Merge tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - Revert the printk format based wchan() symbol resolution as it can
   leak the raw value in case that the symbol is not resolvable.

 - Make wchan() more robust and work with all kind of unwinders by
   enforcing that the task stays blocked while unwinding is in progress.

 - Prevent sched_fork() from accessing an invalid sched_task_group

 - Improve asymmetric packing logic

 - Extend scheduler statistics to RT and DL scheduling classes and add
   statistics for bandwith burst to the SCHED_FAIR class.

 - Properly account SCHED_IDLE entities

 - Prevent a potential deadlock when initial priority is assigned to a
   newly created kthread. A recent change to plug a race between cpuset
   and __sched_setscheduler() introduced a new lock dependency which is
   now triggered. Break the lock dependency chain by moving the priority
   assignment to the thread function.

 - Fix the idle time reporting in /proc/uptime for NOHZ enabled systems.

 - Improve idle balancing in general and especially for NOHZ enabled
   systems.

 - Provide proper interfaces for live patching so it does not have to
   fiddle with scheduler internals.

 - Add cluster aware scheduling support.

 - A small set of tweaks for RT (irqwork, wait_task_inactive(), various
   scheduler options and delaying mmdrop)

 - The usual small tweaks and improvements all over the place

* tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  sched/fair: Cleanup newidle_balance
  sched/fair: Remove sysctl_sched_migration_cost condition
  sched/fair: Wait before decaying max_newidle_lb_cost
  sched/fair: Skip update_blocked_averages if we are defering load balance
  sched/fair: Account update_blocked_averages in newidle_balance cost
  x86: Fix __get_wchan() for !STACKTRACE
  sched,x86: Fix L2 cache mask
  sched/core: Remove rq_relock()
  sched: Improve wake_up_all_idle_cpus() take #2
  irq_work: Also rcuwait for !IRQ_WORK_HARD_IRQ on PREEMPT_RT
  irq_work: Handle some irq_work in a per-CPU thread on PREEMPT_RT
  irq_work: Allow irq_work_sync() to sleep if irq_work() no IRQ support.
  sched/rt: Annotate the RT balancing logic irqwork as IRQ_WORK_HARD_IRQ
  sched: Add cluster scheduler level for x86
  sched: Add cluster scheduler level in core and related Kconfig for ARM64
  topology: Represent clusters of CPUs within a die
  sched: Disable -Wunused-but-set-variable
  sched: Add wrapper for get_wchan() to keep task blocked
  x86: Fix get_wchan() to support the ORC unwinder
  proc: Use task_is_running() for wchan in /proc/$pid/stat
  ...

57 files changed, 153 insertions, 161 deletions

diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 6100431da07a..090499c99c1c 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/arch/alpha/include/asm/processor.h
@@ -42,7 +42,7 @@ extern void start_thread(struct pt_regs *, unsigned long, unsigned long);
 struct task_struct;
 extern void release_thread(struct task_struct *);
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
 
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index a5123ea426ce..5f8527081da9 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -376,12 +376,11 @@ thread_saved_pc(struct task_struct *t)
 }
 
 unsigned long
-get_wchan(struct task_struct *p)
+__get_wchan(struct task_struct *p)
 {
 	unsigned long schedule_frame;
 	unsigned long pc;
-	if (!p || p == current || task_is_running(p))
-		return 0;
+
 	/*
 	 * This one depends on the frame size of schedule().  Do a
 	 * "disass schedule" in gdb to find the frame size.  Also, the
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index f28afcf5c6d1..54db9d7bb562 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -70,7 +70,7 @@ struct task_struct;
 extern void start_thread(struct pt_regs * regs, unsigned long pc,
 			 unsigned long usp);
 
-extern unsigned int get_wchan(struct task_struct *p);
+extern unsigned int __get_wchan(struct task_struct *p);
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index c376ff3147e7..5372dc04e784 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -15,7 +15,7 @@
  *      = specifics of data structs where trace is saved(CONFIG_STACKTRACE etc)
  *
  *  vineetg: March 2009
- *  -Implemented correct versions of thread_saved_pc() and get_wchan()
+ *  -Implemented correct versions of thread_saved_pc() and __get_wchan()
  *
  *  rajeshwarr: 2008
  *  -Initial implementation
@@ -248,7 +248,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
  * Of course just returning schedule( ) would be pointless so unwind until
  * the function is not in schedular code
  */
-unsigned int get_wchan(struct task_struct *tsk)
+unsigned int __get_wchan(struct task_struct *tsk)
 {
 	return arc_unwind_core(tsk, NULL, __get_first_nonsched, NULL);
 }
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 9e6b97286307..6af68edfa53a 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -84,7 +84,7 @@ struct task_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 0e2d3051741e..96f577e59595 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -276,13 +276,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	return 0;
 }
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
 	unsigned long stack_page;
 	int count = 0;
-	if (!p || p == current || task_is_running(p))
-		return 0;
 
