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()
  ...

9 files changed, 124 insertions, 39 deletions

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 383684e30f12..e6b948a6000d 100644
--- a/include/linux/cpumask.h
+++ b/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
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index d6c4cc9ecc77..1fdb4343af9c 100644
--- a/include/linux/debugfs.h
+++ b/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
 
 /**
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index 4e3037dc1204..55dc338f6bcd 100644
--- a/include/linux/kcov.h
+++ b/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;
diff --git a/include/linux/psi.h b/include/linux/psi.h
index 7361023f3fdd..65eb1476ac70 100644
--- a/include/linux/psi.h
+++ b/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);
 
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index b95f3211566a..0a23300d49af 100644
--- a/include/linux/psi_types.h
+++ b/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 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 743a613c9cf3..f652a8ccad73 100644
--- a/include/linux/sched.h
+++ b/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;
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 3c31ba88aca5..db2c0f34aaaf 100644
--- a/include/linux/sched/sysctl.h
+++ b/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
 
 /*
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 1e98548d7cf6..0dbfda8d99d0 100644
--- a/include/linux/signal.h
+++ b/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)
diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
index 83ee45fa634b..3747bf816f9a 100644
--- a/include/uapi/linux/ptrace.h
+++ b/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.