Merge tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - reorganize & clean up the SD* flags definitions and add a bunch of
   sanity checks. These new checks caught quite a few bugs or at least
   inconsistencies, resulting in another set of patches.

 - rseq updates, add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

 - add a new tracepoint to improve CPU capacity tracking

 - improve overloaded SMP system load-balancing behavior

 - tweak SMT balancing

 - energy-aware scheduling updates

 - NUMA balancing improvements

 - deadline scheduler fixes and improvements

 - CPU isolation fixes

 - misc cleanups, simplifications and smaller optimizations

* tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  sched/deadline: Unthrottle PI boosted threads while enqueuing
  sched/debug: Add new tracepoint to track cpu_capacity
  sched/fair: Tweak pick_next_entity()
  rseq/selftests: Test MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
  rseq/selftests,x86_64: Add rseq_offset_deref_addv()
  rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
  sched/fair: Use dst group while checking imbalance for NUMA balancer
  sched/fair: Reduce busy load balance interval
  sched/fair: Minimize concurrent LBs between domain level
  sched/fair: Reduce minimal imbalance threshold
  sched/fair: Relax constraint on task's load during load balance
  sched/fair: Remove the force parameter of update_tg_load_avg()
  sched/fair: Fix wrong cpu selecting from isolated domain
  sched: Remove unused inline function uclamp_bucket_base_value()
  sched/rt: Disable RT_RUNTIME_SHARE by default
  sched/deadline: Fix stale throttling on de-/boosted tasks
  sched/numa: Use runnable_avg to classify node
  sched/topology: Move sd_flag_debug out of #ifdef CONFIG_SYSCTL
  MAINTAINERS: Add myself as SCHED_DEADLINE reviewer
  sched/topology: Move SD_DEGENERATE_GROUPS_MASK out of linux/sched/topology.h
  ...

MAINTAINERS

@@ -15407,6 +15407,7 @@ R:	Dietmar Eggemann <dietmar.eggemann@arm.com> (SCHED_NORMAL)
 R:	Steven Rostedt <rostedt@goodmis.org> (SCHED_FIFO/SCHED_RR)
 R:	Ben Segall <bsegall@google.com> (CONFIG_CFS_BANDWIDTH)
 R:	Mel Gorman <mgorman@suse.de> (CONFIG_NUMA_BALANCING)
+R:	Daniel Bristot de Oliveira <bristot@redhat.com> (SCHED_DEADLINE)
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core

arch/arm/kernel/topology.c

@@ -177,15 +177,6 @@ static inline void parse_dt_topology(void) {}
 static inline void update_cpu_capacity(unsigned int cpuid) {}
 #endif
 
-/*
- * The current assumption is that we can power gate each core independently.
- * This will be superseded by DT binding once available.
- */
-const struct cpumask *cpu_corepower_mask(int cpu)
-{
-	return &cpu_topology[cpu].thread_sibling;
-}
-
 /*
  * store_cpu_topology is called at boot when only one cpu is running
  * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
@@ -241,20 +232,6 @@ void store_cpu_topology(unsigned int cpuid)
 	update_siblings_masks(cpuid);
 }
 
-static inline int cpu_corepower_flags(void)
-{
-	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
-}
-
-static struct sched_domain_topology_level arm_topology[] = {
-#ifdef CONFIG_SCHED_MC
-	{ cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
-#endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
-
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
@@ -265,7 +242,4 @@ void __init init_cpu_topology(void)
 	smp_wmb();
 
 	parse_dt_topology();
-
-	/* Set scheduler topology descriptor */
-	set_sched_topology(arm_topology);
 }

include/linux/sched.h

@@ -1491,9 +1491,10 @@ extern struct pid *cad_pid;
 /*
  * Per process flags
  */
+#define PF_VCPU			0x00000001	/* I'm a virtual CPU */
 #define PF_IDLE			0x00000002	/* I am an IDLE thread */
 #define PF_EXITING		0x00000004	/* Getting shut down */
-#define PF_VCPU			0x00000010	/* I'm a virtual CPU */
+#define PF_IO_WORKER		0x00000010	/* Task is an IO worker */
 #define PF_WQ_WORKER		0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC		0x00000040	/* Forked but didn't exec */
 #define PF_MCE_PROCESS		0x00000080      /* Process policy on mce errors */
@@ -1517,7 +1518,6 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_NOCMA	0x10000000	/* All allocation request will have _GFP_MOVABLE cleared */
-#define PF_IO_WORKER		0x20000000	/* Task is an IO worker */
 #define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
@@ -2046,6 +2046,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_cpu_capacity(struct rq *rq);
 int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);

include/linux/sched/mm.h

@@ -348,10 +348,13 @@ enum {
 	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY		= (1U << 6),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ			= (1U << 7),
 };
 
 enum {
 	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+	MEMBARRIER_FLAG_RSEQ		= (1U << 1),
 };
 
