Merge tag 'sched-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core facilities:

   - Add the "Lazy preemption" model (CONFIG_PREEMPT_LAZY=y), which
     optimizes fair-class preemption by delaying preemption requests to
     the tick boundary, while working as full preemption for
     RR/FIFO/DEADLINE classes. (Peter Zijlstra)
        - x86: Enable Lazy preemption (Peter Zijlstra)
        - riscv: Enable Lazy preemption (Jisheng Zhang)

   - Initialize idle tasks only once (Thomas Gleixner)

   - sched/ext: Remove sched_fork() hack (Thomas Gleixner)

  Fair scheduler:

   - Optimize the PLACE_LAG when se->vlag is zero (Huang Shijie)

  Idle loop:

   - Optimize the generic idle loop by removing unnecessary memory
     barrier (Zhongqiu Han)

  RSEQ:

   - Improve cache locality of RSEQ concurrency IDs for intermittent
     workloads (Mathieu Desnoyers)

  Waitqueues:

   - Make wake_up_{bit,var} less fragile (Neil Brown)

  PSI:

   - Pass enqueue/dequeue flags to psi callbacks directly (Johannes
     Weiner)

  Preparatory patches for proxy execution:

   - Add move_queued_task_locked helper (Connor O'Brien)

   - Consolidate pick_*_task to task_is_pushable helper (Connor O'Brien)

   - Split out __schedule() deactivate task logic into a helper (John
     Stultz)

   - Split scheduler and execution contexts (Peter Zijlstra)

   - Make mutex::wait_lock irq safe (Juri Lelli)

   - Expose __mutex_owner() (Juri Lelli)

   - Remove wakeups from under mutex::wait_lock (Peter Zijlstra)

  Misc fixes and cleanups:

   - Remove unused __HAVE_THREAD_FUNCTIONS hook support (David
     Disseldorp)

   - Update the comment for TIF_NEED_RESCHED_LAZY (Sebastian Andrzej
     Siewior)

   - Remove unused bit_wait_io_timeout (Dr. David Alan Gilbert)

   - remove the DOUBLE_TICK feature (Huang Shijie)

   - fix the comment for PREEMPT_SHORT (Huang Shijie)

   - Fix unnused variable warning (Christian Loehle)

   - No PREEMPT_RT=y for all{yes,mod}config"

* tag 'sched-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  sched, x86: Update the comment for TIF_NEED_RESCHED_LAZY.
  sched: No PREEMPT_RT=y for all{yes,mod}config
  riscv: add PREEMPT_LAZY support
  sched, x86: Enable Lazy preemption
  sched: Enable PREEMPT_DYNAMIC for PREEMPT_RT
  sched: Add Lazy preemption model
  sched: Add TIF_NEED_RESCHED_LAZY infrastructure
  sched/ext: Remove sched_fork() hack
  sched: Initialize idle tasks only once
  sched: psi: pass enqueue/dequeue flags to psi callbacks directly
  sched/uclamp: Fix unnused variable warning
  sched: Split scheduler and execution contexts
  sched: Split out __schedule() deactivate task logic into a helper
  sched: Consolidate pick_*_task to task_is_pushable helper
  sched: Add move_queued_task_locked helper
  locking/mutex: Expose __mutex_owner()
  locking/mutex: Make mutex::wait_lock irq safe
  locking/mutex: Remove wakeups from under mutex::wait_lock
  sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads
  sched: idle: Optimize the generic idle loop by removing needless memory barrier
  ...

Author: torvalds

arch/riscv/Kconfig

@@ -39,6 +39,7 @@ config RISCV
 	select ARCH_HAS_MMIOWB
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API
+	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PREPARE_SYNC_CORE_CMD
 	select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU
 	select ARCH_HAS_PTE_SPECIAL

arch/riscv/include/asm/thread_info.h

@@ -107,19 +107,21 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
  * - pending work-to-be-done flags are in lowest half-word
  * - other flags in upper half-word(s)
  */
-#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
-#define TIF_SIGPENDING		2	/* signal pending */
-#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_NEED_RESCHED	0	/* rescheduling necessary */
+#define TIF_NEED_RESCHED_LAZY	1       /* Lazy rescheduling needed */
+#define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
+#define TIF_SIGPENDING		3	/* signal pending */
 #define TIF_RESTORE_SIGMASK	4	/* restore signal mask in do_signal() */
 #define TIF_MEMDIE		5	/* is terminating due to OOM killer */
 #define TIF_NOTIFY_SIGNAL	9	/* signal notifications exist */
 #define TIF_UPROBE		10	/* uprobe breakpoint or singlestep */
 #define TIF_32BIT		11	/* compat-mode 32bit process */
 #define TIF_RISCV_V_DEFER_RESTORE	12 /* restore Vector before returing to user */
 
