Merge tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve the scalability of the CFS bandwidth unthrottling logic with
   large number of CPUs.

 - Fix & rework various cpuidle routines, simplify interaction with the
   generic scheduler code. Add __cpuidle methods as noinstr to objtool's
   noinstr detection and fix boatloads of cpuidle bugs & quirks.

 - Add new ABI: introduce MEMBARRIER_CMD_GET_REGISTRATIONS, to query
   previously issued registrations.

 - Limit scheduler slice duration to the sysctl_sched_latency period, to
   improve scheduling granularity with a large number of SCHED_IDLE
   tasks.

 - Debuggability enhancement on sys_exit(): warn about disabled IRQs,
   but also enable them to prevent a cascade of followup problems and
   repeat warnings.

 - Fix the rescheduling logic in prio_changed_dl().

 - Micro-optimize cpufreq and sched-util methods.

 - Micro-optimize ttwu_runnable()

 - Micro-optimize the idle-scanning in update_numa_stats(),
   select_idle_capacity() and steal_cookie_task().

 - Update the RSEQ code & self-tests

 - Constify various scheduler methods

 - Remove unused methods

 - Refine __init tags

 - Documentation updates

 - Misc other cleanups, fixes

* tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
  sched/rt: pick_next_rt_entity(): check list_entry
  sched/deadline: Add more reschedule cases to prio_changed_dl()
  sched/fair: sanitize vruntime of entity being placed
  sched/fair: Remove capacity inversion detection
  sched/fair: unlink misfit task from cpu overutilized
  objtool: mem*() are not uaccess safe
  cpuidle: Fix poll_idle() noinstr annotation
  sched/clock: Make local_clock() noinstr
  sched/clock/x86: Mark sched_clock() noinstr
  x86/pvclock: Improve atomic update of last_value in pvclock_clocksource_read()
  x86/atomics: Always inline arch_atomic64*()
  cpuidle: tracing, preempt: Squash _rcuidle tracing
  cpuidle: tracing: Warn about !rcu_is_watching()
  cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG
  cpuidle: drivers: firmware: psci: Dont instrument suspend code
  KVM: selftests: Fix build of rseq test
  exit: Detect and fix irq disabled state in oops
  cpuidle, arm64: Fix the ARM64 cpuidle logic
  cpuidle: mvebu: Fix duplicate flags assignment
  sched/fair: Limit sched slice duration
  ...

25 files changed, 689 insertions, 366 deletions

diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 77978e372377..a09f1c19336a 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -510,7 +510,7 @@ void noinstr __ct_user_enter(enum ctx_state state)
 			 * In this we case we don't care about any concurrency/ordering.
 			 */
 			if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE))
-				atomic_set(&ct->state, state);
+				arch_atomic_set(&ct->state, state);
 		} else {
 			/*
 			 * Even if context tracking is disabled on this CPU, because it's outside
@@ -527,7 +527,7 @@ void noinstr __ct_user_enter(enum ctx_state state)
 			 */
 			if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) {
 				/* Tracking for vtime only, no concurrent RCU EQS accounting */
-				atomic_set(&ct->state, state);
+				arch_atomic_set(&ct->state, state);
 			} else {
 				/*
 				 * Tracking for vtime and RCU EQS. Make sure we don't race
@@ -535,7 +535,7 @@ void noinstr __ct_user_enter(enum ctx_state state)
 				 * RCU only requires RCU_DYNTICKS_IDX increments to be fully
 				 * ordered.
 				 */
-				atomic_add(state, &ct->state);
+				arch_atomic_add(state, &ct->state);
 			}
 		}
 	}
@@ -630,12 +630,12 @@ void noinstr __ct_user_exit(enum ctx_state state)
 			 * In this we case we don't care about any concurrency/ordering.
 			 */
 			if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE))
-				atomic_set(&ct->state, CONTEXT_KERNEL);
+				arch_atomic_set(&ct->state, CONTEXT_KERNEL);
 
