Merge tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Clean up SCHED_DEBUG: move the decades old mess of sysctl, procfs and
   debugfs interfaces to a unified debugfs interface.

 - Signals: Allow caching one sigqueue object per task, to improve
   performance & latencies.

 - Improve newidle_balance() irq-off latencies on systems with a large
   number of CPU cgroups.

 - Improve energy-aware scheduling

 - Improve the PELT metrics for certain workloads

 - Reintroduce select_idle_smt() to improve load-balancing locality -
   but without the previous regressions

 - Add 'scheduler latency debugging': warn after long periods of pending
   need_resched. This is an opt-in feature that requires the enabling of
   the LATENCY_WARN scheduler feature, or the use of the
   resched_latency_warn_ms=xx boot parameter.

 - CPU hotplug fixes for HP-rollback, and for the 'fail' interface. Fix
   remaining balance_push() vs. hotplug holes/races

 - PSI fixes, plus allow /proc/pressure/ files to be written by
   CAP_SYS_RESOURCE tasks as well

 - Fix/improve various load-balancing corner cases vs. capacity margins

 - Fix sched topology on systems with NUMA diameter of 3 or above

 - Fix PF_KTHREAD vs to_kthread() race

 - Minor rseq optimizations

 - Misc cleanups, optimizations, fixes and smaller updates

* tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  cpumask/hotplug: Fix cpu_dying() state tracking
  kthread: Fix PF_KTHREAD vs to_kthread() race
  sched/debug: Fix cgroup_path[] serialization
  sched,psi: Handle potential task count underflow bugs more gracefully
  sched: Warn on long periods of pending need_resched
  sched/fair: Move update_nohz_stats() to the CONFIG_NO_HZ_COMMON block to simplify the code & fix an unused function warning
  sched/debug: Rename the sched_debug parameter to sched_verbose
  sched,fair: Alternative sched_slice()
  sched: Move /proc/sched_debug to debugfs
  sched,debug: Convert sysctl sched_domains to debugfs
  debugfs: Implement debugfs_create_str()
  sched,preempt: Move preempt_dynamic to debug.c
  sched: Move SCHED_DEBUG sysctl to debugfs
  sched: Don't make LATENCYTOP select SCHED_DEBUG
  sched: Remove sched_schedstats sysctl out from under SCHED_DEBUG
  sched/numa: Allow runtime enabling/disabling of NUMA balance without SCHED_DEBUG
  sched: Use cpu_dying() to fix balance_push vs hotplug-rollback
  cpumask: Introduce DYING mask
  cpumask: Make cpu_{online,possible,present,active}() inline
  rseq: Optimise rseq_get_rseq_cs() and clear_rseq_cs()
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -4754,7 +4754,7 @@
 
 	sbni=		[NET] Granch SBNI12 leased line adapter
 
-	sched_debug	[KNL] Enables verbose scheduler debug messages.
+	sched_verbose	[KNL] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
 			Allowed values are enable and disable. This feature

Documentation/scheduler/sched-domains.rst

@@ -74,8 +74,8 @@ for a given topology level by creating a sched_domain_topology_level array and
 calling set_sched_topology() with this array as the parameter.
 
 The sched-domains debugging infrastructure can be enabled by enabling
-CONFIG_SCHED_DEBUG and adding 'sched_debug' to your cmdline. If you forgot to
-tweak your cmdline, you can also flip the /sys/kernel/debug/sched_debug
-knob. This enables an error checking parse of the sched domains which should
-catch most possible errors (described above). It also prints out the domain
-structure in a visual format.
+CONFIG_SCHED_DEBUG and adding 'sched_debug_verbose' to your cmdline. If you
+forgot to tweak your cmdline, you can also flip the
+/sys/kernel/debug/sched/verbose knob. This enables an error checking parse of
+the sched domains which should catch most possible errors (described above). It
+also prints out the domain structure in a visual format.

drivers/usb/usbip/usbip_common.h

@@ -18,6 +18,7 @@
 #include <linux/usb.h>
 #include <linux/wait.h>
 #include <linux/sched/task.h>
+#include <linux/kcov.h>
 #include <uapi/linux/usbip.h>
 
 #undef pr_fmt

fs/debugfs/file.c

@@ -864,6 +864,97 @@ struct dentry *debugfs_create_bool(const char *name, umode_t mode,
 }
 EXPORT_SYMBOL_GPL(debugfs_create_bool);
 
+ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	struct dentry *dentry = F_DENTRY(file);
+	char *str, *copy = NULL;
+	int copy_len, len;
+	ssize_t ret;
+
+	ret = debugfs_file_get(dentry);
+	if (unlikely(ret))
+		return ret;
+
+	str = *(char **)file->private_data;
+	len = strlen(str) + 1;
+	copy = kmalloc(len, GFP_KERNEL);
+	if (!copy) {
+		debugfs_file_put(dentry);
+		return -ENOMEM;
+	}
+
+	copy_len = strscpy(copy, str, len);
+	debugfs_file_put(dentry);
+	if (copy_len < 0) {
+		kfree(copy);
+		return copy_len;
+	}
+
+	copy[copy_len] = '\n';
+
+	ret = simple_read_from_buffer(user_buf, count, ppos, copy, copy_len);
+	kfree(copy);
+
+	return ret;
+}
+
+static ssize_t debugfs_write_file_str(struct file *file, const char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	/* This is really only for read-only strings */
+	return -EINVAL;
+}
+
+static const struct file_operations fops_str = {
+	.read =		debugfs_read_file_str,
+	.write =	debugfs_write_file_str,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static const struct file_operations fops_str_ro = {
+	.read =		debugfs_read_file_str,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static const struct file_operations fops_str_wo = {
+	.write =	debugfs_write_file_str,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+/**
+ * debugfs_create_str - create a debugfs file that is used to read and write a string value
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          file will be created in the root of the debugfs filesystem.
+ * @value: a pointer to the variable that the file should read to and write
+ *         from.
+ *
+ * This function creates a file in debugfs with the given name that
+ * contains the value of the variable @value.  If the @mode variable is so
+ * set, it can be read from, and written to.
+ *
+ * This function will return a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the debugfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here.)  If an error occurs, ERR_PTR(-ERROR) will be
+ * returned.
+ *
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
+ * be returned.
+ */
+void debugfs_create_str(const char *name, umode_t mode,
+			struct dentry *parent, char **value)
+{
+	debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str,
+				   &fops_str_ro, &fops_str_wo);
+}
+
 static ssize_t read_file_blob(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos)
 {

include/linux/cpumask.h

@@ -91,44 +91,15 @@ extern struct cpumask __cpu_possible_mask;
 extern struct cpumask __cpu_online_mask;
 extern struct cpumask __cpu_present_mask;
 extern struct cpumask __cpu_active_mask;
+extern struct cpumask __cpu_dying_mask;
 #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
 #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
 #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
 #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
+#define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
 
 extern atomic_t __num_online_cpus;
 
-#if NR_CPUS > 1
-/**
- * num_online_cpus() - Read the number of online CPUs
- *
- * Despite the fact that __num_online_cpus is of type atomic_t, this
- * interface gives only a momentary snapshot and is not protected against
- * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
- * region.
- */
-static inline unsigned int num_online_cpus(void)
-{
-	return atomic_read(&__num_online_cpus);
-}
-#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
-#define num_present_cpus()	cpumask_weight(cpu_present_mask)
-#define num_active_cpus()	cpumask_weight(cpu_active_mask)
-#define cpu_online(cpu)		cpumask_test_cpu((cpu), cpu_online_mask)
-#define cpu_possible(cpu)	cpumask_test_cpu((cpu), cpu_possible_mask)
-#define cpu_present(cpu)	cpumask_test_cpu((cpu), cpu_present_mask)
-#define cpu_active(cpu)		cpumask_test_cpu((cpu), cpu_active_mask)
-#else
-#define num_online_cpus()	1U
-#define num_possible_cpus()	1U
-#define num_present_cpus()	1U
-#define num_active_cpus()	1U
-#define cpu_online(cpu)		((cpu) == 0)
-#define cpu_possible(cpu)	((cpu) == 0)
-#define cpu_present(cpu)	((cpu) == 0)
-#define cpu_active(cpu)		((cpu) == 0)
-#endif
-
 extern cpumask_t cpus_booted_once_mask;
 
 static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
@@ -857,6 +828,14 @@ set_cpu_active(unsigned int cpu, bool active)
 		cpumask_clear_cpu(cpu, &__cpu_active_mask);
 }
 
