18 files changed, 195 insertions, 122 deletions

diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/affinity.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/cond_resched.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 4d9e3a656875..8270ad7ae14c 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm)
 #endif
 					/* leave room for more dump flags */
 #define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
-#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
+#define MMF_VM_HUGEPAGE		17	/* set when mm is available for
+					   khugepaged */
 /*
  * This one-shot flag is dropped due to necessity of changing exe once again
  * on NFS restore
@@ -70,9 +71,8 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
-#define MMF_OOM_VICTIM		25	/* mm is the oom victim */
-#define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
-#define MMF_MULTIPROCESS	27	/* mm is shared between processes */
+#define MMF_OOM_REAP_QUEUED	25	/* mm was queued for oom_reaper */
+#define MMF_MULTIPROCESS	26	/* mm is shared between processes */
 /*
  * MMF_HAS_PINNED: Whether this mm has pinned any pages.  This can be either
  * replaced in the future by mm.pinned_vm when it becomes stable, or grow into
@@ -80,7 +80,7 @@ static inline int get_dumpable(struct mm_struct *mm)
  * pinned pages were unpinned later on, we'll still keep this bit set for the
  * lifecycle of this mm, just for simplicity.
  */
-#define MMF_HAS_PINNED		28	/* FOLL_PIN has run, never cleared */
+#define MMF_HAS_PINNED		27	/* FOLL_PIN has run, never cleared */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 1aff00b65f3c..7c83d4d5a971 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -6,6 +6,8 @@
  * NORMAL/BATCH tasks.
  */
 
+#include <linux/sched.h>
+
 #define MAX_DL_PRIO		0
 
 static inline int dl_prio(int prio)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index cc9f393e2a70..8c15abd67aed 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -5,54 +5,55 @@
 #include <linux/init.h>
 #include <linux/tick.h>
 
-enum hk_flags {
-	HK_FLAG_TIMER		= 1,
-	HK_FLAG_RCU		= (1 << 1),
-	HK_FLAG_MISC		= (1 << 2),
-	HK_FLAG_SCHED		= (1 << 3),
-	HK_FLAG_TICK		= (1 << 4),
-	HK_FLAG_DOMAIN		= (1 << 5),
-	HK_FLAG_WQ		= (1 << 6),
-	HK_FLAG_MANAGED_IRQ	= (1 << 7),
-	HK_FLAG_KTHREAD		= (1 << 8),
+enum hk_type {
+	HK_TYPE_TIMER,
+	HK_TYPE_RCU,
+	HK_TYPE_MISC,
+	HK_TYPE_SCHED,
+	HK_TYPE_TICK,
+	HK_TYPE_DOMAIN,
+	HK_TYPE_WQ,
+	HK_TYPE_MANAGED_IRQ,
+	HK_TYPE_KTHREAD,
+	HK_TYPE_MAX
 };
 
 #ifdef CONFIG_CPU_ISOLATION
 DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
-extern int housekeeping_any_cpu(enum hk_flags flags);
-extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
-extern bool housekeeping_enabled(enum hk_flags flags);
-extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
-extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
+extern int housekeeping_any_cpu(enum hk_type type);
+extern const struct cpumask *housekeeping_cpumask(enum hk_type type);
+extern bool housekeeping_enabled(enum hk_type type);
+extern void housekeeping_affine(struct task_struct *t, enum hk_type type);
+extern bool housekeeping_test_cpu(int cpu, enum hk_type type);
 extern void __init housekeeping_init(void);
 
 #else
 
-static inline int housekeeping_any_cpu(enum hk_flags flags)
+static inline int housekeeping_any_cpu(enum hk_type type)
 {
 	return smp_processor_id();
 }
 
-static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+static inline const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	return cpu_possible_mask;
 }
 
-static inline bool housekeeping_enabled(enum hk_flags flags)
+static inline bool housekeeping_enabled(enum hk_type type)
 {
 	return false;
 }
 
 static inline void housekeeping_affine(struct task_struct *t,
-				       enum hk_flags flags) { }
+				       enum hk_type type) { }
 static inline void housekeeping_init(void) { }
 #endif /* CONFIG_CPU_ISOLATION */
 