 		} else {
 			if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) {
 				/* Tracking for vtime only, no concurrent RCU EQS accounting */
-				atomic_set(&ct->state, CONTEXT_KERNEL);
+				arch_atomic_set(&ct->state, CONTEXT_KERNEL);
 			} else {
 				/*
 				 * Tracking for vtime and RCU EQS. Make sure we don't race
@@ -643,7 +643,7 @@ void noinstr __ct_user_exit(enum ctx_state state)
 				 * RCU only requires RCU_DYNTICKS_IDX increments to be fully
 				 * ordered.
 				 */
-				atomic_sub(state, &ct->state);
+				arch_atomic_sub(state, &ct->state);
 			}
 		}
 	}
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index ba4ba71facf9..b0f0d15085db 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -30,16 +30,9 @@ static int cpu_pm_notify(enum cpu_pm_event event)
 {
 	int ret;
 
-	/*
-	 * This introduces a RCU read critical section, which could be
-	 * disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know
-	 * this.
-	 */
-	ct_irq_enter_irqson();
 	rcu_read_lock();
 	ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL);
 	rcu_read_unlock();
-	ct_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
 }
@@ -49,11 +42,9 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev
 	unsigned long flags;
 	int ret;
 
-	ct_irq_enter_irqson();
 	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
 	ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL);
 	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
-	ct_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 15dc2ec80c46..bccfa4218356 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -807,6 +807,8 @@ void __noreturn do_exit(long code)
 	struct task_struct *tsk = current;
 	int group_dead;
 
+	WARN_ON(irqs_disabled());
+
 	synchronize_group_exit(tsk, code);
 
 	WARN_ON(tsk->plug);
@@ -938,6 +940,11 @@ void __noreturn make_task_dead(int signr)
 	if (unlikely(!tsk->pid))
 		panic("Attempted to kill the idle task!");
 
+	if (unlikely(irqs_disabled())) {
+		pr_info("note: %s[%d] exited with irqs disabled\n",
+			current->comm, task_pid_nr(current));
+		local_irq_enable();
+	}
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
 			current->comm, task_pid_nr(current),
diff --git a/kernel/fork.c b/kernel/fork.c
index d9c97704b7c9..038b898dad52 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1060,6 +1060,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->reported_split_lock = 0;
 #endif
 
+#ifdef CONFIG_SCHED_MM_CID
+	tsk->mm_cid = -1;
+	tsk->mm_cid_active = 0;
+#endif
 	return tsk;
 
 free_stack:
@@ -1169,6 +1173,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 
 	mm->user_ns = get_user_ns(user_ns);
 	lru_gen_init_mm(mm);
+	mm_init_cid(mm);
 	return mm;
 
 fail_pcpu:
@@ -1601,6 +1606,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 
 	tsk->mm = mm;
 	tsk->active_mm = mm;
+	sched_mm_cid_fork(tsk);
 	return 0;
 }
 
@@ -3034,7 +3040,7 @@ void __init mm_cache_init(void)
 	 * dynamically sized based on the maximum CPU number this system
 	 * can have, taking hotplug into account (nr_cpu_ids).
 	 */
-	mm_size = sizeof(struct mm_struct) + cpumask_size();
+	mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size();
 
 	mm_cachep = kmem_cache_create_usercopy("mm_struct",
 			mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e3375bc40dad..50d4863974e7 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -55,6 +55,7 @@
 #include <linux/rcupdate.h>
 #include <linux/kprobes.h>
 #include <linux/lockdep.h>
+#include <linux/context_tracking.h>
 
 #include <asm/sections.h>
 
@@ -6555,6 +6556,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 {
 	struct task_struct *curr = current;
 	int dl = READ_ONCE(debug_locks);
+	bool rcu = warn_rcu_enter();
 
 	/* Note: the following can be executed concurrently, so be careful. */
 	pr_warn("\n");
@@ -6595,5 +6597,6 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	lockdep_print_held_locks(curr);
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
+	warn_rcu_exit(rcu);
 }
 EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious);
diff --git a/kernel/panic.c b/kernel/panic.c
index 463c9295bc28..487f5b03bf83 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -34,6 +34,7 @@
 #include <linux/ratelimit.h>
 #include <linux/debugfs.h>
 #include <linux/sysfs.h>
+#include <linux/context_tracking.h>
 #include <trace/events/error_report.h>
 #include <asm/sections.h>
 
