Initial commit: Linux kernel 4.19 for Unplugged OS

include/linux/sched/autogroup.h

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_AUTOGROUP_H
+#define _LINUX_SCHED_AUTOGROUP_H
+
+struct signal_struct;
+struct task_struct;
+struct task_group;
+struct seq_file;
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern void sched_autogroup_create_attach(struct task_struct *p);
+extern void sched_autogroup_detach(struct task_struct *p);
+extern void sched_autogroup_fork(struct signal_struct *sig);
+extern void sched_autogroup_exit(struct signal_struct *sig);
+extern void sched_autogroup_exit_task(struct task_struct *p);
+#ifdef CONFIG_PROC_FS
+extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
+#endif
+#else
+static inline void sched_autogroup_create_attach(struct task_struct *p) { }
+static inline void sched_autogroup_detach(struct task_struct *p) { }
+static inline void sched_autogroup_fork(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit_task(struct task_struct *p) { }
+#endif
+
+#ifdef CONFIG_CGROUP_SCHED
+extern struct task_group root_task_group;
+#endif /* CONFIG_CGROUP_SCHED */
+
+#endif /* _LINUX_SCHED_AUTOGROUP_H */

include/linux/sched/clock.h

@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_CLOCK_H
+#define _LINUX_SCHED_CLOCK_H
+
+#include <linux/smp.h>
+
+/*
+ * Do not use outside of architecture code which knows its limitations.
+ *
+ * sched_clock() has no promise of monotonicity or bounded drift between
+ * CPUs, use (which you should not) requires disabling IRQs.
+ *
+ * Please use one of the three interfaces below.
+ */
+extern unsigned long long notrace sched_clock(void);
+
+/*
+ * alternative sched_clock to get arch_timer cycle as well
+ */
+extern unsigned long long notrace sched_clock_get_cyc(
+	unsigned long long *cyc_ret);
+
+/*
+ * See the comment in kernel/sched/clock.c
+ */
+extern u64 running_clock(void);
+extern u64 sched_clock_cpu(int cpu);
+
+
+extern void sched_clock_init(void);
+
+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_tick(void)
+{
+}
+
+static inline void clear_sched_clock_stable(void)
+{
+}
+
+static inline void sched_clock_idle_sleep_event(void)
+{
+}
+
+static inline void sched_clock_idle_wakeup_event(void)
+{
+}
+
+static inline u64 cpu_clock(int cpu)
+{
+	return sched_clock();
+}
+
+static inline u64 local_clock(void)
+{
+	return sched_clock();
+}
+#else
+extern int sched_clock_stable(void);
+extern void clear_sched_clock_stable(void);
+
+/*
+ * When sched_clock_stable(), __sched_clock_offset provides the offset
+ * between local_clock() and sched_clock().
+ */
+extern u64 __sched_clock_offset;
+
+extern void sched_clock_tick(void);
+extern void sched_clock_tick_stable(void);
+extern void sched_clock_idle_sleep_event(void);
+extern void sched_clock_idle_wakeup_event(void);
+
+/*
+ * As outlined in clock.c, provides a fast, high resolution, nanosecond
+ * time source that is monotonic per cpu argument and has bounded drift
+ * between cpus.
+ *
+ * ######################### BIG FAT WARNING ##########################
+ * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
+ * # go backwards !!                                                  #
+ * ####################################################################
+ */
+static inline u64 cpu_clock(int cpu)
+{
+	return sched_clock_cpu(cpu);
+}
+
+static inline u64 local_clock(void)
+{
+	return sched_clock_cpu(raw_smp_processor_id());
+}
+#endif
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+extern void enable_sched_clock_irqtime(void);
+extern void disable_sched_clock_irqtime(void);
+#else
+static inline void enable_sched_clock_irqtime(void) {}
+static inline void disable_sched_clock_irqtime(void) {}
+#endif
+
+#endif /* _LINUX_SCHED_CLOCK_H */

include/linux/sched/coredump.h

@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_COREDUMP_H
+#define _LINUX_SCHED_COREDUMP_H
+
+#include <linux/mm_types.h>
+
+#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
+#define SUID_DUMP_USER		1	/* Dump as user of process */
+#define SUID_DUMP_ROOT		2	/* Dump as root */
+
+/* mm flags */
+
+/* for SUID_DUMP_* above */
+#define MMF_DUMPABLE_BITS 2
+#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
+
+extern void set_dumpable(struct mm_struct *mm, int value);
+/*
+ * This returns the actual value of the suid_dumpable flag. For things
+ * that are using this for checking for privilege transitions, it must
+ * test against SUID_DUMP_USER rather than treating it as a boolean
+ * value.
+ */
+static inline int __get_dumpable(unsigned long mm_flags)
+{
+	return mm_flags & MMF_DUMPABLE_MASK;
+}
+
+static inline int get_dumpable(struct mm_struct *mm)
+{
+	return __get_dumpable(mm->flags);
+}
+
+/* coredump filter bits */
+#define MMF_DUMP_ANON_PRIVATE	2
+#define MMF_DUMP_ANON_SHARED	3
+#define MMF_DUMP_MAPPED_PRIVATE	4
+#define MMF_DUMP_MAPPED_SHARED	5
+#define MMF_DUMP_ELF_HEADERS	6
+#define MMF_DUMP_HUGETLB_PRIVATE 7
+#define MMF_DUMP_HUGETLB_SHARED  8
+#define MMF_DUMP_DAX_PRIVATE	9
+#define MMF_DUMP_DAX_SHARED	10
+
+#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
+#define MMF_DUMP_FILTER_BITS	9
+#define MMF_DUMP_FILTER_MASK \
+	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
+#define MMF_DUMP_FILTER_DEFAULT \
+	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
+	 (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
+
+#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
+# define MMF_DUMP_MASK_DEFAULT_ELF	(1 << MMF_DUMP_ELF_HEADERS)
+#else
+# define MMF_DUMP_MASK_DEFAULT_ELF	0
+#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 */
+/*
+ * This one-shot flag is dropped due to necessity of changing exe once again
+ * on NFS restore
+ */
+//#define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
+
+#define MMF_HAS_UPROBES		19	/* has uprobes */
+#define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
+#define MMF_OOM_SKIP		21	/* mm is of no interest for the OOM killer */
+#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_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
+
+#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
+				 MMF_DISABLE_THP_MASK)
+
+#endif /* _LINUX_SCHED_COREDUMP_H */

include/linux/sched/cpufreq.h

@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_CPUFREQ_H
+#define _LINUX_SCHED_CPUFREQ_H
+
+#include <linux/types.h>
+#include "../../../drivers/misc/mediatek/base/power/include/mtk_upower.h"
+/*
+ * Interface between cpufreq drivers and the scheduler:
+ */
+
+#define SCHED_CPUFREQ_IOWAIT	(1U << 0)
+#define SCHED_CPUFREQ_MIGRATION	(1U << 1)
+
+#ifdef CONFIG_CPU_FREQ
+struct cpufreq_policy;
+
+struct update_util_data {
+       void (*func)(struct update_util_data *data, u64 time, unsigned int flags);
+};
+
+void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
+                       void (*func)(struct update_util_data *data, u64 time,
+				    unsigned int flags));
+void cpufreq_remove_update_util_hook(int cpu);
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy);
+
+static inline unsigned long map_util_freq(unsigned long util,
+					unsigned long freq, unsigned long cap)
+{
+	return (freq + (freq >> 2)) * util / cap;
+}
+
+#ifdef CONFIG_NONLINEAR_FREQ_CTL
+extern unsigned int capacity_margin;
+extern unsigned int mt_cpufreq_get_cpu_freq(int cpu, int idx);
+__attribute__((unused)) static unsigned long mtk_map_util_freq(int cpu, unsigned long util)
+{
+	struct upower_tbl *tbl;
+	int idx, cap, target_idx = 0;
+
+#ifdef CONFIG_MTK_SCHED_EXTENSION
+	util = util * capacity_margin / SCHED_CAPACITY_SCALE;
+#endif
+
+	tbl = upower_get_core_tbl(cpu);
+	for (idx = 0; idx < tbl->row_num ; idx++) {
+		cap = tbl->row[idx].cap;
+		if (!cap)
+			break;
+
+		target_idx = idx;
+
+		if (cap >= util)
+			break;
+	}
+
+	return mt_cpufreq_get_cpu_freq(cpu, target_idx);
+}
+#endif /* CONFIG_NONLINEAR_FREQ_CTL */
+
+#endif /* CONFIG_CPU_FREQ */
+
+#endif /* _LINUX_SCHED_CPUFREQ_H */