-static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
+static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 {
 #ifdef CONFIG_CPU_ISOLATION
 	if (static_branch_unlikely(&housekeeping_overridden))
-		return housekeeping_test_cpu(cpu, flags);
+		return housekeeping_test_cpu(cpu, type);
 #endif
 	return true;
 }
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de9f1a9..68876d0a7ef9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,10 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
+#define JOBCTL_PTRACE_FROZEN_BIT	24	/* frozen for ptrace */
+
+#define JOBCTL_STOPPED_BIT	26	/* do_signal_stop() */
+#define JOBCTL_TRACED_BIT	27	/* ptrace_stop() */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,6 +32,10 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
+#define JOBCTL_PTRACE_FROZEN	(1UL << JOBCTL_PTRACE_FROZEN_BIT)
+
+#define JOBCTL_STOPPED		(1UL << JOBCTL_STOPPED_BIT)
+#define JOBCTL_TRACED		(1UL << JOBCTL_TRACED_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index aca874d33fe6..2a243616f222 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -8,6 +8,7 @@
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
 #include <linux/sync_core.h>
+#include <linux/ioasid.h>
 
 /*
  * Routines for handling mm_structs
@@ -28,7 +29,7 @@ extern struct mm_struct *mm_alloc(void);
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
  *
- * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
+ * See also <Documentation/mm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
 static inline void mmgrab(struct mm_struct *mm)
@@ -91,7 +92,7 @@ static inline void mmdrop_sched(struct mm_struct *mm)
  *
  * Use mmput() to release the reference acquired by mmget().
  *
- * See also <Documentation/vm/active_mm.rst> for an in-depth explanation
+ * See also <Documentation/mm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
 static inline void mmget(struct mm_struct *mm)
@@ -135,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 #endif /* CONFIG_MEMCG */
 
 #ifdef CONFIG_MMU
+#ifndef arch_get_mmap_end
+#define arch_get_mmap_end(addr, len, flags)	(TASK_SIZE)
+#endif
+
+#ifndef arch_get_mmap_base
+#define arch_get_mmap_base(addr, base) (base)
+#endif
+
 extern void arch_pick_mmap_layout(struct mm_struct *mm,
 				  struct rlimit *rlim_stack);
 extern unsigned long
@@ -144,6 +153,15 @@ extern unsigned long
 arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
+
+unsigned long
+generic_get_unmapped_area(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags);
+unsigned long
+generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags);
 #else
 static inline void arch_pick_mmap_layout(struct mm_struct *mm,
 					 struct rlimit *rlim_stack) {}
@@ -214,6 +232,32 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
 static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
 
+/* Any memory-allocation retry loop should use
+ * memalloc_retry_wait(), and pass the flags for the most
+ * constrained allocation attempt that might have failed.
+ * This provides useful documentation of where loops are,
+ * and a central place to fine tune the waiting as the MM
+ * implementation changes.
+ */
+static inline void memalloc_retry_wait(gfp_t gfp_flags)
+{
+	/* We use io_schedule_timeout because waiting for memory
+	 * typically included waiting for dirty pages to be
+	 * written out, which requires IO.
+	 */
+	__set_current_state(TASK_UNINTERRUPTIBLE);
+	gfp_flags = current_gfp_context(gfp_flags);
+	if (gfpflags_allow_blocking(gfp_flags) &&
+	    !(gfp_flags & __GFP_NORETRY))
+		/* Probably waited already, no need for much more */
+		io_schedule_timeout(1);
+	else
+		/* Probably didn't wait, and has now released a lock,
+		 * so now is a good time to wait
+		 */
+		io_schedule_timeout(HZ/50);
+}
+
 /**
  * might_alloc - Mark possible allocation sites
  * @gfp_mask: gfp_t flags that would be used to allocate
@@ -407,4 +451,29 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
 }
 #endif
 
