;
@@ -307,7 +332,11 @@ static bool klp_try_switch_task(struct task_struct *task)
 	 * functions.  If all goes well, switch the task to the target patch
 	 * state.
 	 */
-	ret = task_call_func(task, klp_check_and_switch_task, &old_name);
+	if (task == current)
+		ret = klp_check_and_switch_task(current, &old_name);
+	else
+		ret = task_call_func(task, klp_check_and_switch_task, &old_name);
+
 	switch (ret) {
 	case 0:		/* success */
 		break;
@@ -334,6 +363,44 @@ static bool klp_try_switch_task(struct task_struct *task)
 	return !ret;
 }
 
+void __klp_sched_try_switch(void)
+{
+	if (likely(!klp_patch_pending(current)))
+		return;
+
+	/*
+	 * This function is called from cond_resched() which is called in many
+	 * places throughout the kernel.  Using the klp_mutex here might
+	 * deadlock.
+	 *
+	 * Instead, disable preemption to prevent racing with other callers of
+	 * klp_try_switch_task().  Thanks to task_call_func() they won't be
+	 * able to switch this task while it's running.
+	 */
+	preempt_disable();
+
+	/*
+	 * Make sure current didn't get patched between the above check and
+	 * preempt_disable().
+	 */
+	if (unlikely(!klp_patch_pending(current)))
+		goto out;
+
+	/*
+	 * Enforce the order of the TIF_PATCH_PENDING read above and the
+	 * klp_target_state read in klp_try_switch_task().  The corresponding
+	 * write barriers are in klp_init_transition() and
+	 * klp_reverse_transition().
+	 */
+	smp_rmb();
+
+	klp_try_switch_task(current);
+
+out:
+	preempt_enable();
+}
+EXPORT_SYMBOL(__klp_sched_try_switch);
+
 /*
  * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
  * Kthreads with TIF_PATCH_PENDING set are woken up.
@@ -440,7 +507,8 @@ void klp_try_complete_transition(void)
 		return;
 	}
 
-	/* we're done, now cleanup the data structures */
+	/* Done!  Now cleanup the data structures. */
+	klp_cond_resched_disable();
 	patch = klp_transition_patch;
 	klp_complete_transition();
 
@@ -492,6 +560,8 @@ void klp_start_transition(void)
 			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
 	}
 
+	klp_cond_resched_enable();
+
 	klp_signals_cnt = 0;
 }
 
@@ -547,8 +617,9 @@ void klp_init_transition(struct klp_patch *patch, int state)
 	 * see a func in transition with a task->patch_state of KLP_UNDEFINED.
 	 *
 	 * Also enforce the order of the klp_target_state write and future
-	 * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() doesn't
-	 * set a task->patch_state to KLP_UNDEFINED.
+	 * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() and
+	 * __klp_sched_try_switch() don't set a task->patch_state to
+	 * KLP_UNDEFINED.
 	 */
 	smp_wmb();
 
@@ -584,14 +655,10 @@ void klp_reverse_transition(void)
 		 klp_target_state == KLP_PATCHED ? "patching to unpatching" :
 						   "unpatching to patching");
 
-	klp_transition_patch->enabled = !klp_transition_patch->enabled;
-
-	klp_target_state = !klp_target_state;
-
 	/*
 	 * Clear all TIF_PATCH_PENDING flags to prevent races caused by
-	 * klp_update_patch_state() running in parallel with
-	 * klp_start_transition().
+	 * klp_update_patch_state() or __klp_sched_try_switch() running in
+	 * parallel with the reverse transition.
 	 */
 	read_lock(&tasklist_lock);
 	for_each_process_thread(g, task)
@@ -601,9 +668,28 @@ void klp_reverse_transition(void)
 	for_each_possible_cpu(cpu)
 		clear_tsk_thread_flag(idle_task(cpu), TIF_PATCH_PENDING);
 