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_SIGNAL	(1 << TIF_NOTIFY_SIGNAL)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_RISCV_V_DEFER_RESTORE	(1 << TIF_RISCV_V_DEFER_RESTORE)

arch/x86/Kconfig

@@ -93,6 +93,7 @@ config X86
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API		if X86_64
+	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_HW_PTE_YOUNG

arch/x86/include/asm/thread_info.h

@@ -87,8 +87,9 @@ struct thread_info {
 #define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
-#define TIF_SSBD		5	/* Speculative store bypass disable */
+#define TIF_NEED_RESCHED_LAZY	4	/* Lazy rescheduling needed */
+#define TIF_SINGLESTEP		5	/* reenable singlestep on user return*/
+#define TIF_SSBD		6	/* Speculative store bypass disable */
 #define TIF_SPEC_IB		9	/* Indirect branch speculation mitigation */
 #define TIF_SPEC_L1D_FLUSH	10	/* Flush L1D on mm switches (processes) */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
@@ -110,6 +111,7 @@ struct thread_info {
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_SSBD		(1 << TIF_SSBD)
 #define _TIF_SPEC_IB		(1 << TIF_SPEC_IB)

fs/exec.c

@@ -990,7 +990,7 @@ static int exec_mmap(struct mm_struct *mm)
 	active_mm = tsk->active_mm;
 	tsk->active_mm = mm;
 	tsk->mm = mm;
-	mm_init_cid(mm);
+	mm_init_cid(mm, tsk);
 	/*
 	 * This prevents preemption while active_mm is being loaded and
 	 * it and mm are being updated, which could cause problems for

include/linux/entry-common.h

@@ -64,7 +64,8 @@
 
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
+	 _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY |			\
+	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |			\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**

include/linux/entry-kvm.h

@@ -17,8 +17,9 @@
 #endif
 
 #define XFER_TO_GUEST_MODE_WORK						\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
-	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
+	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \
+	 _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME |			\
+	 ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;
 

include/linux/mm_types.h

@@ -782,6 +782,7 @@ struct vm_area_struct {
 struct mm_cid {
 	u64 time;
 	int cid;
+	int recent_cid;
 };
 #endif
 
@@ -852,6 +853,27 @@ struct mm_struct {
 		 * When the next mm_cid scan is due (in jiffies).
 		 */
 		unsigned long mm_cid_next_scan;
+		/**
+		 * @nr_cpus_allowed: Number of CPUs allowed for mm.
+		 *
+		 * Number of CPUs allowed in the union of all mm's
+		 * threads allowed CPUs.
+		 */
+		unsigned int nr_cpus_allowed;
+		/**
+		 * @max_nr_cid: Maximum number of concurrency IDs allocated.
+		 *
+		 * Track the highest number of concurrency IDs allocated for the
+		 * mm.
+		 */
+		atomic_t max_nr_cid;
+		/**
+		 * @cpus_allowed_lock: Lock protecting mm cpus_allowed.
+		 *
+		 * Provide mutual exclusion for mm cpus_allowed and
+		 * mm nr_cpus_allowed updates.
+		 */
+		raw_spinlock_t cpus_allowed_lock;
 #endif
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* size of all page tables */
@@ -1170,36 +1192,53 @@ static inline int mm_cid_clear_lazy_put(int cid)
 	return cid & ~MM_CID_LAZY_PUT;
 }
 
