12 files changed, 121 insertions, 74 deletions

diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 53f883f5a2fd..6c9f19a33865 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -61,8 +61,7 @@ extern void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
  * 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);
-
+void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples);
 
 /*
  * The following are functions that support scheduler-internal time accounting.
@@ -71,7 +70,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
  */
 
 /**
- * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimers are active
  *
  * @tsk:	Pointer to target task.
  */
@@ -81,8 +80,11 @@ 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))
+	/*
+	 * Check whether posix CPU timers are active. If not the thread
+	 * group accounting is not active either. Lockless check.
+	 */
+	if (!READ_ONCE(tsk->signal->posix_cputimers.timers_active))
 		return NULL;
 
 	/*
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 0cb034331cbb..1aff00b65f3c 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -24,3 +24,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 {
 	return (s64)(a - b) < 0;
 }
+
+#ifdef CONFIG_SMP
+
+struct root_domain;
+extern void dl_add_task_root_domain(struct task_struct *p);
+extern void dl_clear_root_domain(struct root_domain *rd);
+
+#endif /* CONFIG_SMP */
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index b0fb1446fe04..6c8512d3be88 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -19,6 +19,7 @@ enum hk_flags {
 DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
 extern int housekeeping_any_cpu(enum hk_flags flags);
 extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
+extern bool housekeeping_enabled(enum hk_flags flags);
 extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
 extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
 extern void __init housekeeping_init(void);
@@ -35,6 +36,11 @@ static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
 	return cpu_possible_mask;
 }
 
+static inline bool housekeeping_enabled(enum hk_flags flags)
+{
+	return false;
+}
+
 static inline void housekeeping_affine(struct task_struct *t,
 				       enum hk_flags flags) { }
 static inline void housekeeping_init(void) { }
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index b36f4cf38111..1abe91ff6e4a 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -7,14 +7,6 @@
  */
 
 #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
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index e7dd04a84ba8..3988762efe15 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -19,7 +19,7 @@
 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);
+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
@@ -34,7 +34,7 @@ static inline pid_t task_numa_group_id(struct task_struct *p)
 static inline void set_numabalancing_state(bool enabled)
 {
 }
-static inline void task_numa_free(struct task_struct *p)
+static inline void task_numa_free(struct task_struct *p, bool final)
 {
 }
 static inline bool should_numa_migrate_memory(struct task_struct *p,
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 38a0f0785323..88050259c466 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -9,16 +9,17 @@
 #include <linux/sched/task.h>
 #include <linux/cred.h>
 #include <linux/refcount.h>
+#include <linux/posix-timers.h>
 
 /*
  * Types defining task->signal and task->sighand and APIs using them:
  */
 
 struct sighand_struct {
-	refcount_t		count;
-	struct k_sigaction	action[_NSIG];
 	spinlock_t		siglock;
+	refcount_t		count;
 	wait_queue_head_t	signalfd_wqh;
+	struct k_sigaction	action[_NSIG];
 };
 
 /*
@@ -56,18 +57,12 @@ struct task_cputime_atomic {
 /**
  * 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 {
@@ -148,12 +143,9 @@ struct signal_struct {
 	 */
 	struct thread_group_cputimer cputimer;
 
-	/* Earliest-expiration cache. */
-	struct task_cputime cputime_expires;
-
-	struct list_head cpu_timers[3];
-
 #endif
+	/* Empty if CONFIG_POSIX_TIMERS=n */
+	struct posix_cputimers posix_cputimers;
 
 	/* PID/PID hash table linkage. */
 	struct pid *pids[PIDTYPE_MAX];
@@ -307,16 +299,19 @@ static inline void kernel_signal_stop(void)
 # define ___ARCH_SI_IA64(_a1, _a2, _a3)
 #endif
 
-int force_sig_fault(int sig, int code, void __user *addr
+int force_sig_fault_to_task(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_fault(int sig, int code, void __user *addr
+	___ARCH_SI_TRAPNO(int trapno)
+	___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr));
 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 force_sig_mceerr(int code, void __user *, short);
 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);
@@ -325,17 +320,17 @@ 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 kernel_siginfo *, struct task_struct *);
-extern void force_sigsegv(int sig, struct task_struct *p);
-extern int force_sig_info(int, struct kernel_siginfo *, struct task_struct *);
+extern void force_sigsegv(int sig);
+extern int force_sig_info(struct kernel_siginfo *);
 extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp);
 extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid);
-extern int kill_pid_info_as_cred(int, struct kernel_siginfo *, struct pid *,
+extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, 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 void force_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);
@@ -417,7 +412,6 @@ void task_join_group_stop(struct task_struct *task);
 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 *task)
@@ -448,7 +442,6 @@ static inline bool test_and_clear_restore_sigmask(void)
 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 *task)
 {
@@ -481,6 +474,16 @@ static inline void restore_saved_sigmask(void)
 		__set_current_blocked(&current->saved_sigmask);
 }
 
+extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
+
+static inline void restore_saved_sigmask_unless(bool interrupted)
+{
+	if (interrupted)
+		WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+	else
+		restore_saved_sigmask();
+}
+
 static inline sigset_t *sigmask_to_save(void)
 {
 	sigset_t *res = &current->blocked;
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 99ce6d728df7..d4f6215ee03f 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -56,6 +56,11 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 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
@@ -75,6 +80,12 @@ 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);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index f1227f2c38a4..3d90ed8f75f0 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -8,11 +8,26 @@
  */
 
 #include <linux/sched.h>
+#include <linux/uaccess.h>
 
 struct task_struct;
 struct rusage;
 union thread_union;
 
+/* All the bits taken by the old clone syscall. */
+#define CLONE_LEGACY_FLAGS 0xffffffffULL
+
+struct kernel_clone_args {
+	u64 flags;
+	int __user *pidfd;
+	int __user *child_tid;
+	int __user *parent_tid;
+	int exit_signal;
+	unsigned long stack;
+	unsigned long stack_size;
+	unsigned long tls;
+};
+
 /*
  * This serializes "schedule()" and also protects
  * the run-queue from deletions/modifications (but
@@ -73,7 +88,8 @@ extern void do_group_exit(int);
 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(struct kernel_clone_args *kargs);
+extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
@@ -89,7 +105,11 @@ extern void sched_exec(void);
 #define sched_exec()   {}
 #endif
 
-#define get_task_struct(tsk) do { refcount_inc(&(tsk)->usage); } while(0)
+static inline struct task_struct *get_task_struct(struct task_struct *t)
+{
+	refcount_inc(&t->usage);
+	return t;
+}
 
 extern void __put_task_struct(struct task_struct *t);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index cfc0a89a7159..f341163fedc9 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -7,12 +7,6 @@
 #include <linux/sched/idle.h>
 
 /*
- * Increase resolution of cpu_capacity calculations
- */
-#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
-#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
-
-/*
  * sched-domains (multiprocessor balancing) declarations:
  */
 #ifdef CONFIG_SMP
@@ -84,11 +78,6 @@ struct sched_domain {
 	unsigned int busy_factor;	/* less balancing by factor if busy */
 	unsigned int imbalance_pct;	/* No balance until over watermark */
 	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
-	unsigned int busy_idx;
-	unsigned int idle_idx;
-	unsigned int newidle_idx;
-	unsigned int wake_idx;
-	unsigned int forkexec_idx;
 
 	int nohz_idle;			/* NOHZ IDLE status */
 	int flags;			/* See SD_* */
@@ -161,6 +150,10 @@ 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);
 
@@ -201,19 +194,17 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl);
 # 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)
-{
-	return SCHED_CAPACITY_SCALE;
-}
-#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)
 {
@@ -224,16 +215,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 	return true;
 }
 
+#endif	/* !CONFIG_SMP */
+
 #ifndef arch_scale_cpu_capacity
 static __always_inline
-unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
+unsigned long arch_scale_cpu_capacity(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));
diff --git a/include/linux/sched/types.h b/include/linux/sched/types.h
new file mode 100644
index 000000000000..3c3e049224ae
--- /dev/null
+++ b/include/linux/sched/types.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_TYPES_H
+#define _LINUX_SCHED_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * struct task_cputime - collected CPU time counts
+ * @stime:		time spent in kernel mode, in nanoseconds
+ * @utime:		time spent in user mode, in nanoseconds
+ * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
+ *
+ * This structure groups together three kinds of CPU time that are tracked for
+ * threads and thread groups.  Most things considering CPU time want to group
+ * these counts together and treat all three of them in parallel.
+ */
+struct task_cputime {
+	u64				stime;
+	u64				utime;
+	unsigned long long		sum_exec_runtime;
+};
+
+#endif
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 468d2565a9fe..917d88edb7b9 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -7,8 +7,6 @@
 #include <linux/refcount.h>
 #include <linux/ratelimit.h>
 
-struct key;
-
 /*
  * Some day this will be a full-fledged user tracking system..
  */
@@ -30,18 +28,6 @@ struct user_struct {
 	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
-	/*
-	 * These pointers can only change from NULL to a non-NULL value once.
-	 * Writes are protected by key_user_keyring_mutex.
-	 * Unlocked readers should use READ_ONCE() unless they know that
-	 * install_user_keyrings() has been called successfully (which sets
-	 * these members to non-NULL values, preventing further modifications).
-	 */
-	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;
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index ad826d2a4557..26a2013ac39c 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -51,6 +51,11 @@ static inline void wake_q_init(struct wake_q_head *head)
 	head->lastp = &head->first;
 }
 
+static inline bool wake_q_empty(struct wake_q_head *head)
+{
+	return head->first == WAKE_Q_TAIL;
+}
+
 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);