Merge: Scheduler updates for 10.2

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1424

JIRA: https://issues.redhat.com/browse/RHEL-110301
Depends: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1415
Tested: In addition to sched regression and functional tests this
will be tested by the perf QE team.

Scheduler updates for 10.2. This is up through 6.16 and includes some
of the 6.17 merge window and fixes.

Signed-off-by: Phil Auld <pauld@redhat.com>

Approved-by: Joe Lawrence <joe.lawrence@redhat.com>
Approved-by: Herton R. Krzesinski <herton@redhat.com>
Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

include/linux/livepatch_sched.h

@@ -3,27 +3,23 @@
 #define _LINUX_LIVEPATCH_SCHED_H_
 
 #include <linux/jump_label.h>
-#include <linux/static_call_types.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_LIVEPATCH
 
 void __klp_sched_try_switch(void);
 
-#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
 DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
 
-static __always_inline void klp_sched_try_switch(void)
+static __always_inline void klp_sched_try_switch(struct task_struct *curr)
 {
-	if (static_branch_unlikely(&klp_sched_try_switch_key))
+	if (static_branch_unlikely(&klp_sched_try_switch_key) &&
+	    READ_ONCE(curr->__state) & TASK_FREEZABLE)
 		__klp_sched_try_switch();
 }
 
-#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
 #else /* !CONFIG_LIVEPATCH */
-static inline void klp_sched_try_switch(void) {}
-static inline void __klp_sched_try_switch(void) {}
+static inline void klp_sched_try_switch(struct task_struct *curr) {}
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _LINUX_LIVEPATCH_SCHED_H_ */

include/linux/psi_types.h

@@ -84,11 +84,9 @@ enum psi_aggregators {
 struct psi_group_cpu {
 	/* 1st cacheline updated by the scheduler */
 
-	/* Aggregator needs to know of concurrent changes */
-	seqcount_t seq ____cacheline_aligned_in_smp;
-
 	/* States of the tasks belonging to this group */
-	unsigned int tasks[NR_PSI_TASK_COUNTS];
+	unsigned int tasks[NR_PSI_TASK_COUNTS]
+			____cacheline_aligned_in_smp;
 
 	/* Aggregate pressure state derived from the tasks */
 	u32 state_mask;

include/linux/sched.h

@@ -45,7 +45,6 @@
 #include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
-#include <linux/livepatch_sched.h>
 #include <linux/uidgid_types.h>
 #include <linux/tracepoint-defs.h>
 #include <asm/kmap_size.h>
@@ -2042,9 +2041,6 @@ extern int __cond_resched(void);
 
 #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
-void sched_dynamic_klp_enable(void);
-void sched_dynamic_klp_disable(void);
-
 DECLARE_STATIC_CALL(cond_resched, __cond_resched);
 
 static __always_inline int _cond_resched(void)
@@ -2065,7 +2061,6 @@ static __always_inline int _cond_resched(void)
 
 static inline int _cond_resched(void)
 {
-	klp_sched_try_switch();
 	return __cond_resched();
 }
 
@@ -2075,7 +2070,6 @@ static inline int _cond_resched(void)
 
 static inline int _cond_resched(void)
 {
-	klp_sched_try_switch();
 	return 0;
 }
 

include/linux/sched/sd_flags.h

@@ -153,14 +153,6 @@ SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS)
  */
 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
  *

include/linux/sched/topology.h

@@ -175,8 +175,6 @@ bool cpus_share_resources(int this_cpu, int that_cpu);
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
 
-#define SDTL_OVERLAP	0x01
-
 struct sd_data {
 	struct sched_domain *__percpu *sd;
 	struct sched_domain_shared *__percpu *sds;
@@ -187,7 +185,6 @@ struct sd_data {
 struct sched_domain_topology_level {
 	sched_domain_mask_f mask;
 	sched_domain_flags_f sd_flags;
-	int		    flags;
 	int		    numa_level;
 	struct sd_data      data;
 	char                *name;

