14 files changed, 95 insertions, 135 deletions

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index e62ff805cfc9..6eb65ceed213 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -8,12 +8,6 @@
 #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
@@ -31,80 +25,4 @@ 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 mm is available for
-					   khugepaged */
-/*
- * 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_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
-#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
- * a counter on its own. We're aggresive on this bit for now: even if the
- * 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		27	/* FOLL_PIN has run, never cleared */
-
-#define MMF_HAS_MDWE		28
-#define MMF_HAS_MDWE_MASK	(1 << MMF_HAS_MDWE)
-
-
-#define MMF_HAS_MDWE_NO_INHERIT	29
-
-#define MMF_VM_MERGE_ANY	30
-#define MMF_VM_MERGE_ANY_MASK	(1 << MMF_VM_MERGE_ANY)
-
-#define MMF_TOPDOWN		31	/* mm searches top down by default */
-#define MMF_TOPDOWN_MASK	(1 << MMF_TOPDOWN)
-
-#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
-				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
-				 MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK)
-
-static inline unsigned long mmf_init_flags(unsigned long flags)
-{
-	if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT))
-		flags &= ~((1UL << MMF_HAS_MDWE) |
-			   (1UL << MMF_HAS_MDWE_NO_INHERIT));
-	return flags & MMF_INIT_MASK;
-}
-
 #endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 3a912ab42bb5..f9aabbc9d22e 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -34,7 +34,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 struct root_domain;
 extern void dl_add_task_root_domain(struct task_struct *p);
 extern void dl_clear_root_domain(struct root_domain *rd);
+extern void dl_clear_root_domain_cpu(int cpu);
 
 #endif /* CONFIG_SMP */
 
+extern u64 dl_cookie;
+extern bool dl_bw_visited(int cpu, u64 cookie);
+
 #endif /* _LINUX_SCHED_DEADLINE_H */
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index b5035afa2396..35ed4577a6cc 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -35,12 +35,10 @@ 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		__section(".sched.text")
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 1ddbde64a31b..f7545430a548 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -146,6 +146,7 @@ struct sched_ext_entity {
 	u32			weight;
 	s32			sticky_cpu;
 	s32			holding_cpu;
+	s32			selected_cpu;
 	u32			kf_mask;	/* see scx_kf_mask above */
 	struct task_struct	*kf_tasks[2];	/* see SCX_CALL_OP_TASK() */
 	atomic_long_t		ops_state;
@@ -199,17 +200,18 @@ struct sched_ext_entity {
 #ifdef CONFIG_EXT_GROUP_SCHED
 	struct cgroup		*cgrp_moving_from;
 #endif
-	/* must be the last field, see init_scx_entity() */
 	struct list_head	tasks_node;
 };
 
 void sched_ext_free(struct task_struct *p);
 void print_scx_info(const char *log_lvl, struct task_struct *p);
+void scx_softlockup(u32 dur_s);
 
 #else	/* !CONFIG_SCHED_CLASS_EXT */
 
 static inline void sched_ext_free(struct task_struct *p) {}
 static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
+static inline void scx_softlockup(u32 dur_s) {}
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */
 #endif	/* _LINUX_SCHED_EXT_H */
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index 412cdaba33eb..17e04859b9a4 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -18,10 +18,6 @@ extern int sched_cpu_dying(unsigned int cpu);
 # 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 */
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index e670ac282333..439f6029d3b9 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -79,6 +79,21 @@ static __always_inline bool __must_check current_clr_polling_and_test(void)
 	return unlikely(tif_need_resched());
 }
 
+static __always_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__after_atomic(); /* paired with resched_curr() */
+
+	preempt_fold_need_resched();
+}
+
 #else
 static inline void __current_set_polling(void) { }
 static inline void __current_clr_polling(void) { }
@@ -91,21 +106,15 @@ static inline bool __must_check current_clr_polling_and_test(void)
 {
 	return unlikely(tif_need_resched());
 }
-#endif
 
 static __always_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
 
 #endif /* _LINUX_SCHED_IDLE_H */
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 2b461129d1fa..d8501f4709b5 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -7,16 +7,21 @@
 #include <linux/tick.h>
 
 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
+	HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_MAX,
+
+	/*
+	 * The following housekeeping types are only set by the nohz_full
+	 * boot commandline option. So they can share the same value.
+	 */
+	HK_TYPE_TICK    = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_TIMER   = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_RCU     = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_MISC    = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_WQ      = HK_TYPE_KERNEL_NOISE,
+	HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 928a626725e6..b13474825130 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -531,6 +531,13 @@ enum {
 
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
+	/*
+	 * The atomic_read() below prevents CSE. The following should
+	 * help the compiler generate more efficient code on architectures
+	 * where sync_core_before_usermode() is a no-op.
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE))
+		return;
 	if (current->mm != mm)
 		return;
 	if (likely(!(atomic_read(&mm->membarrier_state) &
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index c8ed09ac29ac..1ef1edbaaf79 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -136,8 +136,10 @@ struct signal_struct {
 #ifdef CONFIG_POSIX_TIMERS
 