+#ifdef CONFIG_IOMMU_SVA
+static inline void mm_pasid_init(struct mm_struct *mm)
+{
+	mm->pasid = INVALID_IOASID;
+}
+
+/* Associate a PASID with an mm_struct: */
+static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid)
+{
+	mm->pasid = pasid;
+}
+
+static inline void mm_pasid_drop(struct mm_struct *mm)
+{
+	if (pasid_valid(mm->pasid)) {
+		ioasid_free(mm->pasid);
+		mm->pasid = INVALID_IOASID;
+	}
+}
+#else
+static inline void mm_pasid_init(struct mm_struct *mm) {}
+static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {}
+static inline void mm_pasid_drop(struct mm_struct *mm) {}
+#endif
+
 #endif /* _LINUX_SCHED_MM_H */
diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h
new file mode 100644
index 000000000000..523a381d6c88
--- /dev/null
+++ b/include/linux/sched/posix-timers.h
@@ -0,0 +1 @@
+#include <linux/posix-timers.h>
diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h
new file mode 100644
index 000000000000..cf2af72693e1
--- /dev/null
+++ b/include/linux/sched/rseq_api.h
@@ -0,0 +1 @@
+#include <linux/rseq.h>
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index e5af028c08b4..994c25640e15 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -39,20 +39,12 @@ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
 }
 extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return tsk->pi_blocked_on != NULL;
-}
 #else
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
 }
 # define rt_mutex_adjust_pi(p)		do { } while (0)
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return false;
-}
 #endif
 
 extern void normalize_rt_tasks(void);
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 33a50642cf41..20099268fa25 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -94,6 +94,7 @@ struct signal_struct {
 	refcount_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	int			quick_threads;
 	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
@@ -109,13 +110,9 @@ struct signal_struct {
 
 	/* thread group exit support */
 	int			group_exit_code;
-	/* overloaded:
-	 * - notify group_exit_task when ->count is equal to notify_count
-	 * - everyone except group_exit_task is stopped during signal delivery
-	 *   of fatal signals, group_exit_task processes the signal.
-	 */
+	/* notify group_exec_task when notify_count is less or equal to 0 */
 	int			notify_count;
-	struct task_struct	*group_exit_task;
+	struct task_struct	*group_exec_task;
 
 	/* thread group stop support, overloads group_exit_code too */
 	int			group_stop_count;
@@ -256,7 +253,6 @@ struct signal_struct {
 #define SIGNAL_STOP_STOPPED	0x00000001 /* job control stop in effect */
 #define SIGNAL_STOP_CONTINUED	0x00000002 /* SIGCONT since WCONTINUED reap */
 #define SIGNAL_GROUP_EXIT	0x00000004 /* group exit in progress */
-#define SIGNAL_GROUP_COREDUMP	0x00000008 /* coredump in progress */
 /*
  * Pending notifications to parent.
  */
@@ -272,31 +268,25 @@ struct signal_struct {
 static inline void signal_set_stop_flags(struct signal_struct *sig,
 					 unsigned int flags)
 {
-	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+	WARN_ON(sig->flags & SIGNAL_GROUP_EXIT);
 	sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
 }
 
-/* If true, all threads except ->group_exit_task have pending SIGKILL */
-static inline int signal_group_exit(const struct signal_struct *sig)
-{
-	return	(sig->flags & SIGNAL_GROUP_EXIT) ||
-		(sig->group_exit_task != NULL);
-}
-
 extern void flush_signals(struct task_struct *);
 extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
-extern int dequeue_signal(struct task_struct *task,
-			  sigset_t *mask, kernel_siginfo_t *info);
+extern int dequeue_signal(struct task_struct *task, sigset_t *mask,
+			  kernel_siginfo_t *info, enum pid_type *type);
 
 static inline int kernel_dequeue_signal(void)
 {
 	struct task_struct *task = current;
 	kernel_siginfo_t __info;
+	enum pid_type __type;
 	int ret;
 
 	spin_lock_irq(&task->sighand->siglock);
-	ret = dequeue_signal(task, &task->blocked, &__info);
+	ret = dequeue_signal(task, &task->blocked, &__info, &__type);
 	spin_unlock_irq(&task->sighand->siglock);
 