-	/* Let any remaining calls to klp_update_patch_state() complete */
+	/*
+	 * Make sure all existing invocations of klp_update_patch_state() and
+	 * __klp_sched_try_switch() see the cleared TIF_PATCH_PENDING before
+	 * starting the reverse transition.
+	 */
 	klp_synchronize_transition();
 
+	/*
+	 * All patching has stopped, now re-initialize the global variables to
+	 * prepare for the reverse transition.
+	 */
+	klp_transition_patch->enabled = !klp_transition_patch->enabled;
+	klp_target_state = !klp_target_state;
+
+	/*
+	 * Enforce the order of the klp_target_state write and the
+	 * TIF_PATCH_PENDING writes in klp_start_transition() to ensure
+	 * klp_update_patch_state() and __klp_sched_try_switch() don't set
+	 * task->patch_state to the wrong value.
+	 */
+	smp_wmb();
+
 	klp_start_transition();
 }
 
@@ -617,9 +703,9 @@ void klp_copy_process(struct task_struct *child)
 	 * the task flag up to date with the parent here.
 	 *
 	 * The operation is serialized against all klp_*_transition()
-	 * operations by the tasklist_lock. The only exception is
-	 * klp_update_patch_state(current), but we cannot race with
-	 * that because we are current.
+	 * operations by the tasklist_lock. The only exceptions are
+	 * klp_update_patch_state(current) and __klp_sched_try_switch(), but we
+	 * cannot race with them because we are current.
 	 */
 	if (test_tsk_thread_flag(current, TIF_PATCH_PENDING))
 		set_tsk_thread_flag(child, TIF_PATCH_PENDING);

kernel/sched/clock.c

@@ -300,6 +300,9 @@ noinstr u64 local_clock(void)
 	if (static_branch_likely(&__sched_clock_stable))
 		return sched_clock() + __sched_clock_offset;
 
+	if (!static_branch_likely(&sched_clock_running))
+		return sched_clock();
+
 	preempt_disable_notrace();
 	clock = sched_clock_local(this_scd());
 	preempt_enable_notrace();

kernel/sched/deadline.c

@@ -2246,6 +2246,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
 				     task_on_cpu(rq, task) ||
 				     !dl_task(task) ||
+				     is_migration_disabled(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
 				later_rq = NULL;
@@ -2704,6 +2705,13 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 #endif
 }
 
+#ifdef CONFIG_SCHED_CORE
+static int task_is_throttled_dl(struct task_struct *p, int cpu)
+{
+	return p->dl.dl_throttled;
+}
+#endif
+
 DEFINE_SCHED_CLASS(dl) = {
 
 	.enqueue_task		= enqueue_task_dl,
@@ -2736,6 +2744,9 @@ DEFINE_SCHED_CLASS(dl) = {
 	.switched_to		= switched_to_dl,
 
 	.update_curr		= update_curr_dl,
+#ifdef CONFIG_SCHED_CORE
+	.task_is_throttled	= task_is_throttled_dl,
+#endif
 };
 
 /* Used for dl_bw check and update, used under sched_rt_handler()::mutex */

kernel/sched/fair.c

@@ -6016,6 +6016,10 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
 	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	cfs_b->period_timer.function = sched_cfs_period_timer;
+
+	/* Add a random offset so that timers interleave */
+	hrtimer_set_expires(&cfs_b->period_timer,
+			    get_random_u32_below(cfs_b->period));
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
 	cfs_b->slack_started = false;
@@ -6671,7 +6675,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->stats.nr_wakeups_affine_attempts);
-	if (target == nr_cpumask_bits)
+	if (target != this_cpu)
 		return prev_cpu;
 
 	schedstat_inc(sd->ttwu_move_affine);
@@ -12033,6 +12037,18 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
 
 	return delta > 0;
 }
+
+static int task_is_throttled_fair(struct task_struct *p, int cpu)
+{
+	struct cfs_rq *cfs_rq;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	cfs_rq = task_group(p)->cfs_rq[cpu];
+#else
+	cfs_rq = &cpu_rq(cpu)->cfs;
+#endif
+	return throttled_hierarchy(cfs_rq);
+}
 #else
 static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {}
 #endif
@@ -12659,6 +12675,10 @@ DEFINE_SCHED_CLASS(fair) = {
 	.task_change_group	= task_change_group_fair,
 #endif
 
