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
  ...

Author: torvalds

Documentation/ABI/stable/sysfs-devices-system-cpu

@@ -42,6 +42,12 @@ Description:    the CPU core ID of cpuX. Typically it is the hardware platform's
                 architecture and platform dependent.
 Values:         integer
 
+What:           /sys/devices/system/cpu/cpuX/topology/cluster_id
+Description:    the cluster ID of cpuX.  Typically it is the hardware platform's
+                identifier (rather than the kernel's). The actual value is
+                architecture and platform dependent.
+Values:         integer
+
 What:           /sys/devices/system/cpu/cpuX/topology/book_id
 Description:    the book ID of cpuX. Typically it is the hardware platform's
                 identifier (rather than the kernel's). The actual value is
@@ -85,6 +91,15 @@ Description:    human-readable list of CPUs within the same die.
                 The format is like 0-3, 8-11, 14,17.
 Values:         decimal list.
 
+What:           /sys/devices/system/cpu/cpuX/topology/cluster_cpus
+Description:    internal kernel map of CPUs within the same cluster.
+Values:         hexadecimal bitmask.
+
+What:           /sys/devices/system/cpu/cpuX/topology/cluster_cpus_list
+Description:    human-readable list of CPUs within the same cluster.
+                The format is like 0-3, 8-11, 14,17.
+Values:         decimal list.
+
 What:           /sys/devices/system/cpu/cpuX/topology/book_siblings
 Description:    internal kernel map of cpuX's hardware threads within the same
                 book_id. it's only used on s390.

Documentation/admin-guide/cgroup-v2.rst

@@ -1016,6 +1016,8 @@ All time durations are in microseconds.
 	- nr_periods
 	- nr_throttled
 	- throttled_usec
+	- nr_bursts
+	- burst_usec
 
   cpu.weight
 	A read-write single value file which exists on non-root
@@ -1047,6 +1049,12 @@ All time durations are in microseconds.
 	$PERIOD duration.  "max" for $MAX indicates no limit.  If only
 	one number is written, $MAX is updated.
 
+  cpu.max.burst
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	The burst in the range [0, $MAX].
+
   cpu.pressure
 	A read-write nested-keyed file.
 

Documentation/admin-guide/cputopology.rst

@@ -19,11 +19,13 @@ these macros in include/asm-XXX/topology.h::
 
 	#define topology_physical_package_id(cpu)
 	#define topology_die_id(cpu)
+	#define topology_cluster_id(cpu)
 	#define topology_core_id(cpu)
 	#define topology_book_id(cpu)
 	#define topology_drawer_id(cpu)
 	#define topology_sibling_cpumask(cpu)
 	#define topology_core_cpumask(cpu)
+	#define topology_cluster_cpumask(cpu)
 	#define topology_die_cpumask(cpu)
 	#define topology_book_cpumask(cpu)
 	#define topology_drawer_cpumask(cpu)
@@ -39,10 +41,12 @@ not defined by include/asm-XXX/topology.h:
 
 1) topology_physical_package_id: -1
 2) topology_die_id: -1
-3) topology_core_id: 0
-4) topology_sibling_cpumask: just the given CPU
-5) topology_core_cpumask: just the given CPU
-6) topology_die_cpumask: just the given CPU
+3) topology_cluster_id: -1
+4) topology_core_id: 0
+5) topology_sibling_cpumask: just the given CPU
+6) topology_core_cpumask: just the given CPU
+7) topology_cluster_cpumask: just the given CPU
+8) topology_die_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().

Documentation/scheduler/sched-bwc.rst

@@ -22,39 +22,90 @@ cfs_quota units at each period boundary. As threads consume this bandwidth it
 is transferred to cpu-local "silos" on a demand basis. The amount transferred
 within each of these updates is tunable and described as the "slice".
 
+Burst feature
+-------------
+This feature borrows time now against our future underrun, at the cost of
+increased interference against the other system users. All nicely bounded.
+
+Traditional (UP-EDF) bandwidth control is something like:
+
+  (U = \Sum u_i) <= 1
+
+This guaranteeds both that every deadline is met and that the system is
+stable. After all, if U were > 1, then for every second of walltime,
+we'd have to run more than a second of program time, and obviously miss
+our deadline, but the next deadline will be further out still, there is
+never time to catch up, unbounded fail.
+
+The burst feature observes that a workload doesn't always executes the full
+quota; this enables one to describe u_i as a statistical distribution.
+
+For example, have u_i = {x,e}_i, where x is the p(95) and x+e p(100)
+(the traditional WCET). This effectively allows u to be smaller,
+increasing the efficiency (we can pack more tasks in the system), but at
+the cost of missing deadlines when all the odds line up. However, it
+does maintain stability, since every overrun must be paired with an
+underrun as long as our x is above the average.
+
+That is, suppose we have 2 tasks, both specify a p(95) value, then we
+have a p(95)*p(95) = 90.25% chance both tasks are within their quota and
+everything is good. At the same time we have a p(5)p(5) = 0.25% chance
+both tasks will exceed their quota at the same time (guaranteed deadline
+fail). Somewhere in between there's a threshold where one exceeds and
+the other doesn't underrun enough to compensate; this depends on the
+specific CDFs.
+
+At the same time, we can say that the worst case deadline miss, will be
+\Sum e_i; that is, there is a bounded tardiness (under the assumption
+that x+e is indeed WCET).
+
+The interferenece when using burst is valued by the possibilities for
+missing the deadline and the average WCET. Test results showed that when
+there many cgroups or CPU is under utilized, the interference is
+limited. More details are shown in:
+https://lore.kernel.org/lkml/[email protected]/
+
 Management
 ----------
-Quota and period are managed within the cpu subsystem via cgroupfs.
+Quota, period and burst are managed within the cpu subsystem via cgroupfs.
 