include/linux/sched/cputime.h

@@ -0,0 +1,189 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_CPUTIME_H
+#define _LINUX_SCHED_CPUTIME_H
+
+#include <linux/sched/signal.h>
+
+/*
+ * cputime accounting APIs:
+ */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+#include <asm/cputime.h>
+
+#ifndef cputime_to_nsecs
+# define cputime_to_nsecs(__ct)	\
+	(cputime_to_usecs(__ct) * NSEC_PER_USEC)
+#endif
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void task_cputime(struct task_struct *t,
+			 u64 *utime, u64 *stime);
+extern u64 task_gtime(struct task_struct *t);
+#else
+static inline void task_cputime(struct task_struct *t,
+				u64 *utime, u64 *stime)
+{
+	*utime = t->utime;
+	*stime = t->stime;
+}
+
+static inline u64 task_gtime(struct task_struct *t)
+{
+	return t->gtime;
+}
+#endif
+
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+static inline void task_cputime_scaled(struct task_struct *t,
+				       u64 *utimescaled,
+				       u64 *stimescaled)
+{
+	*utimescaled = t->utimescaled;
+	*stimescaled = t->stimescaled;
+}
+#else
+static inline void task_cputime_scaled(struct task_struct *t,
+				       u64 *utimescaled,
+				       u64 *stimescaled)
+{
+	task_cputime(t, utimescaled, stimescaled);
+}
+#endif
+
+extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
+			   u64 *ut, u64 *st);
+
+/*
+ * Thread group CPU time accounting.
+ */
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
+
+
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+/**
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
+ *
+ * @tsk:	Pointer to target task.
+ */
+#ifdef CONFIG_POSIX_TIMERS
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	/* Check if cputimer isn't running. This is accessed without locking. */
+	if (!READ_ONCE(cputimer->running))
+		return NULL;
+
+	/*
+	 * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
+	 * in __exit_signal(), we won't account to the signal struct further
+	 * cputime consumed by that task, even though the task can still be
+	 * ticking after __exit_signal().
+	 *
+	 * In order to keep a consistent behaviour between thread group cputime
+	 * and thread group cputimer accounting, lets also ignore the cputime
+	 * elapsing after __exit_signal() in any thread group timer running.
+	 *
+	 * This makes sure that POSIX CPU clocks and timers are synchronized, so
+	 * that a POSIX CPU timer won't expire while the corresponding POSIX CPU
+	 * clock delta is behind the expiring timer value.
+	 */
+	if (unlikely(!tsk->sighand))
+		return NULL;
+
+	return cputimer;
+}
+#else
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
+{
+	return NULL;
+}
+#endif
+
+/**
+ * account_group_user_time - Maintain utime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the utime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+					   u64 cputime)
+{
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
+
+	if (!cputimer)
+		return;
+
+	atomic64_add(cputime, &cputimer->cputime_atomic.utime);
+}
+
+/**
+ * account_group_system_time - Maintain stime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the stime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void account_group_system_time(struct task_struct *tsk,
+					     u64 cputime)
+{
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
+
+	if (!cputimer)
+		return;
+
+	atomic64_add(cputime, &cputimer->cputime_atomic.stime);
+}
+
+/**
+ * account_group_exec_runtime - Maintain exec runtime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of the thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					      unsigned long long ns)
+{
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
+
+	if (!cputimer)
+		return;
+
+	atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
+}
+
+static inline void prev_cputime_init(struct prev_cputime *prev)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	prev->utime = prev->stime = 0;
+	raw_spin_lock_init(&prev->lock);
+#endif
+}
+
+extern unsigned long long
+task_sched_runtime(struct task_struct *task);
+
+#endif /* _LINUX_SCHED_CPUTIME_H */

include/linux/sched/deadline.h

@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+ * NORMAL/BATCH tasks.
+ */
+
+#define MAX_DL_PRIO		0
+
+static inline int dl_prio(int prio)
+{
+	if (unlikely(prio < MAX_DL_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int dl_task(struct task_struct *p)
+{
+	return dl_prio(p->prio);
+}
+
+static inline bool dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}

include/linux/sched/debug.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_DEBUG_H
+#define _LINUX_SCHED_DEBUG_H
+
+/*
+ * Various scheduler/task debugging interfaces:
+ */
+
+struct task_struct;
+struct pid_namespace;
+
+extern void dump_cpu_task(int cpu);
+
+/*
+ * Only dump TASK_* tasks. (0 for all tasks)
+ */
+extern void show_state_filter(unsigned long state_filter);
+
+static inline void show_state(void)
+{
+	show_state_filter(0);
+}
+
+struct pt_regs;
+
+extern void show_regs(struct pt_regs *);
+
+/*
+ * TASK is a pointer to the task whose backtrace we want to see (or NULL for current
+ * task), SP is the stack pointer of the first frame that should be shown in the back
+ * trace (or NULL if the entire call-chain of the task should be shown).
+ */
+extern void show_stack(struct task_struct *task, unsigned long *sp);
+
+extern void sched_show_task(struct task_struct *p);
+
+#ifdef CONFIG_SCHED_DEBUG
+struct seq_file;
+extern void proc_sched_show_task(struct task_struct *p,
+				 struct pid_namespace *ns, struct seq_file *m);
+extern void proc_sched_set_task(struct task_struct *p);
+#endif
+
+/* Attach to any functions which should be ignored in wchan output. */
+#define __sched		__attribute__((__section__(".sched.text")))
+
+/* Linker adds these: start and end of __sched functions */
+extern char __sched_text_start[], __sched_text_end[];
+
+/* Is this address in the __sched functions? */
+extern int in_sched_functions(unsigned long addr);
+
+#endif /* _LINUX_SCHED_DEBUG_H */

include/linux/sched/hotplug.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_HOTPLUG_H
+#define _LINUX_SCHED_HOTPLUG_H
+
+/*
+ * Scheduler interfaces for hotplug CPU support:
+ */
+
+extern int sched_cpu_starting(unsigned int cpu);
+extern int sched_cpu_activate(unsigned int cpu);
+extern int sched_cpu_deactivate(unsigned int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_dying(unsigned int cpu);
+#else
+# define sched_cpu_dying	NULL
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern void idle_task_exit(void);
+#else
+static inline void idle_task_exit(void) {}
+#endif
+
+#endif /* _LINUX_SCHED_HOTPLUG_H */

include/linux/sched/idle.h

@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_IDLE_H
+#define _LINUX_SCHED_IDLE_H
+
+#include <linux/sched.h>
+
+enum cpu_idle_type {
+	CPU_IDLE,
+	CPU_NOT_IDLE,
+	CPU_NEWLY_IDLE,
+	CPU_MAX_IDLE_TYPES
+};
+
+extern void wake_up_if_idle(int cpu);
+
+/*
+ * Idle thread specific functions to determine the need_resched
+ * polling state.
+ */
+#ifdef TIF_POLLING_NRFLAG
+
+static inline void __current_set_polling(void)
+{
+	set_thread_flag(TIF_POLLING_NRFLAG);
+}
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	__current_set_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_curr()
+	 */
+	smp_mb__after_atomic();
+
+	return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
+{
+	clear_thread_flag(TIF_POLLING_NRFLAG);
+}
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_curr()
+	 */
+	smp_mb__after_atomic();
+
+	return unlikely(tif_need_resched());
+}
+
+#else
+static inline void __current_set_polling(void) { }
+static inline void __current_clr_polling(void) { }
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
+#endif
+
+static inline void current_clr_polling(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
+	 * Once the bit is cleared, we'll get IPIs with every new
+	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
+	 * fold.
+	 */
+	smp_mb(); /* paired with resched_curr() */
+
+	preempt_fold_need_resched();
+}
+
+#endif /* _LINUX_SCHED_IDLE_H */

include/linux/sched/init.h

@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_INIT_H
+#define _LINUX_SCHED_INIT_H
+
+/*
+ * Scheduler init related prototypes:
+ */
+
+extern void sched_init(void);
+extern void sched_init_smp(void);
+
+#endif /* _LINUX_SCHED_INIT_H */

include/linux/sched/isolation.h

@@ -0,0 +1,52 @@
+#ifndef _LINUX_SCHED_ISOLATION_H
+#define _LINUX_SCHED_ISOLATION_H
+
+#include <linux/cpumask.h>
+#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),
+};
+
+#ifdef CONFIG_CPU_ISOLATION
+DECLARE_STATIC_KEY_FALSE(housekeeping_overriden);
+extern int housekeeping_any_cpu(enum hk_flags flags);
+extern const struct cpumask *housekeeping_cpumask(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 void __init housekeeping_init(void);
+
+#else
+
+static inline int housekeeping_any_cpu(enum hk_flags flags)
+{
+	return smp_processor_id();
+}
+
+static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+{
+	return cpu_possible_mask;
+}
+
+static inline void housekeeping_affine(struct task_struct *t,
+				       enum hk_flags flags) { }
+static inline void housekeeping_init(void) { }
+#endif /* CONFIG_CPU_ISOLATION */
+
+static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
+{
+#ifdef CONFIG_CPU_ISOLATION
+	if (static_branch_unlikely(&housekeeping_overriden))
+		return housekeeping_test_cpu(cpu, flags);
+#endif
+	return true;
+}
+
+#endif /* _LINUX_SCHED_ISOLATION_H */

include/linux/sched/jobctl.h

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_JOBCTL_H
+#define _LINUX_SCHED_JOBCTL_H
+
+#include <linux/types.h>
+
+struct task_struct;
+
+/*
+ * task->jobctl flags
+ */
+#define JOBCTL_STOP_SIGMASK	0xffff	/* signr of the last group stop */
+
+#define JOBCTL_STOP_DEQUEUED_BIT 16	/* stop signal dequeued */
+#define JOBCTL_STOP_PENDING_BIT	17	/* task should stop for group stop */
+#define JOBCTL_STOP_CONSUME_BIT	18	/* consume group stop count */
+#define JOBCTL_TRAP_STOP_BIT	19	/* trap for STOP */
+#define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
+#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_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#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_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+
+extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
+extern void task_clear_jobctl_trapping(struct task_struct *task);
+extern void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask);
+
+#endif /* _LINUX_SCHED_JOBCTL_H */