@@ -679,6 +680,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 void warn_slowpath_fmt(const char *file, int line, unsigned taint,
 		       const char *fmt, ...)
 {
+	bool rcu = warn_rcu_enter();
 	struct warn_args args;
 
 	pr_warn(CUT_HERE);
@@ -693,11 +695,13 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint,
 	va_start(args.args, fmt);
 	__warn(file, line, __builtin_return_address(0), taint, NULL, &args);
 	va_end(args.args);
+	warn_rcu_exit(rcu);
 }
 EXPORT_SYMBOL(warn_slowpath_fmt);
 #else
 void __warn_printk(const char *fmt, ...)
 {
+	bool rcu = warn_rcu_enter();
 	va_list args;
 
 	pr_warn(CUT_HERE);
@@ -705,6 +709,7 @@ void __warn_printk(const char *fmt, ...)
 	va_start(args, fmt);
 	vprintk(fmt, args);
 	va_end(args);
+	warn_rcu_exit(rcu);
 }
 EXPORT_SYMBOL(__warn_printk);
 #endif
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a5ed2e53547c..94f136b25f6a 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2196,7 +2196,7 @@ static u16 printk_sprint(char *text, u16 size, int facility,
 		}
 	}
 
-	trace_console_rcuidle(text, text_len);
+	trace_console(text, text_len);
 
 	return text_len;
 }
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54482193e1ed..0786450074c1 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -813,7 +813,7 @@ static long ptrace_get_rseq_configuration(struct task_struct *task,
 {
 	struct ptrace_rseq_configuration conf = {
 		.rseq_abi_pointer = (u64)(uintptr_t)task->rseq,
-		.rseq_abi_size = sizeof(*task->rseq),
+		.rseq_abi_size = task->rseq_len,
 		.signature = task->rseq_sig,
 		.flags = 0,
 	};
diff --git a/kernel/rseq.c b/kernel/rseq.c
index d38ab944105d..9de6e35fe679 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -18,6 +18,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/rseq.h>
 
+/* The original rseq structure size (including padding) is 32 bytes. */
+#define ORIG_RSEQ_SIZE		32
+
 #define RSEQ_CS_NO_RESTART_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT | \
 				  RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \
 				  RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE)
@@ -82,15 +85,25 @@
  *   F1. <failure>
  */
 
-static int rseq_update_cpu_id(struct task_struct *t)
+static int rseq_update_cpu_node_id(struct task_struct *t)
 {
-	u32 cpu_id = raw_smp_processor_id();
 	struct rseq __user *rseq = t->rseq;
+	u32 cpu_id = raw_smp_processor_id();
+	u32 node_id = cpu_to_node(cpu_id);
+	u32 mm_cid = task_mm_cid(t);
 
-	if (!user_write_access_begin(rseq, sizeof(*rseq)))
+	WARN_ON_ONCE((int) mm_cid < 0);
+	if (!user_write_access_begin(rseq, t->rseq_len))
 		goto efault;
 	unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
 	unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
+	unsafe_put_user(node_id, &rseq->node_id, efault_end);
+	unsafe_put_user(mm_cid, &rseq->mm_cid, efault_end);
+	/*
+	 * Additional feature fields added after ORIG_RSEQ_SIZE
+	 * need to be conditionally updated only if
+	 * t->rseq_len != ORIG_RSEQ_SIZE.
+	 */
 	user_write_access_end();
 	trace_rseq_update(t);
 	return 0;
@@ -101,9 +114,10 @@ efault:
 	return -EFAULT;
 }
 
-static int rseq_reset_rseq_cpu_id(struct task_struct *t)
+static int rseq_reset_rseq_cpu_node_id(struct task_struct *t)
 {
-	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED;
+	u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0,
+	    mm_cid = 0;
 
 	/*
 	 * Reset cpu_id_start to its initial state (0).
@@ -117,6 +131,21 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 	 */
 	if (put_user(cpu_id, &t->rseq->cpu_id))
 		return -EFAULT;
+	/*
+	 * Reset node_id to its initial state (0).
+	 */
+	if (put_user(node_id, &t->rseq->node_id))
+		return -EFAULT;
+	/*
+	 * Reset mm_cid to its initial state (0).
+	 */
+	if (put_user(mm_cid, &t->rseq->mm_cid))
+		return -EFAULT;
+	/*
+	 * Additional feature fields added after ORIG_RSEQ_SIZE
+	 * need to be conditionally reset only if
+	 * t->rseq_len != ORIG_RSEQ_SIZE.
+	 */
 	return 0;
 }
 