 .. note::
    The cgroupfs files described in this section are only applicable
    to cgroup v1. For cgroup v2, see
    :ref:`Documentation/admin-guide/cgroup-v2.rst <cgroup-v2-cpu>`.
 
 - cpu.cfs_quota_us: the total available run-time within a period (in
-  microseconds)
+- cpu.cfs_quota_us: run-time replenished within a period (in microseconds)
 - cpu.cfs_period_us: the length of a period (in microseconds)
 - cpu.stat: exports throttling statistics [explained further below]
+- cpu.cfs_burst_us: the maximum accumulated run-time (in microseconds)
 
 The default values are::
 
 	cpu.cfs_period_us=100ms
-	cpu.cfs_quota=-1
+	cpu.cfs_quota_us=-1
+	cpu.cfs_burst_us=0
 
 A value of -1 for cpu.cfs_quota_us indicates that the group does not have any
 bandwidth restriction in place, such a group is described as an unconstrained
 bandwidth group. This represents the traditional work-conserving behavior for
 CFS.
 
-Writing any (valid) positive value(s) will enact the specified bandwidth limit.
-The minimum quota allowed for the quota or period is 1ms. There is also an
-upper bound on the period length of 1s. Additional restrictions exist when
-bandwidth limits are used in a hierarchical fashion, these are explained in
-more detail below.
+Writing any (valid) positive value(s) no smaller than cpu.cfs_burst_us will
+enact the specified bandwidth limit. The minimum quota allowed for the quota or
+period is 1ms. There is also an upper bound on the period length of 1s.
+Additional restrictions exist when bandwidth limits are used in a hierarchical
+fashion, these are explained in more detail below.
 
 Writing any negative value to cpu.cfs_quota_us will remove the bandwidth limit
 and return the group to an unconstrained state once more.
 
+A value of 0 for cpu.cfs_burst_us indicates that the group can not accumulate
+any unused bandwidth. It makes the traditional bandwidth control behavior for
+CFS unchanged. Writing any (valid) positive value(s) no larger than
+cpu.cfs_quota_us into cpu.cfs_burst_us will enact the cap on unused bandwidth
+accumulation.
+
 Any updates to a group's bandwidth specification will result in it becoming
 unthrottled if it is in a constrained state.
 
@@ -74,14 +125,17 @@ for more fine-grained consumption.
 
 Statistics
 ----------
-A group's bandwidth statistics are exported via 3 fields in cpu.stat.
+A group's bandwidth statistics are exported via 5 fields in cpu.stat.
 
 cpu.stat:
 
 - nr_periods: Number of enforcement intervals that have elapsed.
 - nr_throttled: Number of times the group has been throttled/limited.
 - throttled_time: The total time duration (in nanoseconds) for which entities
   of the group have been throttled.
+- nr_bursts: Number of periods burst occurs.
+- burst_time: Cumulative wall-time (in nanoseconds) that any CPUs has used
+  above quota in respective periods
 
 This interface is read-only.
 
@@ -179,3 +233,15 @@ Examples
 
    By using a small period here we are ensuring a consistent latency
    response at the expense of burst capacity.
+
+4. Limit a group to 40% of 1 CPU, and allow accumulate up to 20% of 1 CPU
+   additionally, in case accumulation has been done.
+
+   With 50ms period, 20ms quota will be equivalent to 40% of 1 CPU.
+   And 10ms burst will be equivalent to 20% of 1 CPU.
+
+	# echo 20000 > cpu.cfs_quota_us /* quota = 20ms */
+	# echo 50000 > cpu.cfs_period_us /* period = 50ms */
+	# echo 10000 > cpu.cfs_burst_us /* burst = 10ms */
+
+   Larger buffer setting (no larger than quota) allows greater burst capacity.

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)
 

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

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__ */
 

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);
 }

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)

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);