Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index cc6bcc1..3ed5aa1 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -9,7 +9,6 @@
  */
 
 #define SCHED_CPUFREQ_IOWAIT	(1U << 0)
-#define SCHED_CPUFREQ_MIGRATION	(1U << 1)
 
 #ifdef CONFIG_CPU_FREQ
 struct cpufreq_policy;
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 95fb9e0..ae51f45 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -30,7 +30,8 @@
  * 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 show_stack(struct task_struct *task, unsigned long *sp,
+		       const char *loglvl);
 
 extern void sched_show_task(struct task_struct *p);
 
@@ -42,7 +43,7 @@
 #endif
 
 /* Attach to any functions which should be ignored in wchan output. */
-#define __sched		__attribute__((__section__(".sched.text")))
+#define __sched		__section(".sched.text")
 
 /* Linker adds these: start and end of __sched functions */
 extern char __sched_text_start[], __sched_text_end[];
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 6c8512d..cc9f393 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -13,6 +13,8 @@
 	HK_FLAG_TICK		= (1 << 4),
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
+	HK_FLAG_MANAGED_IRQ	= (1 << 7),
+	HK_FLAG_KTHREAD		= (1 << 8),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de..d2b4204 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,7 @@
 #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_TASK_WORK_BIT	24	/* set by TWA_SIGNAL */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,9 +29,10 @@
 #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_TASK_WORK	(1UL << JOBCTL_TASK_WORK_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 4859bea..83ec54b 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -43,6 +43,6 @@
 #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);
+extern void calc_global_load(void);
 
 #endif /* _LINUX_SCHED_LOADAVG_H */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3a1d899..dc1f4dc 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -23,7 +23,7 @@
  * 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
+ * This is a preferred way to pin @mm for a longer/unbounded amount
  * of time.
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
@@ -49,33 +49,6 @@
 		__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.
@@ -178,24 +151,20 @@
  * 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))) {
+	unsigned int pflags = READ_ONCE(current->flags);
+
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
 		/*
 		 * 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)
+		if (pflags & PF_MEMALLOC_NOIO)
 			flags &= ~(__GFP_IO | __GFP_FS);
-		else if (current->flags & PF_MEMALLOC_NOFS)
+		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
-#ifdef CONFIG_CMA
-		if (current->flags & PF_MEMALLOC_NOCMA)
-			flags &= ~__GFP_MOVABLE;
-#endif
 	}
 	return flags;
 }
@@ -235,7 +204,7 @@
  * @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
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_noio_save call.
  */
 static inline void memalloc_noio_restore(unsigned int flags)
@@ -266,7 +235,7 @@
  * @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
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_nofs_save call.
  */
 static inline void memalloc_nofs_restore(unsigned int flags)
@@ -311,39 +280,38 @@
 #endif
 
 #ifdef CONFIG_MEMCG
+DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
 /**
- * memalloc_use_memcg - Starts the remote memcg charging scope.
+ * set_active_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.
+ * NOTE: This function can nest. Users must save the return value and
+ * reset the previous value after their own charging scope is over.
  */
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
-	WARN_ON_ONCE(current->active_memcg);
-	current->active_memcg = memcg;
-}
+	struct mem_cgroup *old;
 
-/**
- * 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;
+	if (in_interrupt()) {
+		old = this_cpu_read(int_active_memcg);
+		this_cpu_write(int_active_memcg, memcg);
+	} else {
+		old = current->active_memcg;
+		current->active_memcg = memcg;
+	}
+
+	return old;
 }
 #else
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
-}
-
-static inline void memalloc_unuse_memcg(void)
-{
+	return NULL;
 }
 #endif
 
@@ -355,10 +323,13 @@
 	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY		= (1U << 6),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ			= (1U << 7),
 };
 
 enum {
 	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+	MEMBARRIER_FLAG_RSEQ		= (1U << 1),
 };
 