@@ -301,7 +330,7 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 		if (unlikely(ret < 0))
 			goto error;
 	}
-	if (unlikely(rseq_update_cpu_id(t)))
+	if (unlikely(rseq_update_cpu_node_id(t)))
 		goto error;
 	return;
 
@@ -344,15 +373,16 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		/* Unregister rseq for current thread. */
 		if (current->rseq != rseq || !current->rseq)
 			return -EINVAL;
-		if (rseq_len != sizeof(*rseq))
+		if (rseq_len != current->rseq_len)
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
-		ret = rseq_reset_rseq_cpu_id(current);
+		ret = rseq_reset_rseq_cpu_node_id(current);
 		if (ret)
 			return ret;
 		current->rseq = NULL;
 		current->rseq_sig = 0;
+		current->rseq_len = 0;
 		return 0;
 	}
 
@@ -365,7 +395,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		 * the provided address differs from the prior
 		 * one.
 		 */
-		if (current->rseq != rseq || rseq_len != sizeof(*rseq))
+		if (current->rseq != rseq || rseq_len != current->rseq_len)
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
@@ -374,15 +404,24 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	}
 
 	/*
-	 * If there was no rseq previously registered,
-	 * ensure the provided rseq is properly aligned and valid.
+	 * If there was no rseq previously registered, ensure the provided rseq
+	 * is properly aligned, as communcated to user-space through the ELF
+	 * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq
+	 * size, the required alignment is the original struct rseq alignment.
+	 *
+	 * In order to be valid, rseq_len is either the original rseq size, or
+	 * large enough to contain all supported fields, as communicated to
+	 * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
 	 */
-	if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
-	    rseq_len != sizeof(*rseq))
+	if (rseq_len < ORIG_RSEQ_SIZE ||
+	    (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) ||
+	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
+					    rseq_len < offsetof(struct rseq, end))))
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
 	current->rseq = rseq;
+	current->rseq_len = rseq_len;
 	current->rseq_sig = sig;
 	/*
 	 * If rseq was previously inactive, and has just been
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e374c0c923da..5732fa75ebab 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -93,7 +93,7 @@ struct sched_clock_data {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
 
-notrace static inline struct sched_clock_data *this_scd(void)
+static __always_inline struct sched_clock_data *this_scd(void)
 {
 	return this_cpu_ptr(&sched_clock_data);
 }
@@ -244,12 +244,12 @@ late_initcall(sched_clock_init_late);
  * min, max except they take wrapping into account
  */
 
-notrace static inline u64 wrap_min(u64 x, u64 y)
+static __always_inline u64 wrap_min(u64 x, u64 y)
 {
 	return (s64)(x - y) < 0 ? x : y;
 }
 
-notrace static inline u64 wrap_max(u64 x, u64 y)
+static __always_inline u64 wrap_max(u64 x, u64 y)
 {
 	return (s64)(x - y) > 0 ? x : y;
 }
@@ -260,7 +260,7 @@ notrace static inline u64 wrap_max(u64 x, u64 y)
  *  - filter out backward motion
  *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-notrace static u64 sched_clock_local(struct sched_clock_data *scd)
+static __always_inline u64 sched_clock_local(struct sched_clock_data *scd)
 {
 	u64 now, clock, old_clock, min_clock, max_clock, gtod;
 	s64 delta;
@@ -287,13 +287,28 @@ again:
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
 
-	if (!try_cmpxchg64(&scd->clock, &old_clock, clock))
+	if (!arch_try_cmpxchg64(&scd->clock, &old_clock, clock))
 		goto again;
 
 	return clock;
 }
 
-notrace static u64 sched_clock_remote(struct sched_clock_data *scd)
+noinstr u64 local_clock(void)
+{
+	u64 clock;
+
+	if (static_branch_likely(&__sched_clock_stable))
+		return sched_clock() + __sched_clock_offset;
+
+	preempt_disable_notrace();
+	clock = sched_clock_local(this_scd());
+	preempt_enable_notrace();
+
+	return clock;
+}
+EXPORT_SYMBOL_GPL(local_clock);
+
+static notrace u64 sched_clock_remote(struct sched_clock_data *scd)
 {
 	struct sched_clock_data *my_scd = this_scd();
 	u64 this_clock, remote_clock;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2a4918a1faa9..fb49dbf61273 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -152,7 +152,7 @@ __read_mostly int scheduler_running;
 DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);
 