include/linux/sched/loadavg.h

@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_LOADAVG_H
+#define _LINUX_SCHED_LOADAVG_H
+
+/*
+ * These are the constant used to fake the fixed-point load-average
+ * counting. Some notes:
+ *  - 11 bit fractions expand to 22 bits by the multiplies: this gives
+ *    a load-average precision of 10 bits integer + 11 bits fractional
+ *  - if you want to count load-averages more often, you need more
+ *    precision, or rounding will get you. With 2-second counting freq,
+ *    the EXP_n values would be 1981, 2034 and 2043 if still using only
+ *    11 bit fractions.
+ */
+extern unsigned long avenrun[];		/* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
+
+#define FSHIFT		11		/* nr of bits of precision */
+#define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
+#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
+#define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
+#define EXP_5		2014		/* 1/exp(5sec/5min) */
+#define EXP_15		2037		/* 1/exp(5sec/15min) */
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
+static inline unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	unsigned long newload;
+
+	newload = load * exp + active * (FIXED_1 - exp);
+	if (active >= load)
+		newload += FIXED_1-1;
+
+	return newload / FIXED_1;
+}
+
+extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
+				 unsigned long active, unsigned int n);
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+
+extern void calc_global_load(unsigned long ticks);
+
+#endif /* _LINUX_SCHED_LOADAVG_H */

include/linux/sched/mm.h

@@ -0,0 +1,398 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_MM_H
+#define _LINUX_SCHED_MM_H
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+#include <linux/sched.h>
+#include <linux/mm_types.h>
+#include <linux/gfp.h>
+#include <linux/sync_core.h>
+
+/*
+ * Routines for handling mm_structs
+ */
+extern struct mm_struct *mm_alloc(void);
+
+/**
+ * mmgrab() - Pin a &struct mm_struct.
+ * @mm: The &struct mm_struct to pin.
+ *
+ * Make sure that @mm will not get freed even after the owning task
+ * exits. This doesn't guarantee that the associated address space
+ * will still exist later on and mmget_not_zero() has to be used before
+ * accessing it.
+ *
+ * This is a preferred way to to pin @mm for a longer/unbounded amount
+ * of time.
+ *
+ * Use mmdrop() to release the reference acquired by mmgrab().
+ *
+ * See also <Documentation/vm/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)
+{
+	atomic_inc(&mm->mm_count);
+}
+
+extern void __mmdrop(struct mm_struct *mm);
+
+static inline void mmdrop(struct mm_struct *mm)
+{
+	/*
+	 * The implicit full barrier implied by atomic_dec_and_test() is
+	 * required by the membarrier system call before returning to
+	 * user-space, after storing to rq->curr.
+	 */
+	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
+		__mmdrop(mm);
+}
+
+void mmdrop(struct mm_struct *mm);
+
+/*
+ * This has to be called after a get_task_mm()/mmget_not_zero()
+ * followed by taking the mmap_sem for writing before modifying the
+ * vmas or anything the coredump pretends not to change from under it.
+ *
+ * It also has to be called when mmgrab() is used in the context of
+ * the process, but then the mm_count refcount is transferred outside
+ * the context of the process to run down_write() on that pinned mm.
+ *
+ * NOTE: find_extend_vma() called from GUP context is the only place
+ * that can modify the "mm" (notably the vm_start/end) under mmap_sem
+ * for reading and outside the context of the process, so it is also
+ * the only case that holds the mmap_sem for reading that must call
+ * this function. Generally if the mmap_sem is hold for reading
+ * there's no need of this check after get_task_mm()/mmget_not_zero().
+ *
+ * This function can be obsoleted and the check can be removed, after
+ * the coredump code will hold the mmap_sem for writing before
+ * invoking the ->core_dump methods.
+ */
+static inline bool mmget_still_valid(struct mm_struct *mm)
+{
+	return likely(!mm->core_state);
+}
+
+/**
+ * mmget() - Pin the address space associated with a &struct mm_struct.
+ * @mm: The address space to pin.
+ *
+ * Make sure that the address space of the given &struct mm_struct doesn't
+ * go away. This does not protect against parts of the address space being
+ * modified or freed, however.
+ *
+ * Never use this function to pin this address space for an
+ * unbounded/indefinite amount of time.
+ *
+ * Use mmput() to release the reference acquired by mmget().
+ *
+ * See also <Documentation/vm/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)
+{
+	atomic_inc(&mm->mm_users);
+}
+
+static inline bool mmget_not_zero(struct mm_struct *mm)
+{
+	return atomic_inc_not_zero(&mm->mm_users);
+}
+
+/* mmput gets rid of the mappings and all user-space */
+extern void mmput(struct mm_struct *);
+#ifdef CONFIG_MMU
+/* same as above but performs the slow path from the async context. Can
+ * be called from the atomic context as well
+ */
+void mmput_async(struct mm_struct *);
+#endif
+
+/* Grab a reference to a task's mm, if it is not already going away */
+extern struct mm_struct *get_task_mm(struct task_struct *task);
+/*
+ * Grab a reference to a task's mm, if it is not already going away
+ * and ptrace_may_access with the mode parameter passed to it
+ * succeeds.
+ */
+extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
+/* Remove the current tasks stale references to the old mm_struct on exit() */
+extern void exit_mm_release(struct task_struct *, struct mm_struct *);
+/* Remove the current tasks stale references to the old mm_struct on exec() */
+extern void exec_mm_release(struct task_struct *, struct mm_struct *);
+
+#ifdef CONFIG_MEMCG
+extern void mm_update_next_owner(struct mm_struct *mm);
+#else
+static inline void mm_update_next_owner(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_MEMCG */
+
+#ifdef CONFIG_MMU
+extern void arch_pick_mmap_layout(struct mm_struct *mm,
+				  struct rlimit *rlim_stack);
+extern unsigned long
+arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
+		       unsigned long, unsigned long);
+extern unsigned long
+arch_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) {}
+#endif
+
+static inline bool in_vfork(struct task_struct *tsk)
+{
+	bool ret;
+
+	/*
+	 * need RCU to access ->real_parent if CLONE_VM was used along with
+	 * CLONE_PARENT.
+	 *
+	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
+	 * imply CLONE_VM
+	 *
+	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
+	 * ->real_parent is not necessarily the task doing vfork(), so in
+	 * theory we can't rely on task_lock() if we want to dereference it.
+	 *
+	 * And in this case we can't trust the real_parent->mm == tsk->mm
+	 * check, it can be false negative. But we do not care, if init or
+	 * another oom-unkillable task does this it should blame itself.
+	 */
+	rcu_read_lock();
+	ret = tsk->vfork_done &&
+			rcu_dereference(tsk->real_parent)->mm == tsk->mm;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/*
+ * Applies per-task gfp context to the given allocation flags.
+ * PF_MEMALLOC_NOIO implies GFP_NOIO
+ * PF_MEMALLOC_NOFS implies GFP_NOFS
+ * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
+ */
+static inline gfp_t current_gfp_context(gfp_t flags)
+{
+	if (unlikely(current->flags &
+		     (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+		/*
+		 * NOIO implies both NOIO and NOFS and it is a weaker context
+		 * so always make sure it makes precedence
+		 */
+		if (current->flags & PF_MEMALLOC_NOIO)
+			flags &= ~(__GFP_IO | __GFP_FS);
+		else if (current->flags & PF_MEMALLOC_NOFS)
+			flags &= ~__GFP_FS;
+#ifdef CONFIG_CMA
+		if (current->flags & PF_MEMALLOC_NOCMA)
+			flags &= ~__GFP_MOVABLE;
+#endif
+	}
+	return flags;
+}
+
+#ifdef CONFIG_LOCKDEP
+extern void __fs_reclaim_acquire(void);
+extern void __fs_reclaim_release(void);
+extern void fs_reclaim_acquire(gfp_t gfp_mask);
+extern void fs_reclaim_release(gfp_t gfp_mask);
+#else
+static inline void __fs_reclaim_acquire(void) { }
+static inline void __fs_reclaim_release(void) { }
+static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
+static inline void fs_reclaim_release(gfp_t gfp_mask) { }
+#endif
+
+/**
+ * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOIO allocation scope.
+ * All further allocations will implicitly drop __GFP_IO flag and so
+ * they are safe for the IO critical section from the allocation recursion
+ * point of view. Use memalloc_noio_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
+static inline unsigned int memalloc_noio_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+	current->flags |= PF_MEMALLOC_NOIO;
+	return flags;
+}
+
+/**
+ * memalloc_noio_restore - Ends the implicit GFP_NOIO scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_noio_save call.
+ */
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
+/**
+ * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope.
+ *
+ * This functions marks the beginning of the GFP_NOFS allocation scope.
+ * All further allocations will implicitly drop __GFP_FS flag and so
+ * they are safe for the FS critical section from the allocation recursion
+ * point of view. Use memalloc_nofs_restore to end the scope with flags
+ * returned by this function.
+ *
+ * This function is safe to be used from any context.
+ */
+static inline unsigned int memalloc_nofs_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
+	current->flags |= PF_MEMALLOC_NOFS;
+	return flags;
+}
+
+/**
+ * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope.
+ * @flags: Flags to restore.
+ *
+ * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
+ * Always make sure that that the given flags is the return value from the
+ * pairing memalloc_nofs_save call.
+ */
+static inline void memalloc_nofs_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
+}
+
+static inline unsigned int memalloc_noreclaim_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC;
+	current->flags |= PF_MEMALLOC;
+	return flags;
+}
+
+static inline void memalloc_noreclaim_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
+}
+
+#ifdef CONFIG_CMA
+static inline unsigned int memalloc_nocma_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
+
+	current->flags |= PF_MEMALLOC_NOCMA;
+	return flags;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
+}
+#else
+static inline unsigned int memalloc_nocma_save(void)
+{
+	return 0;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+}
+#endif
+
+#ifdef CONFIG_MEMCG
+/**
+ * memalloc_use_memcg - Starts the remote memcg charging scope.
+ * @memcg: memcg to charge.
+ *
+ * This function marks the beginning of the remote memcg charging scope. All the
+ * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
+ * given memcg.
+ *
+ * NOTE: This function is not nesting safe.
+ */
+static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+{
+	WARN_ON_ONCE(current->active_memcg);
+	current->active_memcg = memcg;
+}
+
+/**
+ * memalloc_unuse_memcg - Ends the remote memcg charging scope.
+ *
+ * This function marks the end of the remote memcg charging scope started by
+ * memalloc_use_memcg().
+ */
+static inline void memalloc_unuse_memcg(void)
+{
+	current->active_memcg = NULL;
+}
+#else
+static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+{
+}
+
+static inline void memalloc_unuse_memcg(void)
+{
+}
+#endif
+
+#ifdef CONFIG_MEMBARRIER
+enum {
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY		= (1U << 0),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED			= (1U << 1),
+	MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY			= (1U << 2),
+	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+};
+
+enum {
+	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+};
+
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
+#include <asm/membarrier.h>
+#endif
+
+static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
+{
+	if (current->mm != mm)
+		return;
+	if (likely(!(atomic_read(&mm->membarrier_state) &
+		     MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
+		return;
+	sync_core_before_usermode();
+}
+
+static inline void membarrier_execve(struct task_struct *t)
+{
+	atomic_set(&t->mm->membarrier_state, 0);
+}
+#else
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+					     struct mm_struct *next,
+					     struct task_struct *tsk)
+{
+}
+#endif
+static inline void membarrier_execve(struct task_struct *t)
+{
+}
+static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
+{
+}
+#endif
+
+#endif /* _LINUX_SCHED_MM_H */