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
new file mode 100644
index 0000000..34b21e9
--- /dev/null
+++ b/include/linux/sched/sd_flags.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sched-domains (multiprocessor balancing) flag declarations.
+ */
+
+#ifndef SD_FLAG
+# error "Incorrect import of SD flags definitions"
+#endif
+
+/*
+ * Hierarchical metaflags
+ *
+ * SHARED_CHILD: These flags are meant to be set from the base domain upwards.
+ * If a domain has this flag set, all of its children should have it set. This
+ * is usually because the flag describes some shared resource (all CPUs in that
+ * domain share the same resource), or because they are tied to a scheduling
+ * behaviour that we want to disable at some point in the hierarchy for
+ * scalability reasons.
+ *
+ * In those cases it doesn't make sense to have the flag set for a domain but
+ * not have it in (some of) its children: sched domains ALWAYS span their child
+ * domains, so operations done with parent domains will cover CPUs in the lower
+ * child domains.
+ *
+ *
+ * SHARED_PARENT: These flags are meant to be set from the highest domain
+ * downwards. If a domain has this flag set, all of its parents should have it
+ * set. This is usually for topology properties that start to appear above a
+ * certain level (e.g. domain starts spanning CPUs outside of the base CPU's
+ * socket).
+ */
+#define SDF_SHARED_CHILD       0x1
+#define SDF_SHARED_PARENT      0x2
+
+/*
+ * Behavioural metaflags
+ *
+ * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has
+ * more than one group. This is usually for balancing flags (load balancing
+ * involves equalizing a metric between groups), or for flags describing some
+ * shared resource (which would be shared between groups).
+ */
+#define SDF_NEEDS_GROUPS       0x4
+
+/*
+ * Balance when about to become idle
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on exec
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on fork, clone
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on wakeup
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Consider waking task on waking CPU.
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
+
+/*
+ * Domain members have different CPU capacities
+ *
+ * SHARED_PARENT: Set from the topmost domain down to the first domain where
+ *                asymmetry is detected.
+ * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups.
+ */
+SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU capacity (i.e. SMT)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               CPU capacity.
+ * NEEDS_GROUPS: Capacity is shared between groups.
+ */
+SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU package resources (i.e. caches)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               the same cache(s).
+ * NEEDS_GROUPS: Caches are shared between groups.
+ */
+SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Only a single load balancing instance
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a
+ *                different level upwards, but it doesn't change that if a
+ *                domain has this flag set, then all of its parents need to have
+ *                it too (otherwise the serialization doesn't make sense).
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Place busy tasks earlier in the domain
+ *
+ * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
+ *               up, but currently assumed to be set from the base domain
+ *               upwards (see update_top_cache_domain()).
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Prefer to place tasks in a sibling domain
+ *
+ * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
+ * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ *
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
+
+/*
+ * sched_groups of this level overlap
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: Overlaps can only exist with more than one group.
+ */
+SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Cross-node balancing
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index b3f8847..6576400 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -10,6 +10,8 @@
 #include <linux/cred.h>
 #include <linux/refcount.h>
 #include <linux/posix-timers.h>
+#include <linux/mm_types.h>
+#include <asm/ptrace.h>
 
 /*
  * Types defining task->signal and task->sighand and APIs using them:
@@ -378,6 +380,20 @@
 }
 
 /*
+ * This should only be used in fault handlers to decide whether we
+ * should stop the current fault routine to handle the signals
+ * instead, especially with the case where we've got interrupted with
+ * a VM_FAULT_RETRY.
+ */
+static inline bool fault_signal_pending(vm_fault_t fault_flags,
+					struct pt_regs *regs)
+{
+	return unlikely((fault_flags & VM_FAULT_RETRY) &&
+			(fatal_signal_pending(current) ||
+			 (user_mode(regs) && signal_pending(current))));
+}
+
+/*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
  * This is required every time the blocked sigset_t changes.
@@ -644,17 +660,6 @@
 	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)
 {
@@ -675,6 +680,8 @@
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
+extern bool thread_group_exited(struct pid *pid);
+
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
 							unsigned long *flags);
 
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index d4f6215..3c31ba8 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -7,14 +7,20 @@
 struct ctl_table;
 
 #ifdef CONFIG_DETECT_HUNG_TASK
+
+#ifdef CONFIG_SMP
+extern unsigned int sysctl_hung_task_all_cpu_backtrace;
+#else
+#define sysctl_hung_task_all_cpu_backtrace 0
+#endif /* CONFIG_SMP */
+
 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);
+int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
 #else
 /* Avoid need for ifdefs elsewhere in the code */
 enum { sysctl_hung_task_timeout_secs = 0 };
@@ -43,8 +49,7 @@
 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);
+		void *buffer, size_t *length, loff_t *ppos);
 #endif
 