 /* kernel prio, less is more */
-static inline int __task_prio(struct task_struct *p)
+static inline int __task_prio(const struct task_struct *p)
 {
 	if (p->sched_class == &stop_sched_class) /* trumps deadline */
 		return -2;
@@ -174,7 +174,8 @@ static inline int __task_prio(struct task_struct *p)
  */
 
 /* real prio, less is less */
-static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi)
+static inline bool prio_less(const struct task_struct *a,
+			     const struct task_struct *b, bool in_fi)
 {
 
 	int pa = __task_prio(a), pb = __task_prio(b);
@@ -194,7 +195,8 @@ static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool
 	return false;
 }
 
-static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b)
+static inline bool __sched_core_less(const struct task_struct *a,
+				     const struct task_struct *b)
 {
 	if (a->core_cookie < b->core_cookie)
 		return true;
@@ -3675,14 +3677,39 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 }
 
 /*
- * Mark the task runnable and perform wakeup-preemption.
+ * Mark the task runnable.
  */
-static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
-			   struct rq_flags *rf)
+static inline void ttwu_do_wakeup(struct task_struct *p)
 {
-	check_preempt_curr(rq, p, wake_flags);
 	WRITE_ONCE(p->__state, TASK_RUNNING);
 	trace_sched_wakeup(p);
+}
+
+static void
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
+		 struct rq_flags *rf)
+{
+	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
+
+	lockdep_assert_rq_held(rq);
+
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible--;
+
+#ifdef CONFIG_SMP
+	if (wake_flags & WF_MIGRATED)
+		en_flags |= ENQUEUE_MIGRATED;
+	else
+#endif
+	if (p->in_iowait) {
+		delayacct_blkio_end(p);
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
+	activate_task(rq, p, en_flags);
+	check_preempt_curr(rq, p, wake_flags);
+
+	ttwu_do_wakeup(p);
 
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
@@ -3712,31 +3739,6 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 #endif
 }
 
-static void
-ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
-		 struct rq_flags *rf)
-{
-	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
-
-	lockdep_assert_rq_held(rq);
-
-	if (p->sched_contributes_to_load)
-		rq->nr_uninterruptible--;
-
-#ifdef CONFIG_SMP
-	if (wake_flags & WF_MIGRATED)
-		en_flags |= ENQUEUE_MIGRATED;
-	else
-#endif
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
-	activate_task(rq, p, en_flags);
-	ttwu_do_wakeup(rq, p, wake_flags, rf);
-}
-
 /*
  * Consider @p being inside a wait loop:
  *
@@ -3770,9 +3772,15 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 
 	rq = __task_rq_lock(p, &rf);
 	if (task_on_rq_queued(p)) {
-		/* check_preempt_curr() may use rq clock */
-		update_rq_clock(rq);
-		ttwu_do_wakeup(rq, p, wake_flags, &rf);
+		if (!task_on_cpu(rq, p)) {
+			/*
+			 * When on_rq && !on_cpu the task is preempted, see if
+			 * it should preempt the task that is current now.
+			 */
+			update_rq_clock(rq);
+			check_preempt_curr(rq, p, wake_flags);
+		}
+		ttwu_do_wakeup(p);
 		ret = 1;
 	}
 	__task_rq_unlock(rq, &rf);
@@ -4138,8 +4146,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		trace_sched_waking(p);
-		WRITE_ONCE(p->__state, TASK_RUNNING);
-		trace_sched_wakeup(p);
+		ttwu_do_wakeup(p);
 		goto out;
 	}
 
@@ -5104,6 +5111,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	rseq_preempt(prev);
+	switch_mm_cid(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
 	kmap_local_sched_out();
 	prepare_task(next);
@@ -6260,7 +6268,7 @@ static bool steal_cookie_task(int cpu, struct sched_domain *sd)
 {
 	int i;
 
-	for_each_cpu_wrap(i, sched_domain_span(sd), cpu) {
+	for_each_cpu_wrap(i, sched_domain_span(sd), cpu + 1) {
 		if (i == cpu)
 			continue;
 