include/linux/sched/nohz.h

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_NOHZ_H
+#define _LINUX_SCHED_NOHZ_H
+
+/*
+ * This is the interface between the scheduler and nohz/dynticks:
+ */
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void cpu_load_update_nohz_start(void);
+extern void cpu_load_update_nohz_stop(void);
+#else
+static inline void cpu_load_update_nohz_start(void) { }
+static inline void cpu_load_update_nohz_stop(void) { }
+#endif
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void nohz_balance_enter_idle(int cpu);
+extern int get_nohz_timer_target(void);
+#else
+static inline void nohz_balance_enter_idle(int cpu) { }
+#endif
+
+#ifdef CONFIG_NO_HZ_COMMON
+void calc_load_nohz_start(void);
+void calc_load_nohz_stop(void);
+#else
+static inline void calc_load_nohz_start(void) { }
+static inline void calc_load_nohz_stop(void) { }
+#endif /* CONFIG_NO_HZ_COMMON */
+
+#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
+extern void wake_up_nohz_cpu(int cpu);
+#else
+static inline void wake_up_nohz_cpu(int cpu) { }
+#endif
+
+#endif /* _LINUX_SCHED_NOHZ_H */

include/linux/sched/numa_balancing.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_NUMA_BALANCING_H
+#define _LINUX_SCHED_NUMA_BALANCING_H
+
+/*
+ * This is the interface between the scheduler and the MM that
+ * implements memory access pattern based NUMA-balancing:
+ */
+
+#include <linux/sched.h>
+
+#define TNF_MIGRATED	0x01
+#define TNF_NO_GROUP	0x02
+#define TNF_SHARED	0x04
+#define TNF_FAULT_LOCAL	0x08
+#define TNF_MIGRATE_FAIL 0x10
+
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int last_node, int node, int pages, int flags);
+extern pid_t task_numa_group_id(struct task_struct *p);
+extern void set_numabalancing_state(bool enabled);
+extern void task_numa_free(struct task_struct *p, bool final);
+extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
+					int src_nid, int dst_cpu);
+#else
+static inline void task_numa_fault(int last_node, int node, int pages,
+				   int flags)
+{
+}
+static inline pid_t task_numa_group_id(struct task_struct *p)
+{
+	return 0;
+}
+static inline void set_numabalancing_state(bool enabled)
+{
+}
+static inline void task_numa_free(struct task_struct *p, bool final)
+{
+}
+static inline bool should_numa_migrate_memory(struct task_struct *p,
+				struct page *page, int src_nid, int dst_cpu)
+{
+	return true;
+}
+#endif
+
+#endif /* _LINUX_SCHED_NUMA_BALANCING_H */

include/linux/sched/prio.h

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_PRIO_H
+#define _LINUX_SCHED_PRIO_H
+
+#define MAX_NICE	19
+#define MIN_NICE	-20
+#define NICE_WIDTH	(MAX_NICE - MIN_NICE + 1)
+
+/*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
+ * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
+ * values are inverted: lower p->prio value means higher priority.
+ *
+ * The MAX_USER_RT_PRIO value allows the actual maximum
+ * RT priority to be separate from the value exported to
+ * user-space.  This allows kernel threads to set their
+ * priority to a value higher than any user task. Note:
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
+#define MAX_USER_RT_PRIO	100
+#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+
+#define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
+#define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	((nice) + DEFAULT_PRIO)
+#define PRIO_TO_NICE(prio)	((prio) - DEFAULT_PRIO)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+
+/*
+ * Convert nice value [19,-20] to rlimit style value [1,40].
+ */
+static inline long nice_to_rlimit(long nice)
+{
+	return (MAX_NICE - nice + 1);
+}
+
+/*
+ * Convert rlimit style value [1,40] to nice value [-20, 19].
+ */
+static inline long rlimit_to_nice(long prio)
+{
+	return (MAX_NICE - prio + 1);
+}
+
+#endif /* _LINUX_SCHED_PRIO_H */

include/linux/sched/rt.h

@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_RT_H
+#define _LINUX_SCHED_RT_H
+
+#include <linux/sched.h>
+
+struct task_struct;
+
+static inline int rt_prio(int prio)
+{
+	if (unlikely(prio < MAX_RT_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int rt_task(struct task_struct *p)
+{
+	return rt_prio(p->prio);
+}
+
+static inline bool task_is_realtime(struct task_struct *tsk)
+{
+	int policy = tsk->policy;
+
+	if (policy == SCHED_FIFO || policy == SCHED_RR)
+		return true;
+	if (policy == SCHED_DEADLINE)
+		return true;
+	return false;
+}
+
+#ifdef CONFIG_RT_MUTEXES
+/*
+ * Must hold either p->pi_lock or task_rq(p)->lock.
+ */
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
+{
+	return p->pi_top_task;
+}
+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);
+
+
+/*
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
+ * Timeslices get refilled after they expire.
+ */
+#define RR_TIMESLICE		(100 * HZ / 1000)
+
+#endif /* _LINUX_SCHED_RT_H */

