Merge tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Scheduler SMP load-balancer improvements:

   - Avoid unnecessary migrations within SMT domains on hybrid systems.

     Problem:

        On hybrid CPU systems, (processors with a mixture of
        higher-frequency SMT cores and lower-frequency non-SMT cores),
        under the old code lower-priority CPUs pulled tasks from the
        higher-priority cores if more than one SMT sibling was busy -
        resulting in many unnecessary task migrations.

     Solution:

        The new code improves the load balancer to recognize SMT cores
        with more than one busy sibling and allows lower-priority CPUs
        to pull tasks, which avoids superfluous migrations and lets
        lower-priority cores inspect all SMT siblings for the busiest
        queue.

   - Implement the 'runnable boosting' feature in the EAS balancer:
     consider CPU contention in frequency, EAS max util & load-balance
     busiest CPU selection.

     This improves CPU utilization for certain workloads, while leaves
     other key workloads unchanged.

  Scheduler infrastructure improvements:

   - Rewrite the scheduler topology setup code by consolidating it into
     the build_sched_topology() helper function and building it
     dynamically on the fly.

   - Resolve the local_clock() vs. noinstr complications by rewriting
     the code: provide separate sched_clock_noinstr() and
     local_clock_noinstr() functions to be used in instrumentation code,
     and make sure it is all instrumentation-safe.

  Fixes:

   - Fix a kthread_park() race with wait_woken()

   - Fix misc wait_task_inactive() bugs unearthed by the -rt merge:
       - Fix UP PREEMPT bug by unifying the SMP and UP implementations
       - Fix task_struct::saved_state handling

   - Fix various rq clock update bugs, unearthed by turning on the rq
     clock debugging code.

   - Fix the PSI WINDOW_MIN_US trigger limit, which was easy to trigger
     by creating enough cgroups, by removing the warnign and restricting
     window size triggers to PSI file write-permission or
     CAP_SYS_RESOURCE.

   - Propagate SMT flags in the topology when removing degenerate domain

   - Fix grub_reclaim() calculation bug in the deadline scheduler code

   - Avoid resetting the min update period when it is unnecessary, in
     psi_trigger_destroy().

   - Don't balance a task to its current running CPU in load_balance(),
     which was possible on certain NUMA topologies with overlapping
     groups.

   - Fix the sched-debug printing of rq->nr_uninterruptible

  Cleanups:

   - Address various -Wmissing-prototype warnings, as a preparation to
     (maybe) enable this warning in the future.

   - Remove unused code

   - Mark more functions __init

   - Fix shadow-variable warnings"

* tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
  sched/core: Avoid double calling update_rq_clock() in __balance_push_cpu_stop()
  sched/core: Fixed missing rq clock update before calling set_rq_offline()
  sched/deadline: Update GRUB description in the documentation
  sched/deadline: Fix bandwidth reclaim equation in GRUB
  sched/wait: Fix a kthread_park race with wait_woken()
  sched/topology: Mark set_sched_topology() __init
  sched/fair: Rename variable cpu_util eff_util
  arm64/arch_timer: Fix MMIO byteswap
  sched/fair, cpufreq: Introduce 'runnable boosting'
  sched/fair: Refactor CPU utilization functions
  cpuidle: Use local_clock_noinstr()
  sched/clock: Provide local_clock_noinstr()
  x86/tsc: Provide sched_clock_noinstr()
  clocksource: hyper-v: Provide noinstr sched_clock()
  clocksource: hyper-v: Adjust hv_read_tsc_page_tsc() to avoid special casing U64_MAX
  x86/vdso: Fix gettimeofday masking
  math64: Always inline u128 version of mul_u64_u64_shr()
  s390/time: Provide sched_clock_noinstr()
  loongarch: Provide noinstr sched_clock_read()
  ...

9 files changed, 40 insertions, 35 deletions

diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index 536f897375d0..6cdc873ac907 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -38,8 +38,9 @@ extern void hv_remap_tsc_clocksource(void);
 extern unsigned long hv_get_tsc_pfn(void);
 extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
 
-static inline notrace u64
-hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
+static __always_inline bool
+hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+		     u64 *cur_tsc, u64 *time)
 {
 	u64 scale, offset;
 	u32 sequence;
@@ -63,7 +64,7 @@ hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
 	do {
 		sequence = READ_ONCE(tsc_pg->tsc_sequence);
 		if (!sequence)
-			return U64_MAX;
+			return false;
 		/*
 		 * Make sure we read sequence before we read other values from
 		 * TSC page.
@@ -82,15 +83,8 @@ hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
 
 	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
 
-	return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
-}
-
-static inline notrace u64
-hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
-{
-	u64 cur_tsc;
-
-	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
+	*time = mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
+	return true;
 }
 
 #else /* CONFIG_HYPERV_TIMER */
@@ -104,10 +98,10 @@ static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 	return NULL;
 }
 