@@ -11365,3 +11373,53 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count)
 {
         trace_sched_update_nr_running_tp(rq, count);
 }
+
+#ifdef CONFIG_SCHED_MM_CID
+void sched_mm_cid_exit_signals(struct task_struct *t)
+{
+	struct mm_struct *mm = t->mm;
+	unsigned long flags;
+
+	if (!mm)
+		return;
+	local_irq_save(flags);
+	mm_cid_put(mm, t->mm_cid);
+	t->mm_cid = -1;
+	t->mm_cid_active = 0;
+	local_irq_restore(flags);
+}
+
+void sched_mm_cid_before_execve(struct task_struct *t)
+{
+	struct mm_struct *mm = t->mm;
+	unsigned long flags;
+
+	if (!mm)
+		return;
+	local_irq_save(flags);
+	mm_cid_put(mm, t->mm_cid);
+	t->mm_cid = -1;
+	t->mm_cid_active = 0;
+	local_irq_restore(flags);
+}
+
+void sched_mm_cid_after_execve(struct task_struct *t)
+{
+	struct mm_struct *mm = t->mm;
+	unsigned long flags;
+
+	if (!mm)
+		return;
+	local_irq_save(flags);
+	t->mm_cid = mm_cid_get(mm);
+	t->mm_cid_active = 1;
+	local_irq_restore(flags);
+	rseq_set_notify_resume(t);
+}
+
+void sched_mm_cid_fork(struct task_struct *t)
+{
+	WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
+	t->mm_cid_active = 1;
+}
+#endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1207c78f85c1..5c840151f3bb 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -48,7 +48,6 @@ struct sugov_cpu {
 
 	unsigned long		util;
 	unsigned long		bw_dl;
-	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -158,7 +157,6 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
 
-	sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
 					  FREQUENCY_UTIL, NULL);
@@ -238,6 +236,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * sugov_iowait_apply() - Apply the IO boost to a CPU.
  * @sg_cpu: the sugov data for the cpu to boost
  * @time: the update time from the caller
+ * @max_cap: the max CPU capacity
  *
  * A CPU running a task which woken up after an IO operation can have its
  * utilization boosted to speed up the completion of those IO operations.
@@ -251,7 +250,8 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * This mechanism is designed to boost high frequently IO waiting tasks, while
  * being more conservative on tasks which does sporadic IO operations.
  */
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
+static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+			       unsigned long max_cap)
 {
 	unsigned long boost;
 
@@ -280,7 +280,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+	boost = (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT;
 	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
 	if (sg_cpu->util < boost)
 		sg_cpu->util = boost;
@@ -310,7 +310,8 @@ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 }
 
 static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
-					      u64 time, unsigned int flags)
+					      u64 time, unsigned long max_cap,
+					      unsigned int flags)
 {
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
@@ -321,7 +322,7 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
 		return false;
 
 	sugov_get_util(sg_cpu);
-	sugov_iowait_apply(sg_cpu, time);
+	sugov_iowait_apply(sg_cpu, time, max_cap);
 
 	return true;
 }
@@ -332,12 +333,15 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned int cached_freq = sg_policy->cached_raw_freq;
+	unsigned long max_cap;
 	unsigned int next_f;
 
-	if (!sugov_update_single_common(sg_cpu, time, flags))
+	max_cap = arch_scale_cpu_capacity(sg_cpu->cpu);
+
+	if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
 		return;
 
-	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
+	next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
@@ -374,6 +378,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
 	unsigned long prev_util = sg_cpu->util;
+	unsigned long max_cap;
 
 	/*
 	 * Fall back to the "frequency" path if frequency invariance is not
@@ -385,7 +390,9 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		return;
 	}
 
-	if (!sugov_update_single_common(sg_cpu, time, flags))
+	max_cap = arch_scale_cpu_capacity(sg_cpu->cpu);
+
+	if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
 		return;
 
 	/*
@@ -399,7 +406,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util), sg_cpu->max);
+				   map_util_perf(sg_cpu->util), max_cap);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
@@ -408,25 +415,21 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned long util = 0, max = 1;
+	unsigned long util = 0, max_cap;
 	unsigned int j;
 
+	max_cap = arch_scale_cpu_capacity(sg_cpu->cpu);
+
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
-		unsigned long j_util, j_max;
 
 		sugov_get_util(j_sg_cpu);
-		sugov_iowait_apply(j_sg_cpu, time);
-		j_util = j_sg_cpu->util;
-		j_max = j_sg_cpu->max;
+		sugov_iowait_apply(j_sg_cpu, time, max_cap);
 
-		if (j_util * max > j_max * util) {
-			util = j_util;