include/linux/sched/signal.h

@@ -0,0 +1,707 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_SIGNAL_H
+#define _LINUX_SCHED_SIGNAL_H
+
+#include <linux/rculist.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/sched/jobctl.h>
+#include <linux/sched/task.h>
+#include <linux/cred.h>
+#include <linux/android_kabi.h>
+
+/*
+ * Types defining task->signal and task->sighand and APIs using them:
+ */
+
+struct sighand_struct {
+	atomic_t		count;
+	struct k_sigaction	action[_NSIG];
+	spinlock_t		siglock;
+	wait_queue_head_t	signalfd_wqh;
+};
+
+/*
+ * Per-process accounting stats:
+ */
+struct pacct_struct {
+	int			ac_flag;
+	long			ac_exitcode;
+	unsigned long		ac_mem;
+	u64			ac_utime, ac_stime;
+	unsigned long		ac_minflt, ac_majflt;
+};
+
+struct cpu_itimer {
+	u64 expires;
+	u64 incr;
+};
+
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+	atomic64_t utime;
+	atomic64_t stime;
+	atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+	(struct task_cputime_atomic) {				\
+		.utime = ATOMIC64_INIT(0),			\
+		.stime = ATOMIC64_INIT(0),			\
+		.sum_exec_runtime = ATOMIC64_INIT(0),		\
+	}
+/**
+ * struct thread_group_cputimer - thread group interval timer counts
+ * @cputime_atomic:	atomic thread group interval timers.
+ * @running:		true when there are timers running and
+ *			@cputime_atomic receives updates.
+ * @checking_timer:	true when a thread in the group is in the
+ *			process of checking for thread group timers.
+ *
+ * This structure contains the version of task_cputime, above, that is
+ * used for thread group CPU timer calculations.
+ */
+struct thread_group_cputimer {
+	struct task_cputime_atomic cputime_atomic;
+	bool running;
+	bool checking_timer;
+};
+
+struct multiprocess_signals {
+	sigset_t signal;
+	struct hlist_node node;
+};
+
+/*
+ * NOTE! "signal_struct" does not have its own
+ * locking, because a shared signal_struct always
+ * implies a shared sighand_struct, so locking
+ * sighand_struct is always a proper superset of
+ * the locking of signal_struct.
+ */
+struct signal_struct {
+	atomic_t		sigcnt;
+	atomic_t		live;
+	int			nr_threads;
+	struct list_head	thread_head;
+
+	wait_queue_head_t	wait_chldexit;	/* for wait4() */
+
+	/* current thread group signal load-balancing target: */
+	struct task_struct	*curr_target;
+
+	/* shared signal handling: */
+	struct sigpending	shared_pending;
+
+	/* For collecting multiprocess signals during fork */
+	struct hlist_head	multiprocess;
+
+	/* 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.
+	 */
+	int			notify_count;
+	struct task_struct	*group_exit_task;
+
+	/* thread group stop support, overloads group_exit_code too */
+	int			group_stop_count;
+	unsigned int		flags; /* see SIGNAL_* flags below */
+
+	/*
+	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
+	 * manager, to re-parent orphan (double-forking) child processes
+	 * to this process instead of 'init'. The service manager is
+	 * able to receive SIGCHLD signals and is able to investigate
+	 * the process until it calls wait(). All children of this
+	 * process will inherit a flag if they should look for a
+	 * child_subreaper process at exit.
+	 */
+	unsigned int		is_child_subreaper:1;
+	unsigned int		has_child_subreaper:1;
+
+#ifdef CONFIG_POSIX_TIMERS
+
+	/* POSIX.1b Interval Timers */
+	int			posix_timer_id;
+	struct list_head	posix_timers;
+
+	/* ITIMER_REAL timer for the process */
+	struct hrtimer real_timer;
+	ktime_t it_real_incr;
+
+	/*
+	 * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
+	 * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
+	 * values are defined to 0 and 1 respectively
+	 */
+	struct cpu_itimer it[2];
+
+	/*
+	 * Thread group totals for process CPU timers.
+	 * See thread_group_cputimer(), et al, for details.
+	 */
+	struct thread_group_cputimer cputimer;
+
+	/* Earliest-expiration cache. */
+	struct task_cputime cputime_expires;
+
+	struct list_head cpu_timers[3];
+
+#endif
+
+	/* PID/PID hash table linkage. */
+	struct pid *pids[PIDTYPE_MAX];
+
+#ifdef CONFIG_NO_HZ_FULL
+	atomic_t tick_dep_mask;
+#endif
+
+	struct pid *tty_old_pgrp;
+
+	/* boolean value for session group leader */
+	int leader;
+
+	struct tty_struct *tty; /* NULL if no tty */
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
+	/*
+	 * Cumulative resource counters for dead threads in the group,
+	 * and for reaped dead child processes forked by this group.
+	 * Live threads maintain their own counters and add to these
+	 * in __exit_signal, except for the group leader.
+	 */
+	seqlock_t stats_lock;
+	u64 utime, stime, cutime, cstime;
+	u64 gtime;
+	u64 cgtime;
+	struct prev_cputime prev_cputime;
+	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
+	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+	unsigned long inblock, oublock, cinblock, coublock;
+	unsigned long maxrss, cmaxrss;
+	struct task_io_accounting ioac;
+
+	/*
+	 * Cumulative ns of schedule CPU time fo dead threads in the
+	 * group, not including a zombie group leader, (This only differs
+	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
+	 * other than jiffies.)
+	 */
+	unsigned long long sum_sched_runtime;
+
+	/*
+	 * We don't bother to synchronize most readers of this at all,
+	 * because there is no reader checking a limit that actually needs
+	 * to get both rlim_cur and rlim_max atomically, and either one
+	 * alone is a single word that can safely be read normally.
+	 * getrlimit/setrlimit use task_lock(current->group_leader) to
+	 * protect this instead of the siglock, because they really
+	 * have no need to disable irqs.
+	 */
+	struct rlimit rlim[RLIM_NLIMITS];
+
+#ifdef CONFIG_BSD_PROCESS_ACCT
+	struct pacct_struct pacct;	/* per-process accounting information */
+#endif
+#ifdef CONFIG_TASKSTATS
+	struct taskstats *stats;
+#endif
+#ifdef CONFIG_AUDIT
+	unsigned audit_tty;
+	struct tty_audit_buf *tty_audit_buf;
+#endif
+
+	/*
+	 * Thread is the potential origin of an oom condition; kill first on
+	 * oom
+	 */
+	bool oom_flag_origin;
+	short oom_score_adj;		/* OOM kill score adjustment */
+	short oom_score_adj_min;	/* OOM kill score adjustment min value.
+					 * Only settable by CAP_SYS_RESOURCE. */
+	struct mm_struct *oom_mm;	/* recorded mm when the thread group got
+					 * killed by the oom killer */
+
+	struct mutex cred_guard_mutex;	/* guard against foreign influences on
+					 * credential calculations
+					 * (notably. ptrace) */
+	ANDROID_KABI_RESERVE(1);
+	ANDROID_KABI_RESERVE(2);
+	ANDROID_KABI_RESERVE(3);
+	ANDROID_KABI_RESERVE(4);
+} __randomize_layout;
+
+/*
+ * Bits in flags field of 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.
+ */
+#define SIGNAL_CLD_STOPPED	0x00000010
+#define SIGNAL_CLD_CONTINUED	0x00000020
+#define SIGNAL_CLD_MASK		(SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
+
+#define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */
+
+#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
+			  SIGNAL_STOP_CONTINUED)
+
+static inline void signal_set_stop_flags(struct signal_struct *sig,
+					 unsigned int flags)
+{
+	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+	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 *tsk, sigset_t *mask, siginfo_t *info);
+
+static inline int kernel_dequeue_signal(siginfo_t *info)
+{
+	struct task_struct *tsk = current;
+	siginfo_t __info;
+	int ret;
+
+	spin_lock_irq(&tsk->sighand->siglock);
+	ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	return ret;
+}
+
+static inline void kernel_signal_stop(void)
+{
+	spin_lock_irq(&current->sighand->siglock);
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+		set_special_state(TASK_STOPPED);
+	spin_unlock_irq(&current->sighand->siglock);
+
+	schedule();
+}
+#ifdef __ARCH_SI_TRAPNO
+# define ___ARCH_SI_TRAPNO(_a1) , _a1
+#else
+# define ___ARCH_SI_TRAPNO(_a1)
+#endif
+#ifdef __ia64__
+# define ___ARCH_SI_IA64(_a1, _a2, _a3) , _a1, _a2, _a3
+#else
+# define ___ARCH_SI_IA64(_a1, _a2, _a3)
+#endif
+
+int force_sig_fault(int sig, int code, void __user *addr
+	___ARCH_SI_TRAPNO(int trapno)
+	___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
+	, struct task_struct *t);
+int send_sig_fault(int sig, int code, void __user *addr
+	___ARCH_SI_TRAPNO(int trapno)
+	___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
+	, struct task_struct *t);
+
+int force_sig_mceerr(int code, void __user *, short, struct task_struct *);
+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_ptrace_errno_trap(int errno, void __user *addr);
+
+extern int send_sig_info(int, struct siginfo *, struct task_struct *);
+extern void force_sigsegv(int sig, struct task_struct *p);
+extern int force_sig_info(int, struct siginfo *, struct task_struct *);
+extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
+extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
+extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
+				const struct cred *);
+extern int kill_pgrp(struct pid *pid, int sig, int priv);
+extern int kill_pid(struct pid *pid, int sig, int priv);
+extern __must_check bool do_notify_parent(struct task_struct *, int);
+extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
+extern void force_sig(int, struct task_struct *);
+extern int send_sig(int, struct task_struct *, int);
+extern int zap_other_threads(struct task_struct *p);
+extern struct sigqueue *sigqueue_alloc(void);
+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 int restart_syscall(void)
+{
+	set_tsk_thread_flag(current, TIF_SIGPENDING);
+	return -ERESTARTNOINTR;
+}
+
+static inline int signal_pending(struct task_struct *p)
+{
+	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
+}
+
+static inline int __fatal_signal_pending(struct task_struct *p)
+{
+	return unlikely(sigismember(&p->pending.signal, SIGKILL));
+}
+
+static inline int fatal_signal_pending(struct task_struct *p)
+{
+	return signal_pending(p) && __fatal_signal_pending(p);
+}
+
+static inline int signal_pending_state(long state, struct task_struct *p)
+{
+	if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
+		return 0;
+	if (!signal_pending(p))
+		return 0;
+
+	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
+}
+
+/*
+ * Reevaluate whether the task has signals pending delivery.
+ * Wake the task if so.
+ * This is required every time the blocked sigset_t changes.
+ * callers must hold sighand->siglock.
+ */
+extern void recalc_sigpending_and_wake(struct task_struct *t);
+extern void recalc_sigpending(void);
+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)
+{
+	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+}
+static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+}
+
+void task_join_group_stop(struct task_struct *task);
+
+#ifdef TIF_RESTORE_SIGMASK
+/*
+ * Legacy restore_sigmask accessors.  These are inefficient on
+ * SMP architectures because they require atomic operations.
+ */
+
+/**
+ * set_restore_sigmask() - make sure saved_sigmask processing gets done
+ *
+ * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
+ * will run before returning to user mode, to process the flag.  For
+ * all callers, TIF_SIGPENDING is already set or it's no harm to set
+ * it.  TIF_RESTORE_SIGMASK need not be in the set of bits that the
+ * arch code will notice on return to user mode, in case those bits
+ * are scarce.  We set TIF_SIGPENDING here to ensure that the arch
+ * signal code always gets run when TIF_RESTORE_SIGMASK is set.
+ */
+static inline void set_restore_sigmask(void)
+{
+	set_thread_flag(TIF_RESTORE_SIGMASK);
+	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+
+static inline void clear_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	clear_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK);
+}
+
+static inline void clear_restore_sigmask(void)
+{
+	clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	return test_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK);
+}
+static inline bool test_restore_sigmask(void)
+{
+	return test_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+
+#else	/* TIF_RESTORE_SIGMASK */
+
+/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
+static inline void set_restore_sigmask(void)
+{
+	current->restore_sigmask = true;
+	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	tsk->restore_sigmask = false;
+}
+static inline void clear_restore_sigmask(void)
+{
+	current->restore_sigmask = false;
+}
+static inline bool test_restore_sigmask(void)
+{
+	return current->restore_sigmask;
+}
+static inline bool test_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	return tsk->restore_sigmask;
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+	if (!current->restore_sigmask)
+		return false;
+	current->restore_sigmask = false;
+	return true;
+}
+#endif
+
+static inline void restore_saved_sigmask(void)
+{
+	if (test_and_clear_restore_sigmask())
+		__set_current_blocked(&current->saved_sigmask);
+}
+
+static inline sigset_t *sigmask_to_save(void)
+{
+	sigset_t *res = &current->blocked;
+	if (unlikely(test_restore_sigmask()))
+		res = &current->saved_sigmask;
+	return res;
+}
+
+static inline int kill_cad_pid(int sig, int priv)
+{
+	return kill_pid(cad_pid, sig, priv);
+}
+
+/* These can be the second arg to send_sig_info/send_group_sig_info.  */
+#define SEND_SIG_NOINFO ((struct siginfo *) 0)
+#define SEND_SIG_PRIV	((struct siginfo *) 1)
+#define SEND_SIG_FORCED	((struct siginfo *) 2)
+
+/*
+ * True if we are on the alternate signal stack.
+ */
+static inline int on_sig_stack(unsigned long sp)
+{
+	/*
+	 * If the signal stack is SS_AUTODISARM then, by construction, we
+	 * can't be on the signal stack unless user code deliberately set
+	 * SS_AUTODISARM when we were already on it.
+	 *
+	 * This improves reliability: if user state gets corrupted such that
+	 * the stack pointer points very close to the end of the signal stack,
+	 * then this check will enable the signal to be handled anyway.
+	 */
+	if (current->sas_ss_flags & SS_AUTODISARM)
+		return 0;
+
+#ifdef CONFIG_STACK_GROWSUP
+	return sp >= current->sas_ss_sp &&
+		sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+	return sp > current->sas_ss_sp &&
+		sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
+}
+
+static inline int sas_ss_flags(unsigned long sp)
+{
+	if (!current->sas_ss_size)
+		return SS_DISABLE;
+
+	return on_sig_stack(sp) ? SS_ONSTACK : 0;
+}
+
+static inline void sas_ss_reset(struct task_struct *p)
+{
+	p->sas_ss_sp = 0;
+	p->sas_ss_size = 0;
+	p->sas_ss_flags = SS_DISABLE;
+}
+
+static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig)
+{
+	if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp))
+#ifdef CONFIG_STACK_GROWSUP
+		return current->sas_ss_sp;
+#else
+		return current->sas_ss_sp + current->sas_ss_size;
+#endif
+	return sp;
+}
+
+extern void __cleanup_sighand(struct sighand_struct *);
+extern void flush_itimer_signals(void);
+
+#define tasklist_empty() \
+	list_empty(&init_task.tasks)
+
+#define next_task(p) \
+	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
+
+#define for_each_process(p) \
+	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
+
+extern bool current_is_single_threaded(void);
+
+/*
+ * Careful: do_each_thread/while_each_thread is a double loop so
+ *          'break' will not work as expected - use goto instead.
+ */
+#define do_each_thread(g, t) \
+	for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
+
+#define while_each_thread(g, t) \
+	while ((t = next_thread(t)) != g)
+
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
+typedef int (*proc_visitor)(struct task_struct *p, void *data);
+void walk_process_tree(struct task_struct *top, proc_visitor, void *);
+
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+{
+	struct pid *pid;
+	if (type == PIDTYPE_PID)
+		pid = task_pid(task);
+	else
+		pid = task->signal->pids[type];
+	return pid;
+}
+
+static inline struct pid *task_tgid(struct task_struct *task)
+{
+	return task->signal->pids[PIDTYPE_TGID];
+}
+
+/*
+ * Without tasklist or RCU lock it is not safe to dereference
+ * the result of task_pgrp/task_session even if task == current,
+ * we can race with another thread doing sys_setsid/sys_setpgid.
+ */
+static inline struct pid *task_pgrp(struct task_struct *task)
+{
+	return task->signal->pids[PIDTYPE_PGID];
+}
+
+static inline struct pid *task_session(struct task_struct *task)
+{
+	return task->signal->pids[PIDTYPE_SID];
+}
+
+static inline int get_nr_threads(struct task_struct *tsk)
+{
+	return tsk->signal->nr_threads;
+}
+
+static inline bool thread_group_leader(struct task_struct *p)
+{
+	return p->exit_signal >= 0;
+}
+
+/* Do to the insanities of de_thread it is possible for a process
+ * to have the pid of the thread group leader without actually being
+ * the thread group leader.  For iteration through the pids in proc
+ * all we care about is that we have a task with the appropriate
+ * pid, we don't actually care if we have the right task.
+ */
+static inline bool has_group_leader_pid(struct task_struct *p)
+{
+	return task_pid(p) == task_tgid(p);
+}
+
+static inline
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
+{
+	return p1->signal == p2->signal;
+}
+
+static inline struct task_struct *next_thread(const struct task_struct *p)
+{
+	return list_entry_rcu(p->thread_group.next,
+			      struct task_struct, thread_group);
+}
+
+static inline int thread_group_empty(struct task_struct *p)
+{
+	return list_empty(&p->thread_group);
+}
+
+#define delay_group_leader(p) \
+		(thread_group_leader(p) && !thread_group_empty(p))
+
+extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
+							unsigned long *flags);
+
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+						       unsigned long *flags)
+{
+	struct sighand_struct *ret;
+
+	ret = __lock_task_sighand(tsk, flags);
+	(void)__cond_lock(&tsk->sighand->siglock, ret);
+	return ret;
+}
+
+static inline void unlock_task_sighand(struct task_struct *tsk,
+						unsigned long *flags)
+{
+	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
+}
+
+static inline unsigned long task_rlimit(const struct task_struct *tsk,
+		unsigned int limit)
+{
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
+}
+
+static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
+		unsigned int limit)
+{
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
+}
+
+static inline unsigned long rlimit(unsigned int limit)
+{
+	return task_rlimit(current, limit);
+}
+
+static inline unsigned long rlimit_max(unsigned int limit)
+{
+	return task_rlimit_max(current, limit);
+}
+
+#endif /* _LINUX_SCHED_SIGNAL_H */