+static inline void
+set_cpu_dying(unsigned int cpu, bool dying)
+{
+	if (dying)
+		cpumask_set_cpu(cpu, &__cpu_dying_mask);
+	else
+		cpumask_clear_cpu(cpu, &__cpu_dying_mask);
+}
 
 /**
  * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
@@ -894,6 +873,82 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 	return to_cpumask(p);
 }
 
+#if NR_CPUS > 1
+/**
+ * num_online_cpus() - Read the number of online CPUs
+ *
+ * Despite the fact that __num_online_cpus is of type atomic_t, this
+ * interface gives only a momentary snapshot and is not protected against
+ * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
+ * region.
+ */
+static inline unsigned int num_online_cpus(void)
+{
+	return atomic_read(&__num_online_cpus);
+}
+#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
+#define num_present_cpus()	cpumask_weight(cpu_present_mask)
+#define num_active_cpus()	cpumask_weight(cpu_active_mask)
+
+static inline bool cpu_online(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_online_mask);
+}
+
+static inline bool cpu_possible(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_possible_mask);
+}
+
+static inline bool cpu_present(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_present_mask);
+}
+
+static inline bool cpu_active(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_active_mask);
+}
+
+static inline bool cpu_dying(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_dying_mask);
+}
+
+#else
+
+#define num_online_cpus()	1U
+#define num_possible_cpus()	1U
+#define num_present_cpus()	1U
+#define num_active_cpus()	1U
+
+static inline bool cpu_online(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
+static inline bool cpu_possible(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
+static inline bool cpu_present(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
+static inline bool cpu_active(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
+static inline bool cpu_dying(unsigned int cpu)
+{
+	return false;
+}
+
+#endif /* NR_CPUS > 1 */
+
 #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
 
 #if NR_CPUS <= BITS_PER_LONG

include/linux/debugfs.h

@@ -128,6 +128,8 @@ void debugfs_create_atomic_t(const char *name, umode_t mode,
 			     struct dentry *parent, atomic_t *value);
 struct dentry *debugfs_create_bool(const char *name, umode_t mode,
 				  struct dentry *parent, bool *value);
+void debugfs_create_str(const char *name, umode_t mode,
+			struct dentry *parent, char **value);
 
 struct dentry *debugfs_create_blob(const char *name, umode_t mode,
 				  struct dentry *parent,
@@ -156,6 +158,9 @@ ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf,
 ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 				size_t count, loff_t *ppos);
 
+ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos);
+
 #else
 
 #include <linux/err.h>
@@ -297,6 +302,11 @@ static inline struct dentry *debugfs_create_bool(const char *name, umode_t mode,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline void debugfs_create_str(const char *name, umode_t mode,
+				      struct dentry *parent,
+				      char **value)
+{ }
+
 static inline struct dentry *debugfs_create_blob(const char *name, umode_t mode,
 				  struct dentry *parent,
 				  struct debugfs_blob_wrapper *blob)
@@ -348,6 +358,13 @@ static inline ssize_t debugfs_write_file_bool(struct file *file,
 	return -ENODEV;
 }
 
+static inline ssize_t debugfs_read_file_str(struct file *file,
+					    char __user *user_buf,
+					    size_t count, loff_t *ppos)
+{
+	return -ENODEV;
+}
+
 #endif
 
 /**

include/linux/kcov.h

@@ -2,6 +2,7 @@
 #ifndef _LINUX_KCOV_H
 #define _LINUX_KCOV_H
 
+#include <linux/sched.h>
 #include <uapi/linux/kcov.h>
 
 struct task_struct;

include/linux/psi.h

@@ -20,7 +20,6 @@ void psi_task_change(struct task_struct *task, int clear, int set);
 void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		     bool sleep);
 
-void psi_memstall_tick(struct task_struct *task, int cpu);
 void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 

include/linux/psi_types.h

@@ -50,9 +50,10 @@ enum psi_states {
 	PSI_MEM_SOME,
 	PSI_MEM_FULL,
 	PSI_CPU_SOME,
+	PSI_CPU_FULL,
 	/* Only per-CPU, to weigh the CPU in the global average: */
 	PSI_NONIDLE,
-	NR_PSI_STATES = 6,
+	NR_PSI_STATES = 7,
 };
 
 enum psi_aggregators {

include/linux/sched.h

@@ -14,7 +14,6 @@
 #include <linux/pid.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
-#include <linux/kcov.h>
 #include <linux/mutex.h>
 #include <linux/plist.h>
 #include <linux/hrtimer.h>
@@ -985,6 +984,7 @@ struct task_struct {
 	/* Signal handlers: */
 	struct signal_struct		*signal;
 	struct sighand_struct __rcu		*sighand;
+	struct sigqueue			*sigqueue_cache;
 	sigset_t			blocked;
 	sigset_t			real_blocked;
 	/* Restored if set_restore_sigmask() was used: */
@@ -1101,7 +1101,7 @@ struct task_struct {
 #ifdef CONFIG_CPUSETS
 	/* Protected by ->alloc_lock: */
 	nodemask_t			mems_allowed;
-	/* Seqence number to catch updates: */
+	/* Sequence number to catch updates: */
 	seqcount_spinlock_t		mems_allowed_seq;
 	int				cpuset_mem_spread_rotor;
 	int				cpuset_slab_spread_rotor;

include/linux/sched/sysctl.h

@@ -26,10 +26,11 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
 enum { sysctl_hung_task_timeout_secs = 0 };
 #endif
 
+extern unsigned int sysctl_sched_child_runs_first;
+
 extern unsigned int sysctl_sched_latency;
 extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
-extern unsigned int sysctl_sched_child_runs_first;
 
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
@@ -37,7 +38,7 @@ enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_LINEAR,
 	SCHED_TUNABLESCALING_END,
 };
-extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+extern unsigned int sysctl_sched_tunable_scaling;
 
 extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
@@ -48,8 +49,8 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 extern __read_mostly unsigned int sysctl_sched_migration_cost;
 extern __read_mostly unsigned int sysctl_sched_nr_migrate;
 
-int sched_proc_update_handler(struct ctl_table *table, int write,
-		void *buffer, size_t *length, loff_t *ppos);
+extern int sysctl_resched_latency_warn_ms;
+extern int sysctl_resched_latency_warn_once;
 #endif
 
 /*

include/linux/signal.h

@@ -266,6 +266,7 @@ static inline void init_sigpending(struct sigpending *sig)
 }
 
 extern void flush_sigqueue(struct sigpending *queue);
+extern void exit_task_sigqueue_cache(struct task_struct *tsk);
 
 /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
 static inline int valid_signal(unsigned long sig)

include/uapi/linux/ptrace.h

@@ -102,6 +102,16 @@ struct ptrace_syscall_info {
 	};
 };
 
+#define PTRACE_GET_RSEQ_CONFIGURATION	0x420f
+
+struct ptrace_rseq_configuration {
+	__u64 rseq_abi_pointer;
+	__u32 rseq_abi_size;
+	__u32 signature;
+	__u32 flags;
+	__u32 pad;
+};
+
 /*
  * These values are stored in task->ptrace_message
  * by tracehook_report_syscall_* to describe the current syscall-stop.

kernel/cpu.c

@@ -63,6 +63,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	int			cpu;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
@@ -135,6 +136,11 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
 	return cpuhp_hp_states + state;
 }
 
+static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step)
+{
+	return bringup ? !step->startup.single : !step->teardown.single;
+}
+
 /**
  * cpuhp_invoke_callback _ Invoke the callbacks for a given state
  * @cpu:	The cpu for which the callback should be invoked
@@ -157,26 +163,24 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
 
 	if (st->fail == state) {
 		st->fail = CPUHP_INVALID;
-
-		if (!(bringup ? step->startup.single : step->teardown.single))
-			return 0;
-
 		return -EAGAIN;
 	}
 
