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
  ...

4 files changed, 24 insertions, 20 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 49be8c8ef555..77cf4187adec 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -541,7 +541,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	}
 
 	if (permitted && (!whole || num_threads < 2))
-		wchan = get_wchan(task);
+		wchan = !task_is_running(task);
 	if (!whole) {
 		min_flt = task->min_flt;
 		maj_flt = task->maj_flt;
@@ -606,10 +606,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	 *
 	 * This works with older implementations of procps as well.
 	 */
-	if (wchan)
-		seq_puts(m, " 1");
-	else
-		seq_puts(m, " 0");
+	seq_put_decimal_ull(m, " ", wchan);
 
 	seq_put_decimal_ull(m, " ", 0);
 	seq_put_decimal_ull(m, " ", 0);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 533d5836eb9a..1f394095eb88 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -67,6 +67,7 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/rcupdate.h>
+#include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
 #include <linux/resource.h>
 #include <linux/module.h>
@@ -386,17 +387,19 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
 {
 	unsigned long wchan;
+	char symname[KSYM_NAME_LEN];
 
-	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
-		wchan = get_wchan(task);
-	else
-		wchan = 0;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+		goto print0;
 
-	if (wchan)
-		seq_printf(m, "%ps", (void *) wchan);
-	else
-		seq_putc(m, '0');
+	wchan = get_wchan(task);
+	if (wchan && !lookup_symbol_name(wchan, symname)) {
+		seq_puts(m, symname);
+		return 0;
+	}
 
+print0:
+	seq_putc(m, '0');
 	return 0;
 }
 #endif /* CONFIG_KALLSYMS */
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 6561a06ef905..4fb8729a68d4 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -24,7 +24,7 @@
 
 #ifdef arch_idle_time
 
-static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
+u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
 {
 	u64 idle;
 
@@ -46,7 +46,7 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
 
 #else
 
-static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
+u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
 {
 	u64 idle, idle_usecs = -1ULL;
 
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 5a1b228964fb..deb99bc9b7e6 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -12,18 +12,22 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec64 uptime;
 	struct timespec64 idle;
-	u64 nsec;
+	u64 idle_nsec;
 	u32 rem;
 	int i;
 
-	nsec = 0;
-	for_each_possible_cpu(i)
-		nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+	idle_nsec = 0;
+	for_each_possible_cpu(i) {
+		struct kernel_cpustat kcs;
+
+		kcpustat_cpu_fetch(&kcs, i);
+		idle_nsec += get_idle_time(&kcs, i);
+	}
 
 	ktime_get_boottime_ts64(&uptime);
 	timens_add_boottime(&uptime);
 
-	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+	idle.tv_sec = div_u64_rem(idle_nsec, NSEC_PER_SEC, &rem);
 	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
 			(unsigned long) uptime.tv_sec,