 	frame.fp = thread_saved_fp(p);
 	frame.sp = thread_saved_sp(p);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3d027ce8f7a3..bc8d3702f4ed 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -988,6 +988,15 @@ config SCHED_MC
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
+config SCHED_CLUSTER
+	bool "Cluster scheduler support"
+	help
+	  Cluster scheduler support improves the CPU scheduler's decision
+	  making when dealing with machines that have clusters of CPUs.
+	  Cluster usually means a couple of CPUs which are placed closely
+	  by sharing mid-level caches, last-level cache tags or internal
+	  busses.
+
 config SCHED_SMT
 	bool "SMT scheduler support"
 	help
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ee2bdc1b9f5b..55ca034238ea 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -257,7 +257,7 @@ struct task_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 void update_sctlr_el1(u64 sctlr);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 40adb8cdbf5a..aacf2f5559a8 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -528,13 +528,11 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	return last;
 }
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
 	unsigned long stack_page, ret = 0;
 	int count = 0;
-	if (!p || p == current || task_is_running(p))
-		return 0;
 
 	stack_page = (unsigned long)try_get_task_stack(p);
 	if (!stack_page)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 4dd14a6620c1..9ab78ad826e2 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -103,6 +103,8 @@ int __init parse_acpi_topology(void)
 			cpu_topology[cpu].thread_id  = -1;
 			cpu_topology[cpu].core_id    = topology_id;
 		}
+		topology_id = find_acpi_cpu_topology_cluster(cpu);
+		cpu_topology[cpu].cluster_id = topology_id;
 		topology_id = find_acpi_cpu_topology_package(cpu);
 		cpu_topology[cpu].package_id = topology_id;
 
diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h
index 9e933021fe8e..817dd60ff152 100644
--- a/arch/csky/include/asm/processor.h
+++ b/arch/csky/include/asm/processor.h
@@ -81,7 +81,7 @@ static inline void release_thread(struct task_struct *dead_task)
 
 extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk)		(task_pt_regs(tsk)->pc)
 #define KSTK_ESP(tsk)		(task_pt_regs(tsk)->usp)
diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c
index 1b280ef08004..9f78f5d21511 100644
--- a/arch/csky/kernel/stacktrace.c
+++ b/arch/csky/kernel/stacktrace.c
@@ -111,12 +111,11 @@ static bool save_wchan(unsigned long pc, void *arg)
 	return false;
 }
 
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
 {
 	unsigned long pc = 0;
 
-	if (likely(task && task != current && !task_is_running(task)))
-		walk_stackframe(task, NULL, save_wchan, &pc);
+	walk_stackframe(task, NULL, save_wchan, &pc);
 	return pc;
 }
 
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
index a060b41b2d31..141a23eb62b7 100644
--- a/arch/h8300/include/asm/processor.h
+++ b/arch/h8300/include/asm/processor.h
@@ -105,7 +105,7 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)	\
 	({			 \
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 2ac27e4248a4..8833fa4f5d51 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -128,15 +128,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	return 0;
 }
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	unsigned long fp, pc;
 	unsigned long stack_page;
 	int count = 0;
 
-	if (!p || p == current || task_is_running(p))
-		return 0;
-
 	stack_page = (unsigned long)p;
 	fp = ((struct pt_regs *)p->thread.ksp)->er6;
 	do {
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index 9f0cc99420be..615f7e49968e 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/arch/hexagon/include/asm/processor.h
@@ -64,7 +64,7 @@ struct thread_struct {
 extern void release_thread(struct task_struct *dead_task);
 
 /* Get wait channel for task P.  */
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
 
 /*  The following stuff is pretty HEXAGON specific.  */
 
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 6a6835fb4242..232dfd8956aa 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -130,13 +130,11 @@ void flush_thread(void)
  * is an identification of the point at which the scheduler
  * was invoked by a blocked thread.
  */
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	unsigned long fp, pc;
 	unsigned long stack_page;
 	int count = 0;
-	if (!p || p == current || task_is_running(p))
-		return 0;
 
 	stack_page = (unsigned long)task_stack_page(p);
 	fp = ((struct hexagon_switch_stack *)p->thread.switch_sp)->fp;
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 2d8bcdc27d7f..45365c2ef598 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -330,7 +330,7 @@ struct task_struct;
 #define release_thread(dead_task)
 
 /* Get wait channel for task P.  */
-extern unsigned long get_wchan (struct task_struct *p);
+extern unsigned long __get_wchan (struct task_struct *p);
 