+	if (cpuhp_step_empty(bringup, step)) {
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
 	if (!step->multi_instance) {
 		WARN_ON_ONCE(lastp && *lastp);
 		cb = bringup ? step->startup.single : step->teardown.single;
-		if (!cb)
-			return 0;
+
 		trace_cpuhp_enter(cpu, st->target, state, cb);
 		ret = cb(cpu);
 		trace_cpuhp_exit(cpu, st->state, state, ret);
 		return ret;
 	}
 	cbm = bringup ? step->startup.multi : step->teardown.multi;
-	if (!cbm)
-		return 0;
 
 	/* Single invocation for instance add/remove */
 	if (node) {
@@ -461,13 +465,16 @@ static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {
 	enum cpuhp_state prev_state = st->state;
+	bool bringup = st->state < target;
 
 	st->rollback = false;
 	st->last = NULL;
 
 	st->target = target;
 	st->single = false;
-	st->bringup = st->state < target;
+	st->bringup = bringup;
+	if (cpu_dying(st->cpu) != !bringup)
+		set_cpu_dying(st->cpu, !bringup);
 
 	return prev_state;
 }
@@ -475,6 +482,17 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 static inline void
 cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
 {
+	bool bringup = !st->bringup;
+
+	st->target = prev_state;
+
+	/*
+	 * Already rolling back. No need invert the bringup value or to change
+	 * the current state.
+	 */
+	if (st->rollback)
+		return;
+
 	st->rollback = true;
 
 	/*
@@ -488,8 +506,9 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
 			st->state++;
 	}
 
-	st->target = prev_state;
-	st->bringup = !st->bringup;
+	st->bringup = bringup;
+	if (cpu_dying(st->cpu) != !bringup)
+		set_cpu_dying(st->cpu, !bringup);
 }
 
 /* Regular hotplug invocation of the AP hotplug thread */
@@ -591,10 +610,53 @@ static int finish_cpu(unsigned int cpu)
  * Hotplug state machine related functions
  */
 
-static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
+/*
+ * Get the next state to run. Empty ones will be skipped. Returns true if a
+ * state must be run.
+ *
+ * st->state will be modified ahead of time, to match state_to_run, as if it
+ * has already ran.
+ */
+static bool cpuhp_next_state(bool bringup,
+			     enum cpuhp_state *state_to_run,
+			     struct cpuhp_cpu_state *st,
+			     enum cpuhp_state target)
+{
+	do {
+		if (bringup) {
+			if (st->state >= target)
+				return false;
+
+			*state_to_run = ++st->state;
+		} else {
+			if (st->state <= target)
+				return false;
+
+			*state_to_run = st->state--;
+		}
+
+		if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run)))
+			break;
+	} while (true);
+
+	return true;
+}
+
+static int cpuhp_invoke_callback_range(bool bringup,
+				       unsigned int cpu,
+				       struct cpuhp_cpu_state *st,
+				       enum cpuhp_state target)
 {
-	for (st->state--; st->state > st->target; st->state--)
-		cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
+	enum cpuhp_state state;
+	int err = 0;
+
+	while (cpuhp_next_state(bringup, &state, st, target)) {
+		err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL);
+		if (err)
+			break;
+	}
+
+	return err;
 }
 
 static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
@@ -617,16 +679,12 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
 	enum cpuhp_state prev_state = st->state;
 	int ret = 0;
 
-	while (st->state < target) {
-		st->state++;
-		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
-		if (ret) {
-			if (can_rollback_cpu(st)) {
-				st->target = prev_state;
-				undo_cpu_up(cpu, st);
-			}
-			break;
-		}
+	ret = cpuhp_invoke_callback_range(true, cpu, st, target);
+	if (ret) {
+		cpuhp_reset_state(st, prev_state);
+		if (can_rollback_cpu(st))
+			WARN_ON(cpuhp_invoke_callback_range(false, cpu, st,
+							    prev_state));
 	}
 	return ret;
 }
@@ -640,6 +698,7 @@ static void cpuhp_create(unsigned int cpu)
 
 	init_completion(&st->done_up);
 	init_completion(&st->done_down);
+	st->cpu = cpu;
 }
 
 static int cpuhp_should_run(unsigned int cpu)
@@ -690,17 +749,9 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		state = st->cb_state;
 		st->should_run = false;
 	} else {
-		if (bringup) {
-			st->state++;
-			state = st->state;
-			st->should_run = (st->state < st->target);
-			WARN_ON_ONCE(st->state > st->target);
-		} else {
-			state = st->state;
-			st->state--;
-			st->should_run = (st->state > st->target);
-			WARN_ON_ONCE(st->state < st->target);
-		}
+		st->should_run = cpuhp_next_state(bringup, &state, st, st->target);
+		if (!st->should_run)
+			goto end;
 	}
 
 	WARN_ON_ONCE(!cpuhp_is_ap_state(state));
@@ -728,6 +779,7 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		st->should_run = false;
 	}
 
+end:
 	cpuhp_lock_release(bringup);
 	lockdep_release_cpus_lock();
 
@@ -881,19 +933,18 @@ static int take_cpu_down(void *_param)
 		return err;
 
 	/*
-	 * We get here while we are in CPUHP_TEARDOWN_CPU state and we must not
-	 * do this step again.
+	 * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going
+	 * down, that the current state is CPUHP_TEARDOWN_CPU - 1.
 	 */
-	WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
-	st->state--;
+	WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1));
+
 	/* Invoke the former CPU_DYING callbacks */
-	for (; st->state > target; st->state--) {
-		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
-		/*
-		 * DYING must not fail!
-		 */
-		WARN_ON_ONCE(ret);
-	}
+	ret = cpuhp_invoke_callback_range(false, cpu, st, target);
+
+	/*
+	 * DYING must not fail!
+	 */
+	WARN_ON_ONCE(ret);
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
@@ -975,27 +1026,22 @@ void cpuhp_report_idle_dead(void)
 				 cpuhp_complete_idle_dead, st, 0);
 }
 
-static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
-	for (st->state++; st->state < st->target; st->state++)
-		cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
-}
-
 static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
 				enum cpuhp_state target)
 {
 	enum cpuhp_state prev_state = st->state;
 	int ret = 0;
 
-	for (; st->state > target; st->state--) {
-		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
-		if (ret) {
-			st->target = prev_state;
-			if (st->state < prev_state)
-				undo_cpu_down(cpu, st);
-			break;
-		}
+	ret = cpuhp_invoke_callback_range(false, cpu, st, target);
+	if (ret) {
+
+		cpuhp_reset_state(st, prev_state);
+
+		if (st->state < prev_state)
+			WARN_ON(cpuhp_invoke_callback_range(true, cpu, st,
+							    prev_state));
 	}
+
 	return ret;
 }
 
@@ -1045,9 +1091,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	 * to do the further cleanups.
 	 */
 	ret = cpuhp_down_callbacks(cpu, st, target);
-	if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) {
-		cpuhp_reset_state(st, prev_state);
-		__cpuhp_kick_ap(st);
+	if (ret && st->state < prev_state) {
+		if (st->state == CPUHP_TEARDOWN_CPU) {
+			cpuhp_reset_state(st, prev_state);
+			__cpuhp_kick_ap(st);
+		} else {
+			WARN(1, "DEAD callback error for CPU%d", cpu);
+		}
 	}
 
 out:
@@ -1164,14 +1214,12 @@ void notify_cpu_starting(unsigned int cpu)
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
 	cpumask_set_cpu(cpu, &cpus_booted_once_mask);
-	while (st->state < target) {
-		st->state++;
-		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
-		/*
-		 * STARTING must not fail!
-		 */
-		WARN_ON_ONCE(ret);
-	}
+	ret = cpuhp_invoke_callback_range(true, cpu, st, target);
+
+	/*
+	 * STARTING must not fail!
+	 */
+	WARN_ON_ONCE(ret);
 }
 