 /*
@@ -56,9 +61,13 @@
 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
@@ -72,33 +81,21 @@
 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);
+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;
-extern int sched_energy_aware_handler(struct ctl_table *table, int write,
-				 void __user *buffer, size_t *lenp,
-				 loff_t *ppos);
+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 4b1c3b6..fa75f32 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -13,6 +13,7 @@
 struct task_struct;
 struct rusage;
 union thread_union;
+struct css_set;
 
 /* All the bits taken by the old clone syscall. */
 #define CLONE_LEGACY_FLAGS 0xffffffffULL
@@ -26,6 +27,12 @@
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
+	pid_t *set_tid;
+	/* Number of elements in *set_tid */
+	size_t set_tid_size;
+	int cgroup;
+	struct cgroup *cgrp;
+	struct css_set *cset;
 };
 
 /*
@@ -48,6 +55,8 @@
 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_post_fork(struct task_struct *p,
+			    struct kernel_clone_args *kargs);
 extern void sched_dead(struct task_struct *p);
 
 void __noreturn do_task_dead(void);
@@ -58,22 +67,9 @@
 
 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 *);
+		       struct task_struct *, unsigned long);
 
-/* 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
@@ -88,13 +84,12 @@
 extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
-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 *);
+extern pid_t kernel_clone(struct kernel_clone_args *kargs);
 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 *);
+int kernel_wait(pid_t pid, int *stat);
 
 extern void free_task(struct task_struct *tsk);
 
@@ -119,6 +114,12 @@
 		__put_task_struct(t);
 }
 
+static inline void put_task_struct_many(struct task_struct *t, int nr)
+{
+	if (refcount_sub_and_test(nr, &t->usage))
+		__put_task_struct(t);
+}
+
 void put_task_struct_rcu_user(struct task_struct *task);
 
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
@@ -157,7 +158,7 @@
  * 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.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 2413427..d101505 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -25,7 +25,11 @@
 
 static inline unsigned long *end_of_stack(const struct task_struct *task)
 {
+#ifdef CONFIG_STACK_GROWSUP
+	return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1;
+#else
 	return task->stack;
+#endif
 }
 
 #elif !defined(__HAVE_THREAD_FUNCTIONS)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index f341163..9ef7bf6 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -11,21 +11,29 @@
  */
 #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 */
+/* Generate SD flag indexes */
+#define SD_FLAG(name, mflags) __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+	__SD_FLAG_CNT,
+};
+#undef SD_FLAG
+/* Generate SD flag bits */
+#define SD_FLAG(name, mflags) name = 1 << __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+};
+#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)
@@ -142,7 +150,7 @@
 	 * 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];
+	unsigned long span[];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
@@ -218,6 +226,16 @@
 #endif	/* !CONFIG_SMP */
 
 #ifndef arch_scale_cpu_capacity
+/**
+ * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the CPU scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *             max_perf(cpu)
+ *      ----------------------------- * SCHED_CAPACITY_SCALE
+ *      max(max_perf(c) : c \in CPUs)
+ */
 static __always_inline
 unsigned long arch_scale_cpu_capacity(int cpu)
 {
@@ -225,6 +243,21 @@
 }
 #endif
 
+#ifndef arch_scale_thermal_pressure
+static __always_inline
+unsigned long arch_scale_thermal_pressure(int cpu)
+{
+	return 0;
+}
+#endif
+
+#ifndef arch_set_thermal_pressure
+static __always_inline
+void arch_set_thermal_pressure(const struct cpumask *cpus,
+			       unsigned long th_pressure)
+{ }
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 917d88e..a8ec3b6 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -36,6 +36,9 @@
     defined(CONFIG_NET) || defined(CONFIG_IO_URING)
 	atomic_long_t locked_vm;
 #endif
+#ifdef CONFIG_WATCH_QUEUE
+	atomic_t nr_watches;	/* The number of watches this user currently has */
+#endif
 
 	/* Miscellaneous per-user rate limit */
 	struct ratelimit_state ratelimit;