+#ifdef CONFIG_SCHED_CORE
+	.task_is_throttled	= task_is_throttled_fair,
+#endif
+
 #ifdef CONFIG_UCLAMP_TASK
 	.uclamp_enabled		= 1,
 #endif

kernel/sched/rt.c

@@ -2000,11 +2000,15 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * the mean time, task could have
 			 * migrated already or had its affinity changed.
 			 * Also make sure that it wasn't scheduled on its rq.
+			 * It is possible the task was scheduled, set
+			 * "migrate_disabled" and then got preempted, so we must
+			 * check the task migration disable flag here too.
 			 */
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
 				     task_on_cpu(rq, task) ||
 				     !rt_task(task) ||
+				     is_migration_disabled(task) ||
 				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);
@@ -2677,6 +2681,21 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 		return 0;
 }
 
+#ifdef CONFIG_SCHED_CORE
+static int task_is_throttled_rt(struct task_struct *p, int cpu)
+{
+	struct rt_rq *rt_rq;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	rt_rq = task_group(p)->rt_rq[cpu];
+#else
+	rt_rq = &cpu_rq(cpu)->rt;
+#endif
+
+	return rt_rq_throttled(rt_rq);
+}
+#endif
+
 DEFINE_SCHED_CLASS(rt) = {
 
 	.enqueue_task		= enqueue_task_rt,
@@ -2710,6 +2729,10 @@ DEFINE_SCHED_CLASS(rt) = {
 
 	.update_curr		= update_curr_rt,
 
+#ifdef CONFIG_SCHED_CORE
+	.task_is_throttled	= task_is_throttled_rt,
+#endif
+
 #ifdef CONFIG_UCLAMP_TASK
 	.uclamp_enabled		= 1,
 #endif

kernel/sched/sched.h

@@ -2224,6 +2224,10 @@ struct sched_class {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*task_change_group)(struct task_struct *p);
 #endif
+
+#ifdef CONFIG_SCHED_CORE
+	int (*task_is_throttled)(struct task_struct *p, int cpu);
+#endif
 };
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
@@ -3249,61 +3253,238 @@ static inline void update_current_exec_runtime(struct task_struct *curr,
 }
 
 #ifdef CONFIG_SCHED_MM_CID
-static inline int __mm_cid_get(struct mm_struct *mm)
+
+#define SCHED_MM_CID_PERIOD_NS	(100ULL * 1000000)	/* 100ms */
+#define MM_CID_SCAN_DELAY	100			/* 100ms */
+
+extern raw_spinlock_t cid_lock;
+extern int use_cid_lock;
+
+extern void sched_mm_cid_migrate_from(struct task_struct *t);
+extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t);
+extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr);
+extern void init_sched_mm_cid(struct task_struct *t);
+
+static inline void __mm_cid_put(struct mm_struct *mm, int cid)
+{
+	if (cid < 0)
+		return;
+	cpumask_clear_cpu(cid, mm_cidmask(mm));
+}
+
+/*
+ * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to
+ * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to
+ * be held to transition to other states.
+ *
+ * State transitions synchronized with cmpxchg or try_cmpxchg need to be
+ * consistent across cpus, which prevents use of this_cpu_cmpxchg.
+ */
+static inline void mm_cid_put_lazy(struct task_struct *t)
+{
+	struct mm_struct *mm = t->mm;
+	struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
+	int cid;
+
+	lockdep_assert_irqs_disabled();
+	cid = __this_cpu_read(pcpu_cid->cid);
+	if (!mm_cid_is_lazy_put(cid) ||
+	    !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
+		return;
+	__mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
+}
+
+static inline int mm_cid_pcpu_unset(struct mm_struct *mm)
+{
+	struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
+	int cid, res;
+
+	lockdep_assert_irqs_disabled();
+	cid = __this_cpu_read(pcpu_cid->cid);
+	for (;;) {
+		if (mm_cid_is_unset(cid))
+			return MM_CID_UNSET;
+		/*
+		 * Attempt transition from valid or lazy-put to unset.
+		 */
+		res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET);
+		if (res == cid)
+			break;
+		cid = res;
+	}
+	return cid;
+}
+
+static inline void mm_cid_put(struct mm_struct *mm)
+{
+	int cid;
+
+	lockdep_assert_irqs_disabled();
+	cid = mm_cid_pcpu_unset(mm);
+	if (cid == MM_CID_UNSET)
+		return;
+	__mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
+}
+
+static inline int __mm_cid_try_get(struct mm_struct *mm)
 {
 	struct cpumask *cpumask;
 	int cid;
 