 	return ret;
@@ -305,8 +295,10 @@ static inline int kernel_dequeue_signal(void)
 static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
-	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED) {
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
+	}
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();
@@ -331,7 +323,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *);
 
 int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper);
 int force_sig_pkuerr(void __user *addr, u32 pkey);
-int force_sig_perf(void __user *addr, u32 type, u64 sig_data);
+int send_sig_perf(void __user *addr, u32 type, u64 sig_data);
 
 int force_sig_ptrace_errno_trap(int errno, void __user *addr);
 int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno);
@@ -360,6 +352,32 @@ extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type);
 extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
 
+static inline void clear_notify_signal(void)
+{
+	clear_thread_flag(TIF_NOTIFY_SIGNAL);
+	smp_mb__after_atomic();
+}
+
+/*
+ * Returns 'true' if kick_process() is needed to force a transition from
+ * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work.
+ */
+static inline bool __set_notify_signal(struct task_struct *task)
+{
+	return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
+	       !wake_up_state(task, TASK_INTERRUPTIBLE);
+}
+
+/*
+ * Called to break out of interruptible wait loops, and enter the
+ * exit_to_user_mode_loop().
+ */
+static inline void set_notify_signal(struct task_struct *task)
+{
+	if (__set_notify_signal(task))
+		kick_process(task);
+}
+
 static inline int restart_syscall(void)
 {
 	set_tsk_thread_flag(current, TIF_SIGPENDING);
@@ -429,13 +447,23 @@ extern void calculate_sigpending(void);
 
 extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
 
-static inline void signal_wake_up(struct task_struct *t, bool resume)
+static inline void signal_wake_up(struct task_struct *t, bool fatal)
 {
-	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+	unsigned int state = 0;
+	if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) {
+		t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED);
+		state = TASK_WAKEKILL | __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {
-	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+	unsigned int state = 0;
+	if (resume) {
+		t->jobctl &= ~JOBCTL_TRACED;
+		state = __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 
 void task_join_group_stop(struct task_struct *task);
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 304f431178fd..303ee7dd0c7e 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -7,27 +7,13 @@
 struct ctl_table;
 
 #ifdef CONFIG_DETECT_HUNG_TASK
-
-#ifdef CONFIG_SMP
-extern unsigned int sysctl_hung_task_all_cpu_backtrace;
-#else
-#define sysctl_hung_task_all_cpu_backtrace 0
-#endif /* CONFIG_SMP */
-
-extern int	     sysctl_hung_task_check_count;
-extern unsigned int  sysctl_hung_task_panic;
+/* used for hung_task and block/ */
 extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_check_interval_secs;
-extern int sysctl_hung_task_warnings;
-int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
 #else
 /* Avoid need for ifdefs elsewhere in the code */
 enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
-extern unsigned int sysctl_sched_child_runs_first;
-
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,
@@ -35,50 +21,18 @@ enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_END,
 };
 
-/*
- *  control realtime throttling:
- *
- *  /proc/sys/kernel/sched_rt_period_us
- *  /proc/sys/kernel/sched_rt_runtime_us
- */
-extern unsigned int sysctl_sched_rt_period;
-extern int sysctl_sched_rt_runtime;
-
-extern unsigned int sysctl_sched_dl_period_max;
-extern unsigned int sysctl_sched_dl_period_min;
-
-#ifdef CONFIG_UCLAMP_TASK
-extern unsigned int sysctl_sched_uclamp_util_min;
-extern unsigned int sysctl_sched_uclamp_util_max;
-extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
-#endif
-
-#ifdef CONFIG_CFS_BANDWIDTH
-extern unsigned int sysctl_sched_cfs_bandwidth_slice;
-#endif
+#define NUMA_BALANCING_DISABLED		0x0
+#define NUMA_BALANCING_NORMAL		0x1
+#define NUMA_BALANCING_MEMORY_TIERING	0x2
 