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS

include/linux/sched/sd_flags.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sched-domains (multiprocessor balancing) flag declarations.
+ */
+
+#ifndef SD_FLAG
+# error "Incorrect import of SD flags definitions"
+#endif
+
+/*
+ * Hierarchical metaflags
+ *
+ * SHARED_CHILD: These flags are meant to be set from the base domain upwards.
+ * If a domain has this flag set, all of its children should have it set. This
+ * is usually because the flag describes some shared resource (all CPUs in that
+ * domain share the same resource), or because they are tied to a scheduling
+ * behaviour that we want to disable at some point in the hierarchy for
+ * scalability reasons.
+ *
+ * In those cases it doesn't make sense to have the flag set for a domain but
+ * not have it in (some of) its children: sched domains ALWAYS span their child
+ * domains, so operations done with parent domains will cover CPUs in the lower
+ * child domains.
+ *
+ *
+ * SHARED_PARENT: These flags are meant to be set from the highest domain
+ * downwards. If a domain has this flag set, all of its parents should have it
+ * set. This is usually for topology properties that start to appear above a
+ * certain level (e.g. domain starts spanning CPUs outside of the base CPU's
+ * socket).
+ */
+#define SDF_SHARED_CHILD       0x1
+#define SDF_SHARED_PARENT      0x2
+
+/*
+ * Behavioural metaflags
+ *
+ * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has
+ * more than one group. This is usually for balancing flags (load balancing
+ * involves equalizing a metric between groups), or for flags describing some
+ * shared resource (which would be shared between groups).
+ */
+#define SDF_NEEDS_GROUPS       0x4
+
+/*
+ * Balance when about to become idle
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on exec
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on fork, clone
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on wakeup
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Consider waking task on waking CPU.
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
+
+/*
+ * Domain members have different CPU capacities
+ *
+ * SHARED_PARENT: Set from the topmost domain down to the first domain where
+ *                asymmetry is detected.
+ * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups.
+ */
+SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU capacity (i.e. SMT)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               CPU capacity.
+ * NEEDS_GROUPS: Capacity is shared between groups.
+ */
+SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU package resources (i.e. caches)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               the same cache(s).
+ * NEEDS_GROUPS: Caches are shared between groups.
+ */
+SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Only a single load balancing instance
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a
+ *                different level upwards, but it doesn't change that if a
+ *                domain has this flag set, then all of its parents need to have
+ *                it too (otherwise the serialization doesn't make sense).
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Place busy tasks earlier in the domain
+ *
+ * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
+ *               up, but currently assumed to be set from the base domain
+ *               upwards (see update_top_cache_domain()).
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Prefer to place tasks in a sibling domain
+ *
+ * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
+ * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ *
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
+
+/*
+ * sched_groups of this level overlap
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: Overlaps can only exist with more than one group.
+ */
+SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Cross-node balancing
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)

include/linux/sched/topology.h

@@ -11,20 +11,29 @@
  */
 #ifdef CONFIG_SMP
 
-#define SD_BALANCE_NEWIDLE	0x0001	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		0x0002	/* Balance on exec */
-#define SD_BALANCE_FORK		0x0004	/* Balance on fork, clone */
-#define SD_BALANCE_WAKE		0x0008  /* Balance on wakeup */
-#define SD_WAKE_AFFINE		0x0010	/* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY	0x0020  /* Domain members have different CPU capacities */
-#define SD_SHARE_CPUCAPACITY	0x0040	/* Domain members share CPU capacity */
-#define SD_SHARE_POWERDOMAIN	0x0080	/* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES	0x0100	/* Domain members share CPU pkg resources */
-#define SD_SERIALIZE		0x0200	/* Only a single load balancing instance */
-#define SD_ASYM_PACKING		0x0400  /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING	0x0800	/* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP		0x1000	/* sched_domains of this level overlap */
-#define SD_NUMA			0x2000	/* cross-node balancing */
+/* Generate SD flag indexes */
+#define SD_FLAG(name, mflags) __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+	__SD_FLAG_CNT,
+};
+#undef SD_FLAG
+/* Generate SD flag bits */
+#define SD_FLAG(name, mflags) name = 1 << __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
+#ifdef CONFIG_SCHED_DEBUG
+
+struct sd_flag_debug {
+	unsigned int meta_flags;
+	char *name;
+};
+extern const struct sd_flag_debug sd_flag_debug[];
+
+#endif
 
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)

include/linux/syscalls.h

@@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *argv,
 			const char __user *const __user *envp, int flags);
 asmlinkage long sys_userfaultfd(int flags);
-asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id);
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
 				    int fd_out, loff_t __user *off_out,

include/trace/events/sched.h

@@ -630,6 +630,10 @@ DECLARE_TRACE(pelt_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_cpu_capacity_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(sched_overutilized_tp,
 	TP_PROTO(struct root_domain *rd, bool overutilized),
 	TP_ARGS(rd, overutilized));

include/uapi/linux/membarrier.h

@@ -114,6 +114,26 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          Ensure the caller thread, upon return from
+ *                          system call, that all its running thread
+ *                          siblings have any currently running rseq
+ *                          critical sections restarted if @flags
+ *                          parameter is 0; if @flags parameter is
+ *                          MEMBARRIER_CMD_FLAG_CPU,
+ *                          then this operation is performed only
+ *                          on CPU indicated by @cpu_id. If this command is
+ *                          not implemented by an architecture, -EINVAL
+ *                          is returned. A process needs to register its
+ *                          intent to use the private expedited rseq
+ *                          command prior to using it, otherwise
+ *                          this command returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ *                          Register the process intent to use
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ.
+ *                          If this command is not implemented by an
+ *                          architecture, -EINVAL is returned.
+ *                          Returns 0 on success.
  * @MEMBARRIER_CMD_SHARED:
  *                          Alias to MEMBARRIER_CMD_GLOBAL. Provided for
  *                          header backward compatibility.
@@ -131,9 +151,15 @@ enum membarrier_cmd {
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED		= (1 << 4),
 	MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE		= (1 << 5),
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE	= (1 << 6),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			= (1 << 7),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ		= (1 << 8),
 
 	/* Alias for header backward compatibility. */
 	MEMBARRIER_CMD_SHARED			= MEMBARRIER_CMD_GLOBAL,
 };
 