 	cpumask = mm_cidmask(mm);
-	cid = cpumask_first_zero(cpumask);
-	if (cid >= nr_cpu_ids)
+	/*
+	 * Retry finding first zero bit if the mask is temporarily
+	 * filled. This only happens during concurrent remote-clear
+	 * which owns a cid without holding a rq lock.
+	 */
+	for (;;) {
+		cid = cpumask_first_zero(cpumask);
+		if (cid < nr_cpu_ids)
+			break;
+		cpu_relax();
+	}
+	if (cpumask_test_and_set_cpu(cid, cpumask))
 		return -1;
-	__cpumask_set_cpu(cid, cpumask);
 	return cid;
 }
 
-static inline void mm_cid_put(struct mm_struct *mm, int cid)
+/*
+ * Save a snapshot of the current runqueue time of this cpu
+ * with the per-cpu cid value, allowing to estimate how recently it was used.
+ */
+static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm)
+{
+	struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq));
+
+	lockdep_assert_rq_held(rq);
+	WRITE_ONCE(pcpu_cid->time, rq->clock);
+}
+
+static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm)
 {
-	lockdep_assert_irqs_disabled();
-	if (cid < 0)
-		return;
-	raw_spin_lock(&mm->cid_lock);
-	__cpumask_clear_cpu(cid, mm_cidmask(mm));
-	raw_spin_unlock(&mm->cid_lock);
+	int cid;
+
+	/*
+	 * All allocations (even those using the cid_lock) are lock-free. If
+	 * use_cid_lock is set, hold the cid_lock to perform cid allocation to
+	 * guarantee forward progress.
+	 */
+	if (!READ_ONCE(use_cid_lock)) {
+		cid = __mm_cid_try_get(mm);
+		if (cid >= 0)
+			goto end;
+		raw_spin_lock(&cid_lock);
+	} else {
+		raw_spin_lock(&cid_lock);
+		cid = __mm_cid_try_get(mm);
+		if (cid >= 0)
+			goto unlock;
+	}
+
+	/*
+	 * cid concurrently allocated. Retry while forcing following
+	 * allocations to use the cid_lock to ensure forward progress.
+	 */
+	WRITE_ONCE(use_cid_lock, 1);
+	/*
+	 * Set use_cid_lock before allocation. Only care about program order
+	 * because this is only required for forward progress.
+	 */
+	barrier();
+	/*
+	 * Retry until it succeeds. It is guaranteed to eventually succeed once
+	 * all newcoming allocations observe the use_cid_lock flag set.
+	 */
+	do {
+		cid = __mm_cid_try_get(mm);
+		cpu_relax();
+	} while (cid < 0);
+	/*
+	 * Allocate before clearing use_cid_lock. Only care about
+	 * program order because this is for forward progress.
+	 */
+	barrier();
+	WRITE_ONCE(use_cid_lock, 0);
+unlock:
+	raw_spin_unlock(&cid_lock);
+end:
+	mm_cid_snapshot_time(rq, mm);
+	return cid;
 }
 