include/linux/sched/smt.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_SMT_H
+#define _LINUX_SCHED_SMT_H
+
+#include <linux/static_key.h>
+
+#ifdef CONFIG_SCHED_SMT
+extern struct static_key_false sched_smt_present;
+
+static __always_inline bool sched_smt_active(void)
+{
+	return static_branch_likely(&sched_smt_present);
+}
+#else
+static inline bool sched_smt_active(void) { return false; }
+#endif
+
+void arch_smt_update(void);
+
+#endif

include/linux/sched/stat.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_STAT_H
+#define _LINUX_SCHED_STAT_H
+
+#include <linux/percpu.h>
+
+/*
+ * Various counters maintained by the scheduler and fork(),
+ * exposed via /proc, sys.c or used by drivers via these APIs.
+ *
+ * ( Note that all these values are aquired without locking,
+ *   so they can only be relied on in narrow circumstances. )
+ */
+
+extern unsigned long total_forks;
+extern int nr_threads;
+DECLARE_PER_CPU(unsigned long, process_counts);
+extern int nr_processes(void);
+extern unsigned long nr_running(void);
+extern bool single_task_running(void);
+extern unsigned long nr_iowait(void);
+extern unsigned long nr_iowait_cpu(int cpu);
+extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
+
+static inline int sched_info_on(void)
+{
+#ifdef CONFIG_SCHEDSTATS
+	return 1;
+#elif defined(CONFIG_TASK_DELAY_ACCT)
+	extern int delayacct_on;
+	return delayacct_on;
+#else
+	return 0;
+#endif
+}
+
+#ifdef CONFIG_SCHEDSTATS
+void force_schedstat_enabled(void);
+#endif
+
+#endif /* _LINUX_SCHED_STAT_H */