-#ifdef CONFIG_SCHED_AUTOGROUP
-extern unsigned int sysctl_sched_autogroup_enabled;
+#ifdef CONFIG_NUMA_BALANCING
+extern int sysctl_numa_balancing_mode;
+extern unsigned int sysctl_numa_balancing_promote_rate_limit;
+#else
+#define sysctl_numa_balancing_mode	0
 #endif
 
-extern int sysctl_sched_rr_timeslice;
-extern int sched_rr_timeslice;
-
-int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-extern unsigned int sysctl_sched_energy_aware;
-int sched_energy_aware_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-#endif
 
 #endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 058d7f371e25..d6c48163c6de 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -32,6 +32,10 @@ struct kernel_clone_args {
 	size_t set_tid_size;
 	int cgroup;
 	int io_thread;
+	int kthread;
+	int idle;
+	int (*fn)(void *);
+	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
@@ -54,11 +58,12 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
-extern void sched_post_fork(struct task_struct *p,
-			    struct kernel_clone_args *kargs);
+extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern void sched_post_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 void __noreturn do_task_dead(void);
+void __noreturn make_task_dead(int signr);
 
 extern void proc_caches_init(void);
 
@@ -66,8 +71,7 @@ extern void fork_init(void);
 
 extern void release_task(struct task_struct * p);
 
-extern int copy_thread(unsigned long, unsigned long, unsigned long,
-		       struct task_struct *, unsigned long);
+extern int copy_thread(struct task_struct *, const struct kernel_clone_args *);
 
 extern void flush_thread(void);
 
@@ -78,16 +82,17 @@ static inline void exit_thread(struct task_struct *tsk)
 {
 }
 #endif
-extern void do_group_exit(int);
+extern __noreturn void do_group_exit(int);
 
 extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
 struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 int kernel_wait(pid_t pid, int *stat);
 
@@ -122,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr)
 
 void put_task_struct_rcu_user(struct task_struct *task);
 
+/* Free all architecture-specific resources held by a thread. */
+void release_thread(struct task_struct *dead_task);
+
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
 extern int arch_task_struct_size __read_mostly;
 #else
diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/task_flags.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index d10150587d81..5e799a47431e 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -16,7 +16,7 @@
  * try_get_task_stack() instead.  task_stack_page will return a pointer
  * that could get freed out from under you.
  */
-static inline void *task_stack_page(const struct task_struct *task)
+static __always_inline void *task_stack_page(const struct task_struct *task)
 {
 	return task->stack;
 }
@@ -79,6 +79,8 @@ static inline void *try_get_task_stack(struct task_struct *tsk)
 static inline void put_task_stack(struct task_struct *tsk) {}
 #endif
 
+void exit_task_stack_account(struct task_struct *tsk);
+
 #define task_stack_end_corrupted(task) \
 		(*(end_of_stack(task)) != STACK_END_MAGIC)
 
diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h
new file mode 100644
index 000000000000..2c60fbc16c08
--- /dev/null
+++ b/include/linux/sched/thread_info_api.h
@@ -0,0 +1 @@
+#include <linux/thread_info.h>
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 8054641c0a7b..816df6cc444e 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -81,6 +81,7 @@ struct sched_domain_shared {
 	atomic_t	ref;
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
+	int		nr_idle_scan;
 };
 
 struct sched_domain {
@@ -93,6 +94,7 @@ struct sched_domain {
 	unsigned int busy_factor;	/* less balancing by factor if busy */
 	unsigned int imbalance_pct;	/* No balance until over watermark */
 	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
+	unsigned int imb_numa_nr;	/* Nr running tasks that allows a NUMA imbalance */
 
 	int nohz_idle;			/* NOHZ IDLE status */
 	int flags;			/* See SD_* */
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 00ed419dd464..f054d0360a75 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -24,7 +24,8 @@ struct user_struct {
 	kuid_t uid;
 
 #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
-    defined(CONFIG_NET) || defined(CONFIG_IO_URING)
+	defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
+	defined(CONFIG_VFIO_PCI_ZDEV_KVM)
 	atomic_long_t locked_vm;
 #endif
 #ifdef CONFIG_WATCH_QUEUE