10 files changed, 110 insertions, 53 deletions

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/coredump.h b/include/linux/sched/coredump.h
index 0e17ae7fbfd3..0ee96ea7a0e9 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
 				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
 
+#define MMF_VM_MERGE_ANY	29
 #endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 8c15abd67aed..fe1a46f30d24 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -46,6 +46,12 @@ static inline bool housekeeping_enabled(enum hk_type type)
 
 static inline void housekeeping_affine(struct task_struct *t,
 				       enum hk_type type) { }
+
+static inline bool housekeeping_test_cpu(int cpu, enum hk_type type)
+{
+	return true;
+}
+
 static inline void housekeeping_init(void) { }
 #endif /* CONFIG_CPU_ISOLATION */
 
@@ -58,4 +64,10 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 	return true;
 }
 
+static inline bool cpu_is_isolated(int cpu)
+{
+	return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) ||
+		 !housekeeping_test_cpu(cpu, HK_TYPE_TICK);
+}
+
 #endif /* _LINUX_SCHED_ISOLATION_H */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2a243616f222..8d89c8c4fac1 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -8,7 +8,6 @@
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
 #include <linux/sync_core.h>
-#include <linux/ioasid.h>
 
 /*
  * Routines for handling mm_structs
@@ -37,6 +36,11 @@ static inline void mmgrab(struct mm_struct *mm)
 	atomic_inc(&mm->mm_count);
 }
 
+static inline void smp_mb__after_mmgrab(void)
+{
+	smp_mb__after_atomic();
+}
+
 extern void __mmdrop(struct mm_struct *mm);
 
 static inline void mmdrop(struct mm_struct *mm)
@@ -79,6 +83,34 @@ static inline void mmdrop_sched(struct mm_struct *mm)
 }
 #endif
 
+/* Helpers for lazy TLB mm refcounting */
+static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
+{
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
+		mmgrab(mm);
+}
+
+static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
+{
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) {
+		mmdrop(mm);
+	} else {
+		/*
+		 * mmdrop_lazy_tlb must provide a full memory barrier, see the
+		 * membarrier comment finish_task_switch which relies on this.
+		 */
+		smp_mb();
+	}
+}
+
+static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
+{
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
+		mmdrop_sched(mm);
+	else
+		smp_mb(); /* see mmdrop_lazy_tlb() above */
+}
+
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
  * @mm: The address space to pin.
@@ -451,29 +483,4 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
 }
 #endif
 
-#ifdef CONFIG_IOMMU_SVA
-static inline void mm_pasid_init(struct mm_struct *mm)
-{
-	mm->pasid = INVALID_IOASID;
-}
-
-/* Associate a PASID with an mm_struct: */
-static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid)
-{
-	mm->pasid = pasid;
-}
-
-static inline void mm_pasid_drop(struct mm_struct *mm)
-{
-	if (pasid_valid(mm->pasid)) {
-		ioasid_free(mm->pasid);
-		mm->pasid = INVALID_IOASID;
-	}
-}
-#else
-static inline void mm_pasid_init(struct mm_struct *mm) {}
-static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {}
-static inline void mm_pasid_drop(struct mm_struct *mm) {}
-#endif
-
 #endif /* _LINUX_SCHED_MM_H */
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/signal.h b/include/linux/sched/signal.h
index 20099268fa25..0014d3adaf84 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -135,7 +135,7 @@ struct signal_struct {
 #ifdef CONFIG_POSIX_TIMERS
 
 	/* POSIX.1b Interval Timers */
-	int			posix_timer_id;
+	unsigned int		next_posix_timer_id;
 	struct list_head	posix_timers;
 
 	/* ITIMER_REAL timer for the process */
@@ -649,12 +649,9 @@ extern void flush_itimer_signals(void);
 extern bool current_is_single_threaded(void);
 
 /*
- * Careful: do_each_thread/while_each_thread is a double loop so
- *          'break' will not work as expected - use goto instead.
+ * Without tasklist/siglock it is only rcu-safe if g can't exit/exec,
+ * otherwise next_thread(t) will never reach g after list_del_rcu(g).
  */
-#define do_each_thread(g, t) \
-	for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
-
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 537cbf9a2ade..a23af225c898 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -29,7 +29,6 @@ struct kernel_clone_args {
 	u32 io_thread:1;
 	u32 user_worker:1;
 	u32 no_files:1;
-	u32 ignore_signals:1;
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
@@ -119,13 +118,51 @@ static inline struct task_struct *get_task_struct(struct task_struct *t)
 }
 
 extern void __put_task_struct(struct task_struct *t);
+extern void __put_task_struct_rcu_cb(struct rcu_head *rhp);
 
 static inline void put_task_struct(struct task_struct *t)
 {
-	if (refcount_dec_and_test(&t->usage))
+	if (!refcount_dec_and_test(&t->usage))
+		return;
+
+	/*
+	 * In !RT, it is always safe to call __put_task_struct().
+	 * Under RT, we can only call it in preemptible context.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
+		static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);
+
+		lock_map_acquire_try(&put_task_map);
 		__put_task_struct(t);
+		lock_map_release(&put_task_map);
+		return;
+	}
+
+	/*
+	 * under PREEMPT_RT, we can't call put_task_struct
+	 * in atomic context because it will indirectly
+	 * acquire sleeping locks.
+	 *
+	 * call_rcu() will schedule delayed_put_task_struct_rcu()
+	 * to be called in process context.
+	 *
+	 * __put_task_struct() is called when
+	 * refcount_dec_and_test(&t->usage) succeeds.
+	 *
+	 * This means that it can't "conflict" with
+	 * put_task_struct_rcu_user() which abuses ->rcu the same
+	 * way; rcu_users has a reference so task->usage can't be
+	 * zero after rcu_users 1 -> 0 transition.
+	 *
+	 * delayed_free_task() also uses ->rcu, but it is only called
+	 * when it fails to fork a process. Therefore, there is no
+	 * way it can conflict with put_task_struct().
+	 */
+	call_rcu(&t->rcu, __put_task_struct_rcu_cb);
 }
 
+DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T))
+
 static inline void put_task_struct_many(struct task_struct *t, int nr)
 {
 	if (refcount_sub_and_test(nr, &t->usage))
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 5e799a47431e..f158b025c175 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -23,7 +23,7 @@ static __always_inline void *task_stack_page(const struct task_struct *task)
 
 #define setup_thread_stack(new,old)	do { } while(0)
 
-static inline unsigned long *end_of_stack(const struct task_struct *task)
+static __always_inline unsigned long *end_of_stack(const struct task_struct *task)
 {
 #ifdef CONFIG_STACK_GROWSUP
 	return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1;
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/sched/vhost_task.h b/include/linux/sched/vhost_task.h
index 6123c10b99cf..837a23624a66 100644
--- a/include/linux/sched/vhost_task.h
+++ b/include/linux/sched/vhost_task.h
@@ -2,22 +2,13 @@
 #ifndef _LINUX_VHOST_TASK_H
 #define _LINUX_VHOST_TASK_H
 
-#include <linux/completion.h>
 
-struct task_struct;
+struct vhost_task;
 
-struct vhost_task {
-	int (*fn)(void *data);
-	void *data;
-	struct completion exited;
-	unsigned long flags;
-	struct task_struct *task;
-};
-
-struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg,
+struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg,
 				     const char *name);
 void vhost_task_start(struct vhost_task *vtsk);
 void vhost_task_stop(struct vhost_task *vtsk);
-bool vhost_task_should_stop(struct vhost_task *vtsk);
+void vhost_task_wake(struct vhost_task *vtsk);
 
 #endif