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
-				       u64 *cur_tsc)
+static __always_inline bool
+hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)
 {
-	return U64_MAX;
+	return false;
 }
 
 static inline int hv_stimer_cleanup(unsigned int cpu) { return 0; }
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 30e5bec81d2b..f1f95a71a4bc 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -89,6 +89,7 @@ int kthread_stop(struct task_struct *k);
 bool kthread_should_stop(void);
 bool kthread_should_park(void);
 bool __kthread_should_park(struct task_struct *k);
+bool kthread_should_stop_or_park(void);
 bool kthread_freezable_should_stop(bool *was_frozen);
 void *kthread_func(struct task_struct *k);
 void *kthread_data(struct task_struct *k);
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 8b9191a2849e..bf74478926d4 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -168,7 +168,7 @@ static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
 #endif /* mul_u64_u32_shr */
 
 #ifndef mul_u64_u64_shr
-static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift)
+static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift)
 {
 	return (u64)(((unsigned __int128)a * mul) >> shift);
 }
diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index 3d1a9e716b80..6a0999c26c7c 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -206,7 +206,7 @@ latch_tree_find(void *key, struct latch_tree_root *root,
 	do {
 		seq = raw_read_seqcount_latch(&root->seq);
 		node = __lt_find(key, root, seq & 1, ops->comp);
-	} while (read_seqcount_latch_retry(&root->seq, seq));
+	} while (raw_read_seqcount_latch_retry(&root->seq, seq));
 
 	return node;
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index eed5d65b8d1f..1292d38d66cc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2006,15 +2006,12 @@ static __always_inline void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 }
-extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state);
 #else
 static inline void scheduler_ipi(void) { }
-static inline unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
-{
-	return 1;
-}
 #endif
 
+extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state);
+
 /*
  * Set thread flags in other task's structures.
  * See asm/thread_info.h for TIF_xxxx flags available:
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index ca008f7d3615..196f0ca351a2 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -12,7 +12,16 @@
  *
  * Please use one of the three interfaces below.
  */
-extern unsigned long long notrace sched_clock(void);
+extern u64 sched_clock(void);
+
+#if defined(CONFIG_ARCH_WANTS_NO_INSTR) || defined(CONFIG_GENERIC_SCHED_CLOCK)
+extern u64 sched_clock_noinstr(void);
+#else
+static __always_inline u64 sched_clock_noinstr(void)
+{
+	return sched_clock();
+}
+#endif
 
 /*
  * See the comment in kernel/sched/clock.c
@@ -45,6 +54,11 @@ static inline u64 cpu_clock(int cpu)
 	return sched_clock();
 }
 
+static __always_inline u64 local_clock_noinstr(void)
+{
+	return sched_clock_noinstr();
+}
+
 static __always_inline u64 local_clock(void)
 {
 	return sched_clock();
@@ -79,6 +93,7 @@ static inline u64 cpu_clock(int cpu)
 	return sched_clock_cpu(cpu);
 }
 
+extern u64 local_clock_noinstr(void);
 extern u64 local_clock(void);
 
 #endif
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 57bde66d95f7..fad77b5172e2 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -132,12 +132,9 @@ 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)
+SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS)
 
 /*
  * Prefer to place tasks in a sibling domain
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 816df6cc444e..67b573d5bf28 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -203,7 +203,7 @@ struct sched_domain_topology_level {
 #endif
 };
 
-extern void set_sched_topology(struct sched_domain_topology_level *tl);
+extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
 
 #ifdef CONFIG_SCHED_DEBUG
 # define SD_INIT_NAME(type)		.name = #type
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 3926e9027947..987a59d977c5 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -671,9 +671,9 @@ typedef struct {
  *
  * Return: sequence counter raw value. Use the lowest bit as an index for
  * picking which data copy to read. The full counter must then be checked
- * with read_seqcount_latch_retry().
+ * with raw_read_seqcount_latch_retry().
  */
-static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s)
+static __always_inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s)
 {
 	/*
 	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().
@@ -683,16 +683,17 @@ static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s)
 }
 
 /**
- * read_seqcount_latch_retry() - end a seqcount_latch_t read section
+ * raw_read_seqcount_latch_retry() - end a seqcount_latch_t read section
  * @s:		Pointer to seqcount_latch_t
  * @start:	count, from raw_read_seqcount_latch()
  *
  * Return: true if a read section retry is required, else false
  */
-static inline int
-read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
+static __always_inline int
+raw_read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
 {
-	return read_seqcount_retry(&s->seqcount, start);
+	smp_rmb();
+	return unlikely(READ_ONCE(s->seqcount.sequence) != start);
 }
 
 /**
@@ -752,7 +753,7 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
  *			entry = data_query(latch->data[idx], ...);
  *
  *		// This includes needed smp_rmb()
- *		} while (read_seqcount_latch_retry(&latch->seq, seq));
+ *		} while (raw_read_seqcount_latch_retry(&latch->seq, seq));
  *
  *		return entry;
  *	}