Merge branch into tip/master: 'sched/core'

# New commits in sched/core:
    4a3b51aab6e2 ("smpboot: Don't park the thread if work is pending")
    40dcc9bdbef3 ("irq_work: Flush lazy work CPU down on PREEMPT_RT")
    791b1760accd ("irq_work: Update a comment regarding CPU hotplug invocation")
    648d44bda731 ("sched/topology: Add asymmetric SMT packing override")
    c8fc4136fd3c ("sched/fair: Honor asymmetric SMT priority in idle selection")
    53bc5c556b82 ("sched: Set TIF_NEED_RESCHED before calling __trace_set_need_resched()")
    4b1f75be23c4 ("sched/core: Fix context analysis errors in non-preferred CPU push")
    1fb28c664a19 ("virt/steal_governor: Enable the driver")
    27d47ebce4d6 ("virt/steal_governor: Implement steal_governor policy loop")
    4b9302d494ff ("virt/steal_governor: Add control knobs for handling steal values")
    9a8e740ee9f6 ("virt: Introduce steal governor driver")
    68957caaa9c0 ("sched/debug: Add migration stats due to non preferred CPUs")
    74699f56ebcf ("sched/core: Push current task from non preferred CPU")
    4ee29b029058 ("sched/fair: Load balance only among preferred CPUs")
    d8a3da0de843 ("sched/core: Try to use a preferred CPU in is_cpu_allowed")
    620824516557 ("sysfs: Add preferred CPU file")
    518b32bd5bb3 ("cpumask: Introduce cpu_preferred_mask")
    06a49ef784ac ("sched/docs: Document cpu_preferred_mask and Preferred CPU concept")
    cfb463b7172d ("cpumask: Introduce cpumask_intersects_and")
    a8d0854a76a8 ("sched/cputime: Add kcpustat_field_total helper")
    be100c77178e ("sched: Add sched_ext hooks for proxy execution")
    57c75e3ae38c ("sched: Add helper to block retained proxy donors")
    a49653d0abeb ("sched/core: Mark wakeups completed through ttwu_runnable()")
    8f8c0417e973 ("sched/core: Dequeue waking proxy donors before reset")
    313b652837d0 ("sched/core: Drop mutex locks before proxy rescheduling")
    627ea30aca3b ("sched/wait: Clarify WF_SYNC wakeup semantics")
    d2e010082757 ("sched/eevdf: Handle more short slice waking cases")
    4bf32ec3327d ("sched/eevdf: Align update_protect_slice to set_protect_slice")
    aae2a33ea662 ("sched/eevdf: Ensure that vprot will never go above a min slice")
    c9ce69fc43bd ("sched/fair: Randomize equally shallow slow-path candidates")
    abe440b3770f ("sched/fair: Drop idle recency from slow-path CPU selection")
    fbbc63fed0b0 ("sched/core: Remove redundant core_sched_seq")
    819224e506bc ("sched/fair: Remove dead code on enqueue_task_fair()")
    c72945693b90 ("sched: Restart fair hrtick after same-task repicks")
    a9b3c7570564 ("sched/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in the <uapi/linux/sched.h> header")
    e81ee0630837 ("sched/fair: Reset NUMA fault locality after scan period update")
    ef9293b3b797 ("sched: dynamic: Fix preemption model strings")
    879eaa76e608 ("sched: Remove unneeded function type cast in do_balance_callbacks()")
    f549101187c8 ("sched/deadline: check start_dl_timer expiry with ktime_before()")
    2a672daa4b27 ("sched/feat: Use the new static key API for sched_feat")
    a5576ebce920 ("sched: Convert paravirt_steal to new static key APIs")
    9650ce11f2e3 ("sched: dynamic: Simplify preempt model accessors")
    5b9a28eeed37 ("sched: dynamic: Remove HAVE_PREEMPT_DYNAMIC_{CALL,KEY}")
    aa4178f63847 ("sched: dynamic: Simplify irqentry_exit_cond_resched()")
    b9d267b9d632 ("sched: dynamic: Simplify preempt_schedule{,_notrace}()")
    88e0b3bb9930 ("sched: dynamic: Simplify {cond,might}_resched()")
    d3d16750693b ("sched: dynamic: Make PREEMPT_DYNAMIC depend on ARCH_HAS_PREEMPT_LAZY")
    772d9ffbfd26 ("sched: Migrate whole chain in proxy_migrate_task()")
    6b73a09e943f ("sched: Break out core of attach_tasks() helper into sched.h")
    1f8805138593 ("sched: Switch rq->next_class in proxy_reset_donor()")
    09351db90a28 ("sched/core: Don't proxy-exec unmatched cookie lock owners")
    9be817f991e2 ("sched/core: Avoid migrating blocked_on tasks")
    3dd95f077371 ("sched/core: Don't steal a proxy-exec donor")

Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 89 insertions, 80 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 7df1573a409c..adafbcf2016b 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -52,6 +52,7 @@ struct device;
  *  bitmap_complement(dst, src, nbits)          *dst = ~(*src)
  *  bitmap_equal(src1, src2, nbits)             Are *src1 and *src2 equal?
  *  bitmap_intersects(src1, src2, nbits)        Do *src1 and *src2 overlap?
+ *  bitmap_intersects_and(src1, src2, src3, nbits) Do *src1, *src2 and *src3 overlap?
  *  bitmap_subset(src1, src2, nbits)            Is *src1 a subset of *src2?
  *  bitmap_empty(src, nbits)                    Are all bits zero in *src?
  *  bitmap_full(src, nbits)                     Are all bits set in *src?
@@ -181,6 +182,9 @@ void __bitmap_replace(unsigned long *dst,
 		      const unsigned long *mask, unsigned int nbits);
 bool __bitmap_intersects(const unsigned long *bitmap1,
 			 const unsigned long *bitmap2, unsigned int nbits);
+bool __bitmap_intersects_and(const unsigned long *bitmap1,
+			     const unsigned long *bitmap2,
+			     const unsigned long *bitmap3, unsigned int nbits);
 bool __bitmap_subset(const unsigned long *bitmap1,
 		     const unsigned long *bitmap2, unsigned int nbits);
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
@@ -446,6 +450,16 @@ bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, uns
 }
 
 static __always_inline
+bool bitmap_intersects_and(const unsigned long *src1, const unsigned long *src2,
+			   const unsigned long *src3, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ((*src1 & *src2 & *src3) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+	else
+		return __bitmap_intersects_and(src1, src2, src3, nbits);
+}
+
+static __always_inline
 bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 4c8bb6953107..bf89bb3f30f6 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -121,12 +121,20 @@ extern struct cpumask __cpu_enabled_mask;
 extern struct cpumask __cpu_present_mask;
 extern struct cpumask __cpu_active_mask;
 extern struct cpumask __cpu_dying_mask;
+
+#ifdef CONFIG_PREFERRED_CPU
+extern struct cpumask __cpu_preferred_mask;
+#else
+#define __cpu_preferred_mask __cpu_active_mask
+#endif
+
 #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
 #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
 #define cpu_enabled_mask   ((const struct cpumask *)&__cpu_enabled_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)
+#define cpu_preferred_mask ((const struct cpumask *)&__cpu_preferred_mask)
 
 extern atomic_t __num_online_cpus;
 extern unsigned int __num_possible_cpus;
@@ -825,6 +833,24 @@ bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p
 }
 
 /**
+ * cpumask_intersects_and - (*src1p & *src2p & *src3p) != 0
+ * @src1p: the first input
+ * @src2p: the second input
+ * @src3p: the third input
+ *
+ * Return: true if AND of the three cpumasks is non-empty,
+ *	   otherwise false
+ */
+static __always_inline
+bool cpumask_intersects_and(const struct cpumask *src1p,
+			    const struct cpumask *src2p,
+			    const struct cpumask *src3p)
+{
+	return bitmap_intersects_and(cpumask_bits(src1p), cpumask_bits(src2p),
+				 cpumask_bits(src3p), small_cpumask_bits);
+}
+
+/**
  * cpumask_subset - (*src1p & ~*src2p) == 0
  * @src1p: the first input
  * @src2p: the second input
@@ -1163,6 +1189,12 @@ void init_cpu_possible(const struct cpumask *src);
 #define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
 #define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
 
+#ifdef CONFIG_PREFERRED_CPU
+#define set_cpu_preferred(cpu, preferred) assign_cpu((cpu), &__cpu_preferred_mask, (preferred))
+#else
+#define set_cpu_preferred(cpu, preferred) do { } while (0)
+#endif
+
 void set_cpu_online(unsigned int cpu, bool online);
 void set_cpu_possible(unsigned int cpu, bool possible);
 
@@ -1257,6 +1289,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 	return cpumask_test_cpu(cpu, cpu_dying_mask);
 }
 
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_preferred_mask);
+}
+
 #else
 
 #define num_online_cpus()	1U
@@ -1295,6 +1332,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
 	return false;
 }
 
+static __always_inline bool cpu_preferred(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
 #endif /* NR_CPUS > 1 */
 
 #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
index 0bb6c03481fa..2be273bb68f0 100644
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -346,22 +346,7 @@ typedef struct irqentry_state {
  *
  * Conditional reschedule with additional sanity checks.
  */
-void raw_irqentry_exit_cond_resched(void);
-
-#ifdef CONFIG_PREEMPT_DYNAMIC
-#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
-#define irqentry_exit_cond_resched_dynamic_disabled	NULL
-DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
-#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
-#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-void dynamic_irqentry_exit_cond_resched(void);
-#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
-#endif
-#else /* CONFIG_PREEMPT_DYNAMIC */
-#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
-#endif /* CONFIG_PREEMPT_DYNAMIC */
+void irqentry_exit_cond_resched(void);
 