 /*
@@ -1777,8 +1825,7 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
 	 * If there's nothing to do, we done.
 	 * Relies on the union for multi_instance.
 	 */
-	if ((bringup && !sp->startup.single) ||
-	    (!bringup && !sp->teardown.single))
+	if (cpuhp_step_empty(bringup, sp))
 		return 0;
 	/*
 	 * The non AP bound callbacks can fail on bringup. On teardown
@@ -2207,6 +2254,11 @@ static ssize_t write_cpuhp_fail(struct device *dev,
 	if (ret)
 		return ret;
 
+	if (fail == CPUHP_INVALID) {
+		st->fail = fail;
+		return count;
+	}
+
 	if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE)
 		return -EINVAL;
 
@@ -2216,6 +2268,15 @@ static ssize_t write_cpuhp_fail(struct device *dev,
 	if (cpuhp_is_atomic_state(fail))
 		return -EINVAL;
 
+	/*
+	 * DEAD callbacks cannot fail...
+	 * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter
+	 * triggering STARTING callbacks, a failure in this state would
+	 * hinder rollback.
+	 */
+	if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU)
+		return -EINVAL;
+
 	/*
 	 * Cannot fail anything that doesn't have callbacks.
 	 */
@@ -2460,6 +2521,9 @@ EXPORT_SYMBOL(__cpu_present_mask);
 struct cpumask __cpu_active_mask __read_mostly;
 EXPORT_SYMBOL(__cpu_active_mask);
 
+struct cpumask __cpu_dying_mask __read_mostly;
+EXPORT_SYMBOL(__cpu_dying_mask);
+
 atomic_t __num_online_cpus __read_mostly;
 EXPORT_SYMBOL(__num_online_cpus);
 

kernel/exit.c

@@ -162,6 +162,7 @@ static void __exit_signal(struct task_struct *tsk)
 		flush_sigqueue(&sig->shared_pending);
 		tty_kref_put(tty);
 	}
+	exit_task_sigqueue_cache(tsk);
 }
 
 static void delayed_put_task_struct(struct rcu_head *rhp)

kernel/fork.c

@@ -2009,6 +2009,7 @@ static __latent_entropy struct task_struct *copy_process(
 	spin_lock_init(&p->alloc_lock);
 
 	init_sigpending(&p->pending);
+	p->sigqueue_cache = NULL;
 
 	p->utime = p->stime = p->gtime = 0;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME

kernel/kthread.c

@@ -84,6 +84,25 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 	return (__force void *)k->set_child_tid;
 }
 
+/*
+ * Variant of to_kthread() that doesn't assume @p is a kthread.
+ *
+ * Per construction; when:
+ *
+ *   (p->flags & PF_KTHREAD) && p->set_child_tid
+ *
+ * the task is both a kthread and struct kthread is persistent. However
+ * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and
+ * begin_new_exec()).
+ */
+static inline struct kthread *__to_kthread(struct task_struct *p)
+{
+	void *kthread = (__force void *)p->set_child_tid;
+	if (kthread && !(p->flags & PF_KTHREAD))
+		kthread = NULL;
+	return kthread;
+}
+
 void free_kthread_struct(struct task_struct *k)
 {
 	struct kthread *kthread;
@@ -168,8 +187,9 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
  */
 void *kthread_func(struct task_struct *task)
 {
-	if (task->flags & PF_KTHREAD)
-		return to_kthread(task)->threadfn;
+	struct kthread *kthread = __to_kthread(task);
+	if (kthread)
+		return kthread->threadfn;
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(kthread_func);
@@ -199,10 +219,11 @@ EXPORT_SYMBOL_GPL(kthread_data);
  */
 void *kthread_probe_data(struct task_struct *task)
 {
-	struct kthread *kthread = to_kthread(task);
+	struct kthread *kthread = __to_kthread(task);
 	void *data = NULL;
 
-	copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
+	if (kthread)
+		copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
 	return data;
 }
 
@@ -514,9 +535,9 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
 	set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
 }
 
-bool kthread_is_per_cpu(struct task_struct *k)
+bool kthread_is_per_cpu(struct task_struct *p)
 {
-	struct kthread *kthread = to_kthread(k);
+	struct kthread *kthread = __to_kthread(p);
 	if (!kthread)
 		return false;
 

kernel/ptrace.c

@@ -31,6 +31,7 @@
 #include <linux/cn_proc.h>
 #include <linux/compat.h>
 #include <linux/sched/signal.h>
+#include <linux/minmax.h>
 
 #include <asm/syscall.h>	/* for syscall_get_* */
 
@@ -779,6 +780,24 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 	return ret;
 }
 
+#ifdef CONFIG_RSEQ
+static long ptrace_get_rseq_configuration(struct task_struct *task,
+					  unsigned long size, void __user *data)
+{
+	struct ptrace_rseq_configuration conf = {
+		.rseq_abi_pointer = (u64)(uintptr_t)task->rseq,
+		.rseq_abi_size = sizeof(*task->rseq),
+		.signature = task->rseq_sig,
+		.flags = 0,
+	};
+
+	size = min_t(unsigned long, size, sizeof(conf));
+	if (copy_to_user(data, &conf, size))
+		return -EFAULT;
+	return sizeof(conf);
+}
+#endif
+
 #ifdef PTRACE_SINGLESTEP
 #define is_singlestep(request)		((request) == PTRACE_SINGLESTEP)
 #else
@@ -1222,6 +1241,12 @@ int ptrace_request(struct task_struct *child, long request,
 		ret = seccomp_get_metadata(child, addr, datavp);
 		break;
 
+#ifdef CONFIG_RSEQ
+	case PTRACE_GET_RSEQ_CONFIGURATION:
+		ret = ptrace_get_rseq_configuration(child, addr, datavp);
+		break;
+#endif
+
 	default:
 		break;
 	}

kernel/rseq.c

@@ -84,13 +84,20 @@
 static int rseq_update_cpu_id(struct task_struct *t)
 {
 	u32 cpu_id = raw_smp_processor_id();
+	struct rseq __user *rseq = t->rseq;
 
-	if (put_user(cpu_id, &t->rseq->cpu_id_start))
-		return -EFAULT;
-	if (put_user(cpu_id, &t->rseq->cpu_id))
-		return -EFAULT;
+	if (!user_write_access_begin(rseq, sizeof(*rseq)))
+		goto efault;
+	unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end);
+	unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end);
+	user_write_access_end();
 	trace_rseq_update(t);
 	return 0;
+
+efault_end:
+	user_write_access_end();
+efault:
+	return -EFAULT;
 }
 
 static int rseq_reset_rseq_cpu_id(struct task_struct *t)
@@ -120,8 +127,13 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	u32 sig;
 	int ret;
 
+#ifdef CONFIG_64BIT
+	if (get_user(ptr, &t->rseq->rseq_cs.ptr64))
+		return -EFAULT;
+#else
 	if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
 		return -EFAULT;
+#endif
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
@@ -204,9 +216,13 @@ static int clear_rseq_cs(struct task_struct *t)
 	 *
 	 * Set rseq_cs to NULL.
 	 */
+#ifdef CONFIG_64BIT
+	return put_user(0UL, &t->rseq->rseq_cs.ptr64);
+#else
 	if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
 		return -EFAULT;
 	return 0;
+#endif
 }
 
 /*
@@ -266,8 +282,6 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 
 	if (unlikely(t->flags & PF_EXITING))
 		return;
-	if (unlikely(!access_ok(t->rseq, sizeof(*t->rseq))))
-		goto error;
 	ret = rseq_ip_fixup(regs);
 	if (unlikely(ret < 0))
 		goto error;
@@ -294,8 +308,7 @@ void rseq_syscall(struct pt_regs *regs)
 
 	if (!t->rseq)
 		return;
-	if (!access_ok(t->rseq, sizeof(*t->rseq)) ||
-	    rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs))
+	if (rseq_get_rseq_cs(t, &rseq_cs) || in_rseq_cs(ip, &rseq_cs))
 		force_sig(SIGSEGV);
 }
 

kernel/sched/clock.c

@@ -41,7 +41,7 @@
  * Otherwise it tries to create a semi stable clock from a mixture of other
  * clocks, including:
  *
- *  - GTOD (clock monotomic)
+ *  - GTOD (clock monotonic)
  *  - sched_clock()
  *  - explicit idle events
  *

kernel/sched/cpuacct.c

@@ -104,7 +104,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
 
 	/*
 	 * We allow index == CPUACCT_STAT_NSTATS here to read
-	 * the sum of suages.
+	 * the sum of usages.
 	 */
 	BUG_ON(index > CPUACCT_STAT_NSTATS);
 

kernel/sched/cpufreq_schedutil.c

@@ -466,7 +466,7 @@ static void sugov_work(struct kthread_work *work)
 