 	/* POSIX.1b Interval Timers */
-	unsigned int		next_posix_timer_id;
+	unsigned int		timer_create_restore_ids:1;
+	atomic_t		next_posix_timer_id;
 	struct hlist_head	posix_timers;
+	struct hlist_head	ignored_posix_timers;
 
 	/* ITIMER_REAL timer for the process */
 	struct hrtimer real_timer;
@@ -338,9 +340,6 @@ extern void force_fatal_sig(int);
 extern void force_exit_sig(int);
 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 void clear_notify_signal(void)
diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h
index fb1e295e7e63..166b19af956f 100644
--- a/include/linux/sched/smt.h
+++ b/include/linux/sched/smt.h
@@ -12,7 +12,7 @@ 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; }
+static __always_inline bool sched_smt_active(void) { return false; }
 #endif
 
 void arch_smt_update(void);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 0f2aeb37bbb0..ca1db4b92c32 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -43,6 +43,7 @@ struct kernel_clone_args {
 	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
+	unsigned int kill_seq;
 };
 
 /*
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index bf10bdb487dd..85c5a6392e02 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -9,6 +9,7 @@
 #include <linux/sched.h>
 #include <linux/magic.h>
 #include <linux/refcount.h>
+#include <linux/kasan.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 
@@ -33,7 +34,7 @@ static __always_inline unsigned long *end_of_stack(const struct task_struct *tas
 #endif
 }
 
-#elif !defined(__HAVE_THREAD_FUNCTIONS)
+#else
 
 #define task_stack_page(task)	((void *)(task)->stack)
 
@@ -89,6 +90,7 @@ static inline int object_is_on_stack(const void *obj)
 {
 	void *stack = task_stack_page(current);
 
+	obj = kasan_reset_tag(obj);
 	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
 }
 
@@ -104,7 +106,6 @@ static inline unsigned long stack_not_used(struct task_struct *p)
 #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:
@@ -112,6 +113,5 @@ static inline int kstack_end(void *addr)
 	 */
 	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
 }
-#endif
 
 #endif /* _LINUX_SCHED_TASK_STACK_H */
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 4237daa5ac7a..198bb5cc1774 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -25,16 +25,12 @@ enum {
 };
 #undef SD_FLAG
 
-#ifdef CONFIG_SCHED_DEBUG
-
 struct sd_flag_debug {
 	unsigned int meta_flags;
 	char *name;
 };
 extern const struct sd_flag_debug sd_flag_debug[];
 
-#endif
-
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
 {
@@ -114,7 +110,10 @@ struct sched_domain {
 	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_imbalance_load[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_misfit[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];
@@ -140,9 +139,7 @@ struct sched_domain {
 	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 */
@@ -165,10 +162,6 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
 	return to_cpumask(sd->span);
 }
 
-extern void partition_sched_domains_locked(int ndoms_new,
-					   cpumask_var_t doms_new[],
-					   struct sched_domain_attr *dattr_new);
-
 extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 				    struct sched_domain_attr *dattr_new);
 
@@ -198,30 +191,20 @@ struct sched_domain_topology_level {
 	int		    flags;
 	int		    numa_level;
 	struct sd_data      data;
-#ifdef CONFIG_SCHED_DEBUG
 	char                *name;
-#endif
 };
 
 extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
+extern void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio);
+
 
-#ifdef CONFIG_SCHED_DEBUG
 # define SD_INIT_NAME(type)		.name = #type
-#else
-# define SD_INIT_NAME(type)
-#endif
 
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
 
 static inline void
-partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
-			       struct sched_domain_attr *dattr_new)
-{
-}
-
-static inline void
 partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)
 {
@@ -242,6 +225,10 @@ static inline bool cpus_share_resources(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 06cd8fb2f409..0f28b4623ad4 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -63,4 +63,38 @@ extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
 extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
 
+/* Spin unlock helpers to unlock and call wake_up_q with preempt disabled */
+static inline
+void raw_spin_unlock_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q)
+{
+	guard(preempt)();
+	raw_spin_unlock(lock);
+	if (wake_q) {
+		wake_up_q(wake_q);
+		wake_q_init(wake_q);
+	}
+}
+
+static inline
+void raw_spin_unlock_irq_wake(raw_spinlock_t *lock, struct wake_q_head *wake_q)
+{
+	guard(preempt)();
+	raw_spin_unlock_irq(lock);
+	if (wake_q) {
+		wake_up_q(wake_q);
+		wake_q_init(wake_q);
+	}
+}
+
+static inline
+void raw_spin_unlock_irqrestore_wake(raw_spinlock_t *lock, unsigned long flags,
+				     struct wake_q_head *wake_q)
+{
+	guard(preempt)();
+	raw_spin_unlock_irqrestore(lock, flags);
+	if (wake_q) {
+		wake_up_q(wake_q);
+		wake_q_init(wake_q);
+	}
+}
 #endif /* _LINUX_SCHED_WAKE_Q_H */