 /* Return instruction pointer of blocked task TSK.  */
 #define KSTK_EIP(tsk)					\
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index e56d63f4abf9..834df24a88f1 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -523,15 +523,12 @@ exit_thread (struct task_struct *tsk)
 }
 
 unsigned long
-get_wchan (struct task_struct *p)
+__get_wchan (struct task_struct *p)
 {
 	struct unw_frame_info info;
 	unsigned long ip;
 	int count = 0;
 
-	if (!p || p == current || task_is_running(p))
-		return 0;
-
 	/*
 	 * Note: p may not be a blocked task (it could be current or
 	 * another process running on some other CPU.  Rather than
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index f4d82c619a5c..ffeda9aa526a 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -150,7 +150,7 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)	\
     ({			\
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 1ab692b952cd..a6030dbaa089 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -263,13 +263,11 @@ int dump_fpu (struct pt_regs *regs, struct user_m68kfp_struct *fpu)
 }
 EXPORT_SYMBOL(dump_fpu);
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	unsigned long fp, pc;
 	unsigned long stack_page;
 	int count = 0;
-	if (!p || p == current || task_is_running(p))
-		return 0;
 
 	stack_page = (unsigned long)task_stack_page(p);
 	fp = ((struct switch_stack *)p->thread.ksp)->a6;
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 06c6e493590a..7e9e92670df3 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -68,7 +68,7 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 /* The size allocated for kernel stacks. This _must_ be a power of two! */
 # define KERNEL_STACK_SIZE	0x2000
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 62aa237180b6..5e2b91c1e8ce 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -112,7 +112,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg,
 	return 0;
 }
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 /* TBD (used by procfs) */
 	return 0;
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 0c3550c82b72..252ed38ce8c5 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -369,7 +369,7 @@ static inline void flush_thread(void)
 {
 }
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \
 			 THREAD_SIZE - 32 - sizeof(struct pt_regs))
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 95aa86fa6077..cbff1b974f88 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -511,7 +511,7 @@ static int __init frame_info_init(void)
 
 	/*
 	 * Without schedule() frame info, result given by
-	 * thread_saved_pc() and get_wchan() are not reliable.
+	 * thread_saved_pc() and __get_wchan() are not reliable.
 	 */
 	if (schedule_mfi.pc_offset < 0)
 		printk("Can't analyze schedule() prologue at %p\n", schedule);
@@ -652,9 +652,9 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp,
 #endif
 
 /*
- * get_wchan - a maintenance nightmare^W^Wpain in the ass ...
+ * __get_wchan - a maintenance nightmare^W^Wpain in the ass ...
  */
-unsigned long get_wchan(struct task_struct *task)
+unsigned long __get_wchan(struct task_struct *task)
 {
 	unsigned long pc = 0;
 #ifdef CONFIG_KALLSYMS
@@ -662,8 +662,6 @@ unsigned long get_wchan(struct task_struct *task)
 	unsigned long ra = 0;
 #endif
 
-	if (!task || task == current || task_is_running(task))
-		goto out;
 	if (!task_stack_page(task))
 		goto out;
 
diff --git a/arch/nds32/include/asm/processor.h b/arch/nds32/include/asm/processor.h
index b82369c7659d..e6bfc74972bb 100644
--- a/arch/nds32/include/asm/processor.h
+++ b/arch/nds32/include/asm/processor.h
@@ -83,7 +83,7 @@ extern struct task_struct *last_task_used_math;
 /* Prepare to copy thread state - unlazy all lazy status */
 #define prepare_to_copy(tsk)	do { } while (0)
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
 
diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c
index 391895b54d13..49fab9e39cbf 100644
--- a/arch/nds32/kernel/process.c
+++ b/arch/nds32/kernel/process.c
@@ -233,15 +233,12 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu)
 
 EXPORT_SYMBOL(dump_fpu);
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	unsigned long fp, lr;
 	unsigned long stack_start, stack_end;
 	int count = 0;
 
-	if (!p || p == current || task_is_running(p))
-		return 0;
-
 	if (IS_ENABLED(CONFIG_FRAME_POINTER)) {
 		stack_start = (unsigned long)end_of_stack(p);
 		stack_end = (unsigned long)task_stack_page(p) + THREAD_SIZE;
@@ -258,5 +255,3 @@ unsigned long get_wchan(struct task_struct *p)
 	}
 	return 0;
 }
-
-EXPORT_SYMBOL(get_wchan);
diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h
index 94bcb86f679f..b8125dfbcad2 100644
--- a/arch/nios2/include/asm/processor.h
+++ b/arch/nios2/include/asm/processor.h
@@ -69,7 +69,7 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-extern unsigned long get_wchan(struct task_struct *p);
+extern unsigned long __get_wchan(struct task_struct *p);
 
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 9ff37ba2bb60..f8ea522a1588 100644
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -217,15 +217,12 @@ void dump(struct pt_regs *fp)
 	pr_emerg("\n\n");
 }
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	unsigned long fp, pc;
 	uns