 	/*
 	 * Hold sg_policy->update_lock shortly to handle the case where:
-	 * incase sg_policy->next_freq is read here, and then updated by
+	 * in case sg_policy->next_freq is read here, and then updated by
 	 * sugov_deferred_update() just before work_in_progress is set to false
 	 * here, we may miss queueing the new update.
 	 *

kernel/sched/cpupri.c

@@ -77,7 +77,7 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
 	 * When looking at the vector, we need to read the counter,
 	 * do a memory barrier, then read the mask.
 	 *
-	 * Note: This is still all racey, but we can deal with it.
+	 * Note: This is still all racy, but we can deal with it.
 	 *  Ideally, we only want to look at masks that are set.
 	 *
 	 *  If a mask is not set, then the only thing wrong is that we
@@ -186,7 +186,7 @@ int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
 	 * The cost of this trade-off is not entirely clear and will probably
 	 * be good for some workloads and bad for others.
 	 *
-	 * The main idea here is that if some CPUs were overcommitted, we try
+	 * The main idea here is that if some CPUs were over-committed, we try
 	 * to spread which is what the scheduler traditionally did. Sys admins
 	 * must do proper RT planning to avoid overloading the system if they
 	 * really care.

kernel/sched/cputime.c

@@ -563,7 +563,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 
 	/*
 	 * If either stime or utime are 0, assume all runtime is userspace.
-	 * Once a task gets some ticks, the monotonicy code at 'update:'
+	 * Once a task gets some ticks, the monotonicity code at 'update:'
 	 * will ensure things converge to the observed ratio.
 	 */
 	if (stime == 0) {

kernel/sched/deadline.c

@@ -245,7 +245,7 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 		p->dl.dl_non_contending = 0;
 		/*
 		 * If the timer handler is currently running and the
-		 * timer cannot be cancelled, inactive_task_timer()
+		 * timer cannot be canceled, inactive_task_timer()
 		 * will see that dl_not_contending is not set, and
 		 * will not touch the rq's active utilization,
 		 * so we are still safe.
@@ -267,7 +267,7 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
  * fires.
  *
  * If the task wakes up again before the inactive timer fires,
- * the timer is cancelled, whereas if the task wakes up after the
+ * the timer is canceled, whereas if the task wakes up after the
  * inactive timer fired (and running_bw has been decreased) the
  * task's utilization has to be added to running_bw again.
  * A flag in the deadline scheduling entity (dl_non_contending)
@@ -385,7 +385,7 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
 		dl_se->dl_non_contending = 0;
 		/*
 		 * If the timer handler is currently running and the
-		 * timer cannot be cancelled, inactive_task_timer()
+		 * timer cannot be canceled, inactive_task_timer()
 		 * will see that dl_not_contending is not set, and
 		 * will not touch the rq's active utilization,
 		 * so we are still safe.
@@ -1206,7 +1206,7 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  * Since rq->dl.running_bw and rq->dl.this_bw contain utilizations
  * multiplied by 2^BW_SHIFT, the result has to be shifted right by
  * BW_SHIFT.
- * Since rq->dl.bw_ratio contains 1 / Umax multipled by 2^RATIO_SHIFT,
+ * Since rq->dl.bw_ratio contains 1 / Umax multiplied by 2^RATIO_SHIFT,
  * dl_bw is multiped by rq->dl.bw_ratio and shifted right by RATIO_SHIFT.
  * Since delta is a 64 bit variable, to have an overflow its value
  * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
@@ -1737,7 +1737,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 		p->dl.dl_non_contending = 0;
 		/*
 		 * If the timer handler is currently running and the
-		 * timer cannot be cancelled, inactive_task_timer()
+		 * timer cannot be canceled, inactive_task_timer()
 		 * will see that dl_not_contending is not set, and
 		 * will not touch the rq's active utilization,
 		 * so we are still safe.
@@ -2745,7 +2745,7 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 
 /*
  * Default limits for DL period; on the top end we guard against small util
- * tasks still getting rediculous long effective runtimes, on the bottom end we
+ * tasks still getting ridiculously long effective runtimes, on the bottom end we
  * guard against timer DoS.
  */
 unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */

kernel/sched/features.h

@@ -27,7 +27,7 @@ SCHED_FEAT(NEXT_BUDDY, false)
 SCHED_FEAT(LAST_BUDDY, true)
 
 /*
- * Consider buddies to be cache hot, decreases the likelyness of a
+ * Consider buddies to be cache hot, decreases the likeliness of a
  * cache buddy being migrated away, increases cache locality.
  */
 SCHED_FEAT(CACHE_HOT_BUDDY, true)
@@ -90,3 +90,8 @@ SCHED_FEAT(WA_BIAS, true)
  */
 SCHED_FEAT(UTIL_EST, true)
 SCHED_FEAT(UTIL_EST_FASTUP, true)
+
+SCHED_FEAT(LATENCY_WARN, false)
+
+SCHED_FEAT(ALT_PERIOD, true)
+SCHED_FEAT(BASE_SLICE, true)

kernel/sched/idle.c

@@ -163,7 +163,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  *
  * NOTE: no locks or semaphores should be used here
  *
- * On archs that support TIF_POLLING_NRFLAG, is called with polling
+ * On architectures that support TIF_POLLING_NRFLAG, is called with polling
  * set, and it returns with polling set.  If it ever stops polling, it
  * must clear the polling bit.
  */
@@ -199,7 +199,7 @@ static void cpuidle_idle_call(void)
 	 * Suspend-to-idle ("s2idle") is a system state in which all user space
 	 * has been frozen, all I/O devices have been suspended and the only
 	 * activity happens here and in interrupts (if any). In that case bypass
-	 * the cpuidle governor and go stratight for the deepest idle state
+	 * the cpuidle governor and go straight for the deepest idle state
 	 * available.  Possibly also suspend the local tick and the entire
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
 	 * until a proper wakeup interrupt happens.
@@ -261,6 +261,12 @@ static void cpuidle_idle_call(void)
 static void do_idle(void)
 {
 	int cpu = smp_processor_id();
+
+	/*
+	 * Check if we need to update blocked load
+	 */
+	nohz_run_idle_balance(cpu);
+
 	/*
 	 * If the arch has a polling bit, we maintain an invariant:
 	 *

kernel/sched/loadavg.c

@@ -189,7 +189,7 @@ calc_load_n(unsigned long load, unsigned long exp,
  *    w:0 1 1           0 0           1 1           0 0
  *
  *    This ensures we'll fold the old NO_HZ contribution in this window while
- *    accumlating the new one.
+ *    accumulating the new one.
  *
  *  - When we wake up from NO_HZ during the window, we push up our
  *    contribution, since we effectively move our sample point to a known

kernel/sched/pelt.c

@@ -133,7 +133,7 @@ accumulate_sum(u64 delta, struct sched_avg *sa,
 			 *	runnable = running = 0;
 			 *
 			 * clause from ___update_load_sum(); this results in
-			 * the below usage of @contrib to dissapear entirely,
+			 * the below usage of @contrib to disappear entirely,
 			 * so no point in calculating it.
 			 */
 			contrib = __accumulate_pelt_segments(periods,

kernel/sched/pelt.h

@@ -130,7 +130,7 @@ static inline void update_idle_rq_clock_pelt(struct rq *rq)
 	 * Reflecting stolen time makes sense only if the idle
 	 * phase would be present at max capacity. As soon as the
 	 * utilization of a rq has reached the maximum value, it is
-	 * considered as an always runnig rq without idle time to
+	 * considered as an always running rq without idle time to
 	 * steal. This potential idle time is considered as lost in
 	 * this case. We keep track of this lost idle time compare to
 	 * rq's clock_task.