 /**
  * irqentry_enter_from_kernel_mode - Establish state before invoking the irq handler
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index c5afd053ae32..7184e1273965 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -59,6 +59,7 @@ void irq_work_sync(struct irq_work *work);
 #include <asm/irq_work.h>
 
 void irq_work_run(void);
+void irq_work_run_cpu(unsigned int cpu);
 bool irq_work_needs_cpu(void);
 void irq_work_single(void *arg);
 
@@ -67,6 +68,7 @@ void arch_irq_work_raise(void);
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
+static inline void irq_work_run_cpu(unsigned int cpu) { }
 static inline void irq_work_single(void *arg) { }
 #endif
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 24414c79e59a..4b11d1dc0a67 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -43,30 +43,10 @@ struct completion;
 struct user;
 
 #ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD
-
 extern int __cond_resched(void);
 # define might_resched() __cond_resched()
-
-#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-extern int __cond_resched(void);
-
-DECLARE_STATIC_CALL(might_resched, __cond_resched);
-
-static __always_inline void might_resched(void)
-{
-	static_call_mod(might_resched)();
-}
-
-#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-
-extern int dynamic_might_resched(void);
-# define might_resched() dynamic_might_resched()
-
 #else
-
 # define might_resched() do { } while (0)
-
 #endif /* CONFIG_PREEMPT_* */
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 9ca6c2259dfe..c1e85550bf12 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -196,6 +196,17 @@ static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
 }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
+static inline u64 kcpustat_field_total(enum cpu_usage_stat usage, const struct cpumask *cpus)
+{
+	u64 total = 0;
+	int cpu;
+
+	for_each_cpu(cpu, cpus)
+		total += kcpustat_field(usage, cpu);
+
+	return total;
+}
+
 extern void account_user_time(struct task_struct *, u64);
 extern void account_guest_time(struct task_struct *, u64);
 extern void account_system_time(struct task_struct *, int, u64);
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 2e689de7b29a..06ff44a4b8b6 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -498,21 +498,11 @@ DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_n
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
-extern bool preempt_model_none(void);
-extern bool preempt_model_voluntary(void);
 extern bool preempt_model_full(void);
 extern bool preempt_model_lazy(void);
 
 #else
 
-static inline bool preempt_model_none(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_NONE);
-}
-static inline bool preempt_model_voluntary(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
-}
 static inline bool preempt_model_full(void)
 {
 	return IS_ENABLED(CONFIG_PREEMPT);
@@ -525,6 +515,16 @@ static inline bool preempt_model_lazy(void)
 
 #endif
 
+static inline bool preempt_model_none(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_NONE);
+}
+
+static inline bool preempt_model_voluntary(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
+}
+
 static inline bool preempt_model_rt(void)
 {
 	return IS_ENABLED(CONFIG_PREEMPT_RT);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d35ae49a991f..0cb03f9acfe3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -554,6 +554,7 @@ struct sched_statistics {
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
 	u64				nr_forced_migrations;
+	u64				nr_migrations_cpu_non_preferred;
 
 	u64				nr_wakeups;
 	u64				nr_wakeups_sync;
@@ -2105,10 +2106,9 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
 {
-	if (tracepoint_enabled(sched_set_need_resched_tp) &&
-	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
+	if (!test_and_set_tsk_thread_flag(tsk, TIF_NEED_RESCHED) &&
+	    tracepoint_enabled(sched_set_need_resched_tp))
 		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
-	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
 }
 
 static inline void clear_tsk_need_resched(struct task_struct *tsk)
@@ -2135,44 +2135,19 @@ static inline void set_need_resched_current(void)
  * value indicates whether a reschedule was done in fact.
  * cond_resched_lock() will drop the spinlock before scheduling,
  */
-#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
+#if !defined(CONFIG_PREEMPTION)
 extern int __cond_resched(void);
 
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-DECLARE_STATIC_CALL(cond_resched, __cond_resched);
-
-static __always_inline int _cond_resched(void)
-{
-	return static_call_mod(cond_resched)();
-}
-
-#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-
-extern int dynamic_cond_resched(void);
-
-static __always_inline int _cond_resched(void)
-{
-	return dynamic_cond_resched();
-}
-
-#else /* !CONFIG_PREEMPTION */
-
 static inline int _cond_resched(void)
 {
 	return __cond_resched();
 }
-
-#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
-#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */
-
+#else
 static inline int _cond_resched(void)
 {
 	return 0;
 }
-
-#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */
+#endif
 
 #define cond_resched() ({			\
 	__might_resched(__FILE__, __LINE__, 0);	\
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index e90efaf6d26e..694126411dfe 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -182,9 +182,9 @@ extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 
 #ifdef CONFIG_PARAVIRT
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
+#include <linux/jump_label.h>
+DECLARE_STATIC_KEY_FALSE(paravirt_steal_enabled);
+DECLARE_STATIC_KEY_FALSE(paravirt_steal_rq_enabled);
 
 #ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN
 u64 dummy_steal_clock(int cpu);