13 files changed, 144 insertions, 27 deletions

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ec912d01126f..ecdc6542070f 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #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_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 59667444669f..afa940cd50dc 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -20,6 +20,12 @@ 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);
+
+static inline unsigned long map_util_freq(unsigned long util,
+					unsigned long freq, unsigned long cap)
+{
+	return (freq + (freq >> 2)) * util / cap;
+}
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 4a6582c27dea..b0fb1446fe04 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -16,7 +16,7 @@ enum hk_flags {
 };
 
 #ifdef CONFIG_CPU_ISOLATION
-DECLARE_STATIC_KEY_FALSE(housekeeping_overriden);
+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 void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
@@ -43,7 +43,7 @@ static inline void housekeeping_init(void) { }
 static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
 {
 #ifdef CONFIG_CPU_ISOLATION
-	if (static_branch_unlikely(&housekeeping_overriden))
+	if (static_branch_unlikely(&housekeeping_overridden))
 		return housekeeping_test_cpu(cpu, flags);
 #endif
 	return true;
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index 98228bd48aee..fa067de9f1a9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -18,6 +18,7 @@ struct task_struct;
 #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)
@@ -26,6 +27,7 @@ struct task_struct;
 #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)
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index aebb370a0006..a3fda9f024c3 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(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.
+ *
+ * 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.
@@ -148,17 +169,25 @@ static inline bool in_vfork(struct task_struct *tsk)
  * 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)
 {
-	/*
-	 * NOIO implies both NOIO and NOFS and it is a weaker context
-	 * so always make sure it makes precendence
-	 */
-	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~(__GFP_IO | __GFP_FS);
-	else if (unlikely(current->flags & PF_MEMALLOC_NOFS))
-		flags &= ~__GFP_FS;
+	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;
 }
 
@@ -248,6 +277,30 @@ 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.
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 13789d10a50e..e412c092c1e8 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -8,13 +8,14 @@
 #include <linux/sched/jobctl.h>
 #include <linux/sched/task.h>
 #include <linux/cred.h>
+#include <linux/refcount.h>
 
 /*
  * Types defining task->signal and task->sighand and APIs using them:
  */
 
 struct sighand_struct {
-	atomic_t		count;
+	refcount_t		count;
 	struct k_sigaction	action[_NSIG];
 	spinlock_t		siglock;
 	wait_queue_head_t	signalfd_wqh;
@@ -82,7 +83,7 @@ struct multiprocess_signals {
  * the locking of signal_struct.
  */
 struct signal_struct {
-	atomic_t		sigcnt;
+	refcount_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
 	struct list_head	thread_head;
@@ -417,10 +418,20 @@ 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);
@@ -438,6 +449,10 @@ 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;
@@ -446,6 +461,10 @@ 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)
diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
index f30954cc059d..568286411b43 100644
--- a/include/linux/sched/stat.h
+++ b/include/linux/sched/stat.h
@@ -8,7 +8,7 @@
  * 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,
+ * ( Note that all these values are acquired without locking,
  *   so they can only be relied on in narrow circumstances. )
  */
 
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index a9c32daeb9d8..99ce6d728df7 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -83,4 +83,11 @@ 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 */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 108ede99e533..f1227f2c38a4 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -39,6 +39,8 @@ 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
@@ -74,6 +76,7 @@ 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);
+struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 
@@ -86,13 +89,13 @@ extern void sched_exec(void);
 #define sched_exec()   {}
 #endif
 
-#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+#define get_task_struct(tsk) do { refcount_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))
+	if (refcount_dec_and_test(&t->usage))
 		__put_task_struct(t);
 }
 
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 6a841929073f..2413427e439c 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -61,7 +61,7 @@ static inline unsigned long *end_of_stack(struct task_struct *p)
 #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) ?
+	return refcount_inc_not_zero(&tsk->stack_refcount) ?
 		task_stack_page(tsk) : NULL;
 }
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 6b9976180c1e..cfc0a89a7159 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -76,8 +76,8 @@ struct sched_domain_shared {
 
 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_domain __rcu *parent;	/* top domain must be null terminated */
+	struct sched_domain __rcu *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 */
@@ -89,7 +89,6 @@ struct sched_domain {
 	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_* */
@@ -177,10 +176,10 @@ 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 *__percpu *sd;
+	struct sched_domain_shared *__percpu *sds;
+	struct sched_group *__percpu *sg;
+	struct sched_group_capacity *__percpu *sgc;
 };
 
 struct sched_domain_topology_level {
@@ -202,6 +201,14 @@ 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;
@@ -217,6 +224,14 @@ 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)
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 39ad98c09c58..468d2565a9fe 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -31,6 +31,13 @@ struct user_struct {
 	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
@@ -40,7 +47,7 @@ struct user_struct {
 	kuid_t uid;
 
 #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
-    defined(CONFIG_NET)
+    defined(CONFIG_NET) || defined(CONFIG_IO_URING)
 	atomic_long_t locked_vm;
 #endif
 
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 10b19a192b2d..ad826d2a4557 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -24,9 +24,13 @@
  * 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
+ * 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.
+ *
+ * NOTE that there is no guarantee the wakeup will happen any later than the
+ * wake_q_add() location. Therefore task must be ready to be woken at the
+ * location of the wake_q_add().
  */
 
 #include <linux/sched.h>
@@ -47,8 +51,8 @@ static inline void wake_q_init(struct wake_q_head *head)
 	head->lastp = &head->first;
 }
 
-extern void wake_q_add(struct wake_q_head *head,
-		       struct task_struct *task);
+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);
 
 #endif /* _LINUX_SCHED_WAKE_Q_H */