kernel/sched/rt.c

@@ -700,7 +700,7 @@ static void do_balance_runtime(struct rt_rq *rt_rq)
 		/*
 		 * Either all rqs have inf runtime and there's nothing to steal
 		 * or __disable_runtime() below sets a specific rq to inf to
-		 * indicate its been disabled and disalow stealing.
+		 * indicate its been disabled and disallow stealing.
 		 */
 		if (iter->rt_runtime == RUNTIME_INF)
 			goto next;
@@ -1998,7 +1998,7 @@ static void push_rt_tasks(struct rq *rq)
  *
  * Each root domain has its own irq work function that can iterate over
  * all CPUs with RT overloaded tasks. Since all CPUs with overloaded RT
- * tassk must be checked if there's one or many CPUs that are lowering
+ * task must be checked if there's one or many CPUs that are lowering
  * their priority, there's a single irq work iterator that will try to
  * push off RT tasks that are waiting to run.
  *
@@ -2216,7 +2216,7 @@ static void pull_rt_task(struct rq *this_rq)
 			/*
 			 * There's a chance that p is higher in priority
 			 * than what's currently running on its CPU.
-			 * This is just that p is wakeing up and hasn't
+			 * This is just that p is waking up and hasn't
 			 * had a chance to schedule. We only pull
 			 * p if it is lower in priority than the
 			 * current task on the run queue

kernel/sched/sched.h

@@ -36,6 +36,7 @@
 #include <uapi/linux/sched/types.h>
 
 #include <linux/binfmts.h>
+#include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <linux/compat.h>
 #include <linux/context_tracking.h>
@@ -57,6 +58,7 @@
 #include <linux/prefetch.h>
 #include <linux/profile.h>
 #include <linux/psi.h>
+#include <linux/ratelimit.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/security.h>
 #include <linux/stop_machine.h>
@@ -204,6 +206,13 @@ static inline void update_avg(u64 *avg, u64 sample)
 	*avg += diff / 8;
 }
 
+/*
+ * Shifting a value by an exponent greater *or equal* to the size of said value
+ * is UB; cap at size-1.
+ */
+#define shr_bound(val, shift)							\
+	(val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1))
+
 /*
  * !! For sched_setattr_nocheck() (kernel) only !!
  *
@@ -963,6 +972,11 @@ struct rq {
 
 	atomic_t		nr_iowait;
 
+#ifdef CONFIG_SCHED_DEBUG
+	u64 last_seen_need_resched_ns;
+	int ticks_without_resched;
+#endif
+
 #ifdef CONFIG_MEMBARRIER
 	int membarrier_state;
 #endif
@@ -975,7 +989,6 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
-	unsigned char		balance_push;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
@@ -1147,7 +1160,7 @@ static inline u64 __rq_clock_broken(struct rq *rq)
  *
  *	if (rq-clock_update_flags >= RQCF_UPDATED)
  *
- * to check if %RQCF_UPADTED is set. It'll never be shifted more than
+ * to check if %RQCF_UPDATED is set. It'll never be shifted more than
  * one position though, because the next rq_unpin_lock() will shift it
  * back.
  */
@@ -1206,7 +1219,7 @@ static inline void rq_clock_skip_update(struct rq *rq)
 
 /*
  * See rt task throttling, which is the only time a skip
- * request is cancelled.
+ * request is canceled.
  */
 static inline void rq_clock_cancel_skipupdate(struct rq *rq)
 {
@@ -1545,22 +1558,20 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
-void register_sched_domain_sysctl(void);
+#ifdef CONFIG_SCHED_DEBUG
+void update_sched_domain_debugfs(void);
 void dirty_sched_domain_sysctl(int cpu);
-void unregister_sched_domain_sysctl(void);
 #else
-static inline void register_sched_domain_sysctl(void)
+static inline void update_sched_domain_debugfs(void)
 {
 }
 static inline void dirty_sched_domain_sysctl(int cpu)
 {
 }
-static inline void unregister_sched_domain_sysctl(void)
-{
-}
 #endif
 
+extern int sched_update_scaling(void);
+
 extern void flush_smp_call_function_from_idle(void);
 
 #else /* !CONFIG_SMP: */
@@ -1853,7 +1864,7 @@ struct sched_class {
 
 	/*
 	 * The switched_from() call is allowed to drop rq->lock, therefore we
-	 * cannot assume the switched_from/switched_to pair is serliazed by
+	 * cannot assume the switched_from/switched_to pair is serialized by
 	 * rq->lock. They are however serialized by p->pi_lock.
 	 */
 	void (*switched_from)(struct rq *this_rq, struct task_struct *task);
@@ -2358,7 +2369,7 @@ extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 
 #ifdef	CONFIG_SCHED_DEBUG
-extern bool sched_debug_enabled;
+extern bool sched_debug_verbose;
 
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
@@ -2366,6 +2377,8 @@ extern void print_dl_stats(struct seq_file *m, int cpu);
 extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
+
+extern void resched_latency_warn(int cpu, u64 latency);
 #ifdef CONFIG_NUMA_BALANCING
 extern void
 show_numa_stats(struct task_struct *p, struct seq_file *m);
@@ -2373,6 +2386,8 @@ extern void
 print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 	unsigned long tpf, unsigned long gsf, unsigned long gpf);
 #endif /* CONFIG_NUMA_BALANCING */
+#else
+static inline void resched_latency_warn(int cpu, u64 latency) {}
 #endif /* CONFIG_SCHED_DEBUG */
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
@@ -2385,9 +2400,11 @@ extern void cfs_bandwidth_usage_dec(void);
 #ifdef CONFIG_NO_HZ_COMMON
 #define NOHZ_BALANCE_KICK_BIT	0
 #define NOHZ_STATS_KICK_BIT	1
+#define NOHZ_NEWILB_KICK_BIT	2
 
 #define NOHZ_BALANCE_KICK	BIT(NOHZ_BALANCE_KICK_BIT)
 #define NOHZ_STATS_KICK		BIT(NOHZ_STATS_KICK_BIT)
+#define NOHZ_NEWILB_KICK	BIT(NOHZ_NEWILB_KICK_BIT)
 
 #define NOHZ_KICK_MASK	(NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
 
@@ -2398,6 +2415,11 @@ extern void nohz_balance_exit_idle(struct rq *rq);
 static inline void nohz_balance_exit_idle(struct rq *rq) { }
 #endif
 
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void nohz_run_idle_balance(int cpu);
+#else
+static inline void nohz_run_idle_balance(int cpu) { }
+#endif
 
 #ifdef CONFIG_SMP
 static inline
@@ -2437,7 +2459,7 @@ DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
 
 /*
  * Returns the irqtime minus the softirq time computed by ksoftirqd.
- * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * Otherwise ksoftirqd's sum_exec_runtime is subtracted its own runtime
  * and never move forward.
  */
 static inline u64 irq_time_read(int cpu)
@@ -2718,5 +2740,12 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 #endif
 
-void swake_up_all_locked(struct swait_queue_head *q);
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern void swake_up_all_locked(struct swait_queue_head *q);
+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+extern int preempt_dynamic_mode;
+extern int sched_dynamic_mode(const char *str);
+extern void sched_dynamic_update(int mode);
+#endif
+

kernel/sched/stats.c

@@ -74,7 +74,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 }
 
 /*
- * This itererator needs some explanation.
+ * This iterator needs some explanation.
  * It returns 1 for the header position.
  * This means 2 is cpu 0.
  * In a hotplugged system some CPUs, including cpu 0, may be missing so we have

kernel/sched/stats.h

@@ -84,28 +84,24 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
 
 static inline void psi_dequeue(struct task_struct *p, bool sleep)
 {
-	int clear = TSK_RUNNING, set = 0;
+	int clear = TSK_RUNNING;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	if (!sleep) {
-		if (p->in_memstall)
-			clear |= TSK_MEMSTALL;
-	} else {
-		/*
-		 * When a task sleeps, schedule() dequeues it before
-		 * switching to the next one. Merge the clearing of
-		 * TSK_RUNNING and TSK_ONCPU to save an unnecessary
-		 * psi_task_change() call in psi_sched_switch().
-		 */
-		clear |= TSK_ONCPU;
+	/*
+	 * A voluntary sleep is a dequeue followed by a task switch. To
+	 * avoid walking all ancestors twice, psi_task_switch() handles
+	 * TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU.
+	 * Do nothing here.
+	 */
+	if (sleep)
+		return;
 