+enum membarrier_cmd_flag {
+	MEMBARRIER_CMD_FLAG_CPU		= (1 << 0),
+};
+
 #endif /* _UAPI_LINUX_MEMBARRIER_H */

kernel/sched/core.c

@@ -36,6 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
@@ -940,11 +941,6 @@ static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
 	return clamp_value / UCLAMP_BUCKET_DELTA;
 }
 
-static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value)
-{
-	return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
-}
-
 static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
 {
 	if (clamp_id == UCLAMP_MIN)
@@ -4551,9 +4547,12 @@ void __noreturn do_task_dead(void)
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
+	unsigned int task_flags;
+
 	if (!tsk->state)
 		return;
 
+	task_flags = tsk->flags;
 	/*
 	 * If a worker went to sleep, notify and ask workqueue whether
 	 * it wants to wake up a task to maintain concurrency.
@@ -4562,9 +4561,9 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
 	 * requires it.
 	 */
-	if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
+	if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
 		preempt_disable();
-		if (tsk->flags & PF_WQ_WORKER)
+		if (task_flags & PF_WQ_WORKER)
 			wq_worker_sleeping(tsk);
 		else
 			io_wq_worker_sleeping(tsk);

kernel/sched/deadline.c

@@ -1525,14 +1525,38 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	 */
 	if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) {
 		pi_se = &pi_task->dl;
+		/*
+		 * Because of delays in the detection of the overrun of a
+		 * thread's runtime, it might be the case that a thread
+		 * goes to sleep in a rt mutex with negative runtime. As
+		 * a consequence, the thread will be throttled.
+		 *
+		 * While waiting for the mutex, this thread can also be
+		 * boosted via PI, resulting in a thread that is throttled
+		 * and boosted at the same time.
+		 *
+		 * In this case, the boost overrides the throttle.
+		 */
+		if (p->dl.dl_throttled) {
+			/*
+			 * The replenish timer needs to be canceled. No
+			 * problem if it fires concurrently: boosted threads
+			 * are ignored in dl_task_timer().
+			 */
+			hrtimer_try_to_cancel(&p->dl.dl_timer);
+			p->dl.dl_throttled = 0;
+		}
 	} else if (!dl_prio(p->normal_prio)) {
 		/*
-		 * Special case in which we have a !SCHED_DEADLINE task
-		 * that is going to be deboosted, but exceeds its
-		 * runtime while doing so. No point in replenishing
-		 * it, as it's going to return back to its original
-		 * scheduling class after this.
+		 * Special case in which we have a !SCHED_DEADLINE task that is going
+		 * to be deboosted, but exceeds its runtime while doing so. No point in
+		 * replenishing it, as it's going to return back to its original
+		 * scheduling class after this. If it has been throttled, we need to
+		 * clear the flag, otherwise the task may wake up as throttled after
+		 * being boosted again with no means to replenish the runtime and clear
+		 * the throttle.
 		 */
+		p->dl.dl_throttled = 0;
 		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
 		return;
 	}

kernel/sched/debug.c

@@ -245,6 +245,60 @@ set_table_entry(struct ctl_table *entry,
 	entry->proc_handler = proc_handler;
 }
 
+static int sd_ctl_doflags(struct ctl_table *table, int write,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned long flags = *(unsigned long *)table->data;
+	size_t data_size = 0;
+	size_t len = 0;
+	char *tmp;
+	int idx;
+
+	if (write)
+		return 0;
+
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		char *name = sd_flag_debug[idx].name;
+
+		/* Name plus whitespace */
+		data_size += strlen(name) + 1;
+	}
+
+	if (*ppos > data_size) {
+		*lenp = 0;
+		return 0;
+	}
+
+	tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		char *name = sd_flag_debug[idx].name;
+
+		len += snprintf(tmp + len, strlen(name) + 2, "%s ", name);
+	}
+
+	tmp += *ppos;
+	len -= *ppos;
+
+	if (len > *lenp)
+		len = *lenp;
+	if (len)
+		memcpy(buffer, tmp, len);
+	if (len < *lenp) {
+		((char *)buffer)[len] = '\n';
+		len++;
+	}
+
+	*lenp = len;
+	*ppos += len;
+
+	kfree(tmp);
+
+	return 0;
+}
+
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
@@ -258,7 +312,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
 	set_table_entry(&table[2], "busy_factor",	  &sd->busy_factor,	    sizeof(int),  0644, proc_dointvec_minmax);
 	set_table_entry(&table[3], "imbalance_pct",	  &sd->imbalance_pct,	    sizeof(int),  0644, proc_dointvec_minmax);
 	set_table_entry(&table[4], "cache_nice_tries",	  &sd->cache_nice_tries,    sizeof(int),  0644, proc_dointvec_minmax);
-	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0444, proc_dointvec_minmax);
+	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0444, sd_ctl_doflags);
 	set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax);
 	set_table_entry(&table[7], "name",		  sd->name,	       CORENAME_MAX_SIZE, 0444, proc_dostring);
 	/* &table[8] is terminator */

kernel/sched/fair.c

@@ -831,7 +831,7 @@ void init_entity_runnable_average(struct sched_entity *se)
 void post_init_entity_util_avg(struct task_struct *p)
 {
 }
-static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+static void update_tg_load_avg(struct cfs_rq *cfs_rq)
 {
 }
 #endif /* CONFIG_SMP */
@@ -1504,6 +1504,7 @@ enum numa_type {
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
 	unsigned long load;
+	unsigned long runnable;
 	unsigned long util;
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
@@ -1547,19 +1548,22 @@ struct task_numa_env {
 };
 
 static unsigned long cpu_load(struct rq *rq);
+static unsigned long cpu_runnable(struct rq *rq);
 static unsigned long cpu_util(int cpu);
-static inline long adjust_numa_imbalance(int imbalance, int src_nr_running);
+static inline long adjust_numa_imbalance(int imbalance, int nr_running);
 