include/linux/sched/sysctl.h

@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_SYSCTL_H
+#define _LINUX_SCHED_SYSCTL_H
+
+#include <linux/types.h>
+
+struct ctl_table;
+
+#ifdef CONFIG_DETECT_HUNG_TASK
+extern int	     sysctl_hung_task_check_count;
+extern unsigned int  sysctl_hung_task_panic;
+extern unsigned long sysctl_hung_task_timeout_secs;
+extern unsigned long sysctl_hung_task_check_interval_secs;
+extern int sysctl_hung_task_warnings;
+extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+					 void __user *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_latency;
+extern unsigned int sysctl_sched_min_granularity;
+extern unsigned int sysctl_sched_sync_hint_enable;
+extern unsigned int sysctl_sched_cstate_aware;
+extern unsigned int sysctl_sched_wakeup_granularity;
+extern unsigned int sysctl_sched_child_runs_first;
+
+enum sched_tunable_scaling {
+	SCHED_TUNABLESCALING_NONE,
+	SCHED_TUNABLESCALING_LOG,
+	SCHED_TUNABLESCALING_LINEAR,
+	SCHED_TUNABLESCALING_END,
+};
+extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_size;
+
+#ifdef CONFIG_SCHED_DEBUG
+extern __read_mostly unsigned int sysctl_sched_migration_cost;
+extern __read_mostly unsigned int sysctl_sched_nr_migrate;
+
+int sched_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *length,
+		loff_t *ppos);
+#endif
+
+/*
+ *  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;
+
+#ifdef CONFIG_UCLAMP_TASK
+extern unsigned int sysctl_sched_uclamp_util_min;
+extern unsigned int sysctl_sched_uclamp_util_max;
+#endif
+
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#endif
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern unsigned int sysctl_sched_autogroup_enabled;
+#endif
+
+extern int sysctl_sched_rr_timeslice;
+extern int sched_rr_timeslice;
+
+extern int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
+extern int sched_rt_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
+#ifdef CONFIG_UCLAMP_TASK
+extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+				       void __user *buffer, size_t *lenp,
+				       loff_t *ppos);
+#endif
+
+extern int sysctl_numa_balancing(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
+extern int sysctl_schedstats(struct ctl_table *table, int write,
+				 void __user *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;
+extern int sched_energy_aware_handler(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+#endif
+
+#endif /* _LINUX_SCHED_SYSCTL_H */

include/linux/sched/task.h

@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_TASK_H
+#define _LINUX_SCHED_TASK_H
+
+/*
+ * Interface between the scheduler and various task lifetime (fork()/exit())
+ * functionality:
+ */
+
+#include <linux/sched.h>
+
+struct task_struct;
+struct rusage;
+union thread_union;
+
+/*
+ * This serializes "schedule()" and also protects
+ * the run-queue from deletions/modifications (but
+ * _adding_ to the beginning of the run-queue has
+ * a separate lock).
+ */
+extern rwlock_t tasklist_lock;
+extern spinlock_t mmlist_lock;
+
+extern union thread_union init_thread_union;
+extern struct task_struct init_task;
+
+#ifdef CONFIG_PROVE_RCU
+extern int lockdep_tasklist_lock_is_held(void);
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
+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_dead(struct task_struct *p);
+
+void __noreturn do_task_dead(void);
+
+extern void proc_caches_init(void);
+
+extern void fork_init(void);
+
+extern void release_task(struct task_struct * p);
+
+#ifdef CONFIG_HAVE_COPY_THREAD_TLS
+extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
+			struct task_struct *, unsigned long);
+#else
+extern int copy_thread(unsigned long, unsigned long, unsigned long,
+			struct task_struct *);
+
+/* Architectures that haven't opted into copy_thread_tls get the tls argument
+ * via pt_regs, so ignore the tls argument passed via C. */
+static inline int copy_thread_tls(
+		unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
+{
+	return copy_thread(clone_flags, sp, arg, p);
+}
+#endif
+extern void flush_thread(void);
+
+#ifdef CONFIG_HAVE_EXIT_THREAD
+extern void exit_thread(struct task_struct *tsk);
+#else
+static inline void exit_thread(struct task_struct *tsk)
+{
+}
+#endif
+extern void do_group_exit(int);
+
+#ifdef CONFIG_UCLAMP_TASK
+extern void uclamp_exit_task(struct task_struct *p);
+#else
+static inline void uclamp_exit_task(struct task_struct *p) { }
+#endif /* CONFIG_UCLAMP_TASK */
+
+extern void exit_files(struct task_struct *);
+extern void exit_itimers(struct signal_struct *);
+
+extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
+extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
+struct task_struct *fork_idle(int);
+extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
+
+extern void free_task(struct task_struct *tsk);
+
+/* sched_exec is called by processes performing an exec */
+#ifdef CONFIG_SMP
+extern void sched_exec(void);
+#else
+#define sched_exec()   {}
+#endif
+
+#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+
+extern void __put_task_struct(struct task_struct *t);
+
+static inline void put_task_struct(struct task_struct *t)
+{
+	if (atomic_dec_and_test(&t->usage))
+		__put_task_struct(t);
+}
+
+struct task_struct *task_rcu_dereference(struct task_struct **ptask);
+
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+extern int arch_task_struct_size __read_mostly;
+#else
+# define arch_task_struct_size (sizeof(struct task_struct))
+#endif
+
+#ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST
+/*
+ * If an architecture has not declared a thread_struct whitelist we
+ * must assume something there may need to be copied to userspace.
+ */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+						unsigned long *size)
+{
+	*offset = 0;
+	/* Handle dynamically sized thread_struct. */
+	*size = arch_task_struct_size - offsetof(struct task_struct, thread);
+}
+#endif
+
+#ifdef CONFIG_VMAP_STACK
+static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
+{
+	return t->stack_vm_area;
+}
+#else
+static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
+{
+	return NULL;
+}
+#endif
+
+/*
+ * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
+ * subscriptions and synchronises with wait4().  Also used in procfs.  Also
+ * pins the final release of task.io_context.  Also protects ->cpuset and
+ * ->cgroup.subsys[]. And ->vfork_done.
+ *
+ * Nests both inside and outside of read_lock(&tasklist_lock).
+ * It must not be nested with write_lock_irq(&tasklist_lock),
+ * neither inside nor outside.
+ */
+static inline void task_lock(struct task_struct *p)
+{
+	spin_lock(&p->alloc_lock);
+}
+
+static inline void task_unlock(struct task_struct *p)
+{
+	spin_unlock(&p->alloc_lock);
+}
+
+#endif /* _LINUX_SCHED_TASK_H */

include/linux/sched/task_stack.h

@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_TASK_STACK_H
+#define _LINUX_SCHED_TASK_STACK_H
+
+/*
+ * task->stack (kernel stack) handling interfaces:
+ */
+
+#include <linux/sched.h>
+#include <linux/magic.h>
+
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+
+/*
+ * When accessing the stack of a non-current task that might exit, use
+ * 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)
+{
+	return task->stack;
+}
+
+#define setup_thread_stack(new,old)	do { } while(0)
+
+static inline unsigned long *end_of_stack(const struct task_struct *task)
+{
+	return task->stack;
+}
+
+#elif !defined(__HAVE_THREAD_FUNCTIONS)
+
+#define task_stack_page(task)	((void *)(task)->stack)
+
+static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
+{
+	*task_thread_info(p) = *task_thread_info(org);
+	task_thread_info(p)->task = p;
+}
+
+/*
+ * Return the address of the last usable long on the stack.
+ *
+ * When the stack grows down, this is just above the thread
+ * info struct. Going any lower will corrupt the threadinfo.
+ *
+ * When the stack grows up, this is the highest address.
+ * Beyond that position, we corrupt data on the next page.
+ */
+static inline unsigned long *end_of_stack(struct task_struct *p)
+{
+#ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
+#else
+	return (unsigned long *)(task_thread_info(p) + 1);
+#endif
+}
+
+#endif
+
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+static inline void *try_get_task_stack(struct task_struct *tsk)
+{
+	return atomic_inc_not_zero(&tsk->stack_refcount) ?
+		task_stack_page(tsk) : NULL;
+}
+
+extern void put_task_stack(struct task_struct *tsk);
+#else
+static inline void *try_get_task_stack(struct task_struct *tsk)
+{
+	return task_stack_page(tsk);
+}
+
+static inline void put_task_stack(struct task_struct *tsk) {}
+#endif
+
+#define task_stack_end_corrupted(task) \
+		(*(end_of_stack(task)) != STACK_END_MAGIC)
+
+static inline int object_is_on_stack(const void *obj)
+{
+	void *stack = task_stack_page(current);
+
+	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
+}
+
+extern void thread_stack_cache_init(void);
+
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do { 	/* Skip over canary */
+# ifdef CONFIG_STACK_GROWSUP
+		n--;
+# else
+		n++;
+# endif
+	} while (!*n);
+
+# ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long)end_of_stack(p) - (unsigned long)n;
+# else
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+# endif
+}
+#endif
+extern void set_task_stack_end_magic(struct task_struct *tsk);
+
+#ifndef __HAVE_ARCH_KSTACK_END
+static inline int kstack_end(void *addr)
+{
+	/* Reliable end of stack detection:
+	 * Some APM bios versions misalign the stack
+	 */
+	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
+}
+#endif
+
+#endif /* _LINUX_SCHED_TASK_STACK_H */