-		if (p->in_iowait)
-			set |= TSK_IOWAIT;
-	}
+	if (p->in_memstall)
+		clear |= TSK_MEMSTALL;
 
-	psi_task_change(p, clear, set);
+	psi_task_change(p, clear, 0);
 }
 
 static inline void psi_ttwu_dequeue(struct task_struct *p)
@@ -144,14 +140,6 @@ static inline void psi_sched_switch(struct task_struct *prev,
 	psi_task_switch(prev, next, sleep);
 }
 
-static inline void psi_task_tick(struct rq *rq)
-{
-	if (static_branch_likely(&psi_disabled))
-		return;
-
-	if (unlikely(rq->curr->in_memstall))
-		psi_memstall_tick(rq->curr, cpu_of(rq));
-}
 #else /* CONFIG_PSI */
 static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
 static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
@@ -159,7 +147,6 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {}
 static inline void psi_sched_switch(struct task_struct *prev,
 				    struct task_struct *next,
 				    bool sleep) {}
-static inline void psi_task_tick(struct rq *rq) {}
 #endif /* CONFIG_PSI */
 
 #ifdef CONFIG_SCHED_INFO

kernel/sched/topology.c

@@ -14,15 +14,15 @@ static cpumask_var_t sched_domains_tmpmask2;
 
 static int __init sched_debug_setup(char *str)
 {
-	sched_debug_enabled = true;
+	sched_debug_verbose = true;
 
 	return 0;
 }
-early_param("sched_debug", sched_debug_setup);
+early_param("sched_verbose", sched_debug_setup);
 
 static inline bool sched_debug(void)
 {
-	return sched_debug_enabled;
+	return sched_debug_verbose;
 }
 
 #define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
@@ -131,7 +131,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 {
 	int level = 0;
 
-	if (!sched_debug_enabled)
+	if (!sched_debug_verbose)
 		return;
 
 	if (!sd) {
@@ -152,7 +152,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 }
 #else /* !CONFIG_SCHED_DEBUG */
 
-# define sched_debug_enabled 0
+# define sched_debug_verbose 0
 # define sched_domain_debug(sd, cpu) do { } while (0)
 static inline bool sched_debug(void)
 {
@@ -723,35 +723,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	for (tmp = sd; tmp; tmp = tmp->parent)
 		numa_distance += !!(tmp->flags & SD_NUMA);
 
-	/*
-	 * FIXME: Diameter >=3 is misrepresented.
-	 *
-	 * Smallest diameter=3 topology is:
-	 *
-	 *   node   0   1   2   3
-	 *     0:  10  20  30  40
-	 *     1:  20  10  20  30
-	 *     2:  30  20  10  20
-	 *     3:  40  30  20  10
-	 *
-	 *   0 --- 1 --- 2 --- 3
-	 *
-	 * NUMA-3	0-3		N/A		N/A		0-3
-	 *  groups:	{0-2},{1-3}					{1-3},{0-2}
-	 *
-	 * NUMA-2	0-2		0-3		0-3		1-3
-	 *  groups:	{0-1},{1-3}	{0-2},{2-3}	{1-3},{0-1}	{2-3},{0-2}
-	 *
-	 * NUMA-1	0-1		0-2		1-3		2-3
-	 *  groups:	{0},{1}		{1},{2},{0}	{2},{3},{1}	{3},{2}
-	 *
-	 * NUMA-0	0		1		2		3
-	 *
-	 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
-	 * group span isn't a subset of the domain span.
-	 */
-	WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
-
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);
@@ -963,7 +934,7 @@ static void init_overlap_sched_group(struct sched_domain *sd,
 	int cpu;
 
 	build_balance_mask(sd, sg, mask);
-	cpu = cpumask_first_and(sched_group_span(sg), mask);
+	cpu = cpumask_first(mask);
 
 	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
 	if (atomic_inc_return(&sg->sgc->ref) == 1)
@@ -982,6 +953,31 @@ static void init_overlap_sched_group(struct sched_domain *sd,
 	sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
 }
 
+static struct sched_domain *
+find_descended_sibling(struct sched_domain *sd, struct sched_domain *sibling)
+{
+	/*
+	 * The proper descendant would be the one whose child won't span out
+	 * of sd
+	 */
+	while (sibling->child &&
+	       !cpumask_subset(sched_domain_span(sibling->child),
+			       sched_domain_span(sd)))
+		sibling = sibling->child;
+
+	/*
+	 * As we are referencing sgc across different topology level, we need
+	 * to go down to skip those sched_domains which don't contribute to
+	 * scheduling because they will be degenerated in cpu_attach_domain
+	 */
+	while (sibling->child &&
+	       cpumask_equal(sched_domain_span(sibling->child),
+			     sched_domain_span(sibling)))
+		sibling = sibling->child;
+
+	return sibling;
+}
+
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
@@ -1015,6 +1011,41 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
+		/*
+		 * Usually we build sched_group by sibling's child sched_domain
+		 * But for machines whose NUMA diameter are 3 or above, we move
+		 * to build sched_group by sibling's proper descendant's child
+		 * domain because sibling's child sched_domain will span out of
+		 * the sched_domain being built as below.
+		 *
+		 * Smallest diameter=3 topology is:
+		 *
+		 *   node   0   1   2   3
+		 *     0:  10  20  30  40
+		 *     1:  20  10  20  30
+		 *     2:  30  20  10  20
+		 *     3:  40  30  20  10
+		 *
+		 *   0 --- 1 --- 2 --- 3
+		 *
+		 * NUMA-3       0-3             N/A             N/A             0-3
+		 *  groups:     {0-2},{1-3}                                     {1-3},{0-2}
+		 *
+		 * NUMA-2       0-2             0-3             0-3             1-3
+		 *  groups:     {0-1},{1-3}     {0-2},{2-3}     {1-3},{0-1}     {2-3},{0-2}
+		 *
+		 * NUMA-1       0-1             0-2             1-3             2-3
+		 *  groups:     {0},{1}         {1},{2},{0}     {2},{3},{1}     {3},{2}
+		 *
+		 * NUMA-0       0               1               2               3
+		 *
+		 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+		 * group span isn't a subset of the domain span.
+		 */
+		if (sibling->child &&
+		    !cpumask_subset(sched_domain_span(sibling->child), span))
+			sibling = find_descended_sibling(sd, sibling);
+
 		sg = build_group_from_child_sched_domain(sibling, cpu);
 		if (!sg)
 			goto fail;
@@ -1022,7 +1053,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		sg_span = sched_group_span(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		init_overlap_sched_group(sd, sg);
+		init_overlap_sched_group(sibling, sg);
 
 		if (!first)
 			first = sg;
@@ -2110,7 +2141,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	if (has_asym)
 		static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
 
-	if (rq && sched_debug_enabled) {
+	if (rq && sched_debug_verbose) {
 		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
 			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
 	}
@@ -2128,7 +2159,7 @@ static cpumask_var_t			*doms_cur;
 /* Number of sched domains in 'doms_cur': */
 static int				ndoms_cur;
 
-/* Attribues of custom domains in 'doms_cur' */
+/* Attributes of custom domains in 'doms_cur' */
 static struct sched_domain_attr		*dattr_cur;
 
 /*
@@ -2192,7 +2223,6 @@ int sched_init_domains(const struct cpumask *cpu_map)
 		doms_cur = &fallback_doms;
 	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN));
 	err = build_sched_domains(doms_cur[0], NULL);
-	register_sched_domain_sysctl();
 
 	return err;
 }
@@ -2267,9 +2297,6 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 
 	lockdep_assert_held(&sched_domains_mutex);
 
-	/* Always unregister in case we don't destroy any domains: */
-	unregister_sched_domain_sysctl();
-
 	/* Let the architecture update CPU core mappings: */
 	new_topology = arch_update_cpu_topology();
 
@@ -2358,7 +2385,7 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 	dattr_cur = dattr_new;
 	ndoms_cur = ndoms_new;
 