 static inline enum
 numa_type numa_classify(unsigned int imbalance_pct,
 			 struct numa_stats *ns)
 {
 	if ((ns->nr_running > ns->weight) &&
-	    ((ns->compute_capacity * 100) < (ns->util * imbalance_pct)))
+	    (((ns->compute_capacity * 100) < (ns->util * imbalance_pct)) ||
+	     ((ns->compute_capacity * imbalance_pct) < (ns->runnable * 100))))
 		return node_overloaded;
 
 	if ((ns->nr_running < ns->weight) ||
-	    ((ns->compute_capacity * 100) > (ns->util * imbalance_pct)))
+	    (((ns->compute_capacity * 100) > (ns->util * imbalance_pct)) &&
+	     ((ns->compute_capacity * imbalance_pct) > (ns->runnable * 100))))
 		return node_has_spare;
 
 	return node_fully_busy;
@@ -1610,6 +1614,7 @@ static void update_numa_stats(struct task_numa_env *env,
 		struct rq *rq = cpu_rq(cpu);
 
 		ns->load += cpu_load(rq);
+		ns->runnable += cpu_runnable(rq);
 		ns->util += cpu_util(cpu);
 		ns->nr_running += rq->cfs.h_nr_running;
 		ns->compute_capacity += capacity_of(cpu);
@@ -1925,7 +1930,7 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 		src_running = env->src_stats.nr_running - 1;
 		dst_running = env->dst_stats.nr_running + 1;
 		imbalance = max(0, dst_running - src_running);
-		imbalance = adjust_numa_imbalance(imbalance, src_running);
+		imbalance = adjust_numa_imbalance(imbalance, dst_running);
 
 		/* Use idle CPU if there is no imbalance */
 		if (!imbalance) {
@@ -3084,7 +3089,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		/* commit outstanding execution time */
 		if (cfs_rq->curr == se)
 			update_curr(cfs_rq);
-		account_entity_dequeue(cfs_rq, se);
+		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
@@ -3100,7 +3105,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq)
-		account_entity_enqueue(cfs_rq, se);
+		update_load_add(&cfs_rq->load, se->load.weight);
 
 }
 
@@ -3288,7 +3293,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 /**
  * update_tg_load_avg - update the tg's load avg
  * @cfs_rq: the cfs_rq whose avg changed
- * @force: update regardless of how small the difference
  *
  * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load.
  * However, because tg->load_avg is a global value there are performance
@@ -3300,7 +3304,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
  *
  * Updating tg's load_avg is necessary before update_cfs_share().
  */
-static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 {
 	long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
 
@@ -3310,7 +3314,7 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 	if (cfs_rq->tg == &root_task_group)
 		return;
 
-	if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
+	if (abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
 		atomic_long_add(delta, &cfs_rq->tg->load_avg);
 		cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
 	}
@@ -3612,7 +3616,7 @@ static inline bool skip_blocked_update(struct sched_entity *se)
 
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
-static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
+static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {}
 
 static inline int propagate_entity_load_avg(struct sched_entity *se)
 {
@@ -3800,13 +3804,13 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 		 * IOW we're enqueueing a task on a new CPU.
 		 */
 		attach_entity_load_avg(cfs_rq, se);
-		update_tg_load_avg(cfs_rq, 0);
+		update_tg_load_avg(cfs_rq);
 
 	} else if (decayed) {
 		cfs_rq_util_change(cfs_rq, 0);
 
 		if (flags & UPDATE_TG)
-			update_tg_load_avg(cfs_rq, 0);
+			update_tg_load_avg(cfs_rq);
 	}
 }
 
@@ -4461,17 +4465,17 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 			se = second;
 	}
 
-	/*
-	 * Prefer last buddy, try to return the CPU to a preempted task.
-	 */
-	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
-		se = cfs_rq->last;
-
-	/*
-	 * Someone really wants this to run. If it's not unfair, run it.
-	 */
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) {
+		/*
+		 * Someone really wants this to run. If it's not unfair, run it.
+		 */
 		se = cfs_rq->next;
+	} else if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) {
+		/*
+		 * Prefer last buddy, try to return the CPU to a preempted task.
+		 */
+		se = cfs_rq->last;
+	}
 
 	clear_buddies(cfs_rq, se);
 
@@ -6075,7 +6079,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 /*
  * Scan the local SMT mask for idle CPUs.
  */
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	int cpu;
 
@@ -6083,7 +6087,8 @@ static int select_idle_smt(struct task_struct *p, int target)
 		return -1;
 
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
-		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
+		    !cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
 		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
@@ -6099,7 +6104,7 @@ static inline int select_idle_core(struct task_struct *p, struct sched_domain *s
 	return -1;
 }
 
-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
 }
@@ -6274,7 +6279,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
-	i = select_idle_smt(p, target);
+	i = select_idle_smt(p, sd, target);
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
@@ -6594,7 +6599,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 
 			util = cpu_util_next(cpu, p, cpu);
 			cpu_cap = capacity_of(cpu);
-			spare_cap = cpu_cap - util;
+			spare_cap = cpu_cap;
+			lsub_positive(&spare_cap, util);
 
 			/*
 			 * Skip CPUs that cannot satisfy the capacity request.
@@ -7402,6 +7408,10 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 	if (unlikely(task_has_idle_policy(p)))
 		return 0;
 