-static inline int mm_cid_get(struct mm_struct *mm)
+static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm)
 {
-	int ret;
+	struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
+	struct cpumask *cpumask;
+	int cid;
 
-	lockdep_assert_irqs_disabled();
-	raw_spin_lock(&mm->cid_lock);
-	ret = __mm_cid_get(mm);
-	raw_spin_unlock(&mm->cid_lock);
-	return ret;
+	lockdep_assert_rq_held(rq);
+	cpumask = mm_cidmask(mm);
+	cid = __this_cpu_read(pcpu_cid->cid);
+	if (mm_cid_is_valid(cid)) {
+		mm_cid_snapshot_time(rq, mm);
+		return cid;
+	}
+	if (mm_cid_is_lazy_put(cid)) {
+		if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
+			__mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
+	}
+	cid = __mm_cid_get(rq, mm);
+	__this_cpu_write(pcpu_cid->cid, cid);
+	return cid;
 }
 
-static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next)
+static inline void switch_mm_cid(struct rq *rq,
+				 struct task_struct *prev,
+				 struct task_struct *next)
 {
+	/*
+	 * Provide a memory barrier between rq->curr store and load of
+	 * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition.
+	 *
+	 * Should be adapted if context_switch() is modified.
+	 */
+	if (!next->mm) {                                // to kernel
+		/*
+		 * user -> kernel transition does not guarantee a barrier, but
+		 * we can use the fact that it performs an atomic operation in
+		 * mmgrab().
+		 */
+		if (prev->mm)                           // from user
+			smp_mb__after_mmgrab();
+		/*
+		 * kernel -> kernel transition does not change rq->curr->mm
+		 * state. It stays NULL.
+		 */
+	} else {                                        // to user
+		/*
+		 * kernel -> user transition does not provide a barrier
+		 * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
+		 * Provide it here.
+		 */
+		if (!prev->mm)                          // from kernel
+			smp_mb();
+		/*
+		 * user -> user transition guarantees a memory barrier through
+		 * switch_mm() when current->mm changes. If current->mm is
+		 * unchanged, no barrier is needed.
+		 */
+	}
 	if (prev->mm_cid_active) {
-		if (next->mm_cid_active && next->mm == prev->mm) {
-			/*
-			 * Context switch between threads in same mm, hand over
-			 * the mm_cid from prev to next.
-			 */
-			next->mm_cid = prev->mm_cid;
-			prev->mm_cid = -1;
-			return;
-		}
-		mm_cid_put(prev->mm, prev->mm_cid);
+		mm_cid_snapshot_time(rq, prev->mm);
+		mm_cid_put_lazy(prev);
 		prev->mm_cid = -1;
 	}
 	if (next->mm_cid_active)
-		next->mm_cid = mm_cid_get(next->mm);
+		next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm);
 }
 
 #else
-static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) { }
+static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { }
+static inline void sched_mm_cid_migrate_from(struct task_struct *t) { }
+static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t) { }
+static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
+static inline void init_sched_mm_cid(struct task_struct *t) { }
 #endif
 
 #endif /* _KERNEL_SCHED_SCHED_H */

kernel/sched/topology.c

@@ -209,8 +209,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 DEFINE_STATIC_KEY_FALSE(sched_energy_present);
 static unsigned int sysctl_sched_energy_aware = 1;
-DEFINE_MUTEX(sched_energy_mutex);
-bool sched_energy_update;
+static DEFINE_MUTEX(sched_energy_mutex);
+static bool sched_energy_update;
 
 void rebuild_sched_domains_energy(void)
 {