9 files changed, 46 insertions, 59 deletions

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 4d9e3a656875..4d0a5be28b70 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm)
 #endif
 					/* leave room for more dump flags */
 #define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
-#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
+#define MMF_VM_HUGEPAGE		17	/* set when mm is available for
+					   khugepaged */
 /*
  * This one-shot flag is dropped due to necessity of changing exe once again
  * on NFS restore
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de9f1a9..68876d0a7ef9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,10 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
+#define JOBCTL_PTRACE_FROZEN_BIT	24	/* frozen for ptrace */
+
+#define JOBCTL_STOPPED_BIT	26	/* do_signal_stop() */
+#define JOBCTL_TRACED_BIT	27	/* ptrace_stop() */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,6 +32,10 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
+#define JOBCTL_PTRACE_FROZEN	(1UL << JOBCTL_PTRACE_FROZEN_BIT)
+
+#define JOBCTL_STOPPED		(1UL << JOBCTL_STOPPED_BIT)
+#define JOBCTL_TRACED		(1UL << JOBCTL_TRACED_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1ad1f4bfa025..8cd975a8bfeb 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -137,7 +137,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 
 #ifdef CONFIG_MMU
 #ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr)	(TASK_SIZE)
+#define arch_get_mmap_end(addr, len, flags)	(TASK_SIZE)
 #endif
 
 #ifndef arch_get_mmap_base
@@ -153,6 +153,15 @@ extern unsigned long
 arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
+
+unsigned long
+generic_get_unmapped_area(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags);
+unsigned long
+generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+				  unsigned long len, unsigned long pgoff,
+				  unsigned long flags);
 #else
 static inline void arch_pick_mmap_layout(struct mm_struct *mm,
 					 struct rlimit *rlim_stack) {}
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index e5af028c08b4..994c25640e15 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -39,20 +39,12 @@ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
 }
 extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return tsk->pi_blocked_on != NULL;
-}
 #else
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
 }
 # define rt_mutex_adjust_pi(p)		do { } while (0)
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return false;
-}
 #endif
 
 extern void normalize_rt_tasks(void);
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 20ed5ba2bde4..cafbe03eed01 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void)
 static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
-	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED) {
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
+	}
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();
@@ -444,13 +446,23 @@ extern void calculate_sigpending(void);
 
 extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
 
-static inline void signal_wake_up(struct task_struct *t, bool resume)
+static inline void signal_wake_up(struct task_struct *t, bool fatal)
 {
-	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+	unsigned int state = 0;
+	if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) {
+		t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED);
+		state = TASK_WAKEKILL | __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {
-	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+	unsigned int state = 0;
+	if (resume) {
+		t->jobctl &= ~JOBCTL_TRACED;
+		state = __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 
 void task_join_group_stop(struct task_struct *task);
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c1076b5e17fb..e650946816d0 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -14,8 +14,6 @@ extern unsigned long sysctl_hung_task_timeout_secs;
 enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
-extern unsigned int sysctl_sched_child_runs_first;
-
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,
@@ -33,46 +31,7 @@ extern int sysctl_numa_balancing_mode;
 #define sysctl_numa_balancing_mode	0
 #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;
-
-extern unsigned int sysctl_sched_dl_period_max;
-extern unsigned int sysctl_sched_dl_period_min;
-
-#ifdef CONFIG_UCLAMP_TASK
-extern unsigned int sysctl_sched_uclamp_util_min;
-extern unsigned int sysctl_sched_uclamp_util_max;
-extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
-#endif
-
-#ifdef CONFIG_CFS_BANDWIDTH
-extern unsigned int sysctl_sched_cfs_bandwidth_slice;
-#endif
-
-extern int sysctl_sched_rr_timeslice;
-extern int sched_rr_timeslice;
-
-int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
 int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-extern unsigned int sysctl_sched_energy_aware;
-int sched_energy_aware_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-#endif
 
 #endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 719c9a6cac8d..81cab4b01edc 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -32,6 +32,10 @@ struct kernel_clone_args {
 	size_t set_tid_size;
 	int cgroup;
 	int io_thread;
+	int kthread;
+	int idle;
+	int (*fn)(void *);
+	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
@@ -67,8 +71,7 @@ extern void fork_init(void);
 
 extern void release_task(struct task_struct * p);
 
-extern int copy_thread(unsigned long, unsigned long, unsigned long,
-		       struct task_struct *, unsigned long);
+extern int copy_thread(struct task_struct *, const struct kernel_clone_args *);
 
 extern void flush_thread(void);
 
@@ -82,13 +85,14 @@ static inline void exit_thread(struct task_struct *tsk)
 extern __noreturn void do_group_exit(int);
 
 extern void exit_files(struct task_struct *);
-extern void exit_itimers(struct signal_struct *);
+extern void exit_itimers(struct task_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
 struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 int kernel_wait(pid_t pid, int *stat);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 56cffe42abbc..816df6cc444e 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -81,6 +81,7 @@ struct sched_domain_shared {
 	atomic_t	ref;
 	atomic_t	nr_busy_cpus;
 	int		has_idle_cores;
+	int		nr_idle_scan;
 };
 
 struct sched_domain {
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 00ed419dd464..f054d0360a75 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -24,7 +24,8 @@ struct user_struct {
 	kuid_t uid;
 
 #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
-    defined(CONFIG_NET) || defined(CONFIG_IO_URING)
+	defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
+	defined(CONFIG_VFIO_PCI_ZDEV_KVM)
 	atomic_long_t locked_vm;
 #endif
 #ifdef CONFIG_WATCH_QUEUE