+	/* SMT siblings share cache */
+	if (env->sd->flags & SD_SHARE_CPUCAPACITY)
+		return 0;
+
 	/*
 	 * Buddy candidates are cache hot:
 	 */
@@ -7669,8 +7679,8 @@ static int detach_tasks(struct lb_env *env)
 			 * scheduler fails to find a good waiting task to
 			 * migrate.
 			 */
-			if (load/2 > env->imbalance &&
-			    env->sd->nr_balance_failed <= env->sd->cache_nice_tries)
+
+			if ((load >> env->sd->nr_balance_failed) > env->imbalance)
 				goto next;
 
 			env->imbalance -= load;
@@ -7887,7 +7897,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done)
 		struct sched_entity *se;
 
 		if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
-			update_tg_load_avg(cfs_rq, 0);
+			update_tg_load_avg(cfs_rq);
 
 			if (cfs_rq == &rq->cfs)
 				decayed = true;
@@ -8098,6 +8108,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 		capacity = 1;
 
 	cpu_rq(cpu)->cpu_capacity = capacity;
+	trace_sched_cpu_capacity_tp(cpu_rq(cpu));
+
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;
 	sdg->sgc->max_capacity = capacity;
@@ -8957,7 +8969,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	}
 }
 
-static inline long adjust_numa_imbalance(int imbalance, int src_nr_running)
+static inline long adjust_numa_imbalance(int imbalance, int nr_running)
 {
 	unsigned int imbalance_min;
 
@@ -8966,7 +8978,7 @@ static inline long adjust_numa_imbalance(int imbalance, int src_nr_running)
 	 * tasks that remain local when the source domain is almost idle.
 	 */
 	imbalance_min = 2;
-	if (src_nr_running <= imbalance_min)
+	if (nr_running <= imbalance_min)
 		return 0;
 
 	return imbalance;
@@ -9780,6 +9792,15 @@ get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
 
 	/* scale ms to jiffies */
 	interval = msecs_to_jiffies(interval);
+
+	/*
+	 * Reduce likelihood of busy balancing at higher domains racing with
+	 * balancing at lower domains by preventing their balancing periods
+	 * from being multiples of each other.
+	 */
+	if (cpu_busy)
+		interval -= 1;
+
 	interval = clamp(interval, 1UL, max_load_balance_interval);
 
 	return interval;
@@ -10786,7 +10807,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se)
 	/* Catch up with the cfs_rq and remove our load when we leave */
 	update_load_avg(cfs_rq, se, 0);
 	detach_entity_load_avg(cfs_rq, se);
-	update_tg_load_avg(cfs_rq, false);
+	update_tg_load_avg(cfs_rq);
 	propagate_entity_cfs_rq(se);
 }
 
@@ -10805,7 +10826,7 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
 	/* Synchronize entity with its cfs_rq */
 	update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
 	attach_entity_load_avg(cfs_rq, se);
-	update_tg_load_avg(cfs_rq, false);
+	update_tg_load_avg(cfs_rq);
 	propagate_entity_cfs_rq(se);
 }
 
@@ -11302,6 +11323,18 @@ int sched_trace_rq_cpu(struct rq *rq)
 }
 EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
 
+int sched_trace_rq_cpu_capacity(struct rq *rq)
+{
+	return rq ?
+#ifdef CONFIG_SMP
+		rq->cpu_capacity
+#else
+		SCHED_CAPACITY_SCALE
+#endif
+		: -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity);
+
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 {
 #ifdef CONFIG_SMP

kernel/sched/features.h

@@ -77,7 +77,7 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
 SCHED_FEAT(RT_PUSH_IPI, true)
 #endif
 
-SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(RT_RUNTIME_SHARE, false)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
 

kernel/sched/membarrier.c

@@ -18,6 +18,14 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK	0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK		\
+	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+#else
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK	0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK						\
 	(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED	\
 	| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED			\
@@ -30,6 +38,11 @@ static void ipi_mb(void *info)
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
+static void ipi_rseq(void *info)
+{
+	rseq_preempt(current);
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -129,19 +142,27 @@ static int membarrier_global_expedited(void)
 	return 0;
 }
 
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
 {
-	int cpu;
 	cpumask_var_t tmpmask;
 	struct mm_struct *mm = current->mm;
+	smp_call_func_t ipi_func = ipi_mb;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
 			return -EPERM;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		if (!(atomic_read(&mm->membarrier_state) &
+		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+			return -EPERM;
+		ipi_func = ipi_rseq;
 	} else {
+		WARN_ON_ONCE(flags);
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
 			return -EPERM;
@@ -156,35 +177,59 @@ static int membarrier_private_expedited(int flags)
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
 	cpus_read_lock();
-	rcu_read_lock();
-	for_each_online_cpu(cpu) {
+
+	if (cpu_id >= 0) {
 		struct task_struct *p;
 
-		/*
-		 * Skipping the current CPU is OK even through we can be
-		 * migrated at any point. The current CPU, at the point
-		 * where we read raw_smp_processor_id(), is ensured to
-		 * be in program order with respect to the caller
-		 * thread. Therefore, we can skip this CPU from the
-		 * iteration.
-		 */
-		if (cpu == raw_smp_processor_id())
-			continue;
-		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p && p->mm == mm)
-			__cpumask_set_cpu(cpu, tmpmask);
+		if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
+			goto out;
+		if (cpu_id == raw_smp_processor_id())
+			goto out;
+		rcu_read_lock();
+		p = rcu_dereference(cpu_rq(cpu_id)->curr);
+		if (!p || p->mm != mm) {
+			rcu_read_unlock();
+			goto out;
+		}
+		rcu_read_unlock();
+	} else {
+		int cpu;
+
+		rcu_read_lock();
+		for_each_online_cpu(cpu) {
+			struct task_struct *p;
+
+			/*
+			 * Skipping the current CPU is OK even through we can be
+			 * migrated at any point. The current CPU, at the point
+			 * where we read raw_smp_processor_id(), is ensured to
+			 * be in program order with respect to the caller
+			 * thread. Therefore, we can skip this CPU from the
+			 * iteration.
+			 */
+			if (cpu == raw_smp_processor_id())
+				continue;
+			p = rcu_dereference(cpu_rq(cpu)->curr);
+			if (p && p->mm == mm)
+				__cpumask_set_cpu(cpu, tmpmask);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 
 	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	if (cpu_id >= 0)
+		smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+	else
+		smp_call_function_many(tmpmask, ipi_func, NULL, 1);
 	preempt_enable();
 