-	register_sched_domain_sysctl();
+	update_sched_domain_debugfs();
 }
 
 /*

kernel/signal.c

@@ -408,7 +408,8 @@ void task_join_group_stop(struct task_struct *task)
  *   appropriate lock must be held to stop the target task from exiting
  */
 static struct sigqueue *
-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
+		 int override_rlimit, const unsigned int sigqueue_flags)
 {
 	struct sigqueue *q = NULL;
 	struct user_struct *user;
@@ -430,7 +431,16 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
 	rcu_read_unlock();
 
 	if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
-		q = kmem_cache_alloc(sigqueue_cachep, flags);
+		/*
+		 * Preallocation does not hold sighand::siglock so it can't
+		 * use the cache. The lockless caching requires that only
+		 * one consumer and only one producer run at a time.
+		 */
+		q = READ_ONCE(t->sigqueue_cache);
+		if (!q || sigqueue_flags)
+			q = kmem_cache_alloc(sigqueue_cachep, gfp_flags);
+		else
+			WRITE_ONCE(t->sigqueue_cache, NULL);
 	} else {
 		print_dropped_signal(sig);
 	}
@@ -440,20 +450,51 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
 			free_uid(user);
 	} else {
 		INIT_LIST_HEAD(&q->list);
-		q->flags = 0;
+		q->flags = sigqueue_flags;
 		q->user = user;
 	}
 
 	return q;
 }
 
+void exit_task_sigqueue_cache(struct task_struct *tsk)
+{
+	/* Race free because @tsk is mopped up */
+	struct sigqueue *q = tsk->sigqueue_cache;
+
+	if (q) {
+		tsk->sigqueue_cache = NULL;
+		/*
+		 * Hand it back to the cache as the task might
+		 * be self reaping which would leak the object.
+		 */
+		 kmem_cache_free(sigqueue_cachep, q);
+	}
+}
+
+static void sigqueue_cache_or_free(struct sigqueue *q)
+{
+	/*
+	 * Cache one sigqueue per task. This pairs with the consumer side
+	 * in __sigqueue_alloc() and needs READ/WRITE_ONCE() to prevent the
+	 * compiler from store tearing and to tell KCSAN that the data race
+	 * is intentional when run without holding current->sighand->siglock,
+	 * which is fine as current obviously cannot run __sigqueue_free()
+	 * concurrently.
+	 */
+	if (!READ_ONCE(current->sigqueue_cache))
+		WRITE_ONCE(current->sigqueue_cache, q);
+	else
+		kmem_cache_free(sigqueue_cachep, q);
+}
+
 static void __sigqueue_free(struct sigqueue *q)
 {
 	if (q->flags & SIGQUEUE_PREALLOC)
 		return;
 	if (atomic_dec_and_test(&q->user->sigpending))
 		free_uid(q->user);
-	kmem_cache_free(sigqueue_cachep, q);
+	sigqueue_cache_or_free(q);
 }
 
 void flush_sigqueue(struct sigpending *queue)
@@ -1111,7 +1152,8 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	else
 		override_rlimit = 0;
 
-	q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit);
+	q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit, 0);
+
 	if (q) {
 		list_add_tail(&q->list, &pending->list);
 		switch ((unsigned long) info) {
@@ -1806,12 +1848,7 @@ EXPORT_SYMBOL(kill_pid);
  */
 struct sigqueue *sigqueue_alloc(void)
 {
-	struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
-
-	if (q)
-		q->flags |= SIGQUEUE_PREALLOC;
-
-	return q;
+	return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC);
 }
 
 void sigqueue_free(struct sigqueue *q)

kernel/stop_machine.c

@@ -409,6 +409,7 @@ static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 		work->fn = fn;
 		work->arg = arg;
 		work->done = done;
+		work->caller = _RET_IP_;
 		if (cpu_stop_queue_work(cpu, work))
 			queued = true;
 	}

kernel/sysctl.c

@@ -184,17 +184,6 @@ static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT;
 int sysctl_legacy_va_layout;
 #endif
 
-#ifdef CONFIG_SCHED_DEBUG
-static int min_sched_granularity_ns = 100000;		/* 100 usecs */
-static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
-static int min_wakeup_granularity_ns;			/* 0 usecs */
-static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
-#ifdef CONFIG_SMP
-static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
-static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-#endif /* CONFIG_SMP */
-#endif /* CONFIG_SCHED_DEBUG */
-
 #ifdef CONFIG_COMPACTION
 static int min_extfrag_threshold;
 static int max_extfrag_threshold = 1000;
@@ -1659,58 +1648,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#ifdef CONFIG_SCHED_DEBUG
-	{
-		.procname	= "sched_min_granularity_ns",
-		.data		= &sysctl_sched_min_granularity,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_proc_update_handler,
-		.extra1		= &min_sched_granularity_ns,
-		.extra2		= &max_sched_granularity_ns,
-	},
-	{
-		.procname	= "sched_latency_ns",
-		.data		= &sysctl_sched_latency,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_proc_update_handler,
-		.extra1		= &min_sched_granularity_ns,
-		.extra2		= &max_sched_granularity_ns,
-	},
-	{
-		.procname	= "sched_wakeup_granularity_ns",
-		.data		= &sysctl_sched_wakeup_granularity,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_proc_update_handler,
-		.extra1		= &min_wakeup_granularity_ns,
-		.extra2		= &max_wakeup_granularity_ns,
-	},
-#ifdef CONFIG_SMP
-	{
-		.procname	= "sched_tunable_scaling",
-		.data		= &sysctl_sched_tunable_scaling,
-		.maxlen		= sizeof(enum sched_tunable_scaling),
-		.mode		= 0644,
-		.proc_handler	= sched_proc_update_handler,
-		.extra1		= &min_sched_tunable_scaling,
-		.extra2		= &max_sched_tunable_scaling,
-	},
-	{
-		.procname	= "sched_migration_cost_ns",
-		.data		= &sysctl_sched_migration_cost,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "sched_nr_migrate",
-		.data		= &sysctl_sched_nr_migrate,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",
@@ -1722,37 +1659,7 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif /* CONFIG_SCHEDSTATS */
-#endif /* CONFIG_SMP */
 #ifdef CONFIG_NUMA_BALANCING
-	{
-		.procname	= "numa_balancing_scan_delay_ms",
-		.data		= &sysctl_numa_balancing_scan_delay,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "numa_balancing_scan_period_min_ms",
-		.data		= &sysctl_numa_balancing_scan_period_min,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "numa_balancing_scan_period_max_ms",
-		.data		= &sysctl_numa_balancing_scan_period_max,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "numa_balancing_scan_size_mb",
-		.data		= &sysctl_numa_balancing_scan_size,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-	},
 	{
 		.procname	= "numa_balancing",
 		.data		= NULL, /* filled in by handler */
@@ -1763,7 +1670,6 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif /* CONFIG_NUMA_BALANCING */
-#endif /* CONFIG_SCHED_DEBUG */
 	{
 		.procname	= "sched_rt_period_us",
 		.data		= &sysctl_sched_rt_period,

lib/Kconfig.debug

@@ -1710,7 +1710,6 @@ config LATENCYTOP
 	select KALLSYMS_ALL
 	select STACKTRACE
 	select SCHEDSTATS
-	select SCHED_DEBUG
 	help
 	  Enable this option if you want to use the LatencyTOP tool
 	  to find out which userspace is blocking on what kernel operations.

net/core/skbuff.c

@@ -60,6 +60,7 @@
 #include <linux/prefetch.h>
 #include <linux/if_vlan.h>
 #include <linux/mpls.h>
+#include <linux/kcov.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>

net/mac80211/iface.c

@@ -15,6 +15,7 @@
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
 #include <linux/rtnetlink.h>
+#include <linux/kcov.h>
 #include <net/mac80211.h>
 #include <net/ieee80211_radiotap.h>
 #include "ieee80211_i.h"

net/mac80211/rx.c

@@ -17,6 +17,7 @@
 #include <linux/etherdevice.h>
 #include <linux/rcupdate.h>
 #include <linux/export.h>
+#include <linux/kcov.h>
 #include <linux/bitops.h>
 #include <net/mac80211.h>
 #include <net/ieee80211_radiotap.h>