include/trace/events/sched.h

@@ -745,6 +745,39 @@ TRACE_EVENT(sched_skip_vma_numa,
 		  __entry->vm_end,
 		  __print_symbolic(__entry->reason, NUMAB_SKIP_REASON))
 );
+
+TRACE_EVENT(sched_skip_cpuset_numa,
+
+	TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr),
+
+	TP_ARGS(tsk, mem_allowed_ptr),
+
+	TP_STRUCT__entry(
+		__array( char,		comm,		TASK_COMM_LEN		)
+		__field( pid_t,		pid					)
+		__field( pid_t,		tgid					)
+		__field( pid_t,		ngid					)
+		__array( unsigned long, mem_allowed, BITS_TO_LONGS(MAX_NUMNODES))
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		 = task_pid_nr(tsk);
+		__entry->tgid		 = task_tgid_nr(tsk);
+		__entry->ngid		 = task_numa_group_id(tsk);
+		BUILD_BUG_ON(sizeof(nodemask_t) != \
+			     BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long));
+		memcpy(__entry->mem_allowed, mem_allowed_ptr->bits,
+		       sizeof(__entry->mem_allowed));
+	),
+
+	TP_printk("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl",
+		  __entry->comm,
+		  __entry->pid,
+		  __entry->tgid,
+		  __entry->ngid,
+		  MAX_NUMNODES, __entry->mem_allowed)
+);
 #endif /* CONFIG_NUMA_BALANCING */
 
 /*

kernel/livepatch/transition.c

@@ -29,22 +29,13 @@ static unsigned int klp_signals_cnt;
 
 /*
  * When a livepatch is in progress, enable klp stack checking in
- * cond_resched().  This helps CPU-bound kthreads get patched.
+ * schedule().  This helps CPU-bound kthreads get patched.
  */
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-#define klp_cond_resched_enable() sched_dynamic_klp_enable()
-#define klp_cond_resched_disable() sched_dynamic_klp_disable()
-
-#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
 DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
-EXPORT_SYMBOL(klp_sched_try_switch_key);
 
-#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
-#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
-
-#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+#define klp_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
+#define klp_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
 
 /*
  * This work can be performed periodically to finish patching or unpatching any
@@ -365,26 +356,18 @@ static bool klp_try_switch_task(struct task_struct *task)
 
 void __klp_sched_try_switch(void)
 {
-	if (likely(!klp_patch_pending(current)))
-		return;
-
 	/*
-	 * This function is called from cond_resched() which is called in many
-	 * places throughout the kernel.  Using the klp_mutex here might
-	 * deadlock.
-	 *
-	 * Instead, disable preemption to prevent racing with other callers of
-	 * klp_try_switch_task().  Thanks to task_call_func() they won't be
-	 * able to switch this task while it's running.
+	 * This function is called from __schedule() while a context switch is
+	 * about to happen. Preemption is already disabled and klp_mutex
+	 * can't be acquired.
+	 * Disabled preemption is used to prevent racing with other callers of
+	 * klp_try_switch_task(). Thanks to task_call_func() they won't be
+	 * able to switch to this task while it's running.
 	 */
-	preempt_disable();
+	lockdep_assert_preemption_disabled();
 
-	/*
-	 * Make sure current didn't get patched between the above check and
-	 * preempt_disable().
-	 */
-	if (unlikely(!klp_patch_pending(current)))
-		goto out;
+	if (likely(!klp_patch_pending(current)))
+		return;
 
 	/*
 	 * Enforce the order of the TIF_PATCH_PENDING read above and the
@@ -395,11 +378,7 @@ void __klp_sched_try_switch(void)
 	smp_rmb();
 
 	klp_try_switch_task(current);
-
-out:
-	preempt_enable();
 }
-EXPORT_SYMBOL(__klp_sched_try_switch);
 
 /*
  * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
@@ -508,7 +487,7 @@ void klp_try_complete_transition(void)
 	}
 
 	/* Done!  Now cleanup the data structures. */
-	klp_cond_resched_disable();
+	klp_resched_disable();
 	patch = klp_transition_patch;
 	klp_complete_transition();
 
@@ -560,7 +539,7 @@ void klp_start_transition(void)
 			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
 	}
 
-	klp_cond_resched_enable();
+	klp_resched_enable();
 
 	klp_signals_cnt = 0;
 }