-	free_cpumask_var(tmpmask);
+out:
+	if (cpu_id < 0)
+		free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -283,11 +328,18 @@ static int membarrier_register_private_expedited(int flags)
 	    set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
 	    ret;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		ready_state =
 			MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		ready_state =
+			MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
+	} else {
+		WARN_ON_ONCE(flags);
 	}
 
 	/*
@@ -299,6 +351,8 @@ static int membarrier_register_private_expedited(int flags)
 		return 0;
 	if (flags & MEMBARRIER_FLAG_SYNC_CORE)
 		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
+	if (flags & MEMBARRIER_FLAG_RSEQ)
+		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
 	atomic_or(set_state, &mm->membarrier_state);
 	ret = sync_runqueues_membarrier_state(mm);
 	if (ret)
@@ -310,8 +364,15 @@ static int membarrier_register_private_expedited(int flags)
 
 /**
  * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @flags:  Currently needs to be 0 for all commands other than
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ *          contains the CPU on which to interrupt (= restart)
+ *          the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ *          RSEQ CS should be interrupted (@cmd must be
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
  *
  * If this system call is not implemented, -ENOSYS is returned. If the
  * command specified does not exist, not available on the running
@@ -337,10 +398,21 @@ static int membarrier_register_private_expedited(int flags)
  *        smp_mb()           X           O            O
  *        sys_membarrier()   O           O            O
  */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
 {
-	if (unlikely(flags))
-		return -EINVAL;
+	switch (cmd) {
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+			return -EINVAL;
+		break;
+	default:
+		if (unlikely(flags))
+			return -EINVAL;
+	}
+
+	if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+		cpu_id = -1;
+
 	switch (cmd) {
 	case MEMBARRIER_CMD_QUERY:
 	{
@@ -362,13 +434,17 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 	case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
 		return membarrier_register_global_expedited();
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		return membarrier_private_expedited(0);
+		return membarrier_private_expedited(0, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
 		return membarrier_register_private_expedited(0);
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
-		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
 		return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
 	default:
 		return -EINVAL;
 	}

kernel/sched/topology.c

@@ -25,10 +25,18 @@ static inline bool sched_debug(void)
 	return sched_debug_enabled;
 }
 
+#define SD_FLAG(_name, mflags) [__##_name] = { .meta_flags = mflags, .name = #_name },
+const struct sd_flag_debug sd_flag_debug[] = {
+#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  struct cpumask *groupmask)
 {
 	struct sched_group *group = sd->groups;
+	unsigned long flags = sd->flags;
+	unsigned int idx;
 
 	cpumask_clear(groupmask);
 
@@ -43,6 +51,21 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
 	}
 
+	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
+		unsigned int flag = BIT(idx);
+		unsigned int meta_flags = sd_flag_debug[idx].meta_flags;
+
+		if ((meta_flags & SDF_SHARED_CHILD) && sd->child &&
+		    !(sd->child->flags & flag))
+			printk(KERN_ERR "ERROR: flag %s set here but not in child\n",
+			       sd_flag_debug[idx].name);
+
+		if ((meta_flags & SDF_SHARED_PARENT) && sd->parent &&
+		    !(sd->parent->flags & flag))
+			printk(KERN_ERR "ERROR: flag %s set here but not in parent\n",
+			       sd_flag_debug[idx].name);
+	}
+
 	printk(KERN_DEBUG "%*s groups:", level + 1, "");
 	do {
 		if (!group) {
@@ -137,22 +160,22 @@ static inline bool sched_debug(void)
 }
 #endif /* CONFIG_SCHED_DEBUG */
 
+/* Generate a mask of SD flags with the SDF_NEEDS_GROUPS metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_NEEDS_GROUPS)) |
+static const unsigned int SD_DEGENERATE_GROUPS_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
 static int sd_degenerate(struct sched_domain *sd)
 {
 	if (cpumask_weight(sched_domain_span(sd)) == 1)
 		return 1;
 
 	/* Following flags need at least 2 groups */
-	if (sd->flags & (SD_BALANCE_NEWIDLE |
-			 SD_BALANCE_FORK |
-			 SD_BALANCE_EXEC |
-			 SD_SHARE_CPUCAPACITY |
-			 SD_ASYM_CPUCAPACITY |
-			 SD_SHARE_PKG_RESOURCES |
-			 SD_SHARE_POWERDOMAIN)) {
-		if (sd->groups != sd->groups->next)
-			return 0;
-	}
+	if ((sd->flags & SD_DEGENERATE_GROUPS_MASK) &&
+	    (sd->groups != sd->groups->next))
+		return 0;
 
 	/* Following flags don't use groups */
 	if (sd->flags & (SD_WAKE_AFFINE))
@@ -173,18 +196,9 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 		return 0;
 