+/*
+ * mm_cpus_allowed: Union of all mm's threads allowed CPUs.
+ */
+static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm)
+{
+	unsigned long bitmap = (unsigned long)mm;
+
+	bitmap += offsetof(struct mm_struct, cpu_bitmap);
+	/* Skip cpu_bitmap */
+	bitmap += cpumask_size();
+	return (struct cpumask *)bitmap;
+}
+
 /* Accessor for struct mm_struct's cidmask. */
 static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
 {
-	unsigned long cid_bitmap = (unsigned long)mm;
+	unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm);
 
-	cid_bitmap += offsetof(struct mm_struct, cpu_bitmap);
-	/* Skip cpu_bitmap */
+	/* Skip mm_cpus_allowed */
 	cid_bitmap += cpumask_size();
 	return (struct cpumask *)cid_bitmap;
 }
 
-static inline void mm_init_cid(struct mm_struct *mm)
+static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 {
 	int i;
 
 	for_each_possible_cpu(i) {
 		struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i);
 
 		pcpu_cid->cid = MM_CID_UNSET;
+		pcpu_cid->recent_cid = MM_CID_UNSET;
 		pcpu_cid->time = 0;
 	}
+	mm->nr_cpus_allowed = p->nr_cpus_allowed;
+	atomic_set(&mm->max_nr_cid, 0);
+	raw_spin_lock_init(&mm->cpus_allowed_lock);
+	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
 	cpumask_clear(mm_cidmask(mm));
 }
 
-static inline int mm_alloc_cid_noprof(struct mm_struct *mm)
+static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p)
 {
 	mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid);
 	if (!mm->pcpu_cid)
 		return -ENOMEM;
-	mm_init_cid(mm);
+	mm_init_cid(mm, p);
 	return 0;
 }
 #define mm_alloc_cid(...)	alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))
@@ -1212,16 +1251,31 @@ static inline void mm_destroy_cid(struct mm_struct *mm)
 
 static inline unsigned int mm_cid_size(void)
 {
-	return cpumask_size();
+	return 2 * cpumask_size();	/* mm_cpus_allowed(), mm_cidmask(). */
+}
+
+static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask)
+{
+	struct cpumask *mm_allowed = mm_cpus_allowed(mm);
+
+	if (!mm)
+		return;
+	/* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */
+	raw_spin_lock(&mm->cpus_allowed_lock);
+	cpumask_or(mm_allowed, mm_allowed, cpumask);
+	WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed));
+	raw_spin_unlock(&mm->cpus_allowed_lock);
 }
 #else /* CONFIG_SCHED_MM_CID */
-static inline void mm_init_cid(struct mm_struct *mm) { }
-static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; }
+static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { }
+static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; }
 static inline void mm_destroy_cid(struct mm_struct *mm) { }
+
 static inline unsigned int mm_cid_size(void)
 {
 	return 0;
 }
+static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { }
 #endif /* CONFIG_SCHED_MM_CID */
 
 struct mmu_gather;

include/linux/preempt.h

@@ -486,6 +486,7 @@ DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
 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
 
@@ -502,6 +503,11 @@ static inline bool preempt_model_full(void)
 	return IS_ENABLED(CONFIG_PREEMPT);
 }
 
+static inline bool preempt_model_lazy(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_LAZY);
+}
+
 #endif
 
 static inline bool preempt_model_rt(void)
@@ -519,7 +525,7 @@ static inline bool preempt_model_rt(void)
  */
 static inline bool preempt_model_preemptible(void)
 {
-	return preempt_model_full() || preempt_model_rt();
+	return preempt_model_full() || preempt_model_lazy() || preempt_model_rt();
 }
 
 #endif /* __LINUX_PREEMPT_H */

include/linux/sched.h

@@ -1898,7 +1898,7 @@ extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 # define task_thread_info(task)	(&(task)->thread_info)
-#elif !defined(__HAVE_THREAD_FUNCTIONS)
+#else
 # define task_thread_info(task)	((struct thread_info *)(task)->stack)
 #endif
 
@@ -2002,7 +2002,8 @@ static inline void set_tsk_need_resched(struct task_struct *tsk)
 
 static inline void clear_tsk_need_resched(struct task_struct *tsk)
 {
-	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
+	atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY,
+			   (atomic_long_t *)&task_thread_info(tsk)->flags);
 }
 
 static inline int test_tsk_need_resched(struct task_struct *tsk)