include/linux/sched/topology.h

@@ -0,0 +1,247 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_TOPOLOGY_H
+#define _LINUX_SCHED_TOPOLOGY_H
+
+#include <linux/topology.h>
+#include <linux/android_kabi.h>
+
+#include <linux/sched/idle.h>
+
+/*
+ * sched-domains (multiprocessor balancing) declarations:
+ */
+#ifdef CONFIG_SMP
+
+#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
+#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
+#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
+#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
+#define SD_ASYM_CPUCAPACITY	0x0040  /* Domain members have different CPU capacities */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share CPU capacity */
+#define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
+#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share CPU pkg resources */
+#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
+#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
+#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
+#define SD_NUMA			0x4000	/* cross-node balancing */
+
+#ifdef CONFIG_SCHED_SMT
+static inline int cpu_smt_flags(void)
+{
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static inline int cpu_core_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_NUMA
+static inline int cpu_numa_flags(void)
+{
+	return SD_NUMA;
+}
+#endif
+
+extern int arch_asym_cpu_priority(int cpu);
+
+struct sched_domain_attr {
+	int relax_domain_level;
+};
+
+#define SD_ATTR_INIT	(struct sched_domain_attr) {	\
+	.relax_domain_level = -1,			\
+}
+
+extern int sched_domain_level_max;
+
+struct sched_group;
+
+struct sched_domain_shared {
+	atomic_t	ref;
+	atomic_t	nr_busy_cpus;
+	int		has_idle_cores;
+
+	bool            overutilized;
+};
+
+struct sched_domain {
+	/* These fields must be setup */
+	struct sched_domain *parent;	/* top domain must be null terminated */
+	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_group *groups;	/* the balancing groups of the domain */
+	unsigned long min_interval;	/* Minimum balance interval ms */
+	unsigned long max_interval;	/* Maximum balance interval ms */
+	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 busy_idx;
+	unsigned int idle_idx;
+	unsigned int newidle_idx;
+	unsigned int wake_idx;
+	unsigned int forkexec_idx;
+	unsigned int smt_gain;
+
+	int nohz_idle;			/* NOHZ IDLE status */
+	int flags;			/* See SD_* */
+	int level;
+
+	/* Runtime fields. */
+	unsigned long last_balance;	/* init to jiffies. units in jiffies */
+	unsigned int balance_interval;	/* initialise to 1. units in ms. */
+	unsigned int nr_balance_failed; /* initialise to 0 */
+
+	/* idle_balance() stats */
+	u64 max_newidle_lb_cost;
+	unsigned long next_decay_max_lb_cost;
+
+	u64 avg_scan_cost;		/* select_idle_sibling */
+
+#ifdef CONFIG_SCHEDSTATS
+	/* load_balance() stats */
+	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
+
+	/* Active load balancing */
+	unsigned int alb_count;
+	unsigned int alb_failed;
+	unsigned int alb_pushed;
+
+	/* SD_BALANCE_EXEC stats */
+	unsigned int sbe_count;
+	unsigned int sbe_balanced;
+	unsigned int sbe_pushed;
+
+	/* SD_BALANCE_FORK stats */
+	unsigned int sbf_count;
+	unsigned int sbf_balanced;
+	unsigned int sbf_pushed;
+
+	/* try_to_wake_up() stats */
+	unsigned int ttwu_wake_remote;
+	unsigned int ttwu_move_affine;
+	unsigned int ttwu_move_balance;
+#endif
+#ifdef CONFIG_SCHED_DEBUG
+	char *name;
+#endif
+	union {
+		void *private;		/* used during construction */
+		struct rcu_head rcu;	/* used during destruction */
+	};
+	struct sched_domain_shared *shared;
+
+	unsigned int span_weight;
+
+	ANDROID_KABI_RESERVE(1);
+	ANDROID_KABI_RESERVE(2);
+
+	/*
+	 * Span of all CPUs in this domain.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 */
+	unsigned long span[0];
+};
+
+static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
+{
+	return to_cpumask(sd->span);
+}
+
+extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+				    struct sched_domain_attr *dattr_new);
+
+/* Allocate an array of sched domains, for partition_sched_domains(). */
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+
+bool cpus_share_cache(int this_cpu, int that_cpu);
+
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+typedef int (*sched_domain_flags_f)(void);
+
+#define SDTL_OVERLAP	0x01
+
+struct sd_data {
+	struct sched_domain *__percpu *sd;
+	struct sched_domain_shared *__percpu *sds;
+	struct sched_group *__percpu *sg;
+	struct sched_group_capacity *__percpu *sgc;
+};
+
+struct sched_domain_topology_level {
+	sched_domain_mask_f mask;
+	sched_domain_flags_f sd_flags;
+	int		    flags;
+	int		    numa_level;
+	struct sd_data      data;
+#ifdef CONFIG_SCHED_DEBUG
+	char                *name;
+#endif
+};
+
+extern void set_sched_topology(struct sched_domain_topology_level *tl);
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(type)		.name = #type
+#else
+# define SD_INIT_NAME(type)
+#endif
+
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+	if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
+		return sd->smt_gain / sd->span_weight;
+
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
+#else /* CONFIG_SMP */
+
+struct sched_domain_attr;
+
+static inline void
+partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+			struct sched_domain_attr *dattr_new)
+{
+}
+
+static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
+{
+	return SCHED_CAPACITY_SCALE;
+}
+#endif
+
+#endif	/* !CONFIG_SMP */
+
+static inline int task_node(const struct task_struct *p)
+{
+	return cpu_to_node(task_cpu(p));
+}
+
+#endif /* _LINUX_SCHED_TOPOLOGY_H */

include/linux/sched/user.h

@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_USER_H
+#define _LINUX_SCHED_USER_H
+
+#include <linux/uidgid.h>
+#include <linux/atomic.h>
+#include <linux/refcount.h>
+#include <linux/ratelimit.h>
+#include <linux/android_kabi.h>
+
+struct key;
+
+/*
+ * Some day this will be a full-fledged user tracking system..
+ */
+struct user_struct {
+	refcount_t __count;	/* reference count */
+	atomic_t processes;	/* How many processes does this user have? */
+	atomic_t sigpending;	/* How many pending signals does this user have? */
+#ifdef CONFIG_FANOTIFY
+	atomic_t fanotify_listeners;
+#endif
+#ifdef CONFIG_EPOLL
+	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
+#endif
+#ifdef CONFIG_POSIX_MQUEUE
+	/* protected by mq_lock	*/
+	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
+#endif
+	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
+	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
+
+#ifdef CONFIG_KEYS
+	struct key *uid_keyring;	/* UID specific keyring */
+	struct key *session_keyring;	/* UID's default session keyring */
+#endif
+
+	/* Hash table maintenance information */
+	struct hlist_node uidhash_node;
+	kuid_t uid;
+
+#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
+    defined(CONFIG_NET)
+	atomic_long_t locked_vm;
+#endif
+
+	/* Miscellaneous per-user rate limit */
+	struct ratelimit_state ratelimit;
+
+	ANDROID_KABI_RESERVE(1);
+	ANDROID_KABI_RESERVE(2);
+};
+
+extern int uids_sysfs_init(void);
+
+extern struct user_struct *find_user(kuid_t);
+
+extern struct user_struct root_user;
+#define INIT_USER (&root_user)
+
+
+/* per-UID process charging. */
+extern struct user_struct * alloc_uid(kuid_t);
+static inline struct user_struct *get_uid(struct user_struct *u)
+{
+	refcount_inc(&u->__count);
+	return u;
+}
+extern void free_uid(struct user_struct *);
+
+#endif /* _LINUX_SCHED_USER_H */

include/linux/sched/wake_q.h

@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_WAKE_Q_H
+#define _LINUX_SCHED_WAKE_Q_H
+
+/*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The DEFINE_WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function. Otherwise, the list can be
+ * re-initialized for later re-use by wake_q_init().
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+
+#include <linux/sched.h>
+
+struct wake_q_head {
+	struct wake_q_node *first;
+	struct wake_q_node **lastp;
+	int count;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define DEFINE_WAKE_Q(name)				\
+	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+static inline void wake_q_init(struct wake_q_head *head)
+{
+	head->first = WAKE_Q_TAIL;
+	head->lastp = &head->first;
+	head->count = 0;
+}
+
+extern void wake_q_add(struct wake_q_head *head,
+		       struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
+#endif /* _LINUX_SCHED_WAKE_Q_H */

include/linux/sched/xacct.h

@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_XACCT_H
+#define _LINUX_SCHED_XACCT_H
+
+/*
+ * Extended task accounting methods:
+ */
+
+#include <linux/sched.h>
+
+#ifdef CONFIG_TASK_XACCT
+static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
+{
+	tsk->ioac.rchar += amt;
+}
+
+static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
+{
+	tsk->ioac.wchar += amt;
+}
+
+static inline void inc_syscr(struct task_struct *tsk)
+{
+	tsk->ioac.syscr++;
+}
+
+static inline void inc_syscw(struct task_struct *tsk)
+{
+	tsk->ioac.syscw++;
+}
+
+static inline void inc_syscfs(struct task_struct *tsk)
+{
+	tsk->ioac.syscfs++;
+}
+#else
+static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
+{
+}
+
+static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
+{
+}
+
+static inline void inc_syscr(struct task_struct *tsk)
+{
+}
+
+static inline void inc_syscw(struct task_struct *tsk)
+{
+}
+
+static inline void inc_syscfs(struct task_struct *tsk)
+{
+}
+#endif
+
+#endif /* _LINUX_SCHED_XACCT_H */