 	/* Flags needing groups don't count if only 1 group in parent */
-	if (parent->groups == parent->groups->next) {
-		pflags &= ~(SD_BALANCE_NEWIDLE |
-			    SD_BALANCE_FORK |
-			    SD_BALANCE_EXEC |
-			    SD_ASYM_CPUCAPACITY |
-			    SD_SHARE_CPUCAPACITY |
-			    SD_SHARE_PKG_RESOURCES |
-			    SD_PREFER_SIBLING |
-			    SD_SHARE_POWERDOMAIN);
-		if (nr_node_ids == 1)
-			pflags &= ~SD_SERIALIZE;
-	}
+	if (parent->groups == parent->groups->next)
+		pflags &= ~SD_DEGENERATE_GROUPS_MASK;
+
 	if (~cflags & pflags)
 		return 0;
 
@@ -1292,7 +1306,6 @@ int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
  *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
  *   SD_SHARE_PKG_RESOURCES - describes shared caches
  *   SD_NUMA                - describes NUMA topologies
- *   SD_SHARE_POWERDOMAIN   - describes shared power domain
  *
  * Odd one out, which beside describing the topology has a quirk also
  * prescribes the desired behaviour that goes along with it:
@@ -1303,8 +1316,7 @@ int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
 	(SD_SHARE_CPUCAPACITY	|	\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA		|	\
-	 SD_ASYM_PACKING	|	\
-	 SD_SHARE_POWERDOMAIN)
+	 SD_ASYM_PACKING)
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
@@ -1336,8 +1348,8 @@ sd_init(struct sched_domain_topology_level *tl,
 	*sd = (struct sched_domain){
 		.min_interval		= sd_weight,
 		.max_interval		= 2*sd_weight,
-		.busy_factor		= 32,
-		.imbalance_pct		= 125,
+		.busy_factor		= 16,
+		.imbalance_pct		= 117,
 
 		.cache_nice_tries	= 0,
 
@@ -1989,11 +2001,10 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	/* Set up domains for CPUs specified by the cpu_map: */
 	for_each_cpu(i, cpu_map) {
 		struct sched_domain_topology_level *tl;
+		int dflags = 0;
 
 		sd = NULL;
 		for_each_sd_topology(tl) {
-			int dflags = 0;
-
 			if (tl == tl_asym) {
 				dflags |= SD_ASYM_CPUCAPACITY;
 				has_asym = true;

tools/testing/selftests/rseq/param_test.c

 // SPDX-License-Identifier: LGPL-2.1
 #define _GNU_SOURCE
 #include <assert.h>
+#include <linux/membarrier.h>
 #include <pthread.h>
 #include <sched.h>
+#include <stdatomic.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -1131,6 +1133,220 @@ static int set_signal_handler(void)
 	return ret;
 }
 
