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
  ...

1 files changed, 48 insertions, 47 deletions

diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 291b857a6e20..5683ac0d2566 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -13,7 +13,6 @@
 #include "core.h"
 #include "patch.h"
 #include "transition.h"
-#include "../sched/sched.h"
 
 #define MAX_STACK_ENTRIES  100
 #define STACK_ERR_BUF_SIZE 128
@@ -240,7 +239,7 @@ static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
  * Determine whether it's safe to transition the task to the target patch state
  * by looking for any to-be-patched or to-be-unpatched functions on its stack.
  */
-static int klp_check_stack(struct task_struct *task, char *err_buf)
+static int klp_check_stack(struct task_struct *task, const char **oldname)
 {
 	static unsigned long entries[MAX_STACK_ENTRIES];
 	struct klp_object *obj;
@@ -248,12 +247,8 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
 	int ret, nr_entries;
 
 	ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
-	if (ret < 0) {
-		snprintf(err_buf, STACK_ERR_BUF_SIZE,
-			 "%s: %s:%d has an unreliable stack\n",
-			 __func__, task->comm, task->pid);
-		return ret;
-	}
+	if (ret < 0)
+		return -EINVAL;
 	nr_entries = ret;
 
 	klp_for_each_object(klp_transition_patch, obj) {
@@ -262,11 +257,8 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
 		klp_for_each_func(obj, func) {
 			ret = klp_check_stack_func(func, entries, nr_entries);
 			if (ret) {
-				snprintf(err_buf, STACK_ERR_BUF_SIZE,
-					 "%s: %s:%d is sleeping on function %s\n",
-					 __func__, task->comm, task->pid,
-					 func->old_name);
-				return ret;
+				*oldname = func->old_name;
+				return -EADDRINUSE;
 			}
 		}
 	}
@@ -274,6 +266,22 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
 	return 0;
 }
 
+static int klp_check_and_switch_task(struct task_struct *task, void *arg)
+{
+	int ret;
+
+	if (task_curr(task) && task != current)
+		return -EBUSY;
+
+	ret = klp_check_stack(task, arg);
+	if (ret)
+		return ret;
+
+	clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
+	task->patch_state = klp_target_state;
+	return 0;
+}
+
 /*
  * Try to safely switch a task to the target patch state.  If it's currently
  * running, or it's sleeping on a to-be-patched or to-be-unpatched function, or
@@ -281,13 +289,8 @@ static int klp_check_stack(struct task_struct *task, char *err_buf)
  */
 static bool klp_try_switch_task(struct task_struct *task)
 {
-	static char err_buf[STACK_ERR_BUF_SIZE];
-	struct rq *rq;
-	struct rq_flags flags;
+	const char *old_name;
 	int ret;
-	bool success = false;
-
-	err_buf[0] = '\0';
 
 	/* check if this task has already switched over */
 	if (task->patch_state == klp_target_state)
@@ -305,36 +308,31 @@ static bool klp_try_switch_task(struct task_struct *task)
 	 * functions.  If all goes well, switch the task to the target patch
 	 * state.
 	 */
-	rq = task_rq_lock(task, &flags);
+	ret = task_call_func(task, klp_check_and_switch_task, &old_name);
+	switch (ret) {
+	case 0:		/* success */
+		break;
 
-	if (task_running(rq, task) && task != current) {
-		snprintf(err_buf, STACK_ERR_BUF_SIZE,
-			 "%s: %s:%d is running\n", __func__, task->comm,
-			 task->pid);
-		goto done;
+	case -EBUSY:	/* klp_check_and_switch_task() */
+		pr_debug("%s: %s:%d is running\n",
+			 __func__, task->comm, task->pid);
+		break;
+	case -EINVAL:	/* klp_check_and_switch_task() */
+		pr_debug("%s: %s:%d has an unreliable stack\n",
+			 __func__, task->comm, task->pid);
+		break;
+	case -EADDRINUSE: /* klp_check_and_switch_task() */
+		pr_debug("%s: %s:%d is sleeping on function %s\n",
+			 __func__, task->comm, task->pid, old_name);
+		break;
+
+	default:
+		pr_debug("%s: Unknown error code (%d) when trying to switch %s:%d\n",
+			 __func__, ret, task->comm, task->pid);
+		break;
 	}
 
-	ret = klp_check_stack(task, err_buf);
-	if (ret)
-		goto done;
-
-	success = true;
-
-	clear_tsk_thread_flag(task, TIF_PATCH_PENDING);
-	task->patch_state = klp_target_state;
-
-done:
-	task_rq_unlock(rq, task, &flags);
-
-	/*
-	 * Due to console deadlock issues, pr_debug() can't be used while
-	 * holding the task rq lock.  Instead we have to use a temporary buffer
-	 * and print the debug message after releasing the lock.
-	 */
-	if (err_buf[0] != '\0')
-		pr_debug("%s", err_buf);
-
-	return success;
+	return !ret;
 }
 
 /*
@@ -415,8 +413,11 @@ void klp_try_complete_transition(void)
 	for_each_possible_cpu(cpu) {
 		task = idle_task(cpu);
 		if (cpu_online(cpu)) {
-			if (!klp_try_switch_task(task))
+			if (!klp_try_switch_task(task)) {
 				complete = false;
+				/* Make idle task go through the main loop. */
+				wake_up_if_idle(cpu);
+			}
 		} else if (task->patch_state != klp_target_state) {
 			/* offline idle tasks can be switched immediately */
 			clear_tsk_thread_flag(task, TIF_PATCH_PENDING);