+struct test_membarrier_thread_args {
+	int stop;
+	intptr_t percpu_list_ptr;
+};
+
+/* Worker threads modify data in their "active" percpu lists. */
+void *test_membarrier_worker_thread(void *arg)
+{
+	struct test_membarrier_thread_args *args =
+		(struct test_membarrier_thread_args *)arg;
+	const int iters = opt_reps;
+	int i;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	/* Wait for initialization. */
+	while (!atomic_load(&args->percpu_list_ptr)) {}
+
+	for (i = 0; i < iters; ++i) {
+		int ret;
+
+		do {
+			int cpu = rseq_cpu_start();
+
+			ret = rseq_offset_deref_addv(&args->percpu_list_ptr,
+				sizeof(struct percpu_list_entry) * cpu, 1, cpu);
+		} while (rseq_unlikely(ret));
+	}
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	return NULL;
+}
+
+void test_membarrier_init_percpu_list(struct percpu_list *list)
+{
+	int i;
+
+	memset(list, 0, sizeof(*list));
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		struct percpu_list_node *node;
+
+		node = malloc(sizeof(*node));
+		assert(node);
+		node->data = 0;
+		node->next = NULL;
+		list->c[i].head = node;
+	}
+}
+
+void test_membarrier_free_percpu_list(struct percpu_list *list)
+{
+	int i;
+
+	for (i = 0; i < CPU_SETSIZE; i++)
+		free(list->c[i].head);
+}
+
+static int sys_membarrier(int cmd, int flags, int cpu_id)
+{
+	return syscall(__NR_membarrier, cmd, flags, cpu_id);
+}
+
+/*
+ * The manager thread swaps per-cpu lists that worker threads see,
+ * and validates that there are no unexpected modifications.
+ */
+void *test_membarrier_manager_thread(void *arg)
+{
+	struct test_membarrier_thread_args *args =
+		(struct test_membarrier_thread_args *)arg;
+	struct percpu_list list_a, list_b;
+	intptr_t expect_a = 0, expect_b = 0;
+	int cpu_a = 0, cpu_b = 0;
+
+	if (rseq_register_current_thread()) {
+		fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+
+	/* Init lists. */
+	test_membarrier_init_percpu_list(&list_a);
+	test_membarrier_init_percpu_list(&list_b);
+
+	atomic_store(&args->percpu_list_ptr, (intptr_t)&list_a);
+
+	while (!atomic_load(&args->stop)) {
+		/* list_a is "active". */
+		cpu_a = rand() % CPU_SETSIZE;
+		/*
+		 * As list_b is "inactive", we should never see changes
+		 * to list_b.
+		 */
+		if (expect_b != atomic_load(&list_b.c[cpu_b].head->data)) {
+			fprintf(stderr, "Membarrier test failed\n");
+			abort();
+		}
+
+		/* Make list_b "active". */
+		atomic_store(&args->percpu_list_ptr, (intptr_t)&list_b);
+		if (sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+					MEMBARRIER_CMD_FLAG_CPU, cpu_a) &&
+				errno != ENXIO /* missing CPU */) {
+			perror("sys_membarrier");
+			abort();
+		}
+		/*
+		 * Cpu A should now only modify list_b, so the values
+		 * in list_a should be stable.
+		 */
+		expect_a = atomic_load(&list_a.c[cpu_a].head->data);
+
+		cpu_b = rand() % CPU_SETSIZE;
+		/*
+		 * As list_a is "inactive", we should never see changes
+		 * to list_a.
+		 */
+		if (expect_a != atomic_load(&list_a.c[cpu_a].head->data)) {
+			fprintf(stderr, "Membarrier test failed\n");
+			abort();
+		}
+
+		/* Make list_a "active". */
+		atomic_store(&args->percpu_list_ptr, (intptr_t)&list_a);
+		if (sys_membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ,
+					MEMBARRIER_CMD_FLAG_CPU, cpu_b) &&
+				errno != ENXIO /* missing CPU*/) {
+			perror("sys_membarrier");
+			abort();
+		}
+		/* Remember a value from list_b. */
+		expect_b = atomic_load(&list_b.c[cpu_b].head->data);
+	}
+
+	test_membarrier_free_percpu_list(&list_a);
+	test_membarrier_free_percpu_list(&list_b);
+
+	if (rseq_unregister_current_thread()) {
+		fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n",
+			errno, strerror(errno));
+		abort();
+	}
+	return NULL;
+}
+
+/* Test MEMBARRIER_CMD_PRIVATE_RESTART_RSEQ_ON_CPU membarrier command. */
+#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+void test_membarrier(void)
+{
+	const int num_threads = opt_threads;
+	struct test_membarrier_thread_args thread_args;
+	pthread_t worker_threads[num_threads];
+	pthread_t manager_thread;
+	int i, ret;
+
+	if (sys_membarrier(MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ, 0, 0)) {
+		perror("sys_membarrier");
+		abort();
+	}
+
+	thread_args.stop = 0;
+	thread_args.percpu_list_ptr = 0;
+	ret = pthread_create(&manager_thread, NULL,
+			test_membarrier_manager_thread, &thread_args);
+	if (ret) {
+		errno = ret;
+		perror("pthread_create");
+		abort();
+	}
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_create(&worker_threads[i], NULL,
+				test_membarrier_worker_thread, &thread_args);
+		if (ret) {
+			errno = ret;
+			perror("pthread_create");
+			abort();
+		}
+	}
+
+
+	for (i = 0; i < num_threads; i++) {
+		ret = pthread_join(worker_threads[i], NULL);
+		if (ret) {
+			errno = ret;
+			perror("pthread_join");
+			abort();
+		}
+	}
+
+	atomic_store(&thread_args.stop, 1);
+	ret = pthread_join(manager_thread, NULL);
+	if (ret) {
+		errno = ret;
+		perror("pthread_join");
+		abort();
+	}
+}
+#else /* RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV */
+void test_membarrier(void)
+{
+	fprintf(stderr, "rseq_offset_deref_addv is not implemented on this architecture. "
+			"Skipping membarrier test.\n");
+}
+#endif
+
 static void show_usage(int argc, char **argv)
 {
 	printf("Usage : %s <OPTIONS>\n",
@@ -1153,7 +1369,7 @@ static void show_usage(int argc, char **argv)
 	printf("	[-r N] Number of repetitions per thread (default 5000)\n");
 	printf("	[-d] Disable rseq system call (no initialization)\n");
 	printf("	[-D M] Disable rseq for each M threads\n");
-	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n");
+	printf("	[-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n");
 	printf("	[-M] Push into buffer and memcpy buffer with memory barriers.\n");
 	printf("	[-v] Verbose output.\n");
 	printf("	[-h] Show this help.\n");
@@ -1268,6 +1484,7 @@ int main(int argc, char **argv)
 			case 'i':
 			case 'b':
 			case 'm':
+			case 'r':
 				break;
 			default:
 				show_usage(argc, argv);
@@ -1320,6 +1537,10 @@ int main(int argc, char **argv)
 		printf_verbose("counter increment\n");
 		test_percpu_inc();
 		break;
+	case 'r':
+		printf_verbose("membarrier\n");
+		test_membarrier();
+		break;
 	}
 	if (!opt_disable_rseq && rseq_unregister_current_thread())
 		abort();

tools/testing/selftests/rseq/rseq-x86.h

@@ -279,6 +279,63 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 #endif
 }
 
+#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
+
+/*
+ *   pval = *(ptr+off)
+ *  *pval += inc;
+ */
+static inline __attribute__((always_inline))
+int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
+#endif
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+#endif
+		/* get p+v */
+		"movq %[ptr], %%rbx\n\t"
+		"addq %[off], %%rbx\n\t"
+		/* get pv */
+		"movq (%%rbx), %%rcx\n\t"
+		/* *pv += inc */
+		"addq %[inc], (%%rcx)\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [rseq_abi]		"r" (&__rseq_abi),
+		  /* final store input */
+		  [ptr]			"m" (*ptr),
+		  [off]			"er" (off),
+		  [inc]			"er" (inc)
+		: "memory", "cc", "rax", "rbx", "rcx"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 				 intptr_t *v2, intptr_t newv2,

tools/testing/selftests/rseq/run_param_test.sh

@@ -15,6 +15,7 @@ TEST_LIST=(
 	"-T m"
 	"-T m -M"
 	"-T i"
+	"-T r"
 )
 
 TEST_NAME=(
@@ -25,6 +26,7 @@ TEST_NAME=(
 	"memcpy"
 	"memcpy with barrier"
 	"increment"
+	"membarrier"
 )
 IFS="$OLDIFS"